Papers by Qi Qi
Verified Critical Step Optimization for LLM Agents (2026.findings-acl)
Copied to clipboard
| Challenge: | Critical Step Optimization (CSO) focuses preference learning on verified critical steps where alternative actions demonstrably flip task outcomes from failure to success. |
| Approach: | They propose a method which focuses preference learning on verified critical steps where alternative actions demonstrably flip task outcomes from failure to success. |
| Outcome: | The proposed method outperforms the existing methods on GAIA-Text-103 and XBench-DeepSearch while requiring supervision at only 16% of trajectory steps. |
AdaEdit: Advancing Continuous Knowledge Editing For Large Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Existing knowledge editing methods that can efficiently update knowledge in LLMs are limited due to budget constraints. |
| Approach: | They propose a method that can enhance the performance of edited LLMs in large-size continuous editing regimes. |
| Outcome: | Extensive empirical evaluations on multiple LLMs show that the proposed method outperforms existing methods without compromising the general abilities of these models. |
Enhancing Hierarchical Text Classification through Knowledge Graph Integration (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to hierarchical text classification are limited by lack of domain knowledge, which leads to mistakes in a variety of situations. |
| Approach: | They propose a Knowledge-enabled Hierarchical Text Classification model which integrates knowledge graphs into HTC to address the knowledge limitations of traditional methods. |
| Outcome: | The proposed model integrates knowledge graphs into the hierarchical text classification process, addressing the knowledge limitations of traditional methods. |
Beyond Chunks and Graphs: Retrieval-Augmented Generation through Triplet-Driven Thinking (2026.findings-acl)
Copied to clipboard
| Challenge: | Retrieval-augmented generation (RAG) is critical for reducing hallucinations and incorporating external knowledge into Large Language Models (LLMs). |
| Approach: | They propose a framework that leverages an LLM to decompose questions into searchable triplets with placeholders. |
| Outcome: | Empirical results show that T2RAG outperforms state-of-the-art multi-round and Graph RAG methods while reducing retrieval costs by up to 45%. |
Snapshot-Guided Domain Adaptation for ELECTRA (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing domain-specific knowledge of domain-related tasks is lacking in pre-trained language models. |
| Approach: | They propose a domain-adaptation method which can dynamically select domain-specific tokens and guide the discriminator to emphasize them, without introducing new training parameters. |
| Outcome: | The proposed method can capture domain-specific knowledge of domain-related tasks without introducing new training parameters. |
Which Programming Language and What Features at Pre-training Stage Affect Downstream Logical Inference Performance? (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent large language models (LLMs) have demonstrated remarkable generalization abilities in mathematics and reasoning tasks. |
| Approach: | They pre-trained decoder-based language models from scratch using ten programming languages and three natural language datasets. |
| Outcome: | The proposed models outperform natural languages on logical reasoning tasks. |
Through the MUD: A Multi-Defendant Charge Prediction Benchmark with Linked Crime Elements (2024.acl-long)
Copied to clipboard
| Challenge: | Existing charge prediction datasets focus on single-defendant cases, but real-world cases involve multiple defendants. |
| Approach: | They propose a benchmark that encompasses legal cases involving multiple defendants . they develop an interpretable model called EJudge that incorporates crime elements and legal rules to infer charges. |
| Outcome: | The proposed model outperforms state-of-the-art models in predicting crime charges while providing corresponding rationales. |
Towards Explainable Computerized Adaptive Testing with Large Language Model (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods focus on minimizing the number of questions required to assess ability, lacking clear and reliable explanations for the question selection process. |
| Approach: | They propose to use large language models to enhance computer adaptive testing (CAT) by providing human-like interpretability and explanations. |
| Outcome: | The proposed agent-based CAT performs comparably or superior to traditional CAT methods in accuracy and significantly improves student trust and satisfaction. |
Optimizing Code Retrieval: High-Quality and Scalable Dataset Annotation through Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for code retrieval struggle to balance scalability and annotation quality. |
| Approach: | They propose a method that integrates functions called within the repository and information on third-party APIs to enhance the annotation context. |
| Outcome: | The proposed method improves the annotation context by incorporating functions called within the repository and information on third-party API functionalities. |
Multiview Clickbait Detection via Jointly Modeling Subjective and Objective Preference (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing clickbait detection models rely on analyzing the objective semantics of posts or correlating posts with article content only, but fail to identify and exploit the manipulation intention of clickbaiting from a user’s subjective perspective. |
| Approach: | They propose a multiview clickbait detection model to model subjective and objective preferences simultaneously to capture clickbaiting from a user's subjective perspective. |
| Outcome: | The proposed model outperforms state-of-the-art models on two real-world datasets and shows that it integrates subjective and objective preferences simultaneously. |
Neural Topic Modeling with Large Language Models in the Loop (2025.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated promising capabilities in topic discovery, but their direct application to topic modeling suffers from issues such as incomplete topic coverage, misalignment of topics, and inefficiency. |
| Approach: | They propose a novel LLM-in-the-loop framework that integrates Large Language Models with Neural Topic Models (NTMs) global topics and document representations are learned through the NTM, while an LLM refines these topics using an Optimal Transport (OT)-based alignment objective. |
| Outcome: | The proposed framework improves topic interpretability while preserving the efficiency of existing NTMs. |
Searching for an Effective Defender: Benchmarking Defense against Adversarial Word Substitution (2021.emnlp-main)
Copied to clipboard
Zongyi Li, Jianhan Xu, Jiehang Zeng, Linyang Li, Xiaoqing Zheng, Qi Zhang, Kai-Wei Chang, Cho-Jui Hsieh
| Challenge: | Existing methods to defend against adversarial word-substitution attacks have not been evaluated or compared in a systematic manner. |
| Approach: | They propose to compare different defense methods under representative adversarial attacks . they propose a method that improves the robustness of neural text classifiers against such attacks a . |
| Outcome: | The proposed method improves robustness of neural text classifiers against such attacks by a significant margin. |
Uncovering the Impact of Chain-of-Thought Reasoning for Direct Preference Optimization: Lessons from Text-to-SQL (2025.acl-long)
Copied to clipboard
| Challenge: | Direct Preference Optimization (DPO) is effective in complex reasoning tasks like math word problems and code generation, but Text-to-SQL datasets often include only final answers (gold SQL queries) without detailed CoT solutions. |
| Approach: | They found that Direct Preference Optimization (DPO) is crucial for unlocking DPO's potential by augmenting Text-to-SQL datasets with synthetic CoT solutions. |
| Outcome: | The proposed method achieves consistent and significant performance improvements on Text-to-SQL datasets. |
Model Internals-based Answer Attribution for Trustworthy Retrieval-Augmented Generation (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent research has shown that self-citing large language models (LLMs) fail to faithfully reflect their context usage throughout the generation process. |
| Approach: | They propose a plug-and-play approach using model internals for faithful answer attribution in RAG applications that detects context-sensitive answer tokens and pairs them with retrieved documents contributing to their prediction. |
| Outcome: | The proposed approach achieves citation quality and efficiency comparable to self-citation while allowing for a finer-grained control of attribution parameters. |
Muse: Towards Reproducible Long-Form Song Generation with Fine-Grained Style Control (2026.findings-acl)
Copied to clipboard
Changhao Jiang, Jiahao Chen, Zhenghao Xiang, Zhixiong Yang, Hanchen Wang, Jiabao Zhuang, Xinmeng Che, Jiajun Sun, Hui Li, Yifei Cao, Shihan Dou, Ming Zhang, Junjie Ye, Tao Ji, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Recent commercial systems such as Suno demonstrate strong capabilities in long-form song generation, but academic research remains non-reproducible due to the lack of publicly available training data. |
| Approach: | They propose a system for long-form song generation with fine-grained style conditioning that includes a licensed synthetic dataset and a song generation model, Muse. |
| Outcome: | The proposed system achieves competitive performance on phoneme error rate, text–music style similarity, and audio aesthetic quality while enabling controllable segment-level generation across different musical structures. |
GLoCIM: Global-view Long Chain Interest Modeling for news recommendation (2025.coling-main)
Copied to clipboard
| Challenge: | Recent efforts to extract local subgraph information from click graphs have hindered collaboratively utilizing global click graph information. |
| Approach: | They propose a global-view long chain interests model that models a click graph with neighbor interest to enhance news recommendation. |
| Outcome: | The proposed method surpasses baseline methods on two real-world datasets. |
Augmenting Multi-Turn Text-to-SQL Datasets with Self-Play (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Numerous architectures and pretraining methods have been proposed for context-dependent text-to-SQL, but the size of the datasets used has been limited due to the high cost of annotating multi-turn dialogue and SQL pairs. |
| Approach: | They propose to augment training datasets using self-play which leverages contextual information to synthesize new interactions to adapt the model to new databases. |
| Outcome: | The proposed model improves accuracy on SParC and CoSQL, two widely used cross-domain text-to-SQl datasets. |
VLA-Mark: A cross modal watermark for large vision-language alignment models (2025.emnlp-main)
Copied to clipboard
Shuliang Liu, Zheng Qi, Jesse Jiaxi Xu, Yibo Yan, Junyan Zhang, He Geng, Aiwei Liu, Peijie Jiang, Jia Liu, Yik-Cheung Tam, Xuming Hu
| Challenge: | Existing text watermarking methods disrupt visual-textual alignment, leaving semantic-critical concepts vulnerable. |
| Approach: | They propose a vision-aligned framework that embeds detectable watermarks into outputs . they combine localized patch affinity, global semantic coherence, contextual attention patterns . |
| Outcome: | The proposed framework shows lower PPL and higher BLEU than conventional methods with near-perfect detection (98.8% AUC). |
Self-Criticism: Aligning Large Language Models with their Understanding of Helpfulness, Honesty, and Harmlessness (2023.emnlp-industry)
Copied to clipboard
| Challenge: | Recent studies have shown that large language models are useful, honest, harmless (HHH) however, RLHF requires high hardware resources and human efforts. |
| Approach: | They propose a framework that allows LLMs to align themselves with HHH . they use IF and reinforcement learning from human feedback to fine-tune their models . |
| Outcome: | The proposed framework achieves similar performance to RLHF and human-generated models with a minimal alignment tax. |
Zero-knowledge LLM hallucination detection and mitigation through fine-grained cross-model consistency (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Existing methods for hallucination management fail to integrate both detection and mitigation without external knowledge sources. |
| Approach: | They propose a black-box framework that leverages fine-grained cross-model consistency to detect and mitigate hallucinations in LLM outputs without external knowledge sources. |
| Outcome: | The proposed framework improves hallucination detection scores by 6-39% on a FELM dataset . it achieves 9 percentage points improvement in answer accuracy on the GPQA-diamond dataset compared to existing approaches . |
Math Word Problem Solving with Explicit Numerical Values (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods for solving math word problems ignore numerical values in solving problems. |
| Approach: | They propose a numerically-based approach that explicitly incorporates numerical values into a sequence-to-tree network and uses a mathematical properties prediction mechanism to capture category and comparison information of numerals. |
| Outcome: | The proposed model outperforms existing state-of-the-art models on the Math23K and APE datasets. |
Capability Salience Vector: Fine-grained Alignment of Loss and Capabilities for Downstream Task Scaling Law (2025.acl-long)
Copied to clipboard
Qiming Ge, Shuhao Xing, Songyang Gao, Yunhua Zhou, Yicheng Zou, Songyang Zhang, Zhi Chen, Hang Yan, Qi Zhang, Qipeng Guo, Kai Chen
| Challenge: | Large language models have demonstrated impressive performance across a wide range of tasks, but this achievement comes with the trade-off of significant computational demands. |
| Approach: | They propose a scaling law that decomposes the overall validation loss and assigns different importance weights to tokens to assess a specific meta-capability. |
| Outcome: | The proposed model can predict the loss trending of models across different levels of computation without a gap between validation loss and model's downstream capabilities. |
Disentangled Multi-span Evolutionary Network against Temporal Knowledge Graph Reasoning (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for temporal knowledge Graphs neglect internal structural interactions between subgraphs and ignore potential smooth features that do not lead to semantic changes. |
| Approach: | They propose to use a disentangled multi-span evolutionary network to capture local neighbor features while perceiving historical neighbor semantic information. |
| Outcome: | Extensive experiments show that the proposed model outperforms the state-of-the-art in TKG reasoning by 22.7%. |
Sentence-State LSTM for Text Representation (P18-1)
Copied to clipboard
| Challenge: | LSTMs have been shown to suffer from various limitations due to their sequential nature. |
| Approach: | They propose to model hidden states of all words simultaneously at each recurrent step rather than one word at a time. |
| Outcome: | The proposed model has strong representation power, giving competitive performances compared to stacked BiLSTM models with similar parameter numbers. |
ParaMac: A General Unsupervised Paraphrase Generation Framework Leveraging Semantic Constraints and Diversifying Mechanisms (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing unsupervised methods for paraphrase generation are weak in semantic equivalence or expression diversity. |
| Approach: | They propose a framework for unsupervised paraphrase generation that employs multi-aspect equivalence constraints and multi-granularity diversifying mechanisms to achieve good semantic equvalence and expressive diversity. |
| Outcome: | The proposed framework achieves 9.1% and 3.3% absolute gains over previous SOTA on Quora and MSCOCO and can improve to 18.0% and 4.6% on GLUE. |
Cross-media Structured Common Space for Multimedia Event Extraction (2020.acl-main)
Copied to clipboard
| Challenge: | We propose a new task to extract events and their arguments from multimedia documents . traditional methods target text, images or videos, but multimedia content is distributed via multimedia . |
| Approach: | They propose a method that encodes structured representations of semantic information from textual and visual data into a common embedding space. |
| Outcome: | The proposed method achieves 4.0% and 9.8% absolute gains on text event argument role labeling and visual event extraction. |
AT²PO: Agentic Turn-based Policy Optimization via Tree Search (2026.acl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have catalyzed the development of autonomous agents capable of executing complex, multi-turn tasks. |
| Approach: | They propose a framework for agentic reinforcement learning that integrates turn-level tree search with tree search to address key challenges. |
| Outcome: | The proposed framework addresses key challenges: limited exploration diversity, sparse credit assignment, and misaligned policy optimization. |
An Investigation of LLMs’ Inefficacy in Understanding Converse Relations (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing benchmarks for Large Language Models (LLMs) follow the data distribution of pre-training data. |
| Approach: | They propose a benchmark ConvRe focusing on converse relations which contains 17 relations and 1240 triples extracted from popular knowledge graph completion datasets. |
| Outcome: | The proposed benchmark focuses on converse relations, which contains 17 relations and 1240 triples extracted from popular knowledge graph completion datasets. |
Feature Projection for Improved Text Classification (2020.acl-main)
Copied to clipboard
| Challenge: | In sentiment classification, there are some good features that are indicative of class labels, but there are also many common features that do not discriminate for classification. |
| Approach: | They propose to project existing features into the orthogonal space of the common features and make them more discriminative for classification. |
| Outcome: | The proposed method improves CNN, RNN, Transformer, and Bert based text classification and obtains markedly better results. |
Better Process Supervision with Bi-directional Rewarding Signals (2025.findings-acl)
Copied to clipboard
Wenxiang Chen, Wei He, Zhiheng Xi, Honglin Guo, Boyang Hong, Jiazheng Zhang, Nijun Li, Tao Gui, Yun Li, Qi Zhang, Xuanjing Huang
| Challenge: | Existing processes that reward for each step are one-directional and lack a mechanism to model the distance to the final target. |
| Approach: | They propose a process supervision model that evaluates the correctness of previous steps and the probability of future success. |
| Outcome: | The proposed model outperforms existing supervision models like ORM and PRM on reasoning tasks and improves solution re-design. |
RE-Matching: A Fine-Grained Semantic Matching Method for Zero-Shot Relation Extraction (2023.acl-long)
Copied to clipboard
Jun Zhao, WenYu Zhan, Xin Zhao, Qi Zhang, Tao Gui, Zhongyu Wei, Junzhe Wang, Minlong Peng, Mingming Sun
| Challenge: | Existing methods for zero-shot relation extraction lack explicit modeling of matching pattern . et al. (2018) show that our method achieves higher matching accuracy and faster inference speed . |
| Approach: | They propose a fine-grained semantic matching method tailored for zero-shot relation extraction . they decompose sentence-level similarity score into entity matching score and context matching score . |
| Outcome: | The proposed method achieves higher matching accuracy and faster inference speed than state-of-the-art methods. |
Patton: Language Model Pretraining on Text-Rich Networks (2023.acl-long)
Copied to clipboard
| Challenge: | Existing models for text-rich networks do not take inter-document structure into account. |
| Approach: | They propose a pretraining framework for a text-rich network using a masked language model and a masking node prediction framework. |
| Outcome: | The proposed model outperforms baselines on four tasks in academic and e-commerce domains. |
UnifiedMLLM: Enabling Unified Representation for Multi-modal Multi-tasks With Large Language Model (2025.findings-naacl)
Copied to clipboard
Zhaowei Li, Wei Wang, YiQing Cai, Qi Xu, Pengyu Wang, Dong Zhang, Hang Song, Botian Jiang, Zhida Huang, Tao Wang
| Challenge: | Representative models like LLaVA and MiniGPT-4 have great capabilities in various tasks. |
| Approach: | They propose a unified model to represent various multi-modal tasks using a single representation. |
| Outcome: | The proposed model outperforms existing models in a variety of tasks while maintaining generality and scalability. |
Exploring the Capability of Multimodal LLMs with Yonkoma Manga: The YManga Dataset and Its Challenging Tasks (2024.findings-emnlp)
Copied to clipboard
| Challenge: | YManga dataset is the first specifically designed for yonkoma manga understanding . |
| Approach: | They propose to use a dataset of 1,015 yonkoma strips with 10,150 human annotations to define three tasks for panel sequence detection, intent generation and description generation for masked panels. |
| Outcome: | The proposed dataset contains 1,015 high-quality yonkoma strips with 10,150 human annotations. |
FinToolSyn: A forward synthesis Framework for Financial Tool-Use Dialogue Data with Dynamic Tool Retrieval (2026.findings-acl)
Copied to clipboard
Caishuang Huang, Yang Qiao, Rongyu Zhang, Junjie Ye, Pu Lu, null Wuwenxi, Meng Zhou, Xiku Du, Qi Zhang, Tao Gui, Xuanjing Huang
| Challenge: | Existing data synthesis methods rely on static tools to generate queries . this approach fails to capture the implicit, event-driven nature of real-world needs . |
| Approach: | They propose a forward synthesis framework to generate high-quality financial dialogues . they construct a repository of 43,066 tools and synthesize over 148k dialogue instances . |
| Outcome: | Experiments show that models trained on FinToolSyn achieve a 21.06% improvement . the framework is designed to generate high-quality financial dialogues . |
Keyphrase Generation with Fine-Grained Evaluation-Guided Reinforcement Learning (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing KG evaluation metrics are only aware of the exact correctness of predictions on phrase-level and ignore semantic similarities between similar predictions and targets, which inhibits the model from learning deep linguistic patterns. |
| Approach: | They propose a fine-grained evaluation metric to improve the previous KG framework . the evaluation metrics are only aware of the exact correctness of predictions on phrase-level . |
| Outcome: | The proposed method outperforms the existing frameworks among all evaluation scores. |
Rethinking LLM Uncertainty: A Multi-Agent Approach to Estimating Black-Box Model Uncertainty (2025.findings-emnlp)
Copied to clipboard
Yu Feng, Phu Mon Htut, Zheng Qi, Wei Xiao, Manuel Mager, Nikolaos Pappas, Kishaloy Halder, Yang Li, Yassine Benajiba, Dan Roth
| Challenge: | Existing methods to gauge model’s uncertainty through self-consistency in responses to the target query are misleading: an LLM may confidently provide an incorrect answer to a target query, yet give a confident and accurate answer to that same query when answering a knowledge-preserving perturbation of the query. |
| Approach: | They propose a method that uses multi-agent interaction to estimate black-box LLMs' uncertainty. |
| Outcome: | The proposed method outperforms existing self-consistency based methods and improves hallucination detection. |
Sarcasm-R1: Enhancing Sarcasm Detection through Focused Reasoning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for sarcasm detection are limited by supervised learning or prompt engineering . a new approach decomposes sarcasm detection into three dimensions: language, context, and emotion . |
| Approach: | They propose a method that decomposes sarcasm detection into three dimensions: language, context, and emotion. |
| Outcome: | The proposed method outperforms state-of-the-art methods in most cases. |
Sharp Nearby, Fuzzy Far Away: How Neural Language Models Use Context (P18-1)
Copied to clipboard
| Challenge: | Recent studies have shed light on the information encoded by long-term memory networks. |
| Approach: | They propose to use a neural caching model to model the role of context in an LSTM LM . they analyze the increase in perplexity when prior context words are shuffled, replaced, or dropped . |
| Outcome: | The proposed model is highly sensitive to the order of words within the most recent sentence, but ignores word order in the long-range context, suggesting the distant past is modeled only as a rough semantic field or topic. |
Generalizable Cross-Lingual Cognitive Distortion Detection with Standardized Annotations and Multi-Task Learning (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing studies on cognitive distortion have limited generalizability and performance of models in large-scale and cross-linguistic contexts. |
| Approach: | They propose a multi-task learning model based on teacher student architecture solution which improves generalization performance. |
| Outcome: | The proposed model improves generalizability and interpretability of the proposed model. |
Large Language Models are not Fair Evaluators (2024.acl-long)
Copied to clipboard
Peiyi Wang, Lei Li, Liang Chen, Zefan Cai, Dawei Zhu, Binghuai Lin, Yunbo Cao, Lingpeng Kong, Qi Liu, Tianyu Liu, Zhifang Sui
| Challenge: | Existing evaluation frameworks that use large language models as referees are insufficient for accurately assessing their alignment with human intent. |
| Approach: | They propose a calibration framework to address positional bias in large language models as evaluators by manually annotating the “win/tie/lose” outcomes of responses from ChatGPT and Vicuna-13B in the Vicun A Benchmark’s question prompt. |
| Outcome: | The proposed framework alleviates evaluation bias, resulting in closer alignment with human judgments. |
DynamixSFT: Dynamic Mixture Optimization of Instruction Tuning Collections (2026.findings-acl)
Copied to clipboard
| Challenge: | Several studies rely on additional models to optimize mixtures. |
| Approach: | They propose a method that dynamically optimizes instruction-tuning dataset mixtures by prior-scaled Boltzmann Exploration and a multi-armed bandit setup. |
| Outcome: | The proposed method improves the TÜLU-2-mixture and TÜLO-3-mixtures across 10 benchmarks while introducing minimal computational overhead over naive sampling. |
Multi-turn Response Selection using Dialogue Dependency Relations (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing models for multi-turn response selection ignore the dependencies between the turns. |
| Approach: | They propose a dialogue extraction algorithm to transform a dialog history into threads based on their dependency relations. |
| Outcome: | The proposed model outperforms the state-of-the-art models on DSTC7 and DSTF8* with competitive results on UbuntuV2 . |
Towards relation extraction from speech (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for extracting relations from speech have been neglected due to the nature of speech. |
| Approach: | They propose a listening information extraction task that uses speech to extract relation extraction from speech . they use a text-to-speech system and crowd-sourced native English speakers to test the task . |
| Outcome: | The proposed task extracts semantic relationships from speech data using a new model . the proposed task is more challenging than the existing method due to the characteristics of speech . |
SGA-MCTS: Decoupling Planning from Execution via Training-Free Atomic Experience Retrieval (2026.findings-acl)
Copied to clipboard
| Challenge: | a new framework casts LLM planning as non-parametric retrieval, but high latency of inference-time search and supervised fine-tuning are limitations. |
| Approach: | They propose a framework that casts LLM planning as non-parametric retrieval . they leverage Monte Carlo Tree Search to explore the solution space . |
| Outcome: | Empirical results show that SGA-MCTS can match the performance of SOTA systems without task-specific fine-tuning. |
CoCA: Fusing Position Embedding with Collinear Constrained Attention in Transformers for Long Context Window Extending (2024.acl-long)
Copied to clipboard
| Challenge: | Existing models that use self-attention and position embedding have anomalous behavior that hinder long context window extrapolation. |
| Approach: | They propose a collinear constraint between Q and K to integrate RoPE and self-attention. |
| Outcome: | The proposed model integrates self-attention and position embedding into LLMs without fine-tuning. |
DebateQA: Evaluating Question Answering on Debatable Knowledge (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing QA benchmarks that provide fixed answers to debatable questions are inadequate for evaluating their performance. |
| Approach: | They propose to use a dataset of 2,941 debatable questions to assess their ability to provide comprehensive answers to inherently debatably asked questions. |
| Outcome: | The proposed model performs well on 2,941 debatable questions accompanied by human-annotated partial answers that capture a variety of perspectives. |
Beyond Function-Level Search: Repository-Aware Dual-Encoder Code Retrieval with Adversarial Verification (2025.findings-emnlp)
Copied to clipboard
| Challenge: | escalating complexity of modern codebases has intensified the need for code retrieval systems capable of interpreting cross-component change intents. |
| Approach: | RepoAlignBench is a benchmark designed to evaluate repository-level code retrieval . the benchmark proposes an adversarial reflection-augmented dual-tower architecture . |
| Outcome: | The proposed framework achieves 12.2% Top-5 Accuracy and 7.1% Recall improvements over state-of-the-art benchmarks. |
CRITICTOOL: Evaluating Self-Critique Capabilities of Large Language Models in Tool-Calling Error Scenarios (2025.emnlp-main)
Copied to clipboard
| Challenge: | a number of tools are used to perform complex tasks, but the tool utilization process can cause errors. |
| Approach: | They propose a critique evaluation benchmark for tool learning that analyzes function-calling errors on tool evaluation benchmarks. |
| Outcome: | The proposed critique evaluation benchmark holds diverse tool-use errors with varying complexities, which better reflects real-world scenarios. |
MuTIS: Enhancing Reasoning Efficiency through Multi Turn Intervention Sampling in Reinforcement Learning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for training large reasoning models with long chain-of-thought (CoT) are limited by the number of parameters and the complexity of the model. |
| Approach: | They propose a framework that leverages multi-turn interventions to produce concise reasoning chains and demonstrates strong scalability. |
| Outcome: | The proposed framework breaks the accuracy-efficiency trade-off by producing concise reasoning chains and demonstrating strong scalability on 7B models. |
MARS2: Scaling Multi-Agent Tree Search via Reinforcement Learning for Code Generation (2026.acl-long)
Copied to clipboard
Pengfei Li, Shijie Wang, Fangyuan Li, Yikun Fu, Kaifeng Liu, Kaiyan Zhang, Dazhi Zhang, Yuqiang Li, Biqing Qi, Bowen Zhou
| Challenge: | Existing approaches to reinforcement learning are decoupled from structured search due to limited trajectory diversity. |
| Approach: | They propose a unified RL framework that integrates multiple agents within a shared tree-structured search environment. |
| Outcome: | Experiments show that MARS2 improves performance across diverse model combinations and training settings. |
Privacy-Preserving News Recommendation Model Learning (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing news recommendation methods rely on centralized storage of user behavior data for model training, which may lead to privacy concerns and risks due to the privacy-sensitive nature of user behaviors. |
| Approach: | They propose a privacy-preserving method where user behavior data is locally stored on user devices to train accurate news recommendation models. |
| Outcome: | The proposed method can train accurate news recommendation models without centralized storage of user behavior data. |
Opinion Summarization by Weak-Supervision from Mix-structured Data (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for opinion summarization of multiple reviews lack reference summaries . OAs and ISs are often mismatched between review input and summary . |
| Approach: | They propose a method to generate mixed-structured synthetic training data for opinion summarization. |
| Outcome: | The proposed method outperforms existing methods on Yelp, Amazon and RottenTomatos datasets. |
Multilingual BERT Post-Pretraining Alignment (2021.naacl-main)
Copied to clipboard
| Challenge: | Recent work improves on the success of monolingual pretrained language models by adding cross-lingual tasks that always involve English. |
| Approach: | They propose a method to align multilingual contextual embeddings as a post-pretraining step for improved cross-lingual transferability of pretrained language models. |
| Outcome: | The proposed model outperforms XLM-R_Base on translation-train tasks while using less parallel data and fewer parameters. |
FOLIO: Natural Language Reasoning with First-Order Logic (2024.emnlp-main)
Copied to clipboard
Simeng Han, Hailey Schoelkopf, Yilun Zhao, Zhenting Qi, Martin Riddell, Wenfei Zhou, James Coady, David Peng, Yujie Qiao, Luke Benson, Lucy Sun, Alexander Wardle-Solano, Hannah Szabó, Ekaterina Zubova, Matthew Burtell, Jonathan Fan, Yixin Liu, Brian Wong, Malcolm Sailor, Ansong Ni, Linyong Nan, Jungo Kasai, Tao Yu, Rui Zhang, Alexander Fabbri, Wojciech Kryscinski, Semih Yavuz, Ye Liu, Xi Lin, Shafiq Joty, Yingbo Zhou, Caiming Xiong, Rex Ying, Arman Cohan, Dragomir Radev
| Challenge: | Existing benchmarks for logical reasoning in large language models lack language naturalness or limited complexity. |
| Approach: | They propose to use first-order logic annotations to evaluate logical reasoning capabilities of large language models. |
| Outcome: | The proposed dataset evaluates the FOL reasoning ability of supervised fine-tuning on medium-sized language models. |
Velocitune: A Velocity-based Dynamic Domain Reweighting Method for Continual Pre-training (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods to optimise pretraining performance have not addressed the complexities of domain-adaptive continual pretraining. |
| Approach: | They propose a framework that dynamically assesses learning velocity and adjusts data proportions accordingly, favouring slower learning domains while de-emphasising faster learning ones. |
| Outcome: | The proposed framework achieves performance gains in math and code reasoning tasks and command-line generation benchmarks. |
Llama SLayer 8B: Shallow Layers Hold the Key to Knowledge Injection (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to augment pre-trained large language models require extensive computational efforts and massive data volumes, challenging the widespread accessibility of LLM research. |
| Approach: | They propose a post-pretraining strategy of selectively enhancing shallow layers while pruning less effective deep ones to augment pretrained large language models. |
| Outcome: | The proposed approach improves performance on the corpus of code & math and a legal corpus and is widely applicable. |
ReviewRL: Towards Automated Scientific Review with RL (2025.emnlp-main)
Copied to clipboard
Sihang Zeng, Kai Tian, Kaiyan Zhang, Yuru Wang, Junqi Gao, Runze Liu, Sa Yang, Jingxuan Li, Xinwei Long, Jiaheng Ma, Biqing Qi, Bowen Zhou
| Challenge: | Existing automated review systems struggle with factual accuracy, rating consistency, and analytical depth. |
| Approach: | They propose a framework for generating comprehensive and factually grounded scientific paper reviews using supervised fine-tuning and reinforcement learning. |
| Outcome: | The proposed framework outperforms existing methods on ICLR 2025 papers. |
PepRec: Progressive Enhancement of Prompting for Recommendation (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) have been gaining in-depth performance in natural language processing domains. |
| Approach: | They propose a training-free prompting framework that captures knowledge from content-based filtering and collaborative filtering to boost recommendation performance with LLMs. |
| Outcome: | The proposed framework outperforms traditional deep learning recommendation models and prompt-based recommendation systems on two real-world datasets. |
A Goal Without a Plan Is Just a Wish: Efficient and Effective Global Planner Training for Long-Horizon Agent Tasks (2026.acl-long)
Copied to clipboard
Shuzheng Si, Haozhe Zhao, Kangyang Luo, Gang Chen, Fanchao Qi, Minjia Zhang, Baobao Chang, Maosong Sun
| Challenge: | Recent advances in large language models (LLMs) have leapt from static chatbots to versatile agents that tackle complex tasks such as science experiments. |
| Approach: | They propose a plan-and-execute framework and propose 'EAGLET' to enhance the executor agent's planning abilities without human effort. |
| Outcome: | The proposed method outperforms existing methods on three long-horizon tasks and reduces training costs by 8 compared to baselines. |
Rethinking Smoothness for Fast and Adaptable Entity Alignment Decoding (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods for integrating knowledge graphs rely on entity and relation embeddings . Fig. 1 shows how to decode knowledge graph in under 6 seconds . |
| Approach: | They propose a framework that only utilizes entity embeddings to decode knowledge graphs. |
| Outcome: | The proposed framework reconstructs KG representation by maximizing smoothness of entity embeddings. |
A Skeleton-Based Model for Promoting Coherence Among Sentences in Narrative Story Generation (D18-1)
Copied to clipboard
| Challenge: | Existing models for narrative story generation lack semantic dependency among sentences. |
| Approach: | They propose a skeleton-based model that generates the most critical phrases and expands them to a complete sentence. |
| Outcome: | The proposed model can generate significantly more coherent stories according to human evaluation and automatic evaluation. |
AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments (2026.acl-long)
Copied to clipboard
Zhiheng Xi, Dingwen Yang, Jiaqi Liu, Jixuan Huang, Honglin Guo, Baodai Huang, Tinggang Chen, Qi Zhang, Zhonghang Lu, Chenyu Liu, Jiajun Sun, Jiazheng Zhang, Dingwei Zhu, Xin Guo, Junzhe Wang, Zhihao Zhang, Yuming Yang, Junjie Ye, Minghe Gao, Dongrui Liu, Jiaming Ji, Guohao Li, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing benchmarks evaluate agents in simplified, idealized settings, relying on pre-packaged tool interfaces, overlooking critical steps, and assume inputs are clean and fully specified. |
| Approach: | They propose a framework that evaluates language agents in simplified, idealized settings . they show that even SOTA systems like Gemini and GPT-5 struggle on AgentGym2 . |
| Outcome: | Experiments on 15 proprietary and open-source models show that even SOTA systems like Gemini and GPT-5 struggle on AgentGym2 . |
Aegis:An Advanced LLM-Based Multi-Agent for Intelligent Functional Safety Engineering (2024.emnlp-industry)
Copied to clipboard
| Challenge: | Aegis is an advanced LLM-based multi-agent for intelligent functional safety engineering that can perform all phases of a vehicle's lifecycle, including design, development, production, operation, and decommissioning. |
| Approach: | They introduce Aegis: An Advanced LLM-Based Multi-Agent for Intelligent Functional Safety Engineering. |
| Outcome: | The proposed solution can perform Hazard Analysis and Risk Assessment (HARA), document Functional Safety Requirements (FSR), and plan test cases for Automatic Emergency Braking (AEB) systems. |
LoRAMoE: Alleviating World Knowledge Forgetting in Large Language Models via MoE-Style Plugin (2024.acl-long)
Copied to clipboard
Shihan Dou, Enyu Zhou, Yan Liu, Songyang Gao, Wei Shen, Limao Xiong, Yuhao Zhou, Xiao Wang, Zhiheng Xi, Xiaoran Fan, Shiliang Pu, Jiang Zhu, Rui Zheng, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Experimental results show that, as the instruction data increases, LoRAMoE can significantly improve the ability to process downstream tasks, while maintaining the world knowledge stored in the LLM. |
| Approach: | They propose a framework that introduces several low-rank adapters and integrates them by using a router network to freeze the backbone model and force a portion of LoRAs to focus on leveraging world knowledge to solve downstream tasks. |
| Outcome: | The proposed framework freezes the backbone model and forces a portion of LoRAs to focus on leveraging world knowledge to solve downstream tasks, to alleviate world knowledge forgetting. |
Veri-R1: Toward Precise and Faithful Claim Verification via Online Reinforcement Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to online claim verification rely on prompt engineering or pre-designed reasoning workflows. |
| Approach: | They propose an online reinforcement learning framework that enables an LLM to interact with a search engine and receive reward signals that explicitly shape its planning, retrieval, and reasoning behaviors. |
| Outcome: | Empirical results show that Veri-R1 improves joint accuracy by 30% and doubles evidence score, often surpassing larger-scale model counterparts. |
Argue with Me Tersely: Towards Sentence-Level Counter-Argument Generation (2023.emnlp-main)
Copied to clipboard
Jiayu Lin, Rong Ye, Meng Han, Qi Zhang, Ruofei Lai, Xinyu Zhang, Zhao Cao, Xuanjing Huang, Zhongyu Wei
| Challenge: | Existing work describes paragraph-level counter-argument generation task as paragraph-based . however, sentence-level generation can be quite different due to its unique constraints and brevity-focused challenges. |
| Approach: | They propose a benchmark framework for sentence-level counter-argument generation . they use an annotated debate forum dataset to generate high-quality counter-argments . |
| Outcome: | The proposed framework and evaluator are competitive in counter-argument generation tasks. |
Decorrelate Irrelevant, Purify Relevant: Overcome Textual Spurious Correlations from a Feature Perspective (2022.coling-1)
Copied to clipboard
| Challenge: | Existing methods to debiase samples with biased features obstructs the model in learning from non-biased parts of the samples. |
| Approach: | They propose to eliminate spurious correlations in a fine-grained manner from a feature space perspective by using Random Fourier Features and weighted re-sampling to decorrelate dependencies between features. |
| Outcome: | The proposed method eliminates spurious correlations in a fine-grained manner from a feature space perspective. |
Text Fluoroscopy: Detecting LLM-Generated Text through Intrinsic Features (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) have revolutionized the field of natural language processing because of their excellent performance on various tasks. |
| Approach: | They propose a black-box method with better generalizability for detecting LLM-generated text by mining the intrinsic features of the text to be detected. |
| Outcome: | The proposed method achieves 7.36% and 2.84% improvement in detection performance compared to baselines in detecting texts from different domains generated by GPT-4 and Claude3 respectively. |
Enhancing Model Privacy in Federated Learning with Random Masking and Quantization (2025.findings-emnlp)
Copied to clipboard
Zhibo Xu, Zhu JianHao, Jingwen Xu, Changze Lv, Zhenghua Wang, Zisu Huang, Xiaohua Wang, Muling Wu, Qi Qian, Xiaoqing Zheng, Xuanjing Huang
| Challenge: | federated learning approaches are limited by the complexity of large language models and the need for specialized expertise to protect intellectual property. |
| Approach: | They propose a federated learning approach that leverages random masking to obscure a subnetwork of model parameters and applies quantization to the remaining parameters. |
| Outcome: | The proposed approach maintains strong model performance in federated learning settings and achieves enhanced protection of model parameters compared to baseline methods. |
EPO: Hierarchical LLM Agents with Environment Preference Optimization (2024.emnlp-main)
Copied to clipboard
| Challenge: | Long-horizon decision-making tasks require extensive planning over multiple steps, maintaining coherence and goal orientation, which is difficult for LLMs that are typically designed for more immediate and localized predictions. |
| Approach: | They propose a hierarchical framework that decomposes complex tasks into manageable subgoals, utilizing separate LLMs for subgoal prediction and low-level action generation. |
| Outcome: | The proposed framework achieves first place on the ALFRED public leaderboard and demonstrates its potential to improve long-horizon decision-making in diverse environments. |
Causal Intervention Improves Implicit Sentiment Analysis (2022.coling-1)
Copied to clipboard
| Challenge: | Existing neural models struggle with implicit sentiment analysis because they latch onto spurious correlations, resulting in poor generalization and robustness. |
| Approach: | They propose a CausaL intervention model for implicit sEntiment ANalysis using instrumental variable to eliminate confounding causal effects and extract the pure causal effect between sentence and sentiment. |
| Outcome: | The proposed model extracts the pure causal effect between sentence and sentiment using instrumental variable. |
TextMixer: Mixing Multiple Inputs for Privacy-Preserving Inference (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Pre-trained language models (PLMs) are often deployed as cloud services, enabling users to upload textual data and perform inference remotely. |
| Approach: | They propose a privacy-preserving inference framework called MixPi which aims to obfuscate a user's private input by mixing it with multiple other inputs. |
| Outcome: | The proposed framework surpasses existing privacy-preserving methods on token and sentence classification tasks. |
Figurative Language Processing: A Linguistically Informed Feature Analysis of the Behavior of Language Models and Humans (2023.findings-acl)
Copied to clipboard
| Challenge: | Recent years have witnessed a growing interest in investigating what Transformer-based language models (TLMs) actually learn from training data. |
| Approach: | They propose to use a black-box TLM and two intrinsically transparent white-box models to investigate the performance of figurative language models on sarcasm, similes, idioms, and metaphors. |
| Outcome: | The proposed models perform better than other models on figurative language classification tasks. |
Balancing Classification and Calibration Performance in Decision-Making LLMs via Calibration Aware Reinforcement Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) are increasingly deployed in decision-making tasks where accuracy and reliable confidence estimates are essential. |
| Approach: | They propose a calibration-aware reinforcement learning formulation that directly adjusts decision-token probabilities. |
| Outcome: | The proposed model preserves RLVR’s accuracy level while mitigating overconfidence, reducing ECE scores up to 9 points. |
Journey Before Destination: On the importance of Visual Faithfulness in Slow Thinking (2026.eacl-long)
Copied to clipboard
| Challenge: | Existing evaluations for visual hallucinations are narrow. |
| Approach: | They propose a framework that decomposes reasoning chains into perception versus reasoning steps and uses off-the-shelf VLM judges for step-level faithfulness. |
| Outcome: | The proposed framework reduces Unfaithful Perception Rate while preserving final-answer accuracy. |
TriEx: A Game-based Tri-View Framework for Explaining Internal Reasoning in Multi-Agent LLMs (2026.acl-long)
Copied to clipboard
| Challenge: | Existing explainability methods for large language models have been limited in capturing interaction-dependent belief dynamics and multi-agent reasoning. |
| Approach: | They propose a tri-view explainability framework that instruments sequential decision making with aligned artifacts. |
| Outcome: | The proposed framework enables analysis of explanation faithfulness, belief dynamics, and evaluator reliability, revealing systematic mismatches between what agents say, what they believe, and what they do. |
PubSE: A Hierarchical Model for Publication Extraction from Academic Homepages (D18-1)
Copied to clipboard
| Challenge: | Using a hierarchical model, we aim to extract all the publication strings from a researcher's homepage. |
| Approach: | They propose an end-to-end hierarchical model named PubSE based on Bi-LSTM-CRF and an alternating training method for training the model. |
| Outcome: | The proposed model outperforms the state-of-the-art models by 11.8% in F1-score on real data. |
Context-DPO: Aligning Language Models for Context-Faithfulness (2025.findings-acl)
Copied to clipboard
Baolong Bi, Shaohan Huang, Yiwei Wang, Tianchi Yang, Zihan Zhang, Haizhen Huang, Lingrui Mei, Junfeng Fang, Zehao Li, Furu Wei, Weiwei Deng, Feng Sun, Qi Zhang, Shenghua Liu
| Challenge: | Context-DPO is the first alignment method specifically designed to enhance contextfaithfulness for large language models. |
| Approach: | They propose a benchmark that simulates Retrieval-Augmented Generation scenarios with knowledge conflicts to evaluate context-faithfulness. |
| Outcome: | The proposed method improves LLMs' context-faithfulness by 35% to 280% over open-source models. |
MINER: Improving Out-of-Vocabulary Named Entity Recognition from an Information Theoretic Perspective (2022.acl-long)
Copied to clipboard
Xiao Wang, Shihan Dou, Limao Xiong, Yicheng Zou, Qi Zhang, Tao Gui, Liang Qiao, Zhanzhan Cheng, Xuanjing Huang
| Challenge: | Named Entity Recognition models are feature-engineering and machine learning based. |
| Approach: | They propose a new NER learning framework that uses entity mentions to improve model performance. |
| Outcome: | The proposed model achieves better performance on OOV entities on various settings and datasets. |
MicroC-KT: Modeling Community Effect via Learning Micro-Environment for Evidence-Grounded Explainable Knowledge Tracing (2026.acl-long)
Copied to clipboard
| Challenge: | Existing graph-based methods focus on exercise-concept relations, but lack the broader context of group references and contrastive evidence. |
| Approach: | They propose a framework that incorporates learning micro-environments to provide social-cognitive anchors for KT by extracting contrastive group evidence. |
| Outcome: | The proposed framework outperforms state-of-the-art models on four public datasets while providing more reliable and evidence-based explanations. |
TritonBench: Benchmarking Large Language Model Capabilities for Generating Triton Operators (2025.findings-acl)
Copied to clipboard
Jianling Li, ShangZhan Li, Zhenye Gao, Qi Shi, Yuxuan Li, Zefan Wang, Jiacheng Huang, WangHaojie WangHaojie, Jianrong Wang, Xu Han, Zhiyuan Liu, Maosong Sun
| Challenge: | Triton is a high-level Python-like programming language for building efficient GPU kernels. |
| Approach: | They propose a TritonBench benchmark that provides a comprehensive evaluation of Tritonic operators on widely deployed GPUs. |
| Outcome: | The proposed benchmarks show that current LLMs struggle to generate efficient Triton operators on widely deployed GPUs aligned with industry applications. |
Towards Building a Robust Toxicity Predictor (2023.acl-industry)
Copied to clipboard
| Challenge: | Recent studies have focused on robustness of toxicity language predictors, but this is problematic for real-world toxicity detection. |
| Approach: | They propose a novel adversarial attack that exploits greedy search strategies to fool toxic text classifiers. |
| Outcome: | The proposed attack can detect weaker toxicity language detectors even against unseen attacks. |
The Confidence Dichotomy: Analyzing and Mitigating Miscalibration in Tool-Use Agents (2026.acl-long)
Copied to clipboard
| Challenge: | a fundamental pillar of trustworthiness is calibration, which refers to an agent’s ability to express confidence that reliably reflects its actual performance. |
| Approach: | They propose a reinforcement learning framework that jointly optimizes task accuracy and calibration, supported by a holistic benchmark of reward designs. |
| Outcome: | The proposed framework improves calibration across tool types and shows that trained agents achieve superior calibration and exhibit robust generalization from local training environments to noisy web settings and to distinct domains such as mathematical reasoning. |
Debias NLU Datasets via Training-free Perturbations (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to debiase NLU models capture biased features that are independent of the task but spuriously correlated to labels. |
| Approach: | They propose a framework that conducts training-free perturbations on samples containing biased features to Debias NLU Datasets. |
| Outcome: | The proposed framework shows competitive performance with previous state-of-the-art debiasing strategies. |
To Answer or Not to Answer (TAONA): A Robust Textual Graph Understanding and Question Answering Approach (2025.findings-emnlp)
Copied to clipboard
Yuchen Yan, Aakash Kolekar, Sahika Genc, Wenju Xu, Edward W Huang, Anirudh Srinivasan, Mukesh Jain, Qi He, Hanghang Tong
| Challenge: | Existing studies assume that generated answers integrate all relevant information from the textual graph. |
| Approach: | They propose a novel GraphRAG model that integrates all relevant information from the textual graph into the generated answer. |
| Outcome: | Extensive experiments validate TAONA’s superior performance for both A-side and B-side tasks. |
Length Generalization of Causal Transformers without Position Encoding (2024.findings-acl)
Copied to clipboard
| Challenge: | Besides Transformers without position encodings, the success of NoPE provides a new way to overcome the challenge of generalizing to longer sentences. |
| Approach: | They propose a parameter-efficient tuning for searching attention heads’ best temperature hyper-parameters, which substantially expands NoPE’s context size. |
| Outcome: | The proposed tuning significantly expands NoPE's context size, allowing it to generalize to longer sentences with state-of-the-art generalization algorithms. |
VALU: A Benchmark for Video Anomaly Temporal Localization and Understanding at Multiple Semantic Levels (2026.acl-long)
Copied to clipboard
Yixiao He, Menghao Zhang, Haifeng Sun, Jing Wang, Kangheng Lin, Jinghan Wang, Chenye Xu, Pengfei Ren, Qi Qi, Jingyu Wang
| Challenge: | Recent advances in Video Large Language Models (Video-LLMs) enhance the ability of VAU models to describe and interpret anomalies. |
| Approach: | They propose a benchmark that explicitly defines anomalies across five semantic levels and provides detailed temporal boundaries and detailed textual descriptions for each. |
| Outcome: | The proposed benchmark defines anomalies across five semantic levels and provides detailed descriptions for each. |
I-AM-G: Interest Augmented Multimodal Generator for Item Personalization (2024.emnlp-main)
Copied to clipboard
| Challenge: | e-commerce and recommender systems lack a framework for personalized generation . a new framework extracts tags from multimodal information of items that the user has interacted with . |
| Approach: | They propose a framework that extracts tags from multimodal information and rewrites item description . they then use a decoupled text-to-text and image-to image retriever to search for similar item text . |
| Outcome: | The proposed framework can generate results aligned with user preferences . it can be used in e-commerce and recommender systems to win over diverse user base . |
Group, Extract and Aggregate: Summarizing a Large Amount of Finance News for Forex Movement Prediction (D19-51)
Copied to clipboard
| Challenge: | Existing studies on forex prediction ignore related text completely and focus on forex trade data only, which loses important semantic information. |
| Approach: | They propose a BERT-based Hierarchical Aggregation Model to summarize forex news . they group news from different aspects and extract the most crucial news in each group . |
| Outcome: | The proposed model outperforms baseline methods and grouping methods and summarizes the influence patterns for forex trading. |
Leveraging Entity Information for Cross-Modality Correlation Learning: The Entity-Guided Multimodal Summarization (2024.findings-acl)
Copied to clipboard
| Challenge: | Multimodal Summarization with Multimodal Output (MSMO) is a new approach to produce a multimodal summary that integrates both text and relevant images. |
| Approach: | They propose an Entity-Guided Multimodal Summarization model that integrates both text and relevant images to produce a multimodal summary. |
| Outcome: | The proposed model integrates text-image and entity-image information and refines image selection through knowledge distillation from a pre-trained vision-language model. |
MaCP: Minimal yet Mighty Adaptation via Hierarchical Cosine Projection (2025.acl-long)
Copied to clipboard
| Challenge: | MaCP is a new adaptation method for large foundation models that requires minimal parameters and memory for fine-tuning. |
| Approach: | They propose a method that exploits the superior energy compaction and decorrelation properties of cosine projection to improve model efficiency and accuracy. |
| Outcome: | The proposed method improves model efficiency and accuracy across a wide range of single-modality tasks including natural language understanding, natural language generation, text summarization, and multi-modalities such as image classification and video understanding. |
ULMR: Unlearning Large Language Models via Negative Response and Model Parameter Average (2024.emnlp-industry)
Copied to clipboard
| Challenge: | Large language models (LLMs) have attracted significant interest from the research community due to their broad applicability in many language-oriented tasks. |
| Approach: | They propose a framework which uses pre-training datasets to rewrite instructions and generate negative responses to preserve the performance of the original LLM. |
| Outcome: | The proposed framework can erase the pre-training data while maintaining the performance of the original model. |
A Lexicon-Based Graph Neural Network for Chinese NER (D19-1)
Copied to clipboard
| Challenge: | Chinese named entity recognition models are vulnerable to word ambiguities due to the lack of global semantics and chain structure. |
| Approach: | They propose a lexicon-based graph neural network with global semantics to solve word ambiguities in Chinese named entity recognition (NER) Lexicons are used to construct the graph and provide word-level features. |
| Outcome: | The proposed model improves on four NER datasets on Chinese characters, potential words, and the whole-sentence semantics. |
TurboFuzzLLM: Turbocharging Mutation-based Fuzzing for Effectively Jailbreaking Large Language Models in Practice (2025.naacl-industry)
Copied to clipboard
| Challenge: | Existing methods for jailbreaking large-language models are limited by their limitations . authors present a mutation-based fuzzing technique that generates effective jailbreaking templates . |
| Approach: | They propose a mutation-based fuzzing technique for efficiently finding effective jailbreaking templates that combine with harmful questions to generate harmful responses. |
| Outcome: | The proposed technique achieves 95% attack success rates on public datasets for leading LLMs . it also shows impressive generalizability to unseen harmful questions and improves model defenses to prompt attacks. |
Profiling-Free Mixed-Precision Quantization for MoE LLMs via Fuzzy Rule Interpolation (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models are scaling in size and capability, driving substantial computational and memory costs. |
| Approach: | They propose a mixed-precision quantization framework that uses fuzzy rule interpolation to predict quantization error from only sparse samples. |
| Outcome: | The proposed framework accelerates the profiling phase by up to 15.7 on DeepSeek-V2 while achieving comparable or slightly superior zero-shot accuracy. |
From Superficial to Deep: Integrating External Knowledge for Follow-up Question Generation Using Knowledge Graph and LLM (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods for generating follow-up questions are limited to shallow contextual questions that are uninspiring and have a large gap to the human level. |
| Approach: | They propose a three-stage external knowledge-enhanced follow-up question generation method which generates questions by identifying contextual topics, building a knowledge graph online, and finally combining these with a large language model to generate the final question. |
| Outcome: | The proposed method generates questions by identifying contextual topics, building a knowledge graph (KG) online, and finally combining these with a large language model to generate the final question. |
Facet-Aware Evaluation for Extractive Summarization (2020.acl-main)
Copied to clipboard
| Challenge: | lexical overlap is a common evaluation metric for extractive summarization, but recent studies reveal its limitations. |
| Approach: | They propose a facet-aware evaluation setup for better assessment of information coverage in extractive summaries. |
| Outcome: | The proposed evaluation setup improves human correlation with extractive summarization datasets and improves comparative analysis. |
Unleashing the Power of Language Models in Text-Attributed Graph (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies on graph learning on text-attributed graphs have been limited by memory cost and underutilization of relationships between nodes and words. |
| Approach: | They propose a Node Representation Update Pre-training Architecture based on Co-modeling text and graph to learn representations of papers and words simultaneously. |
| Outcome: | The proposed model outperforms baselines on the ogbn-arxiv benchmark dataset. |
Uncertainty Guided Label Denoising for Document-level Distant Relation Extraction (2023.acl-long)
Copied to clipboard
| Challenge: | Document-level relation extraction (DocRE) aims to extract semantic relations between entities in a document. |
| Approach: | They propose a Document-level distant relation extraction framework with unreliable pseudo labels to denoise DS data. |
| Outcome: | The proposed framework outperforms strong baselines on two public datasets. |
Benchmarking Commercial Intent Detection Services with Practice-Driven Evaluations (2021.naacl-industry)
Copied to clipboard
| Challenge: | Intent detection models require large amounts of labeled data to achieve high accuracy, and in practical scenarios it is more common to find small, unbalanced, and noisy datasets. |
| Approach: | They benchmark intent detection methods on a variety of datasets and found that Watson Assistant's model outperforms other commercial solutions. |
| Outcome: | The proposed model outperforms pretrained language models on a variety of datasets while requiring only a fraction of computational resources and training data. |
On LLM-Based Scientific Inductive Reasoning Beyond Equations (2025.emnlp-main)
Copied to clipboard
Brian S. Lin, Jiaxin Yuan, Zihan Zhou, Shouli Wang, Shuo Wang, Cunliang Kong, Qi Shi, Yuxuan Li, Liner Yang, Zhiyuan Liu, Maosong Sun
| Challenge: | Existing research on inductive reasoning models emphasizes rule design without grounding them in specific scenarios. |
| Approach: | They propose to use LLMs to learn underlying patterns from limited examples in entirely new environments. |
| Outcome: | The proposed benchmark evaluates the inductive reasoning abilities of large language models in scientific settings. |
Aggregating Bidirectional Encoder Representations Using MatchLSTM for Sequence Matching (D19-1)
Copied to clipboard
| Challenge: | Recent work on text sequence matching tasks uses task specific supervised datasets, which are always limited to the amount due to the cost of annotation. |
| Approach: | They propose an aggregation method to combine Bidirectional Encoder Representations from Transformer (BERT) with a MatchLSTM layer for Sequence Matching. |
| Outcome: | The proposed model improves on two publicly available datasets, WikiQA and SNLI. |
MDR: Model-Specific Demonstration Retrieval at Inference Time for In-Context Learning (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing methods for retrieval-based in-context learning ignore model biases and fail to retrieve the most appropriate demonstrations for different LLMs. |
| Approach: | They propose a model-specific demonstration retrieval method that considers the biases of different LLMs at inference time. |
| Outcome: | The proposed method improves performance on seen and unseen tasks with multi-scale inference LLMs by up to 41.2%. |
Structural Patent Classification Using Label Hierarchy Optimization (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for patent classification ignore key technical content claims and citation relationships . existing methods treat labels as independent targets, failing to exploit semantic and structural information within the label taxonomy. |
| Approach: | They propose a Claim Structure based Patent Classification model with Label Awareness . structural graph learning is used to mine the internal logic of patent claims . |
| Outcome: | The proposed method is more effective than state-of-the-art classification models. |
Entailment-Preserving First-order Logic Representations in Natural Language Entailment (2025.acl-long)
Copied to clipboard
| Challenge: | First-order logic (FOL) is often used to represent logical entailment, but determining natural language (NL) enanglement using FOL remains a challenge. |
| Approach: | They propose an Entailment-Preserving FOL representations task and a method which trains an NL-to-FOL translator by using the natural language entailment labels as verifiable rewards. |
| Outcome: | The proposed method achieves 1.8–2.7% improvement in EPR and 17.4–20.6% increase in E PR@16 compared to baselines in three datasets. |
ClusterAttn: KV Cache Compression under Intrinsic Attention Clustering (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for sparse attention apply the same pattern across different attention heads and inputs, but fail to capture the intrinsic attention clustering in large language models. |
| Approach: | They propose a training-free sparse attention method that provides an efficient prompt cache compression scheme under intrinsic attention clustering for efficient LLM inference. |
| Outcome: | The proposed method reduces memory usage by 10%–65% and increases throughput by 2.6–4.8 times with no accuracy loss. |
C-World: A Computer Use Agent Environment Creator (2026.acl-long)
Copied to clipboard
Ziqiao Xi, Shuang Liang, Qi Liu, Jiaqing Zhang, Letian Peng, Fang Nan, Meshal Nayim, Tianhui Zhang, Rishika Mundada, Lianhui Qin, Biwei Huang, Kun Zhou
| Challenge: | C-World enables users to build agent environments on demand. |
| Approach: | They propose a system that enables users to build agent environments on demand. |
| Outcome: | The proposed system outperforms baselines on 119k samples and achieves Spearman = 0.883 ranking correlation with real execution. |
MAIN: Mutual Alignment Is Necessary for instruction tuning (2025.emnlp-main)
Copied to clipboard
Fanyi Yang, Jianfeng Liu, Xin Zhang, Haoyu Liu, Xixin Cao, Yuefeng Zhan, Hao Sun, Weiwei Deng, Feng Sun, Qi Zhang
| Challenge: | Instruction tuning has enabled large language models to achieve remarkable performance, yet its success heavily depends on the availability of high-quality instruction-response pairs. |
| Approach: | They propose a mutual alignment framework which enforces coherence between instructions and responses through mutual constraints. |
| Outcome: | The proposed framework generalizes well across model architectures and sizes, achieving state-of-the-art performance on LLaMA, Mistral, and Qwen models across diverse benchmarks. |
Discourse Heuristics For Paradoxically Moral Self-Correction (2025.findings-emnlp)
Copied to clipboard
| Challenge: | moral self-correction is a promising approach for aligning output of Large Language Models with human moral values . authors show that moral self correction relies on discourse constructions that reflect heuristic shortcuts . |
| Approach: | a new method is proposed to strengthen moral self-correction using heuristics extracted from curated datasets. |
| Outcome: | a new method to strengthen moral self-correction is proposed . the proposed method is based on heuristics extracted from curated datasets. |
One Battle After Another: Probing LLMs’ Limits on Multi-Turn Instruction Following with a Benchmark Evolving Framework (2026.acl-long)
Copied to clipboard
| Challenge: | Existing benchmarks for instruction-following in multi-topic dialogues are limited to a fixed number of turns, susceptible to saturation and failing to account for users’ interactive experience. |
| Approach: | They propose a framework featuring a three-layer tracking mechanism and a query synthesis agent to mimic sequential user behaviors. |
| Outcome: | The proposed framework outperforms existing benchmarks in the evaluation of instruction following in multi-topic dialogues and demonstrates deficiencies in failure recovery and fine-grained instruction following. |
Weighed Domain-Invariant Representation Learning for Cross-domain Sentiment Analysis (2020.coling-main)
Copied to clipboard
| Challenge: | Cross-domain sentiment analysis is a hot topic in research and industry . domain-invariant representation learning (DIRL) is used to learn a feature representation across domains . but, when label distribution P(Y) shifts across domain, it degrades performance . |
| Approach: | They propose a domain-invariant representation learning framework to improve cross-domain sentiment analysis performance. |
| Outcome: | The proposed model is easy to transfer existing models to the proposed model. |
VLM Is a Strong Reranker: Advancing Multimodal Retrieval-augmented Generation via Knowledge-enhanced Reranking and Noise-injected Training (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a significant drawback of Vision-language Models is their reliance on static training data, leading to outdated information and limited contextual awareness. |
| Approach: | They propose a framework with knowledge-enhanced reranking and noise-injected training to improve the VLM's ranking ability. |
| Outcome: | The proposed framework is based on a simple yet effective instruction template and is able to induce its ranking ability and serve it as a reranker to precisely filter the top-k retrieved images. |
Pass off Fish Eyes for Pearls: Attacking Model Selection of Pre-trained Models (2022.acl-long)
Copied to clipboard
| Challenge: | Existing feature-based model selection methods are vulnerable to fine-tuning and are not reliable indicators for the PTM’s transferability. |
| Approach: | They propose feature-based model selection methods which assess PTMs’ transferability to a specific task in a fast way without fine-tuning. |
| Outcome: | The proposed methods can make FMS mistakenly judge transferability of models and can be combined with the backdoor attack to misguide the FMS to select poisoned models. |
GeAR: Graph-enhanced Agent for Retrieval-augmented Generation (2025.findings-acl)
Copied to clipboard
Zhili Shen, Chenxin Diao, Pavlos Vougiouklis, Pascual Merita, Shriram Piramanayagam, Enting Chen, Damien Graux, Andre Melo, Ruofei Lai, Zeren Jiang, Zhongyang Li, Ye Qi, Yang Ren, Dandan Tu, Jeff Z. Pan
| Challenge: | Retrieval-augmented Generation (RAG) relies on effective retrieval capabilities, yet traditional sparse and dense retrievers struggle with multi-hop retrieval scenarios. |
| Approach: | They propose a graph expansion mechanism that augments any conventional base retriever and an agent framework that incorporates the resulting graph-based retrieval into a multi-step retrieval framework. |
| Outcome: | The proposed system achieves state-of-the-art results on three multi-hop question answering datasets while consuming fewer tokens and requiring fewer iterations than existing multi-step retrieval systems. |
Exploring the Compositional Deficiency of Large Language Models in Mathematical Reasoning Through Trap Problems (2024.emnlp-main)
Copied to clipboard
| Challenge: | Current LLMs lack systematic compositionality, and therefore cannot serve as reliable cognitive models. |
| Approach: | They propose to introduce logical traps into the original problems of MATH and GSM8K to investigate the compositionality of large language models in mathematical reasoning. |
| Outcome: | The proposed model can generate infinite combinations from finite learned components. |
Improving Discriminative Capability of Reward Models in RLHF Using Contrastive Learning (2024.emnlp-main)
Copied to clipboard
Lu Chen, Rui Zheng, Binghai Wang, Senjie Jin, Caishuang Huang, Junjie Ye, Zhihao Zhang, Yuhao Zhou, Zhiheng Xi, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Current methods rely on ranking losses to teach reward model to assess preferences, but they are susceptible to noise and ambiguous data, often failing to deeply understand human intentions. |
| Approach: | They propose a method that incorporates contrastive learning into the reward modeling process to enhance generalization and stabilize the reinforcement learning training process. |
| Outcome: | The proposed method enhances generalization of the reward model, stabilizes the reinforcement learning training process, and improves the final alignment with human preferences. |
Bit-Flip Error Resilience in LLMs: A Comprehensive Analysis and Defense Framework (2025.emnlp-main)
Copied to clipboard
Yuhang Chen, Zhen Tan, Ajay Kumar Jaiswal, Huaizhi Qu, Xinyu Zhao, Qi Lin, Yu Cheng, Andrew Kwong, Zhichao Cao, Tianlong Chen
| Challenge: | Bit-flip errors (BFEs) are hardware faults where individual bits in memory or processing units are unintentionally flipped. |
| Approach: | They propose a novel defense strategy to mitigate bit-flip errors (BFEs) they propose bfe protection and a self-correction mechanism to minimize performance degradation . |
| Outcome: | The proposed defense strategy minimizes performance degradation while significantly improving robustness against BFEs. |
UFO: A UI-Focused Agent for Windows OS Interaction (2025.naacl-long)
Copied to clipboard
Chaoyun Zhang, Liqun Li, Shilin He, Xu Zhang, Bo Qiao, Si Qin, Minghua Ma, Yu Kang, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang, Qi Zhang
| Challenge: | UFO is a UI-Fcused agent designed to fulfill user requests tailored to Windows OS applications . it decomposes user requests using divide-and-conquer approach, enabling seamless navigation and addressing sub-tasks across multiple applications. |
| Approach: | They propose a UI-Fcused Windows OS agent that decomposes user requests using a divide-and-conquer approach and incorporates a control interaction module tailored for Windows OS. |
| Outcome: | The proposed agent decomposes user requests using divide-and-conquer approach, enabling seamless navigation and addressing sub-tasks across multiple applications. |
MIKE: A New Benchmark for Fine-grained Multimodal Entity Knowledge Editing (2024.findings-acl)
Copied to clipboard
Jiaqi Li, Miaozeng Du, Chuanyi Zhang, Yongrui Chen, Nan Hu, Guilin Qi, Haiyun Jiang, Siyuan Cheng, Bozhong Tian
| Challenge: | Current benchmarks focus on coarse-grained knowledge, leaving the intricacies of fine-grounded knowledge unexplored. |
| Approach: | They propose a benchmark and dataset specifically designed for FG multimodal entity knowledge editing. |
| Outcome: | The proposed benchmark underscoring the complexity of FG knowledge editing in MLLMs. |
From Local to Global: Revisiting Structured Pruning Paradigms for Large Language Models (2026.acl-long)
Copied to clipboard
Ziyan Wang, Enmao Diao, Qi Le, Pu Wang, Minwoo Lee, Shu-ping Yeh, Evgeny Stupachenko, Hao Feng, Li Yang
| Challenge: | Structured pruning is a practical approach to deploying large language models (LLMs) but it fails to capitalize on modest task-specific calibration signals, causing limited downstream gains. |
| Approach: | They propose a method that removes attention heads and MLP channels using loss-based important scores . they use perplexity for language modeling and a margin-based objective for decision-style tasks . |
| Outcome: | The proposed method lowers perplexity and improves accuracy at higher sparsity . it also stabilizes accuracy and mitigates perxity collapse without fine-tuning . |
FaithLens: Detecting and Explaining Faithfulness Hallucination (2026.findings-acl)
Copied to clipboard
Shuzheng Si, Qingyi Wang, Haozhe Zhao, Yuzhuo Bai, Guanqiao Chen, Kangyang Luo, Gang Chen, Fanchao Qi, Minjia Zhang, Baobao Chang, Maosong Sun
| Challenge: | Recent progress in large language models (LLMs) has revolutionized text generation. |
| Approach: | They propose a faithfulness hallucination detection model that can provide binary predictions and corresponding explanations to improve trustworthiness. |
| Outcome: | The proposed model outperforms advanced models on 12 diverse tasks. |
Making Revisions Understandable: A Survey of Edit Intentions, Methods, and Applications (2026.findings-acl)
Copied to clipboard
| Challenge: | Text revision is a core process in document creation, capturing how authors iteratively refine, reorganize, and improve written content. |
| Approach: | They synthesize text revision research through the lens of edit intentions . they review prior work across the revision workflow including corpus construction, edit intention taxonomies, edit intentions, and edit intention identification. |
| Outcome: | The proposed approach synthesizes datasets, taxonomies, identification methods, and applications and highlights key open research directions. |
Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models (2026.findings-acl)
Copied to clipboard
Hengyuan Zhang, Zhihao Zhang, Ercong Nie, Mingyang Wang, Zunhai Su, Yiwei Wang, Qianli Wang, Shuzhou Yuan, Xufeng Duan, Qibo Xue, Zeping Yu, Chenming Shang, Xiao Liang, Jing Xiong, Hui Shen, Chaofan Tao, Zhengwu Liu, Senjie Jin, Zhiheng Xi, Dongdong Zhang, Sophia Ananiadou, Tao Gui, Ruobing Xie, Hayden Kwok-Hay So, Hinrich Schuetze, Xuanjing Huang, Qi Zhang, Ngai Wong
| Challenge: | Existing literature on mechanistic interpretation (MI) treats it as an observational science, leaving practical applications underexplored. |
| Approach: | They propose a survey structured around the pipeline to identify and improve MI models. |
| Outcome: | The proposed framework enables tangible improvements in Alignment, Capability, and Efficiency. |
DI-BENCH: Benchmarking Large Language Models on Dependency Inference with Testable Repositories at Scale (2025.findings-acl)
Copied to clipboard
Linghao Zhang, Junhao Wang, Shilin He, Chaoyun Zhang, Yu Kang, Bowen Li, Jiaheng Wen, Chengxing Xie, Maoquan Wang, Yufan Huang, Elsie Nallipogu, Qingwei Lin, Yingnong Dang, Saravan Rajmohan, Dongmei Zhang, Qi Zhang
| Challenge: | Existing studies highlight that dependency-related issues cause over 40% of observed runtime errors on the generated repository. |
| Approach: | They propose a large-scale benchmark and evaluation framework specifically designed to assess LLMs’ capability on dependency inference. |
| Outcome: | The proposed model achieves only a 48% execution pass rate on Python, indicating room for improvement. |
Auto-Dialabel: Labeling Dialogue Data with Unsupervised Learning (D18-1)
Copied to clipboard
| Challenge: | Existing dialog datasets rely on human labeling, which is expensive, limited in size, and in low coverage. |
| Approach: | They propose a framework to automatically cluster dialogue intents and slots . they collect context features, leverage an autoencoder for feature assembly, and adapt a dynamic hierarchical clustering method for intent and slot labeling. |
| Outcome: | The proposed framework can promote human labeling cost to a great extent and achieve good intent clustering accuracy (84.1%) it also provides reasonable and instructive slot labeling results. |
Revealing and Enhancing Core Visual Regions: Harnessing Internal Attention Dynamics for Hallucination Mitigation in LVLMs (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing training-free methods are vulnerable to the attention sink phenomenon . Existing methods include contrastive decoding and auxiliary expert models . |
| Approach: | They propose a training-free attention intervention that constructs a PAD map to identify semantically core visual regions and applies per-head Median Absolute Deviation Scaling to adaptively control the intervention strength. |
| Outcome: | The proposed intervention improves visual grounding and reduces hallucinations on multiple LVLMs and benchmarks. |
Code-Switching Information Retrieval: Benchmarks, Analysis, and the Limits of Current Retrievers (2026.findings-acl)
Copied to clipboard
Qingcheng Zeng, Yuheng Lu, Zeqi Zhou, Heli Qi, Puxuan Yu, Fuheng Zhao, Hitomi Yanaka, Weihao Xuan, Naoto Yokoya
| Challenge: | a new study examines the performance of code-switching IR in monolingual contexts . code-witching is a pervasive linguistic phenomenon in global communication . |
| Approach: | They propose a benchmark to evaluate code-switching IR in monolingual contexts . they propose CS-MTEB, which measures performance declines of up to 27% . |
| Outcome: | The proposed benchmark shows that code-switching performance is degraded by 27% . the proposed benchmark is based on a dataset of mixed-language queries . |
Modeling Aspect Correlation for Aspect-based Sentiment Analysis via Recurrent Inverse Learning Guidance (2022.coling-1)
Copied to clipboard
| Challenge: | Existing methods to learn complex sentence with multiple aspects do not consider correlation between aspects to distinguish overlapped feature. |
| Approach: | They propose a method that uses aspect correlation to improve aspect correlation modeling . they use Recurrent Mechanism to improve the joint representation of aspects . |
| Outcome: | The proposed method is state-of-the-art in multiaspect scenarios. |
Governance in Motion: Co-evolution of Constitutions and AI models for Scalable Safety (2025.emnlp-main)
Copied to clipboard
Chenhao Huang, Ziyu Shen, Yicong Ren, Huiyuan Zheng, Jiazheng Zhang, Mingxu Chai, Ming Zhang, Shihan Dou, Fan Mo, Jie Shi, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing approaches to align large language models with human preferences lack flexibility . static alignment preferences lack the ability to correct misaligned behaviors as they emerge . |
| Approach: | They propose a framework that enables dynamic and continuous alignment of large language models with human preferences. |
| Outcome: | The proposed framework improves safety and accuracy of a 7B model with human annotations. |
Grouped-Attention for Content-Selection and Content-Plan Generation (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Recent neural data-to-text generation models explicitly learn content-plan given a set of attributes as input. |
| Approach: | They propose a neural content-planner that captures local and global contexts . they use a token-level attention constrained within each input attribute . |
| Outcome: | The proposed model outperforms competitors by 4.92%, 4.70%, and 16.56% on real-world datasets. |
Two Heads Are Better Than One: Improving Fake News Video Detection by Correlating with Neighbors (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing frameworks for detecting fake news videos are limited . a new approach is proposed to integrate neighborhood information of new videos . |
| Approach: | They propose a framework for automatically detecting fake news videos . it integrates neighborhood relationship of new videos belonging to same event . |
| Outcome: | The proposed framework improves performance of existing detectors and graph aggregation and debunking rectification modules. |
Granular Entity Mapper: Advancing Fine-grained Multimodal Named Entity Recognition and Grounding (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for fine-grained content extraction are limited by long-tailed distribution of textual entity categories and performance of object detectors. |
| Approach: | They propose a multi-granularity entity recognition module and a reranking module to integrate hierarchical information of entity categories, visual cues, and external textual resources collectively. |
| Outcome: | The proposed framework achieves state-of-the-art on the fine-grained content extraction task. |
SOTOPIA-π: Interactive Learning of Socially Intelligent Language Agents (2024.acl-long)
Copied to clipboard
Ruiyi Wang, Haofei Yu, Wenxin Zhang, Zhengyang Qi, Maarten Sap, Yonatan Bisk, Graham Neubig, Hao Zhu
| Challenge: | Existing studies on building language agents have not addressed this social learning gap. |
| Approach: | They propose an interactive learning method that improves the social intelligence of language agents by using behavior cloning and self-reinforcement based training on filtered social interaction data. |
| Outcome: | The proposed method allows a 7B LLM to reach the social goal completion ability of an expert model (GPT-4-based agent) without the loss of more generic abilities, such as the ability to answer knowledge-based questions. |
A Web Scale Entity Extraction System (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing systems for large-scale entity extraction are limited by the scale and variety of data available on internet platforms. |
| Approach: | They propose to build an entity extraction system for multiple document types at large scale using multi-modal Transformers. |
| Outcome: | The proposed system extracts multiple types of entities from multiple document types at large scale using multi-modal Transformers. |
KARL: Reinforcement Learning for LLM Agents on Multi-Turn Knowledge-Intensive Agentic Tasks (2026.acl-long)
Copied to clipboard
Xueqiao Sun, Xiao Liu, Bowen Lv, Hanchen Zhang, Bohao Jing, Zehan Qi, Yifan Xu, Yuxiao Dong, Jie Tang
| Challenge: | Large Language Models have shown remarkable potential as autonomous agents, but their effectiveness in knowledge-intensive tasks remains limited by passive knowledge utilization. |
| Approach: | They propose a framework that enables LLM agents to dynamically explore structured knowledge sources through multi-turn interactions. |
| Outcome: | The proposed framework outperforms existing retrieval-augmented approaches on knowledge graph and database tasks while maximizing tool-use behaviors end-to-end. |
PreP-OCR: A Complete Pipeline for Document Image Restoration and Enhanced OCR Accuracy (2025.acl-long)
Copied to clipboard
| Challenge: | Existing pipelines that combine document image restoration with semantic-aware post-OCR correction can improve text extraction from degraded images. |
| Approach: | They propose a two-stage pipeline that combines document image restoration with semantic-aware post-OCR correction to enhance both visual clarity and textual consistency. |
| Outcome: | The proposed pipeline reduces character error rates by 63.9-70.3% on 13,831 pages of real historical documents in English, French, and Spanish compared to OCR on raw images. |
Hybrid Hierarchical Retrieval for Open-Domain Question Answering (2023.findings-acl)
Copied to clipboard
| Challenge: | Recent work shows that dense hierarchical retrieval (DHR) can outperform dense passage retrieval. |
| Approach: | They propose a framework that applies sparse, dense and a combination of them to document and passage retrieval. |
| Outcome: | The proposed framework can outperform dense hierarchical retrieval (DHR) and sparse retrievers (BM25) on open-domain question answering (ODQA) datasets with an average improvement of 4.69% on recall@100 over DHR. |
ProofInfer: Generating Proof via Iterative Hierarchical Inference (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing proof generation models focus on generating several proof paths instead of a whole tree. |
| Approach: | They propose a method that generates the proof tree via iterative hierarchical inference . they propose coding the proof as plain text without losing structure information . |
| Outcome: | The proposed proof generation model significantly improves performance on widely-used datasets. |
How Helpful is Inverse Reinforcement Learning for Table-to-Text Generation? (2021.acl-short)
Copied to clipboard
| Challenge: | Existing approaches to Table-to-Text generation suffer from issues such as missing information, repetition and repetition. |
| Approach: | They propose to use Inverse Reinforcement Learning (IRL) to solve the Table-to-Text task . they use multiple interpretable unsupervised reward components that are combined linearly to form a composite reward function. |
| Outcome: | The proposed task outperforms strong RL baselines marginally in the Table-to-Text task. |
Uni-FedRec: A Unified Privacy-Preserving News Recommendation Framework for Model Training and Online Serving (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing news recommendation methods rely on user behavior data to model user interests and user interests. |
| Approach: | They propose a unified news recommendation framework that uses user data locally stored in user clients to train models and serve users in a privacy-preserving way. |
| Outcome: | The proposed framework outperforms baseline methods and effectively protects user privacy. |
ConKI: Contrastive Knowledge Injection for Multimodal Sentiment Analysis (2023.findings-acl)
Copied to clipboard
Yakun Yu, Mingjun Zhao, Shi-ang Qi, Feiran Sun, Baoxun Wang, Weidong Guo, Xiaoli Wang, Lei Yang, Di Niu
| Challenge: | Existing methods for multimodal sentiment analysis focus on general knowledge, which is inadequate to identify specific sentiments across modalities. |
| Approach: | They propose a method where specific-knowledge representations for each modality can be learned together with general knowledge representations via knowledge injection based on an adapter architecture. |
| Outcome: | The proposed method outperforms all prior methods on three popular benchmarks on multimodal sentiment analysis metrics. |
Preserving Knowledge Invariance: Rethinking Robustness Evaluation of Open Information Extraction (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing evaluation benchmarks focus on pairwise matching, ignoring robustness . current models exhibit frustrating degradation, with a maximum drop of 23.43 F1 score . |
| Approach: | They propose a benchmark that simulates the evaluation of open information extraction models in the real world . they perform experiments on typical models published in the last decade and a representative large language model . |
| Outcome: | The proposed model is rated robust on a knowledge-invariant clique with different syntactic and expressive forms. |
CLEAR: A Framework Enabling Large Language Models to Discern Confusing Legal Paragraphs (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing work focuses on enabling LLMs to leverage legal rules to tackle complex legal reasoning tasks, but ignores their ability to understand legal rules. |
| Approach: | They propose a legal paragraph prediction task that aims to predict the legal paragraph given criminal facts and a framework CLEAR to enhance their legal reasoning ability. |
| Outcome: | The proposed model improves the ability of LLMs to analyze legal cases with the guidance of legal rule insights. |
Logical DA: Enhancing Data Augmentation for Logical Reasoning via a Multi-Agent System (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing data augmentation paradigms isolate data synthesis from label validation, thereby reducing their utility for complex reasoning tasks. |
| Approach: | They propose a framework for enhancing reasoning-focused data augmentation in few-shot learning scenarios that integrates four agents through two synergistic phases: diverse data generation and label verification. |
| Outcome: | The proposed framework achieves the highest average improvement in task accuracy in both fine-tuning and in-context learning paradigms. |
Inductive Relation Inference of Knowledge Graph Enhanced by Ontology Information (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to inference knowledge graphs lack ontology information, which is often too sparse. |
| Approach: | They propose a knowledge graph inductive inference method that fuses ontology information to learn the semantic information of entities. |
| Outcome: | The proposed method outperforms large language models like ChatGPT on two benchmark datasets and improves the MRR metrics by 15.4% and 44.1%, respectively. |
DARM: Distribution-Aware Reward Modeling by Alleviating Biases from Low Preference-Context Dependency Data (2026.acl-long)
Copied to clipboard
Shaofan Liu, Guoqiang Zhang, Shihan Dou, Huiyuan Zheng, Yiming Zhou, Junjie Ye, Shaowen Wang, Shichun Liu, Jiazheng Zhang, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing methods for training reward models are vulnerable to context neglect and degraded accuracy. |
| Approach: | They propose distribution-aware reward modeling that augments the RM objective with a conditional mutual information regularizer that maximizes context and the predicted reward conditioned on the response. |
| Outcome: | The proposed model improves performance in RLHF and improves accuracy in other settings. |
SGPVT: Self-Generated Proximal Visual Tokens for Mitigating Proximal Collateral Damage in MLLM Unlearning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches focus on general utility metrics, overlooking the preservation of semantically related concepts. |
| Approach: | They propose a method that introduces self-generated proximal visual tokens to prevent forgetting vulnerability. |
| Outcome: | The proposed framework outperforms existing methods in preserving semantically related concepts while achieving effective target unlearning. |
CHisIEC: An Information Extraction Corpus for Ancient Chinese History (2024.lrec-main)
Copied to clipboard
| Challenge: | Historical and cultural heritage preservation is an important branch of digital humanities, where the rich tapestry of the past meets the cutting-edge tools of the digital age. |
| Approach: | They present a dataset to evaluate NER and RE tasks in ancient Chinese history . they use four distinct entity types and twelve relation types to identify them . |
| Outcome: | The "Chinese Historical Information Extraction Corpus" is a dataset from 13 dynasties spanning over 1830 years . the dataset encompasses four distinct entity types and twelve relation types . |
Context Reasoner: Incentivizing Reasoning Capability for Contextualized Privacy and Safety Compliance via Reinforcement Learning (2025.emnlp-main)
Copied to clipboard
Wenbin Hu, Haoran Li, Huihao Jing, Qi Hu, Ziqian Zeng, Sirui Han, Xu Heli, Tianshu Chu, Peizhao Hu, Yangqiu Song
| Challenge: | Current mitigation strategies fail to preserve contextual reasoning capabilities in risky scenarios, leading to systemic risks for legal compliance. |
| Approach: | They propose to use reinforcement learning with a rule-based reward to incentivize contextual reasoning capabilities while enhancing compliance with safety and privacy norms. |
| Outcome: | The proposed model outperforms Qwen2.5-7B-Instruct model in safety and privacy benchmarks and achieves +8.58% accuracy improvement. |
Knowledge-enriched, Type-constrained and Grammar-guided Question Generation over Knowledge Bases (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods for question generation over knowledge bases have low diversity and poor fluency due to the limited information contained in the subgraphs and semantic drift due to decoder’s oblivion of the semantics of the answer entity. |
| Approach: | They propose a knowledge-enriched, type-constrained and grammar-guided KBQG model that generates natural-language questions over a set of triples in the KB. |
| Outcome: | The proposed model outperforms existing methods on two widely-used benchmark datasets. |
Textual Backdoor Attacks Can Be More Harmful via Two Simple Tricks (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing textual backdoor attacks are vulnerable to backdoors . researchers add extra training task to distinguish poisoned and clean data . |
| Approach: | They propose two tricks that make existing backdoor attacks much more harmful . first trick is to add an extra task to distinguish poisoned and clean data . second trick is using all the clean training data rather than the original clean data. |
| Outcome: | The proposed tricks can significantly improve attack performance in three tough situations including clean data fine-tuning, low-poisoning-rate, and label-consistent attacks. |
CoGenesis: A Framework Collaborating Large and Small Language Models for Secure Context-Aware Instruction Following (2024.acl-long)
Copied to clipboard
| Challenge: | Large-scale language models (LLMs) are increasingly exposed to private data and are becoming more and more prevalent. |
| Approach: | They propose a collaborative generation framework that integrates large and small language models to address privacy concerns logically. |
| Outcome: | The proposed framework combines large and small models to address privacy concerns logically. |
LongTutor: Benchmarking Large Language Models for Long-term Personalized Tutoring (2026.acl-long)
Copied to clipboard
| Challenge: | Existing evaluations focus on isolated, short-term interactions, overlooking the inherently long-term nature of learning. |
| Approach: | They propose a benchmark for long-term personalized tutoring based on an annotated learning log . they propose an automated generator–verifier pipeline to enable benchmark expansion . |
| Outcome: | The proposed benchmarks evaluate LLMs across three progressive tasks: evidence acquisition, knowledge state diagnosis, and adaptive teaching action. |
NOVER: Incentive Training for Language Models via Verifier-Free Reinforcement Learning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in reinforcement learning, such as DeepSeek R1-Zero, highlight the effectiveness of incentive training, but these methods rely on external verifiers, which limits their applicability to domains like mathematics and coding, where such verifier is readily available. |
| Approach: | They propose a general reinforcement learning framework that requires only standard supervised fine-tuning data with no need for an external verifier. |
| Outcome: | The proposed framework outperforms the model of the same size distilled from large reasoning models such as DeepSeek R1 671B by 7.7%. |
The Mirage of Model Editing: Revisiting Evaluation in the Wild (2025.acl-long)
Copied to clipboard
| Challenge: | despite near-perfect results, effectiveness of model editing in real-world applications remains unclear. |
| Approach: | They propose QAEdit and WILD to better reflect real-world use of model editing . they propose a benchmark aligned with widely used question answering datasets and a task-agnostic evaluation framework . |
| Outcome: | The proposed QAEdit benchmark and WILD evaluation framework show that current models perform worse than previously reported. |
Adaptive Preference Optimization with Uncertainty-aware Utility Anchor (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Offline preference optimization methods are efficient for large language models (LLMs) alignment. |
| Approach: | They propose an offline preference optimization framework that estimates uncertainties from preference data . the method enables training even in scenarios where the data is unpaired . |
| Outcome: | The proposed method enables training even in scenarios where the data is unpaired . |
BeSimulator: A Large Language Model Powered Text-based Behavior Simulator (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing robot simulators focus on physical process modeling and realistic rendering, resulting in high computational costs and limited adaptability. |
| Approach: | They propose a modular and novel LLM-powered framework to analyze and validate robot behaviors in text-based environments. |
| Outcome: | The proposed framework can generalize across scenarios and achieve long-horizon complex simulation. |
Self-Error-Instruct: Generalizing from Errors for LLMs Mathematical Reasoning (2025.acl-long)
Copied to clipboard
Erxin Yu, Jing Li, Ming Liao, Qi Zhu, Boyang Xue, Minghui Xu, Baojun Wang, Lanqing Hong, Fei Mi, Lifeng Shang
| Challenge: | Existing approaches to learning from errors synthesize training data by extrapolating from isolated bad cases, thereby failing to generalize the extensive patterns inherent within these cases. |
| Approach: | They propose a framework that synthesizes more generalized training data from isolated bad cases by extrapolating from isolated cases. |
| Outcome: | The proposed framework synthesizes more generalized training data to address these model weaknesses. |
PairCoder: Pair Programming-Inspired Two-Agent Collaboration for Code Generation (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing multi agent frameworks for large language models are brittle on code generation tasks. |
| Approach: | They propose a framework that brings pair programming to autonomous LLM collaboration. |
| Outcome: | Using PairCoder, large language models achieve better results on code generation tasks and reduce token usage by 40% to 70% on eight representative backbones. |
Tiny-NewsRec: Effective and Efficient PLM-based News Recommendation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing work fine tunes the PLM with the news recommendation task, which can cause a domain shift problem. |
| Approach: | They propose a self-supervised method to adapt general PLM to news domain with a contrastive matching task between news titles and news bodies. |
| Outcome: | The proposed method can improve both the effectiveness and efficiency of the large PLM-based news recommendation model while maintaining its performance. |
HD-Eval: Aligning Large Language Model Evaluators Through Hierarchical Criteria Decomposition (2024.acl-long)
Copied to clipboard
Yuxuan Liu, Tianchi Yang, Shaohan Huang, Zihan Zhang, Haizhen Huang, Furu Wei, Weiwei Deng, Feng Sun, Qi Zhang
| Challenge: | Large language models (LLMs) are a promising alternative to expensive human evaluations. |
| Approach: | They propose a framework that iteratively aligns LLM-based evaluators with human preference . they decompose a given evaluation task into finer-grained criteria . |
| Outcome: | The proposed framework iteratively aligns LLM-based evaluators with human preference . it decomposes a given evaluation task into finer-grained criteria . the framework is efficient to train and more explainable than relying solely on prompts . |
OpenRT: An Open-source Framework for Reasoning Over Tabular Data (2023.acl-demo)
Copied to clipboard
| Challenge: | Existing table pre-training methods are benchmarked on a limited number of datasets with varying configurations, resulting in a lack of unified, standardized, fair, and comprehensive comparison between methods. |
| Approach: | They propose to use OpenRT to reproduce existing table pre-training models and develop new models quickly. |
| Outcome: | The proposed framework reproduces existing table pre-training models and compares them against four question answering, one fact checking, and one faithful text generation datasets. |
Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversarial NLP (2022.emnlp-main)
Copied to clipboard
| Challenge: | Textual adversarial samples are often misrepresented in research on security, evaluation, explainability, and data augmentation. |
| Approach: | They propose to use adversarial samples to evaluate their methods on security tasks to demonstrate the real-world concerns rather than developing impractical methods. |
| Outcome: | The proposed method has higher practical value than the current benchmark. |
DDxTutor: Clinical Reasoning Tutoring System with Differential Diagnosis-Based Structured Reasoning (2025.acl-long)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models (LLMs) have enabled various medical educational applications, but they often provide direct answers that could reduce students’ cognitive engagement and lead to fragmented learning. |
| Approach: | They propose a framework that follows differential diagnosis principles to decompose clinical reasoning into teachable components. |
| Outcome: | The proposed framework decomposes clinical reasoning into teachable components and generates structured teaching references and conducts diagnostic tutoring dialogues. |
Towards Improving Adversarial Training of NLP Models (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Recent methods for generating NLP adversarial examples involve combinatorial search and expensive sentence encoders for constraining the generated instances. |
| Approach: | They propose to use vanilla adversarial training to train NLP models using a word substitution attack optimized for vanilla adversary training. |
| Outcome: | The proposed approach improves model performance and standard accuracy and can defend against other types of word substitution attacks. |
Reviews Meet Graphs: Enhancing User and Item Representations for Recommendation with Hierarchical Attentive Graph Neural Network (D19-1)
Copied to clipboard
| Challenge: | Existing methods to learn user and item representations from review texts do not take into account the user-user and item-item relatedness of the user. |
| Approach: | They propose to use review content and user-item graphs to integrate them as different views. |
| Outcome: | The proposed approach can learn user and item representations from review content and user-item graphs. |
TransferTOD: A Generalizable Chinese Multi-Domain Task-Oriented Dialogue System with Transfer Capabilities (2024.emnlp-main)
Copied to clipboard
Ming Zhang, Caishuang Huang, Yilong Wu, Shichun Liu, Huiyuan Zheng, Yurui Dong, Yujiong Shen, Shihan Dou, Jun Zhao, Junjie Ye, Qi Zhang, Tao Gui, Xuanjing Huang
| Challenge: | Current datasets cater to user-led systems and are limited to predefined specific scenarios and slots. |
| Approach: | They propose to use a Chinese dialogue dataset to train a model that authentically simulates human-computer dialogues in 30 popular life service scenarios. |
| Outcome: | The proposed model achieves a joint accuracy of 75.09% in out-of-domain evaluations . it also achieves notable abilities in slot filling and questioning . |
Mining Evidences for Concept Stock Recommendation (N18-1)
Copied to clipboard
| Challenge: | a recent announcement of a state plan to build a new economic region has led to the rise of hundreds of stocks . concepts can be useful for investors to find out relevant concept stocks for making investment decisions . a chinese research team uses deep learning to mine evidences from large textual data . |
| Approach: | They use distributed word similarities and deep reinforcement learning to learn a strategy of topic expansion from large scale textual data. |
| Outcome: | The proposed method outperforms a baseline method on two Chinese stock market datasets. |
PQR: Improving Dense Retrieval via Potential Query Modeling (2025.acl-long)
Copied to clipboard
| Challenge: | Existing training data is sparse, with each document associated with one or a few labeled queries. |
| Approach: | They propose a training-free potential query retrieval framework to address this problem . they use a Gaussian mixture distribution to model all potential queries for a document . |
| Outcome: | The proposed method is able to capture comprehensive semantic information from a document with multiple queries. |
Travel on the ICD Tree: Benchmarking Agentic Reasoning for ICD Coding from Chinese Electronic Medical Records (2026.findings-acl)
Copied to clipboard
| Challenge: | Accurate International Classification of Diseases (ICD) coding is crucial for hospital management and healthcare data governance. |
| Approach: | They propose a framework to evaluate ICD coding based on complete EMRs . they use a dataset of 560 real clinical records covering 434 common diseases . |
| Outcome: | The proposed framework explores the capability boundaries of large language models under different paradigms. |
A Systematic Survey of Automatic Prompt Optimization Techniques (2025.emnlp-main)
Copied to clipboard
Kiran Ramnath, Kang Zhou, Sheng Guan, Soumya Smruti Mishra, Xuan Qi, Zhengyuan Shen, Shuai Wang, Sangmin Woo, Sullam Jeoung, Yawei Wang, Haozhu Wang, Han Ding, Yuzhe Lu, Zhichao Xu, Yun Zhou, Balasubramaniam Srinivasan, Qiaojing Yan, Yueyan Chen, Haibo Ding, Panpan Xu, Lin Lee Cheong
| Challenge: | Recent advances in prompt engineering have created impediments for end users to adopt . however, prompt engineering remains an impedance due to rapid advances in models, tasks, and associated best practices. |
| Approach: | They propose to define APO as a 5-part unifying framework and categorize all relevant works based on their salient features. |
| Outcome: | The proposed framework aims to improve the performance of large language models on various tasks. |
Connecting Language and Vision to Actions (P18-5)
Copied to clipboard
| Challenge: | Recent advances in language and vision have made incredible progress in describing images and interacting with visual content in a physical or embodied environment. |
| Approach: | This tutorial will provide an overview of the growing number of multimodal tasks and datasets that combine textual and visual understanding. |
| Outcome: | This tutorial will review the state-of-the-art approaches to selected tasks such as image captioning, visual question answering and visual dialog. |
A Confidence-based Partial Label Learning Model for Crowd-Annotated Named Entity Recognition (2023.findings-acl)
Copied to clipboard
Limao Xiong, Jie Zhou, Qunxi Zhu, Xiao Wang, Yuanbin Wu, Qi Zhang, Tao Gui, Xuanjing Huang, Jin Ma, Ying Shan
| Challenge: | Existing models for named entity recognition (NER) are based on large-scale labeled datasets, which always obtain using crowdsourcing. |
| Approach: | They propose a CONfidence-based partial Label Learning method to integrate prior and posterior confidences for crowd-annotated named entity recognition models. |
| Outcome: | The proposed model improves on real-world and synthetic datasets compared with baselines. |
PaCoRe: Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning (2026.acl-long)
Copied to clipboard
Jingcheng Hu, Yinmin Zhang, Shijie Shang, Xiaobo Yang, Yue Peng, Zhewei Huang, Hebin Zhou, Xin Wu, Jie Cheng, Fanqi Wan, Xiangwen Kong, Chengyuan Yao, Kaiwen Yan, Ailin Huang, Hongyu Zhou, Qi Han, Zheng Ge, Xiangyu Zhang, Heung-Yeung Shum
| Challenge: | Parallel Coordinated Reasoning (PaCoRe) overcomes a central limitation of contemporary language models: their inability to scale test-time compute (TTC) far beyond sequential reasoning under a fixed context window. |
| Approach: | They propose a training-and-inference framework to overcome a central limitation of language models: their inability to scale test-time compute (TTC) under a fixed context window. |
| Outcome: | The proposed model scales to multi-million-token effective TTC without exceeding context limits. |
ReAttn: Improving Attention-based Re-ranking via Attention Re-weighting (2026.findings-eacl)
Copied to clipboard
| Challenge: | Attention-based re-ranking methods are highly concentrated a small subset of tokens within a few documents, making others indistinguishable. |
| Approach: | They propose a post-hoc re-weighting strategy that uses attention weights to reduce lexical bias and emphasize distinctive terms. |
| Outcome: | The proposed method reduces lexical bias and emphasizes distinctive terms across documents, while maintaining a balanced distribution across informative tokens. |
P-FOLIO: Evaluating and Improving Logical Reasoning with Abundant Human-Written Reasoning Chains (2024.findings-emnlp)
Copied to clipboard
Simeng Han, Aaron Yu, Rui Shen, Zhenting Qi, Martin Riddell, Wenfei Zhou, Yujie Qiao, Yilun Zhao, Semih Yavuz, Ye Liu, Shafiq Joty, Yingbo Zhou, Caiming Xiong, Dragomir Radev, Rex Ying, Arman Cohan
| Challenge: | Existing methods on understanding the capabilities of LLMs in logical reasoning rely on binary entailment classification or synthetically derived rationales. |
| Approach: | They propose to annotate a human-annotated dataset consisting of diverse and complex reasoning chains for a set of realistic logical reasoning stories also written by humans. |
| Outcome: | The proposed model outperforms existing methods on understanding the capabilities of LLMs in logical reasoning by 10% or more. |
MasRouter: Learning to Route LLMs for Multi-Agent Systems (2025.acl-long)
Copied to clipboard
| Challenge: | Multi-agent systems (MAS) powered by Large Language Models (LLMs) have been demonstrated to push the boundaries of LLM capabilities, yet they often face significant costs and challenges in dynamic LLM selection. |
| Approach: | They propose a multi-agent system routing solution that integrates all components of MAS into a unified routing framework. |
| Outcome: | The proposed solution is high-performing, cost-effective, and efficient . it reduces overhead by up to 52.07 compared to current methods on HumanEval . |
RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within Generation (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods rely on separate retrievers to fetch top-k text chunks for generating evidence, and they lack joint optimization. |
| Approach: | They propose a framework that integrates retrieval and generation into a single, auto-regressive process, enabling LLMs to directly generate fine-grained evidence from the corpus with constrained decoding. |
| Outcome: | Extensive experiments on five open-domain QA datasets demonstrate the proposed framework’s superior performance across both in-domain and out-of-domain tasks. |
Infinity-Parser: Layout-Aware Reinforcement Learning with High-quality Document Parsing Dataset (2026.findings-acl)
Copied to clipboard
Baode Wang, Biao Wu, Weizhen Li, Meng Fang, Zuming Huang, Jun Huang, Yanjie Liang, Haozhe Wang, Ling Chen, Wei Chu, Yuan Qi
| Challenge: | Existing supervised fine-tuning methods struggle to generalize across document types, leading to poor performance. |
| Approach: | They propose layoutRL, a reinforcement learning framework that optimizes layout understanding through composite rewards integrating normalized edit distance, paragraph count accuracy, and reading order preservation. |
| Outcome: | The proposed model outperforms specialized document parsing systems and general-purpose vision-language models on a broad range of document types, languages, and structural complexities. |
BoolQuestions: Does Dense Retrieval Understand Boolean Logic in Language? (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Dense retrieval systems focus on optimizing text embedding space while overlooking Boolean logic in language. |
| Approach: | They propose a task to investigate whether retrieval systems can comprehend Boolean logic in language. |
| Outcome: | The proposed method is based on a benchmark dataset covering complex queries containing basic Boolean logic and corresponding annotated passages. |
A Multi-Format Transfer Learning Model for Event Argument Extraction via Variational Information Bottleneck (2022.coling-1)
Copied to clipboard
| Challenge: | Event argument extraction (EAE) aims to extract arguments with given roles from texts. |
| Approach: | They propose a multi-format transfer learning model with variational information bottleneck to learn from existing datasets. |
| Outcome: | The proposed model improves on three benchmark datasets and obtains state-of-the-art performance on EAE. |
Kernel-Whitening: Overcome Dataset Bias with Isotropic Sentence Embedding (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to reduce dataset bias rely on spurious correlations and obstruct valid feature information while mitigating bias. |
| Approach: | They propose a representation normalization method which disentangles correlations between features of encoded sentences and a kernel approximation method which provides isotropic data distribution. |
| Outcome: | The proposed method eliminates the bias problem by providing isotropic data distribution while maintaining in-distribution accuracy. |
AgentV-RL: Scaling Reward Modeling with Agentic Verifier (2026.findings-acl)
Copied to clipboard
Jiazheng Zhang, Ziche Fu, Zhiheng Xi, Wenqing Jing, Mingxu Chai, Wei He, Guoqiang Zhang, Chenghao Fan, Chenxin An, Wenxiang Chen, Zhicheng Liu, Haojie Pan, Dingwei Zhu, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing approaches to improve LLM reasoning are limited in complex domains and lack external grounding makes verifiers unreliable on computation-intensive tasks. |
| Approach: | They propose a framework that transforms reward modeling into a multi-turn, tool-augmented deliberative process. |
| Outcome: | The proposed framework surpasses state-of-the-art ORMs by 25.2% under parallel and sequential TTS. |
LFKQG: A Controlled Generation Framework with Local Fine-tuning for Question Generation over Knowledge Bases (2022.coling-1)
Copied to clipboard
| Challenge: | Existing KBQG models focus on the most relevant part of the answer entity, while neglecting the rest of the subgraph. |
| Approach: | They propose a controlled generation framework for Question Generation over Knowledge Bases that generates questions with out-of-vocabulary (OOV) predicates. |
| Outcome: | The proposed framework outperforms existing methods significantly on three widely-used benchmark datasets SimpleQuestion, PathQuestions, and WebQuestIONS. |
QiMeng-PRepair: Precise Code Repair via Edit-Aware Reward Optimization (2026.acl-long)
Copied to clipboard
Changxin Ke, Rui Zhang, Jiaming Guo, Yuanbo Wen, Li Ding, Shuo Wang, Xuyuan Zhu, Xiong Peng, Di Huang, Zidong Du, Xing Hu, Qi Guo, Yunji Chen
| Challenge: | Existing approaches to program repair are based on correctness alone. |
| Approach: | They propose a framework that mitigates over-editing and improves repair accuracy by generating buggy programs and re-edits. |
| Outcome: | The proposed framework improves repair precision by 31.4% under fix1@1, a metric that considers repair correctness and extent, and significantly increases decoding throughput when combined with speculative editing. |
A Self-Attentive Model with Gate Mechanism for Spoken Language Understanding (D18-1)
Copied to clipboard
| Challenge: | Spoken language understanding (SLU) involves intent determination and slot filling . existing joint learning methods only consider joint learning by sharing parameters on surface level rather than semantic level. |
| Approach: | They propose a self-attentive model to fully utilize the semantic correlation between slot and intent. |
| Outcome: | The proposed model outperforms existing methods in both intent detection and slot filling tasks on ATIS benchmarks. |
TaKG: A New Dataset for Paragraph-level Table-to-Text Generation Enhanced with Knowledge Graphs (2022.findings-aacl)
Copied to clipboard
| Challenge: | Existing table-to-text generation benchmarks have some limitations, such as E2E and ToTTo focusing on singlesentence generation tasks. |
| Approach: | They propose a new table-to-text generation dataset called TaKG that uses a set of knowledge graphs to enhance table input. |
| Outcome: | The proposed model outperforms existing models for short-text generation tasks and shows reliable performance on long-text generated across a variety of metrics. |
LoSiA: Efficient High-Rank Fine-Tuning via Subnet Localization and Optimization (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods perform extensive matrix multiplications in domain specialization tasks, resulting in computational inefficiency and sub-optimal fine-tuning performance. |
| Approach: | They propose a method that localizes and optimizes critical parameters during training . they propose 'LoSiA-Pro' which reduces training latency by 27% . |
| Outcome: | The proposed method achieves minimal performance drop compared to full fine-tuning while requiring the least training time across domain specialization and common-sense reasoning tasks. |
VLFeedback: A Large-Scale AI Feedback Dataset for Large Vision-Language Models Alignment (2024.emnlp-main)
Copied to clipboard
Lei Li, Zhihui Xie, Mukai Li, Shunian Chen, Peiyi Wang, Liang Chen, Yazheng Yang, Benyou Wang, Lingpeng Kong, Qi Liu
| Challenge: | Large vision-language models (LVLMs) are evolving rapidly and require data with human supervision to achieve better alignment. |
| Approach: | They introduce VLFeedback, the first large-scale vision-language feedback dataset . they train Silkie, an LVLM fine-tuned via direct preference optimization . |
| Outcome: | The proposed model outperforms its base model in helpfulness, visual faithfulness, and safety metrics and exhibits enhanced resilience against red-teaming attacks. |
Unveiling Internal Reasoning Modes in LLMs: A Deep Dive into Latent Reasoning vs. Factual Shortcuts with Attribute Rate Ratio (2025.emnlp-main)
Copied to clipboard
Yiran Yang, Haifeng Sun, Jingyu Wang, Qi Qi, Zirui Zhuang, Huazheng Wang, Pengfei Ren, Jing Wang, Jianxin Liao
| Challenge: | Existing research in multi-hop questions has identified two reasoning modes, but has not investigated how these modes differ during inference. |
| Approach: | They propose a classification metric that compares latent reasoning and factual shortcuts in multi-hop questions. |
| Outcome: | The proposed metric achieves 90% accuracy on the proposed datasets and demonstrates effectiveness in RAG conflict scenarios. |
Unveiling and Consulting Core Experts in Retrieval-Augmented MoE-based LLMs (2024.emnlp-main)
Copied to clipboard
Xin Zhou, Ping Nie, Yiwen Guo, Haojie Wei, Zhanqiu Zhang, Pasquale Minervini, Ruotian Ma, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing research seeks to enhance RAG performance by retrieving higher-quality documents or designing RAG-specific LLMs, but internal mechanisms that contribute to RAG’s effectiveness remain underexplored. |
| Approach: | They propose to examine the internal mechanisms within the popular Mixture-of-Expert (MoE)-based LLMs and examine their ability to improve RAG by examining expert activations. |
| Outcome: | The proposed method significantly improved the ability of Large Language Models (LLMs) to solve knowledge-intensive tasks. |
Asking Clarification Questions in Knowledge-Based Question Answering (D19-1)
Copied to clipboard
| Challenge: | Existing clarification datasets with limited annotated examples do not address ambiguous phenomena. |
| Approach: | They propose a dataset that allows users to ask clarification questions using open-domain examples. |
| Outcome: | The proposed model achieves better performance than strong baselines and provides new challenges. |
Orthogonal Subspace Learning for Language Model Continual Learning (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for continual learning in language models suffer catastrophic forgetting when learning sequential tasks. |
| Approach: | They propose an orthogonal low-rank adaptation approach for continual learning in language models that uses orthogons to learn sequentially. |
| Outcome: | The proposed approach outperforms state-of-the-art methods on continual learning benchmarks and preserves generalization ability of LLMs on unseen tasks. |
WildReward: Learning Reward Models from In-the-Wild Human Interactions (2026.acl-long)
Copied to clipboard
| Challenge: | Prior work focused on collecting preference pairs, requiring substantial annotation efforts. |
| Approach: | They propose a pipeline to extract reliable human feedback from in-the-wild interactions . they propose to use WildChat as an interaction source to train the model . |
| Outcome: | The proposed model achieves comparable or even superior performance compared to conventional models with improved calibration and cross-sample consistency. |
PFDial: A Structured Dialogue Instruction Fine-tuning Method Based on UML Flowcharts (2025.findings-acl)
Copied to clipboard
Ming Zhang, Yuhui Wang, Yujiong Shen, Tingyi Yang, Changhao Jiang, Yilong Wu, Shihan Dou, Qinhao Chen, Zhiheng Xi, Zhihao Zhang, Yi Dong, Zhen Wang, Zhihui Fei, Mingyang Wan, Tao Liang, Guojun Ma, Qi Zhang, Tao Gui, Xuanjing Huang
| Challenge: | Large Language Models (LLMs) have shown remarkable progress in dialogue and reasoning, but they struggle to solve strictly constrained dialogue tasks. |
| Approach: | They construct a dataset that contains 12,705 high-quality Chinese dialogue instructions from 440 flowcharts containing 5,055 process nodes. |
| Outcome: | The proposed model outperforms GPT-4o models on backward transitions and outperformed GPT-42 models on the same dataset. |
Flooding-X: Improving BERT’s Resistance to Adversarial Attacks via Loss-Restricted Fine-Tuning (2022.acl-long)
Copied to clipboard
Qin Liu, Rui Zheng, Bao Rong, Jingyi Liu, ZhiHua Liu, Zhanzhan Cheng, Liang Qiao, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing approaches to generating adversarial perturbations scale up the cost of training computational complexity by the number of gradient steps it takes to obtain the adversarials. |
| Approach: | They propose a flood method which aims at better generalization and a criterion to bring hyper-parameter-dependent flooding into effect with a narrowed-down search space by measuring how the gradient steps taken within one epoch affect the loss of each batch. |
| Outcome: | The proposed method improves BERT’s resistance to textual adversarial attacks by a large margin and achieves state-of-the-art robust accuracy on various text classification and GLUE tasks. |
MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering (2025.findings-acl)
Copied to clipboard
Jingqun Tang, Qi Liu, Yongjie Ye, Jinghui Lu, Shu Wei, An-Lan Wang, Chunhui Lin, Hao Feng, Zhen Zhao, Yanjie Wang, Yuliang Liu, Hao Liu, Xiang Bai, Can Huang
| Challenge: | Text-Centric Visual Question Answering (TEC-VQA) is a text-centric visual task understanding tool. |
| Approach: | They introduce a benchmark that features human expert annotations across 9 languages . they prioritize the text in question-answer pairs while disregarding visual text in images . |
| Outcome: | The proposed benchmarks prioritize the text in question-answer pairs while disregarding visual text in images. |
ResoFilter: Fine-grained Synthetic Data Filtering for Large Language Models through Data-Parameter Resonance Analysis (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods for enhancing large language models lack clear metrics for evaluating data characteristics. |
| Approach: | They propose a method that integrates models, data, and tasks to refine datasets. |
| Outcome: | The proposed method achieves comparable results to full-scale fine-tuning using only half the data in mathematical tasks and exhibits strong generalization across different models and domains. |
Farewell to Aimless Large-scale Pretraining: Influential Subset Selection for Language Model (2023.findings-acl)
Copied to clipboard
Xiao Wang, Weikang Zhou, Qi Zhang, Jie Zhou, SongYang Gao, Junzhe Wang, Menghan Zhang, Xiang Gao, Yun Wen Chen, Tao Gui
| Challenge: | Pretrained language models have achieved remarkable success in various natural language processing tasks. |
| Approach: | They propose to use end-task knowledge to select a tiny subset of pretraining corpus to influence performance. |
| Outcome: | The proposed model outperforms pretrained models on eight datasets covering four domains with 0.45% of the data and a three-orders-of-magnitude lower computational cost. |
Automatic Prompt Engineering for Scalable Prompt Inversion in Text-to-Image Ad Generation (2026.acl-industry)
Copied to clipboard
| Challenge: | PRISM-DUEL is a black-box framework that formalizes prompt optimization as Automatic Prompt Engineering (APE) PRIMS-DUEl is motivated by advertising workflows requiring low-latency, diverse variants faithful to a human-designed ad. |
| Approach: | They propose a black-box framework that formalizes prompt optimization as Automatic Prompt Engineering (APE) they obtain label-free pairwise preferences and rationales from an LLM judge over pairs of generated images and use a dueling-bandit optimizer to optimize a prompt for generating controlled variations while matching the reference ad's visual content. |
| Outcome: | The proposed framework preserves visual similarity and semantic faithfulness while increasing diversity. |
Capturing the Content of a Document through Complex Event Identification (2022.starsem-1)
Copied to clipboard
| Challenge: | Recent work grouped granular events into more general events, called complex events . however, this approach assumes that a given complex event is always described in consecutive sentences . |
| Approach: | They propose a context-augmented representation learning approach that uses contextual information to model pairwise relation between granular events. |
| Outcome: | The proposed approach outperforms baselines on the complex event identification task. |
Call Me When Necessary: LLMs can Efficiently and Faithfully Reason over Structured Environments (2024.findings-acl)
Copied to clipboard
Sitao Cheng, Ziyuan Zhuang, Yong Xu, Fangkai Yang, Chaoyun Zhang, Xiaoting Qin, Xiang Huang, Ling Chen, Qingwei Lin, Dongmei Zhang, Saravan Rajmohan, Qi Zhang
| Challenge: | Large Language Models (LLMs) have shown potential in reasoning over structured environments, e.g., knowledge graphs and tables. |
| Approach: | They propose a framework that allows LLMs to efficiently and faithfully reason over structured environments. |
| Outcome: | The proposed framework surpasses state-of-the-art fine-tuned methods on three KGQA and two TableQA datasets and surpasse CWQ and WTQ methods. |
Domain Generalization via Causal Adjustment for Cross-Domain Sentiment Analysis (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing approaches to domain adaptation fail to generalize well on unknown test data. |
| Approach: | They propose a backdoor adjustment-based causal model to disentangle domain-specific and domain-invariant representations that play essential roles in tackling domain shift. |
| Outcome: | The proposed model disentangles domain-specific and domain-invariant representations that play essential roles in tackling domain shift. |
An Auto-Encoder Matching Model for Learning Utterance-Level Semantic Dependency in Dialogue Generation (D18-1)
Copied to clipboard
| Challenge: | Experimental results show that our model can generate semantically coherent responses compared to baseline models. |
| Approach: | They propose an Auto-Encoder Matching model to learn utterance-level semantic dependency . their model contains two auto-encoders and one mapping module . |
| Outcome: | Experimental results show that the proposed model can generate high coherence and fluency compared to baseline models. |
Relational Memory-Augmented Language Models (2022.tacl-1)
Copied to clipboard
| Challenge: | Existing language models rely on word correlation and are difficult to interpret . existing models often lack explicit representations for such information . |
| Approach: | They propose a memory-augmented approach to condition autoregressive language models on knowledge graphs. |
| Outcome: | The proposed model improves perplexity and bits per character in an autoregressive language model . it is complementary to token-based memory and enables causal interventions . |
TinyScientist: An Interactive, Extensible, and Controllable Framework for Building Research Agents (2025.emnlp-demos)
Copied to clipboard
Haofei Yu, Keyang Xuan, Fenghai Li, Kunlun Zhu, Zijie Lei, Jiaxun Zhang, Ziheng Qi, Kyle Richardson, Jiaxuan You
| Challenge: | Existing research systems often design and use agentic workflows to perform research tasks such as ideation, scientific coding, review writing, and tree-based search. |
| Approach: | They propose an open-source codebase, an interactive web demonstration, and a PyPI Python package to make state-of-the-art auto-research pipelines broadly accessible to every researcher and developer. |
| Outcome: | The proposed framework adapts easily to new tools and supports iterative growth. |
SSH: Sparse Spectrum Adaptation via Discrete Hartley Transformation (2025.naacl-long)
Copied to clipboard
| Challenge: | Low-rank adaptation (LoRA) has been demonstrated effective in reducing the trainable parameter number when fine-tuning a large foundation model (LLM). |
| Approach: | They propose a low-rank adaptation approach that reduces the number of trainable parameters while enhancing model performance. |
| Outcome: | The proposed approach outperforms existing parameter-efficient fine-tuning methods while achieving substantial reductions in computational cost and memory requirements. |
ChartCoder: Advancing Multimodal Large Language Model for Chart-to-Code Generation (2025.acl-long)
Copied to clipboard
| Challenge: | Existing open-source MLLMs fail to fully capture dense information embedded in charts . current models still face significant challenges in understanding and analyzing visual tasks such as captioning and question answering. |
| Approach: | They propose a chart-to-code MLLM which leverages Code LLMs as the language backbone to enhance the executability of the generated code. |
| Outcome: | The proposed model surpasses existing open-source models on chart-to-code benchmarks with only 7B parameters and provides lossless representations that contain all critical details. |
Walking in Others’ Shoes: How Perspective-Taking Guides Large Language Models in Reducing Toxicity and Bias (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing prompting methods that require white-box access to the model or substantial training fail to simultaneously lessen toxicity and bias. |
| Approach: | They propose a strategy that encourages LLMs to integrate diverse human perspectives and self-regulate their responses by incorporating diverse human viewpoints. |
| Outcome: | The proposed approach can significantly diminish toxicity (up to 89%) and bias (up 73%) in LLMs’ responses. |
Counteracting the Matthew Effect in Self-Improvement of LVLMs through Head-Tail Re-balancing (2026.acl-long)
Copied to clipboard
Xin Guo, Zhiheng Xi, Yiwen Ding, Yitao Zhai, Xiaowei Shi, Xunliang Cai, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Large vision language models have impressive reasoning capabilities across complex multimodal tasks. |
| Approach: | They propose to use distribution-reshaping and trajectory-rebalancing to improve visual reasoning capabilities. |
| Outcome: | Experiments on Qwen2-VL-7B-Instruct and InternVL2.5-4B models show that their methods outperform baselines by 3.86 points. |
Retrieval Augmented Instruction Tuning for Open NER with Large Language Models (2025.coling-main)
Copied to clipboard
| Challenge: | Existing studies have focused on integrating large language models (LLMs) with information extraction (IE) however, the best approach to incorporate information with LLMs for IE remains an open question. |
| Approach: | They propose to use a Chinese IT dataset to perform RA-IT for IE . they use semantically similar examples from the training dataset as the context . |
| Outcome: | The proposed approach is evaluated in English and Chinese scenarios. |
VistaWise: Building Cost-Effective Agent with Cross-Modal Knowledge Graph for Minecraft (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) have shown significant promise in embodied decision-making tasks within virtual open-world environments, but lack domain-specific knowledge. |
| Approach: | They propose a cost-effective agent framework that integrates cross-modal domain knowledge and finetunes a dedicated object detection model for visual analysis. |
| Outcome: | The proposed framework reduces the requirement for domain-specific training data from millions of samples to a few hundred. |
Scaling Performance and Low-Resource Annotation with Many-Shot In-Context Learning for Named Entity Recognition (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing studies on ICL for Named Entity Recognition (NER) have mainly explored few-shot settings, but the potential of scaling to hundreds of demonstrations has not been thoroughly investigated. |
| Approach: | They evaluate various LLMs across multiple domains using hundreds of ICL examples and then assess the feasibility of using many-shot ICL as a data annotation framework. |
| Outcome: | The proposed framework can be scaled to hundreds of examples and annotate and refining data for low-resource NER tasks. |
Neural News Recommendation with Heterogeneous User Behavior (D19-1)
Copied to clipboard
| Challenge: | Existing news recommendation methods rely on news click history to model user interest, but data sparsity is a problem . other kinds of user behaviors such as webpage browsing and search queries can provide useful clues of users’ news reading interest. |
| Approach: | They propose to exploit heterogeneous user behaviors to learn news representations from their titles via CNN networks and apply attention networks to select important words. |
| Outcome: | The proposed approach exploits heterogeneous user behaviors on a real-world dataset. |
Query Structure Modeling for Inductive Logical Reasoning Over Knowledge Graphs (2023.acl-long)
Copied to clipboard
| Challenge: | Existing methods for inductive reasoning over knowledge graphs lack the ability to model the logical structures of complex queries. |
| Approach: | They propose a structure-modeled textual encoding framework for inductive logical reasoning over KGs that encodes linearized query structures and entities using pre-trained language models to find answers. |
| Outcome: | The proposed framework encodes query structures and entities using pre-trained language models to find answers. |
Perception, Understanding and Reasoning: A Multimodal Benchmark for Video Fake News Detection (2026.acl-long)
Copied to clipboard
| Challenge: | Existing video fake news detection benchmarks focus on the detection accuracy, while failing to provide fine-grained assessments for the entire detection process. |
| Approach: | They propose a process-oriented video fake news detection benchmark that evaluates MLLMs' perception, understanding, and reasoning capabilities in VFND. |
| Outcome: | The proposed model achieves sota performance on video fake news detection tasks. |
Mitigating Tail Narrowing in LLM Self-Improvement via Socratic-Guided Sampling (2025.naacl-long)
Copied to clipboard
Yiwen Ding, Zhiheng Xi, Wei He, Lizhuoyuan Lizhuoyuan, Yitao Zhai, Shi Xiaowei, Xunliang Cai, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Large language models (LLMs) generate solutions themselves and iteratively train on filtered, high-quality rationales, but performance reaches a ceiling after a few iterations. |
| Approach: | They propose a strategy to improve the efficiency of sampling heavy-tailed data by using Socratic-style guidance signals to help LLMs reasoning with complex queries. |
| Outcome: | The proposed approach is effective on difficult queries and on held-out tasks, while requiring human supervision. |
Metacognitive Self-Correction for Multi-Agent System via Prototype-Guided Next-Execution Reconstruction (2026.findings-acl)
Copied to clipboard
Xu Shen, Qi Zhang, Song Wang, Zhen Tan, Xinyu Zhao, Laura Yao, Vaishnav Tadiparthi, Hossein Nourkhiz Mahjoub, Ehsan Moradi Pari, Kwonjoon Lee, Tianlong Chen
| Challenge: | Large Language Model based multi-agent systems (MAS) excel at collaborative problem solving but remain brittle to cascading errors. |
| Approach: | They propose a metacognitive framework that enables step-level error detection and self-correction in Large Language Model based multi-agent systems (MAS) . |
| Outcome: | The proposed framework outperforms baselines on the Who When benchmark and delivers consistent gains on AgentErrorBench. |
OctoBench: Benchmarking Scaffold-Aware Instruction Following in Repository-Grounded Agentic Coding (2026.acl-long)
Copied to clipboard
Deming Ding, Shichun Liu, Enhui Yang, Jiahang Lin, Ziying Chen, Shihan Dou, Honglin Guo, Weiyu Cheng, Pengyu Zhao, Chengjun Xiao, Qunhong Zeng, Qi Zhang, Xuanjing Huang, Qidi Xu, Tao Gui
| Challenge: | coding scaffolds that follow heterogeneous instructions remain under-examined in software engineering . coding models are capable software agents, but their ability to follow constraints remains under-explored . |
| Approach: | They introduce OctoBench, which benchmarks scaffold-aware instruction following in agentic coding. |
| Outcome: | The proposed benchmark aims to accelerate the development of more scaffold-aware agents. |
Factual Dialogue Summarization via Learning from Large Language Models (2025.coling-main)
Copied to clipboard
| Challenge: | Existing models generate fluent and coherent summaries, but inconsistencies can be found in generated summary. |
| Approach: | They propose to use symbolic knowledge distillation to improve the factual consistency of smaller pretrained models for dialogue summarization. |
| Outcome: | The proposed model outperforms baseline models in BART, PEGASUS, and Flan-T5 in factual consistency and accuracy. |
Document Segmentation Matters for Retrieval-Augmented Generation (2025.findings-acl)
Copied to clipboard
Zhitong Wang, Cheng Gao, Chaojun Xiao, Yufei Huang, Shuzheng Si, Kangyang Luo, Yuzhuo Bai, Wenhao Li, Tangjian Duan, Chuancheng Lv, Guoshan Lu, Gang Chen, Fanchao Qi, Maosong Sun
| Challenge: | Existing rule-based chunking methods lead to suboptimal splits, where overly large chunks introduce irrelevant information and small chunks lack semantic coherence. |
| Approach: | They propose a method that leverages document summaries as pseudo-instructions to guide chunking by computing semantic similarity between sentences and the summary. |
| Outcome: | Experiments on multiple open-domain question-answering benchmarks show that PIC significantly improves retrieval accuracy (Hits@k) and end-to-end QA performance (Exact Match) without any additional training. |
Systematic Generalization on gSCAN with Language Conditioned Embedding (2020.aacl-main)
Copied to clipboard
| Challenge: | Existing deep learning models fail when the test set is systematically different from the training data. |
| Approach: | They propose a method that explicitly models the relations between objects in their contexts while learning their representations. |
| Outcome: | The proposed model outperforms the baseline model and reaches state-of-the-art performance on grounded SCAN (gSCAN), a grounded natural language navigation dataset. |
Spatiotemporal Sycophancy: Negation-Based Gaslighting in Video Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing Vid-LLMs lack robust mechanisms for maintaining grounded spatiotemporal beliefs under conversational feedback. |
| Approach: | They propose a negation-based gaslighting evaluation framework and introduce a benchmark to investigate spatiotemporal sycophancy. |
| Outcome: | The proposed framework evaluates state-of-the-art Vid-LLMs across video understanding tasks. |
Self-Polish: Enhance Reasoning in Large Language Models via Problem Refinement (2023.findings-emnlp)
Copied to clipboard
Zhiheng Xi, Senjie Jin, Yuhao Zhou, Rui Zheng, Songyang Gao, Jia Liu, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing prompting methods have been used to enhance multistep reasoning capabilities of large language models, but they have overlooked the potential of formulating higher-quality problems. |
| Approach: | They propose a method that starts from the problem side and refines problems to be more comprehensible and solvable for models. |
| Outcome: | The proposed method achieves notable and consistent effectiveness on five reasoning benchmarks across different models. |
AutoRubric: Rubric-Based Generative Rewards for Faithful Multimodal Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Multimodal large language models (MLLMs) have advanced from perception tasks to complex multi-step reasoning. |
| Approach: | They propose a framework that integrates reinforcement learning with verifiable rewards with process-level supervision through automatically collected rubric-based generative rewards. |
| Outcome: | The proposed framework achieves state-of-the-art performance on six multimodal reasoning benchmarks and significantly improves reasoning faithfulness in dedicated evaluations. |
“Again, Dozens of Refugees Drowned”: A Computational Study of Political Framing Evoked by Presuppositions (2022.naacl-srw)
Copied to clipboard
| Challenge: | Earlier studies on issue framing have focused heavily on shallow classification of issue framers, while framerical cues remain neglected. |
| Approach: | They take presupposition-triggering adverbs such as ‘again’ as a study case and examine how different German newspapers use them to covertly evoke different attitudinal subtexts. |
| Outcome: | The findings show that iterative adverbs like 'again' can act as subtle but effective cues of framing. |
AgentGym: Evaluating and Training Large Language Model-based Agents across Diverse Environments (2025.acl-long)
Copied to clipboard
Zhiheng Xi, Yiwen Ding, Wenxiang Chen, Boyang Hong, Honglin Guo, Junzhe Wang, Xin Guo, Dingwen Yang, Chenyang Liao, Wei He, Songyang Gao, Lu Chen, Rui Zheng, Yicheng Zou, Tao Gui, Qi Zhang, Xipeng Qiu, Xuanjing Huang, Zuxuan Wu, Yu-Gang Jiang
| Challenge: | Large language models (LLMs) are promising foundations to build generally-capable agents . however, the community lacks a unified interactive framework that covers diverse environments for comprehensive evaluation of agents. |
| Approach: | They propose a framework that features 7 real-world scenarios, 14 environments, and 89 tasks for unified, real-time, and concurrent agent interaction. |
| Outcome: | The proposed framework features 7 real-world scenarios, 14 environments, and 89 tasks for unified, real-time, and concurrent agent interaction. |
MCS: An In-battle Commentary System for MOBA Games (2022.coling-1)
Copied to clipboard
Xiaofeng Qi, Chao Li, Zhongping Liang, Jigang Liu, Cheng Zhang, Yuanxin Wei, Lin Yuan, Guang Yang, Lanxiao Huang, Min Li
| Challenge: | In-battle commentary is an important component of live streaming of e-sports competitions and is applicable to a wide range of scenarios like combat information analysis and live streaming. |
| Approach: | They propose a generative system for in-battle real-time commentary in mobile MOBA games and propose 'transform' method to convert match statistics and utterances into consistent encoding space. |
| Outcome: | The proposed system is based on real-time match statistics and events and can be used for live streaming, e-sports commentary and combat information analysis. |
SRF: Enhancing Document-Level Relation Extraction with a Novel Secondary Reasoning Framework (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for document-level relation extraction ignore bidirectional mention interaction when generating relational features for entity pairs. |
| Approach: | They propose a document-level relation extraction model that incorporates bidirectional mention fusion and a simple yet effective evidence extraction module for relation prediction. |
| Outcome: | The proposed model achieves SOTA performance and the proposed method is effective and general when integrated into existing models. |
ChatHLS: Towards Systematic Design Automation and Optimization for High-Level Synthesis (2026.acl-long)
Copied to clipboard
| Challenge: | High-Level Synthesis (HLS) is a hardware design tool that can be used to design hardware from C-like languages, but its widespread adoption is limited by strict coding constraints and design-specific optimizations. |
| Approach: | They propose a multi-agent HLS design framework that leverages specialized LLMs for automated debugging and directive tuning. |
| Outcome: | The proposed framework outperforms Gemini-3-pro in debugging and speedups across various HLS kernels and neural network accelerators. |
UniICL: An Efficient ICL Framework Unifying Compression, Selection, and Generation (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods to improve reasoning abilities of Large Language Models (LLMs) have limitations due to excessive growth in context length, causing large hardware burden. |
| Approach: | They propose a novel Unified ICL framework that unifies demonstration compression, demonstration selection, and final response generation. |
| Outcome: | The proposed framework unifies demonstration compression, demonstration selection, and final response generation. |
PaD: Program-aided Distillation Can Teach Small Models Reasoning Better than Chain-of-thought Fine-tuning (2024.naacl-long)
Copied to clipboard
| Challenge: | Large language models excel in various tasks, but their huge size and inaccessibility of parameters present challenges for practical deployment. |
| Approach: | They propose to use CoT data to distill task-specific ability from large language models to smaller models . they use reasoning programs to suppress errors in distilled data and improve distillation quality . |
| Outcome: | The proposed model outperforms LLMs on arithmetic reasoning, symbolic reasoning, and general ability. |
SciER: An Entity and Relation Extraction Dataset for Datasets, Methods, and Tasks in Scientific Documents (2024.emnlp-main)
Copied to clipboard
| Challenge: | Scientific information extraction (SciIE) is critical for converting unstructured knowledge from scholarly articles into structured data. |
| Approach: | They propose to use a scientific entity and relation extraction dataset to capture interactions between entities in full texts. |
| Outcome: | The proposed dataset captures the intricate use and interactions among entities in full texts and provides an out-of-distribution test set to offer a more realistic evaluation. |
Multi-Programming Language Sandbox for LLMs (2025.acl-demo)
Copied to clipboard
Shihan Dou, Jiazheng Zhang, Jianxiang Zang, Yunbo Tao, Weikang Zhou, Haoxiang Jia, Shichun Liu, Yuming Yang, Shenxi Wu, Zhiheng Xi, Muling Wu, Rui Zheng, Changze Lv, Limao Xiong, Shaoqing Zhang, Lin Zhang, Wenyu Zhan, Rongxiang Weng, Jingang Wang, Xunliang Cai, Yueming Wu, Ming Wen, Yixin Cao, Tao Gui, Xipeng Qiu, Qi Zhang, Xuanjing Huang
| Challenge: | MPLSandbox is an out-of-the-box multi-programming language sandbox designed to provide unified and comprehensive feedback from compiler and analysis tools for Large Language Models (LLMs). |
| Approach: | They propose a multi-programming language sandbox that provides unified feedback from compilers and analysis tools for Large Language Models. |
| Outcome: | The proposed multi-language sandbox can provide comprehensive feedback from compilers and analysis tools for large language models (LLMs). |
Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution (2021.acl-long)
Copied to clipboard
| Challenge: | Recent studies show that neural natural language processing models are vulnerable to backdoor attacks. |
| Approach: | They propose to inject neural models with backdoors activated by word substitution . their results raise a serious alarm to the security of NLP models, they argue . |
| Outcome: | The proposed backdoors are activated by a learnable combination of word substitution and exhibit higher invisibility than previous methods. |
Se2: Sequential Example Selection for In-Context Learning (2024.findings-acl)
Copied to clipboard
| Challenge: | Prior work has explored the selection of examples for in-context learning, neglecting the internal relationships between examples and exist an inconsistency between training and inference. |
| Approach: | They propose a sequential-aware method that leverages the LLM’s feedback on varying context, aiding in capturing inter-relationships and sequential information among examples. |
| Outcome: | Experiments on 23 NLP tasks show that Se2 surpasses baselines and achieves 42% relative improvement over random selection. |
An Edge-Enhanced Hierarchical Graph-to-Tree Network for Math Word Problem Solving (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing work on graph neural networks to capture word relationships neglects the rest of the problem. |
| Approach: | They propose an edge-enhanced hierarchical graph encoder to incorporate edge label information. |
| Outcome: | The proposed model can improve performance on the MAWPS and Math23K datasets compared with state-of-the-art methods. |
Modeling Evolution of Message Interaction for Rumor Resolution (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods for rumor resolution ignore local interactions during the message diffusion which is important for the identification of rumors. |
| Approach: | They propose to model confrontation and reciprocity between message pairs via discrete variational autoencoders which effectively reflects the diversified opinion interactivity. |
| Outcome: | Experiments on a PHEME dataset show that the proposed model achieves higher accuracy than existing methods. |
HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering (D18-1)
Copied to clipboard
Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William Cohen, Ruslan Salakhutdinov, Christopher D. Manning
| Challenge: | Existing question answering (QA) datasets fail to train QA systems to perform complex reasoning and provide explanations for answers. |
| Approach: | They propose a new dataset with 113k Wikipedia-based question-answer pairs with four key features: (1) the questions require finding and reasoning over multiple supporting documents to answer; (2) the questions are diverse and not constrained to any pre-existing knowledge bases or knowledge schemas; (3) the questions provide sentence-level supporting facts required for reasoning; and (4) a type of factoid comparison questions to test QA systems’ ability to extract relevant facts and perform necessary comparison. |
| Outcome: | The proposed dataset has 113k Wikipedia-based question-answer pairs and four key features that make it challenging for the latest QA systems. |
Coarse-to-fine Few-shot Learning for Named Entity Recognition (2023.findings-acl)
Copied to clipboard
Ruotian Ma, Zhang Lin, Xuanting Chen, Xin Zhou, Junzhe Wang, Tao Gui, Qi Zhang, Xiang Gao, Yun Wen Chen
| Challenge: | Existing few-shot NER solutions do not consider sub-class discrimination and various granularity of new classes during coarse training. |
| Approach: | They propose a method that uses a cluster-based prototype loss to learn group-wise discriminative representations of coarse-grained classes and a mixture prototype loss for learning the representations. |
| Outcome: | The proposed method shows superior performance over baseline methods on in-domain and cross-domain settings with various target granularity. |
Deconvolution-Based Global Decoding for Neural Machine Translation (C18-1)
Copied to clipboard
| Challenge: | Existing models for Neural Machine Translation (NMT) use Recurrent Neural Network (RNN) to generate translation word by word following a sequential order. |
| Approach: | They propose a Neural Machine Translation (NMT) model that decodes the sequence with the guidance of its structural prediction of the target-side context. |
| Outcome: | The proposed model is more competitive compared with the state-of-the-art methods and reduces repetition with the instruction from the target-side context for decoding. |
GenDecider: Integrating “None of the Candidates” Judgments in Zero-Shot Entity Linking Re-ranking (2024.naacl-short)
Copied to clipboard
| Challenge: | Existing methods for zero-shot reranking assume the correct entity is always among the retrieved candidates. |
| Approach: | They propose a novel re-ranking approach for Zero-Shot Entity Linking . they use the Llama model to detect scenarios where the correct entity is not retrieved . |
| Outcome: | The proposed approach significantly improves disambiguation and accuracy on the ZESHEL dataset. |
AIDE: Attribute-Guided MultI-Hop Data Expansion for Data Scarcity in Task-Specific Fine-tuning (2025.acl-industry)
Copied to clipboard
| Challenge: | Existing methods for fine-tuning large language models for specific tasks require extensive seed datasets or struggle to balance task relevance and data diversity. |
| Approach: | They propose a data synthesis framework that uses a multi-hop process to expand very few seed data points while ensuring data diversity and task relevance. |
| Outcome: | The proposed framework outperforms state-of-the-art methods in task-specific fine-tuning by over 30%. |
To Copy Rather Than Memorize: A Vertical Learning Paradigm for Knowledge Graph Completion (2023.acl-long)
Copied to clipboard
Rui Li, Xu Chen, Chaozhuo Li, Yanming Shen, Jianan Zhao, Yujing Wang, Weihao Han, Hao Sun, Weiwei Deng, Qi Zhang, Xing Xie
| Challenge: | Existing methods for embedding knowledge graphs implicitly memorize relation rules to infer missing links, but they are difficult to memorize due to the inherent deficiencies of such implicit memorization strategy. |
| Approach: | They propose a vertical learning paradigm that allows to explicitly copy target information from related factual triples for more accurate prediction. |
| Outcome: | The proposed model improves generalization ability and makes distant link prediction significantly easier. |
MentalGLM Series: Explainable Large Language Models for Mental Health Analysis on Chinese Social Media (2025.emnlp-main)
Copied to clipboard
Wei Zhai, Nan Bai, Qing Zhao, Jianqiang Li, Fan Wang, Hongzhi Qi, Meng Jiang, Xiaoqin Wang, Bing Xiang Yang, Guanghui Fu
| Challenge: | Social media is a key platform for emotional expression, yet deep learning lacks flexibility and interpretability. |
| Approach: | They propose to use Chinese social media to train interpretable mental health instruction datasets to test models' ability to explain their decisions. |
| Outcome: | The proposed models outperform deep learning and LLMs on three mental health downstream tasks and demonstrate their potential for clinical applications. |
Preemptive Answer “Attacks” on Chain-of-Thought Reasoning (2024.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have impressive reasoning capabilities when coupled with Chain-of-Thought (CoT) prompting. |
| Approach: | They propose a scenario where the LLM obtains an answer before engaging in reasoning, and propose two measures to bolster the robustness of this approach. |
| Outcome: | The proposed model significantly impairs its reasoning capability across various CoT methods and a broad spectrum of datasets. |
Leveraging Contrastive Learning and Knowledge Distillation for Incomplete Modality Rumor Detection (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing rumor detection models neglect the semantic coherence between text and image components in multimodal posts . Existing models neglect incomplete modalities in single modal posts, such as missing text or images . |
| Approach: | They propose a framework for incomplete modality rumor detection that captures semantic consistency between text and image pairs while enhancing model generalization to incomplete modalities within individual posts. |
| Outcome: | The proposed framework outperforms state-of-the-art methods on two English and two Chinese benchmark datasets for rumor detection in social media. |
SSS: Editing Factual Knowledge in Language Models towards Semantic Sparse Space (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to modify LMs suffer from sub-optimal locality, where irrelevant neighborhood examples can be adversely influenced. |
| Approach: | They propose to use a model editing method to modify specific examples in LMs to improve locality and reasoning capability by directing the hidden state of edit example towards spaces where semantics are sparse. |
| Outcome: | The proposed method improves locality and reasoning capability on two datasets. |
Multi-level Alignment Pretraining for Multi-lingual Semantic Parsing (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods for multilingual semantic parsing only handle monolingual parsers, while in real world applications such as Chatbot and search engine, we generally need to handle multi-lingual semanticparsing. |
| Approach: | They propose a multi-level alignment pretraining method in a unified architecture for multi-lingual semantic parsing. |
| Outcome: | The proposed method outperforms state-of-the-art methods on a publicly avail-able multi-lingual semantic parsing dataset and a newly constructed dataset. |
TALON: A Multi-Agent Framework for Long-Table Exploration and Question Answering (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to query-relevant content retrieval fail to retrieve contextually relevant data. |
| Approach: | They propose a multi-agent framework for table question answering over long tables . TALON features a planning agent that iteratively invokes a tool agent to access tabular data . |
| Outcome: | The proposed framework achieves average accuracy improvements of 7.5% and 12.0% across all language models. |
DuReadervis: A Chinese Dataset for Open-domain Document Visual Question Answering (2022.findings-acl)
Copied to clipboard
| Challenge: | Open-domain question answering is a task that requires answering questions based on a collection of document images. |
| Approach: | They propose to use document images to answer questions using layouts and visual features instead of text. |
| Outcome: | The proposed approach reduces human cost and improves scalability of QA systems by incorporating layouts and visual features. |
ProphetNet: Predicting Future N-gram for Sequence-to-SequencePre-training (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing sequence-to-sequence models are optimized for future n-gram prediction and n stream self-attention mechanism. |
| Approach: | They propose a self-supervised objective called future n-gram prediction and the proposed n stream self-attention mechanism to optimize the model for sequence-to-sequence learning. |
| Outcome: | The proposed model achieves state-of-the-art on CNN/DailyMail, Gigaword, and SQuAD 1.1 benchmarks compared to the models using the same scale pre-training corpus. |
Adaptive Knowledge-Enhanced Bayesian Meta-Learning for Few-shot Event Detection (2021.findings-acl)
Copied to clipboard
| Challenge: | Event detection typically does not have sufficient labelled data, thus can be formulated as a few-shot learning problem. |
| Approach: | They propose a knowledge-based fewshot event detection method which introduces external event knowledge as the knowledge prior of event types. |
| Outcome: | Experiments show that the proposed method outperforms baselines by 15 F 1 points . event detection is an important task in information extraction . |
How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study (2026.acl-long)
Copied to clipboard
Zhexin Zhang, Xian Qi Loye, Victor Shea-Jay Huang, Junxiao Yang, Qi Zhu, Shiyao Cui, Fei Mi, Lifeng Shang, Yingkang Wang, Hongning Wang, Minlie Huang
| Challenge: | Large Reasoning Models have achieved remarkable success on reasoning-intensive tasks, but their enhanced reasoning capabilities do not translate to improved safety performance. |
| Approach: | They propose to use supervised fine tuning to enhance the safety of Large Reasoning Models. |
| Outcome: | The proposed method improves the safety of large reasoning models on reasoning-intensive tasks. |
ShopSimulator: Evaluating and Exploring RL-Driven LLM Agent for Shopping Assistants (2026.acl-long)
Copied to clipboard
Pei Wang, Yanan Wu, Xiaoshuai Song, Weixun Wang, Gengru Chen, Zhongwen Li, Kezhong Yan, Qi Liu, Ken Deng, Shuaibing Zhao, Shaopan Xiong, Xuepeng Liu, Xuefeng Chen, Wanxi Deng, Wenbo Su, Bo Zheng
| Challenge: | Existing studies on large language model-based agents focus on evaluation benchmarks without training support. |
| Approach: | They propose a large-scale Chinese shopping simulation environment that uses large language models to train agents. |
| Outcome: | The proposed model performs poorly in a large-scale and challenging shopping environment in China. |
SpecAgent: A Speculative Retrieval and Forecasting Agent for Code Completion (2026.acl-long)
Copied to clipboard
George Ma, Anurag Koul, Qi Chen, Yawen Wu, Sachit Kuhar, Yu Yu, Aritra Sengupta, Varun Kumar, Murali Krishna Ramanathan
| Challenge: | Large Language Models (LLMs) excel at code-related tasks but struggle in real software repositories. |
| Approach: | They propose a large-scale agent that injects repository context at inference time to improve both latency and code-generation quality by proactively exploring repository files during indexing and constructing speculative context. |
| Outcome: | Experiments show that SpecAgent achieves 9–11% relative performance gains compared to baselines while significantly reducing inference latency. |
Fast and Scalable Dialogue State Tracking with Explicit Modular Decomposition (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing approaches for dialogue state tracking are mainly based on classification-based and extraction-based methods. |
| Approach: | They propose a model which incorporates both classification-based and extraction-based methods and integrates four modules to jointly extract dialogue states. |
| Outcome: | The proposed model outperforms the state-of-the-art models in multi-domain dialogues with many turns of utterances. |
BoundRL: Efficient Token-level Structured Text Segmentation through Reinforced Boundary Generation (2026.findings-acl)
Copied to clipboard
Haoyuan Li, Zhengyuan Shen, Sullam Jeoung, Yueyan Chen, Jiayu Li, Qi Zhu, Shuai Wang, Vassilis N. Ioannidis, Huzefa Rangwala
| Challenge: | Structured texts often contain elements beyond plain language, such as code snippets, which conventional sentence-level segmentation methods cannot handle effectively. |
| Approach: | They propose a token-level approach that performs efficient token-based text segmentation and label prediction for long structured texts. |
| Outcome: | The proposed approach outperforms existing models on short-shot prompts and SFT and standard RLVR models on complex LLM prompts. |
Aurora-M: Open Source Continual Pre-training for Multilingual Language and Code (2025.coling-industry)
Copied to clipboard
Taishi Nakamura, Mayank Mishra, Simone Tedeschi, Yekun Chai, Jason T. Stillerman, Felix Friedrich, Prateek Yadav, Tanmay Laud, Vu Minh Chien, Terry Yue Zhuo, Diganta Misra, Ben Bogin, Xuan-Son Vu, Marzena Karpinska, Arnav Varma Dantuluri, Wojciech Kusa, Tommaso Furlanello, Rio Yokota, Niklas Muennighoff, Suhas Pai, Tosin Adewumi, Veronika Laippala, Xiaozhe Yao, Adalberto Barbosa Junior, Aleksandr Drozd, Jordan Clive, Kshitij Gupta, Liangyu Chen, Qi Sun, Ken Tsui, Nour Moustafa-Fahmy, Nicolo Monti, Tai Dang, Ziyang Luo, Tien-Tung Bui, Roberto Navigli, Virendra Mehta, Matthew Blumberg, Victor May, Hiep Nguyen, Sampo Pyysalo
| Challenge: | Pretrained language models are integral part of AI applications, but their high computational cost limits accessibility. |
| Approach: | They evaluate Aurora-M, a 15B parameter multilingual open-source model trained on English, Finnish, Hindi, Japanese, Vietnamese, and code. |
| Outcome: | The proposed model outperforms existing models on English, Finnish, Hindi, Japanese, Vietnamese, and code. |
Faster In-Context Learning for LLMs via N-Gram Trie Speculative Decoding (2025.emnlp-main)
Copied to clipboard
| Challenge: | In-Context Learning (ICL) is a key method in prompt engineering, but its long retrieved contexts and limited token throughput will slow reasoning speeds. |
| Approach: | They propose a method that leverages the overlap between context and model output to generate drafts from the context. |
| Outcome: | The proposed method achieves the highest mean speedup on Vicuna-7B, Llama2-7B-Chat, and Llma3-8B-Instruct tasks. |
Parallelism and Generation Order in Masked Diffusion Language Models: Limits Today, Potential Tomorrow (2026.findings-acl)
Copied to clipboard
Yangyang Zhong, Yanmei Gu, Zhengqing Zang, Xiaomeng Li, Yuqi Ding, Xibei Jia, Yuting Shen, Zhenzhong Lan, Liwang Zhu, Weiping Liu, Junlin Zhou, Haisheng Liu, Zhong Xin Yu, Pengxin Luo, Donglian Qi, Yunfeng Yan, Junbo Zhao
| Challenge: | Autoregressive (AR) language models dominate modern natural language processing due to strong likelihood-based training objectives and reliable left-to-right decoding. |
| Approach: | They characterize MDLM behavior along two dimensions: parallelism strength and generation order . authors propose a Generate-then-Edit paradigm that mitigates dependency loss . |
| Outcome: | The proposed model improves on tasks that require "backward information" the Generate-then-Edit paradigm improves parallel decoding efficiency while reducing dependency loss. |
Word-level Textual Adversarial Attacking as Combinatorial Optimization (2020.acl-main)
Copied to clipboard
| Challenge: | Existing word-level attack models are far from perfect because of unsuitable search space reduction methods and inefficient optimization algorithms. |
| Approach: | They propose a novel adversarial adversarialist model that incorporates word substitution and particle swarm optimization to solve two problems separately. |
| Outcome: | The proposed model achieves much higher success rates and crafts more high-quality adversarial examples as compared to baseline methods. |
Improving Robustness of Language Models from a Geometry-aware Perspective (2022.findings-acl)
Copied to clipboard
| Challenge: | Recent studies have found that removing the norm-bounded projection and increasing search steps in adversarial training can significantly improve robustness. |
| Approach: | They propose friendly adversarial data augmentation and geometry-aware adversarial training to achieve stronger robustness using fewer search steps. |
| Outcome: | The proposed method can obtain stronger robustness using fewer steps than existing methods. |
MBA-RAG: a Bandit Approach for Adaptive Retrieval-Augmented Generation through Question Complexity (2025.coling-main)
Copied to clipboard
| Challenge: | Existing RAG frameworks either indiscriminately perform retrieval or rely on rigid single-label classifiers to select retrieval methods. |
| Approach: | They propose a framework that dynamically selects the most suitable retrieval strategy based on query complexity. |
| Outcome: | The proposed framework achieves state-of-the-art results on multiple single-hop and multi-hop datasets while reducing retrieval costs. |
NoisyTune: A Little Noise Can Help You Finetune Pretrained Language Models Better (2022.acl-short)
Copied to clipboard
| Challenge: | Existing methods for finetuning pretrained language models (PLMs) have risks in overfitting the pretraining tasks and data, which may lead to suboptimal performance. |
| Approach: | They propose a method which adds noise to parameters of PLMs before fine-tuning. |
| Outcome: | The proposed method can be used on GLUE English and XTREME multilingual benchmarks. |
ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing models with table-specific architectures and pre-training methods perform well on understanding table structures but lack table reasoning skills. |
| Approach: | They propose to pre-train tables with table reasoning skills without complex architectures . they define 7 table reasoning skill, and then pre-teach them to generate tables . |
| Outcome: | The proposed model improves on four tasks and is available on github. |
Experience is the Teacher: Reusing Atomic Thoughts from LLMs to Improve Medical Dialogue (2026.findings-acl)
Copied to clipboard
Guangya Yu, Hui Luo, Qi Ye, Ruihui Hou, Weiyan Zhang, Mingxi Shang, Xuanwu Li, ChunMing Wang, Tong Ruan
| Challenge: | Recent large reasoning models (LLMs) lack dynamic and diverse thinking capabilities . reusing atomic thoughts provides a practical pathway toward dynamic reasoning . |
| Approach: | They propose a framework that extracts atomic thoughts from teacher models and reuses them to guide reasoning and generate responses. |
| Outcome: | The proposed framework extracts atomic thoughts from teacher models and reuses them to guide reasoning and generate responses. |
Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond (2025.acl-industry)
Copied to clipboard
Liang Wen, Yunke Cai, Fenrui Xiao, Xin He, Qi An, Zhenyu Duan, Yimin Du, Junchen Liu, Tanglifu Tanglifu, Xiaowei Lv, Haosheng Zou, Yongchao Deng, Shousheng Jia, Xiangzheng Zhang
| Challenge: | Experimental results show that opensource curriculum training is more effective when distinct datasets are available for different training stages. |
| Approach: | They propose an opensource suite for training long reasoning models using publicdata and models. |
| Outcome: | The proposed model outperforms DeepSeek-R1-DistillQwen-32B models in math reasoning. |
A Survey of Post-Training Scaling in Large Language Models (2025.acl-long)
Copied to clipboard
Hanyu Lai, Xiao Liu, Junjie Gao, Jiale Cheng, Zehan Qi, Yifan Xu, Shuntian Yao, Dan Zhang, Jinhua Du, Zhenyu Hou, Xin Lv, Minlie Huang, Yuxiao Dong, Jie Tang
| Challenge: | Large language models (LLMs) have demonstrated proficiency in understanding and generating human natural languages. |
| Approach: | They propose a framework for scaling large language models using supervised fine-tuning, RLxF and test-time compute methodologies. |
| Outcome: | The proposed model can be used to understand and generate human natural languages. |
Your Pretrained Model Tells the Difficulty Itself: A Self-Adaptive Curriculum Learning Paradigm for Natural Language Understanding (2025.acl-srw)
Copied to clipboard
| Challenge: | Existing curriculum learning approaches rely on manually defined difficulty metrics which may not accurately reflect the model’s own perspective. |
| Approach: | They propose a self-adaptive curriculum learning paradigm that prioritizes fine-tuning examples based on difficulty scores predicted by pre-trained language models (PLMs) they evaluate four datasets covering binary and multi-class classification tasks. |
| Outcome: | The proposed model leads to faster convergence and improved performance compared to standard random sampling. |
Sub-Character Tokenization for Chinese Pretrained Language Models (2023.tacl-1)
Copied to clipboard
Chenglei Si, Zhengyan Zhang, Yingfa Chen, Fanchao Qi, Xiaozhi Wang, Zhiyuan Liu, Yasheng Wang, Qun Liu, Maosong Sun
| Challenge: | Existing tokenization methods for Chinese PLMs treat each character as an indivisible token, but ignore the unique feature of the writing system where additional linguistic information exists below the character level. |
| Approach: | They propose to encode Chinese characters into short sequences and construct Chinese vocabulary based on the encoded text. |
| Outcome: | The proposed tokenizers can tokenize inputs into much shorter sequences, improving computational efficiency. |
Can Large Language Models Understand DL-Lite Ontologies? An Empirical Study (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models (LLMs) have shown remarkable proficiency in understanding textual data and revolutionizing the field of natural language processing. |
| Approach: | They empirically analyze LLMs' capability of understanding Description Logic (DL) ontologies covering 6 representative tasks from syntactic and semantic aspects. |
| Outcome: | The proposed model can understand formal syntax and model-theoretic semantics of concepts and roles, but struggle with understanding TBox NI transitivity and handling ontologies with large ABoxes. |
SPIDE: Serial and Parallel Intertwined Speculative Decoding (2026.findings-acl)
Copied to clipboard
Wenru Xu, Peixuan Xu, Ziqi Yang, Ming Hu, Zihui Wang, Jianzhong Qi, Rongshan Yu, Xiaoliang Fan, Cheng Wang
| Challenge: | Speculative decoding (SD) is a training-free SD framework that orchestrates dynamic alternation combining serial dynamic drafting with parallel draft verification. |
| Approach: | They propose a serial and parallel intertwined speculative DEcoding framework that orchestrates dynamic alternation combining serial dynamic drafting and parallel draft verification. |
| Outcome: | The proposed framework accelerates inference while reducing the LLM usage costs. |
Divide-Verify-Refine: Can LLMs Self-align with Complex Instructions? (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing research shows LLMs struggle with complex instructions involving multiple constraints. |
| Approach: | They propose a framework to divide complex instructions into single constraints and prepare appropriate tools to verify responses. |
| Outcome: | The proposed framework doubles Llama3.1-8B’s constraint adherence and triples Mistral-7B’ s performance. |
Probabilistic Tree-of-thought Reasoning for Answering Knowledge-intensive Complex Questions (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models (LLMs) are capable of answering knowledge-intensive complex questions with chain-of-thought reasoning. |
| Approach: | They propose a method to solve complex questions with a tree-of-thought approach using parametric knowledge and retrieved external knowledge to augment CoT reasoning. |
| Outcome: | The proposed approach outperforms SOTA methods on three Complex QA datasets under the open-domain setting. |
Diagnosing Vision-and-Language Navigation: What Really Matters (2022.naacl-main)
Copied to clipboard
Wanrong Zhu, Yuankai Qi, Pradyumna Narayana, Kazoo Sone, Sugato Basu, Xin Wang, Qi Wu, Miguel Eckstein, William Yang Wang
| Challenge: | Existing models claim to be able to align object tokens with specific visual targets, but there are non-negligible gaps between the two. |
| Approach: | They conduct diagnostic experiments to examine how the agents perceive multimodal input by ablation diagnostics input data. |
| Outcome: | The results show that indoor and outdoor navigation agents refer to object and direction tokens when making decisions. |
The Devil is in the Distributions: Explicit Modeling of Scene Content is Key in Zero-Shot Video Captioning (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing methods for zero-shot video captioning focus on one key aspect of the scene and ignore the rest of the visual input. |
| Approach: | They propose a novel textual prompting strategy for zero-shot video captioning that uses a category-aware retrieval mechanism to promote prompt diversity while ensuring visual relevance. |
| Outcome: | The proposed method outperforms existing methods on in-domain and cross-domain settings. |
JointLK: Joint Reasoning with Language Models and Knowledge Graphs for Commonsense Question Answering (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing KG-augmented models for commonsense question answering ignore the effectively fusing and reasoning over question context representations and the KG representations. |
| Approach: | They propose a novel model which combines a logical reasoning and a dynamic pruning mechanism to solve these limitations. |
| Outcome: | The proposed model improves existing models and performs interpretable reasoning on the CommonsenseQA and OpenBookQA datasets. |
CARL: Constraint-Aware Reinforcement Learning for Planning with LLMs (2026.findings-acl)
Copied to clipboard
Qiuyi Qi, Jinjian Zhang, Mutian Bao, Tian Liang, Guocong Li, Dongnan Liu, Wei Zhou, Jie Liu, Ming Kong, Linjian Mo, Feng Zhang, Qiang Zhu
| Challenge: | Existing approaches to constraint-aware planning fail to enhance the model’s intrinsic focus on constraints. |
| Approach: | They propose a constraint-aware reinforcement learning framework that encourages constraint focus and penalizes neglect of LLMs. |
| Outcome: | The proposed framework outperforms existing frameworks and state-of-the-art reasoning models in a number of real-world applications. |
Asynchronous Deep Interaction Network for Natural Language Inference (D19-1)
Copied to clipboard
| Challenge: | Existing methods have framed the reasoning problem as a semantic matching task. |
| Approach: | They propose an asynchronous deep interaction network (ADIN) to deconstruct the reasoning process and implement asynchron and multi-step reasoning. |
| Outcome: | The proposed model outperforms strong baselines on three popular benchmarks: SNLI, MultiNLI, and SciTail. |
HyperLoRA: Efficient Cross-task Generalization via Constrained Low-Rank Adapters Generation (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to adapt pre-trained language models (PLMs) to emerging tasks are costly and inefficient. |
| Approach: | They propose a meta-network that generates task-specific weights without any optimization. |
| Outcome: | The proposed approach has flexible generalization ability and superior performance over hypenetworks. |
Reevaluating Adversarial Examples in Natural Language (2020.findings-emnlp)
Copied to clipboard
| Challenge: | State-of-the-art adversarial examples lack a common definition of what constitutes success . human surveys show that to preserve semantics, we need to increase the minimum cosine similarities between the embeddings of swapped words and between the sentence encodings of original and perturbed sentences. |
| Approach: | They propose a unified definition of what constitutes a successful adversarial example . they propose four categories of constraints that are used to define adversarials . |
| Outcome: | The proposed framework is based on the outputs of two state-of-the-art synonym substitution attacks. |
Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language Models (2025.findings-acl)
Copied to clipboard
Yingqian Cui, Pengfei He, Jingying Zeng, Hui Liu, Xianfeng Tang, Zhenwei Dai, Yan Han, Chen Luo, Jing Huang, Zhen Li, Suhang Wang, Yue Xing, Jiliang Tang, Qi He
| Challenge: | Chain-of-Thought (CoT) reasoning has improved the performance of large language models (LLMs) however, the detailed reasoning process in CoT often incurs long generation times and high computational costs due to the inclusion of unnecessary steps. |
| Approach: | They propose a method to identify critical reasoning steps using perplexity as a measure of their importance. |
| Outcome: | The proposed method achieves a better balance between reasoning accuracy and efficiency of CoT. |
Is Large Language Model Performance on Reasoning Tasks Impacted by Different Ways Questions Are Asked? (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing studies on Large Language Models (LLMs) have not investigated the impact of question types on LLM performance. |
| Approach: | They evaluate the performance of five Large Language Models on reasoning tasks . they use quantitative reasoning tasks and deductive reasoning tasks to evaluate the models . |
| Outcome: | The results show that Reasoning accuracy does not correlate with final selection accuracy. |
Improving Question Generation with Multi-level Content Planning (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies suggest key phrase selection is essential for question generation, yet it is difficult to connect disjointed phrases into meaningful questions, especially for long context. |
| Approach: | They propose a QG framework that uses multi-level content planning to generate questions from a given context and an answer. |
| Outcome: | The proposed framework outperforms baselines on two popular QG datasets. |
Uncertainty Aware Learning for Language Model Alignment (2024.acl-long)
Copied to clipboard
| Challenge: | Existing alignment strategies that focus on diverse and high-quality data often overlook the intrinsic uncertainty of tasks, learning all data samples equally. |
| Approach: | They propose to introduce the sample uncertainty into the alignment of different task scenarios by a simple fashion by setting the label smoothing value of training according to the uncertainty of individual samples. |
| Outcome: | The proposed model outperforms standard supervised fine-tuning on high-entropy tasks and complex low-entropic tasks. |
CoLA: A Choice Leakage Attack Framework to Expose Privacy Risks in Subset Training (2026.acl-long)
Copied to clipboard
| Challenge: | Existing threat models underestimate subset-training privacy risks because of the scale of modern datasets. |
| Approach: | They propose a unified framework for analyzing privacy leakage in subset selection based on side-channel metadata from the subset process or via the outputs of the target model. |
| Outcome: | The proposed framework analyzes privacy leakage in subset selection based on two different scenarios . |
PathQG: Neural Question Generation from Facts (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing research for question generation encodes text as a sequence of tokens without explicitly modeling fact information. |
| Approach: | They propose to incorporate facts in the input text for question generation in a comprehensive way. |
| Outcome: | The proposed model outperforms state-of-the-art models and human evaluation shows it generates relevant and informative questions. |
Building Multi-domain Dialog State Trackers from Single-domain Dialogs (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing multi-domain dialog state tracking models require significant manual effort to define domain relations and collect data. |
| Approach: | They propose a divide-and-conquer (DAC) DST paradigm and a multi-domain dialog synthesis framework to build multi- domain DST models from single-domain dialogues. |
| Outcome: | The proposed paradigm makes building multi-domain DST models easier on unseen domain combinations. |
Iterative GNN-based Decoder for Question Generation (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing models ignore the rich structure information that is hidden in the previously generated text. |
| Approach: | They propose to model the previous generation using a Graph Neural Network at each decoding step. |
| Outcome: | The proposed model outperforms the state-of-the-art models with sentence-level QG tasks on SQUAD and MARCO datasets. |
GeAR: Generation Augmented Retrieval (2025.findings-acl)
Copied to clipboard
Haoyu Liu, Shaohan Huang, Jianfeng Liu, Yuefeng Zhan, Hao Sun, Weiwei Deng, Feng Sun, Furu Wei, Qi Zhang
| Challenge: | Document retrieval techniques are used to compute semantic similarity between a query and documents, but the scalar similarity fails to reflect enough information, hindering the interpretation of retrieval results. |
| Approach: | They propose a method which improves the global document-query similarity through contrastive learning and integrates well-designed fusion and decoding modules. |
| Outcome: | The proposed method improves the global document-query similarity through contrastive learning and integrates well-designed fusion and decoding modules. |
LEMON: Language-Based Environment Manipulation via Execution-Guided Pre-training (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to language-based environment manipulation are difficult to generalize across environments. |
| Approach: | They propose a general framework for language-based environment manipulation tasks that can deal with various environments using the same generative language model. |
| Outcome: | The proposed framework achieves new state-of-the-art results on four of the tasks and the execution-guided pre-training strategy brings remarkable improvements on all experimental tasks. |
Improving Multi-view Document Clustering: Leveraging Multi-structure Processor and Hybrid Ensemble Clustering Module (2024.lrec-main)
Copied to clipboard
| Challenge: | Experimental results show that DMsECN outperforms existing models for document clustering . |
| Approach: | They propose a multi-view document clustering model with a processor and hybrid module . they demonstrate that DMsECN outperforms existing models by creating a consensus structure from multiple clustering structures. |
| Outcome: | The proposed model outperforms existing models on four multi-view document clustering datasets. |
Enhancing Contrastive Learning with Noise-Guided Attack: Towards Continual Relation Extraction in the Wild (2024.acl-long)
Copied to clipboard
| Challenge: | Existing methods for continual relation extraction (CRE) excel in preserving old knowledge but falter when confronted with contaminated data streams. |
| Approach: | They propose a noise-resistant contrastive framework for continual relation extraction (CRE) that preserves old knowledge while learning incremental corrupted relations. |
| Outcome: | The proposed framework outperforms state-of-the-art methods on various benchmarks with increasing noise rates. |
Intelligent Document Parsing: Towards End-to-end Document Parsing via Decoupled Content Parsing and Layout Grounding (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods fragment document parsing into pipeline of separated subtasks, resulting in incomplete semantics and error propagation. |
| Approach: | They propose an end-to-end document parsing framework that leverages vision-language priors of MLLMs. |
| Outcome: | The proposed method surpasses existing methods significantly in document parsing . it leverages the vision-language priors of MLLMs to decouple parse and layout grounding based on visual information. |
Investigating Capsule Network and Semantic Feature on Hyperplanes for Text Classification (D19-1)
Copied to clipboard
| Challenge: | Various neural networks are designed for text classification on the basis of word embedding, but polysemy is a fundamental feature of the natural language, which brings challenges to text classification. |
| Approach: | They propose to use capsule networks to construct the vectorized representation of semantics and utilize hyperplanes to decompose each capsule to acquire the specific senses. |
| Outcome: | The proposed model extracts more discriminative semantic features and yields significant performance gain compared to baseline methods. |
Searching for Best Practices in Retrieval-Augmented Generation (2024.emnlp-main)
Copied to clipboard
Xiaohua Wang, Zhenghua Wang, Xuan Gao, Feiran Zhang, Yixin Wu, Zhibo Xu, Tianyuan Shi, Zhengyuan Wang, Shizheng Li, Qi Qian, Ruicheng Yin, Changze Lv, Xiaoqing Zheng, Xuanjing Huang
| Challenge: | Retrieval-augmented generation (RAG) techniques have proven to be effective in integrating up-to-date information, mitigating hallucinations, and enhancing response quality, especially in specialized domains. |
| Approach: | They propose several strategies for deploying RAG that balance performance and efficiency. |
| Outcome: | The proposed approaches can significantly enhance question-answering capabilities and accelerate the generation of multimodal content using a “retrieval as generation” strategy. |
Rescue: Ranking LLM Responses with Partial Ordering to Improve Response Generation (2024.acl-srw)
Copied to clipboard
| Challenge: | Customizing LLMs for a specific task involves separating high-quality responses from lower-quality ones. Obtaining a large volume of expert-annotated data is costly for most tasks. |
| Approach: | They propose a method that trains the model to prioritize the best responses from a pool of candidates created for a task using ranking metrics. |
| Outcome: | The proposed method is more robust, less sensitive to noise, and can be achieved with limited human annotations or through heuristic methods. |
Hierarchical Document Refinement for Long-context Retrieval-augmented Generation (2025.acl-long)
Copied to clipboard
Jiajie Jin, Xiaoxi Li, Guanting Dong, Yuyao Zhang, Yutao Zhu, Yongkang Wu, Zhonghua Li, Ye Qi, Zhicheng Dou
| Challenge: | Real-world RAG applications often encounter long-context input scenarios where redundant information and noise results in higher inference costs and reduced performance. |
| Approach: | They propose an efficient plug-and-play refiner that leverages the structural characteristics of long documents. |
| Outcome: | Experiments on seven QA datasets show that LongRefiner achieves competitive performance in various scenarios while using 10x fewer computational costs and latency compared to baseline. |
Harnessing Consistency for Robust Test-Time LLM Ensemble (2026.findings-eacl)
Copied to clipboard
Zhichen Zeng, Qi Yu, Xiao Lin, Ruizhong Qiu, Xuying Ning, Tianxin Wei, Yuchen Yan, Jingrui He, Hanghang Tong
| Challenge: | Existing efforts to improve LLM ensemble quality have focused on model consistency, but failures are often due to heterogeneous tokenization schemes and varying model expertise. |
| Approach: | They propose a plug-and-play technique that harnesses model consistency for robust LLM ensemble. |
| Outcome: | The proposed technique improves ensemble performance and robustness against erroneous signals. |
A Flexible Multi-Task Model for BERT Serving (2022.acl-short)
Copied to clipboard
| Challenge: | a proposed BERT-based multi-task framework is suitable for iterative and incremental development of the tasks. |
| Approach: | They propose an efficient BERT-based multi-task framework that is suitable for iterative and incremental development of the tasks. |
| Outcome: | The proposed framework achieves 99.6% of performance of the full fine-tuning method while reducing up to two thirds of its overhead. |
One LLM Does Not Simulate All Students: Ability-Aware Student Simulation via Cognitive Diagnosis Guided LLM Assignment (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods rely on a single high-capacity LLM to represent an entire population of diverse learners. |
| Approach: | They propose an ability-aware student simulation framework that matches students with appropriate LLM backbones through cognitive alignment. |
| Outcome: | The proposed framework significantly reduces simulation bias and outperforms single-model baselines across the entire proficiency spectrum. |
REAP: Towards Effective Training-Free Chemical Reasoning with Explicit Atomic Priors (2026.findings-acl)
Copied to clipboard
| Challenge: | Current approaches to instill explicit priors into LLMs often suffer from an information bottleneck . |
| Approach: | They propose a training-free framework that equips LLMs with an external knowledge base, enabling them to reason over retrieved chemical priors dynamically. |
| Outcome: | Experiments show that REAP outperforms current reasoning methods and rivals state-of-the-art training-based models. |
SAPGraph: Structure-aware Extractive Summarization for Scientific Papers with Heterogeneous Graph (2022.aacl-main)
Copied to clipboard
Siya Qi, Lei Li, Yiyang Li, Jin Jiang, Dingxin Hu, Yuze Li, Yingqi Zhu, Yanquan Zhou, Marina Litvak, Natalia Vanetik
| Challenge: | Abstractive and extractive methods are used to condense long text into concise summaries while retaining essential information. |
| Approach: | They propose to use paper structure to extract paper summaries from long text . they provide a large-scale dataset of COVID-19-related papers . |
| Outcome: | The proposed framework generates more comprehensive and valuable summaries compared to previous work on COVID-19-related papers. |
Outcome Accuracy is Not Enough: Aligning the Reasoning Process of Reward Models (2026.acl-long)
Copied to clipboard
Binghai Wang, Yantao Liu, Yuxuan Liu, Tianyi Tang, Shenzhi Wang, Chang Gao, Chujie Zheng, Yichang Zhang, Le Yu, Shixuan Liu, Tao Gui, Qi Zhang, Xuanjing Huang, Bowen Yu, Fei Huang, Junyang Lin
| Challenge: | Recent studies observe a phenomenon where reward models achieve high accuracy on static datasets but fail to generalize effectively during RLHF. |
| Approach: | They propose a method that combines rationale consistency with outcome accuracy to improve performance on RM-Bench and JudgeBench. |
| Outcome: | The proposed method surpasses baselines on RM-Bench and JudgeBench by an average of 5% and improves creative writing tasks by 7%. |
Towards Interpretable Tabular Reasoning: Enhancing LLM Reasoning on Tabular Data with Pre-Constructed Logic Graph (2026.acl-long)
Copied to clipboard
Lirong Gao, Zewei Yu, Zhongrui Yin, Qi Zhang, Yuke Zhu, Bo Zheng, Haobo Wang, Junbo Zhao, Gang Chen, Sheng Guo
| Challenge: | Tabular data is used in fields such as finance and healthcare due to its heterogeneity and complexity. |
| Approach: | They propose a Logic-Graph-Enhanced LLM Reasoning framework that integrates the strengths of tree-based models and LLMs to improve their interpretability. |
| Outcome: | The proposed framework outperforms tree-based models and state-of-the-art LLMs on tabular prediction tasks, achieving superior accuracy and interpretability. |
BYOKG-RAG: Multi-Strategy Graph Retrieval for Knowledge Graph Question Answering (2025.emnlp-main)
Copied to clipboard
Costas Mavromatis, Soji Adeshina, Vassilis N. Ioannidis, Zhen Han, Qi Zhu, Ian Robinson, Bryan Thompson, Huzefa Rangwala, George Karypis
| Challenge: | Existing approaches to knowledge graph question answering (KGQA) rely on Large Language Model (LLM) agents for graph traversal and retrieval. |
| Approach: | They propose a framework that synergizes Large Language Models with specialized graph retrieval tools to enhance KGQA. |
| Outcome: | The proposed framework outperforms the second-best graph retrieval method by 4.5% points while showing better generalization to custom KGs. |
Towards Trustworthy Smart Contract Synthesis: A Multi-Agent Framework with Lean-Based Verification (2026.acl-long)
Copied to clipboard
| Challenge: | Smart Contracts are the foundation of Decentralized Finance (DeFi), executing financial logic without trusted intermediaries. |
| Approach: | They propose a framework that integrates LLM-based generation with Lean-based auto-formalization and verification. |
| Outcome: | LeVer is the first trustworthy smart contract synthesis framework that integrates LLM-based generation with Lean-based auto-formalization and verification. |
CSP:Code-Switching Pre-training for Neural Machine Translation (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to train neural machine translation models are data-hungry and low-resource . et al., 2018; Radford e.t., 2019; Yang ee.,2019) proposes a new pre-training method for NMT . |
| Approach: | They propose a new pre-training method which randomly replaces some words in the input sentence with their translation words in target language. |
| Outcome: | The proposed method improves on unsupervised and supervised NMT models by making full use of monolingual corpora. |
ClusterUCB: Efficient Gradient-Based Data Selection for Targeted Fine-Tuning of LLMs (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Gradient-based data influence approximation is not feasible in practice. |
| Approach: | They propose a gradient-based data selection framework with clustering and a modified Upper Confidence Bound algorithm to solve this problem. |
| Outcome: | The proposed framework can achieve comparable results to the original gradient-based data selection methods while reducing computational consumption. |
Democratizing Reasoning Ability: Tailored Learning from Large Language Model (2023.emnlp-main)
Copied to clipboard
Zhaoyang Wang, Shaohan Huang, Yuxuan Liu, Jiahai Wang, Minghui Song, Zihan Zhang, Haizhen Huang, Furu Wei, Weiwei Deng, Feng Sun, Qi Zhang
| Challenge: | Large language models (LLMs) exhibit impressive emergent abilities in natural language processing, but their democratization is hindered due to huge computation requirements and closed-source nature. |
| Approach: | They propose a tailored learning approach to distill the exclusive reasoning ability to smaller LMs to facilitate democratization. |
| Outcome: | The proposed approach enables the democratization of the exclusive reasoning ability by leveraging the black-box model as a reasoning teacher. |
Medical Graph RAG: Evidence-based Medical Large Language Model via Graph Retrieval-Augmented Generation (2025.acl-long)
Copied to clipboard
Junde Wu, Jiayuan Zhu, Yunli Qi, Jingkun Chen, Min Xu, Filippo Menolascina, Yueming Jin, Vicente Grau
| Challenge: | GraphRAG framework is designed to enhance LLMs in generating evidence-based medical responses. |
| Approach: | They propose a graph-based Retrieval-augmented generation framework to enhance LLMs in generating evidence-based medical responses. |
| Outcome: | The proposed framework outperforms state-of-the-art models on 9 medical Q&A benchmarks, 2 health fact-checking datasets, and a long-form generation test set. |
Sub-Instruction Aware Vision-and-Language Navigation (2020.emnlp-main)
Copied to clipboard
| Challenge: | Despite significant advances, few previous works are able to fully utilize the strong correspondence between visual and textual sequences. |
| Approach: | They propose to provide agents with fine-grained annotations during training and provide them with sub-instructions and their corresponding paths. |
| Outcome: | The proposed method improves the performance of four state-of-the-art agents in a room-to-room (R2R) benchmark dataset. |
UCS: Estimating Unseen Coverage for Improved In-Context Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing selection methods prioritize heuristic notions of relevance or diversity and provide limited insight into the coverage of a demonstration set. |
| Approach: | They propose a training-free, subset-level coverage prior that is unrevealed by a model-consistent embedding and a Smoothed Good-Turing estimator to estimate the number of unrevelled clusters within a candidate subset. |
| Outcome: | Experiments on multiple intent-classification and reasoning benchmarks show that augmenting strong baselines with UCS improves ICL accuracy by 2-6% under the same selection budget. |
ONION: A Simple and Effective Defense Against Textual Backdoor Attacks (2021.emnlp-main)
Copied to clipboard
| Challenge: | Backdoor attacks can manipulate the output of deep neural networks and possess high insidiousness. |
| Approach: | They propose a textual backdoor defense based on outlier word detection that can handle all the textual attacks. |
| Outcome: | The proposed method can handle all the textual backdoor attack situations. |
GAPO: Robust Advantage Estimation for Real-World Code LLMs (2026.findings-acl)
Copied to clipboard
Jianqing Zhang, Zhezheng Hao, Wei Xia, Hande Dong, Hong Wang, Chenxing Wei, Yuyan Zhou, Yubin Qi, Qiang Lin, Jian Cao
| Challenge: | Reinforcement learning (RL) is widely used for post-training large language models (LLMs) in code editing, but in real-world code editing scenarios, reward distributions are often skewed with unpredictable noise, leading to distorted advantage computation and increased rollout outliers. |
| Approach: | They propose a group-relative method that finds an interval with the highest SNR and uses the median of that interval as an adaptive Q to replace the group mean in advantage calculation. |
| Outcome: | The proposed method improves on nine instruction-tuned LLMs while remaining plug-and-play and efficient. |
Unsupervised Chinese Word Segmentation with BERT Oriented Probing and Transformation (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for unsupervised Chinese word segmentation exploit shallow semantic information, which can miss important context. |
| Approach: | They propose to take advantage of deep contextual semantic information with a self-training manner to transform it into explicit word segmentation ability. |
| Outcome: | The proposed approach achieves state-of-the-art F1 score on two CWS benchmark datasets. |
DynClean: Training Dynamics-based Label Cleaning for Distantly-Supervised Named Entity Recognition (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods to identify entities using distant annotations are expensive and time-consuming. |
| Approach: | They propose a training dynamics-based label cleaning approach to characterize distant annotations and an automatic threshold estimation strategy to locate errors in distant labels. |
| Outcome: | The proposed method outperforms several advanced DS-NER approaches across four datasets. |
RECOST: External Knowledge Guided Data-efficient Instruction Tuning (2024.findings-acl)
Copied to clipboard
| Challenge: | Considering the high computing power overhead, data-efficient instruction tuning is proposed to reduce the training data size. |
| Approach: | They propose a framework to improve instruction tuning by integrating external knowledge into a single pipeline. |
| Outcome: | The proposed method achieves better results with only 1% of the full dataset. |
Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction (2023.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in multimodal pre-trained models have significantly improved information extraction from visually-rich documents (VrDs). |
| Approach: | They propose a method to predict token sequences within visually-rich documents by a simple prediction head. |
| Outcome: | The proposed method can be used to predict token mentions as token sequences within documents. |
Cross-modality Information Check for Detecting Jailbreaking in Multimodal Large Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Multimodal Large Language Models (MLLMs) are susceptible to jailbreak attacks, authors say . multimodal information increases the risk of attacks, but also provides additional data . |
| Approach: | They propose a jailbreaking detector that detects maliciously perturbed image inputs . cross-modality information detector is designed to detect cross-modal similarity between harmful queries and adversarial images. |
| Outcome: | a new tool can detect maliciously perturbed image inputs without modification or computation cost. |
SCMAPR: Self-Correcting Multi-Agent Prompt Refinement for Complex-Scenario Text-to-Video Generation (2026.findings-acl)
Copied to clipboard
| Challenge: | Text-to-Video (T2V) generation is a challenge under complex scenarios. |
| Approach: | They propose a scenario-aware and self-correcting multi-agent prompt refinement framework for T2V prompting. |
| Outcome: | The proposed framework improves text-to-video alignment and overall generation quality under complex scenarios. |
Restoring Ancient Ideograph: A Multimodal Multitask Neural Network Approach (2024.lrec-main)
Copied to clipboard
| Challenge: | despite efforts to preserve cultural relics, many ancient artefacts have fallen prey to ravages of time, natural deterioration, or deliberate human actions. |
| Approach: | They propose a multimodal multitask restoration model that uses visual and context understanding to restore ancient texts. |
| Outcome: | The proposed model predicts damaged characters and generates restored images simultaneously. |
Forget the Token and Pixel: Rethinking Gradient Ascent for Concept Unlearning in Multimodal Generative Models (2025.findings-acl)
Copied to clipboard
Jiaqi Li, Chuanyi Zhang, Miaozeng Du, Hui Zhang, Yongrui Chen, Qianshan Wei, Junfeng Fang, Ruipeng Wang, Sheng Bi, Guilin Qi
| Challenge: | Gradient Ascent (GA) has emerged as a promising approach for concept unlearning in Multimodal Generative Models (MGMs). |
| Approach: | They propose a novel approach that selectively applies GA to targeted Conceptual Knowledge while preserving Natural Knowledge through Gradient Descent (GD). |
| Outcome: | The proposed approach removes Conceptual Knowledge and inadvertently diminishes Natural Knowledge, resulting in utility degradation. |
D.Va: Validate Your Demonstration First Before You Use It (2025.acl-long)
Copied to clipboard
| Challenge: | In-context learning (ICL) heavily relies on selecting effective demonstrations to achieve outputs that better align with the expected results. |
| Approach: | They propose a method which integrates a demonstration validation perspective into this field and integrates it into the learning paradigm. |
| Outcome: | The proposed method surpasses all retrieval-based in-context learning techniques across both natural language understanding (NLU) and natural language generation (NLG) tasks. |
Leveraging Argumentation Knowledge Graph for Interactive Argument Pair Identification (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing researches focus on sentence matching but the interaction of opinions requires reasoning of knowledge, which is beyond textual information. |
| Approach: | They propose to leverage external knowledge to enhance the identification of interactive argument pairs by analyzing the discussion thread of the target topic in an online forum. |
| Outcome: | The proposed model achieves state-of-the-art in the benchmark dataset. |
Many Heads Are Better Than One: Improved Scientific Idea Generation by A LLM-Based Multi-Agent System (2025.acl-long)
Copied to clipboard
Haoyang Su, Renqi Chen, Shixiang Tang, Zhenfei Yin, Xinzhe Zheng, Jinzhe Li, Biqing Qi, Qi Wu, Hui Li, Wanli Ouyang, Philip Torr, Bowen Zhou, Nanqing Dong
| Challenge: | Recent AI methods have shown promise in tasks such as hypothesis generation and experimental design, but they fail to replicate the collaborative nature of real-world scientific practices. |
| Approach: | They propose a virtual scientific system that mimics the collaborative nature of scientific research by organizing a team of agents to generate, evaluate, and refine research ideas. |
| Outcome: | The proposed system outperforms the state-of-the-art method in producing new scientific ideas and offers valuable insights to guide future research. |
A Bounding Box is Worth One Token - Interleaving Layout and Text in a Large Language Model for Document Understanding (2025.findings-acl)
Copied to clipboard
Jinghui Lu, Haiyang Yu, Yanjie Wang, Yongjie Ye, Jingqun Tang, Ziwei Yang, Binghong Wu, Qi Liu, Hao Feng, Han Wang, Hao Liu, Can Huang
| Challenge: | Existing methods for integrating spatial layouts with text have limitations . existing methods produce overly long text sequences or lack autoregressive traits of LLMs . |
| Approach: | They introduce Interleaving Layout and Text in a Large Language Model (LayTextLLM) they use OCR-derived text and spatial layouts to integrate with LLMs for document understanding . |
| Outcome: | The proposed model shows an increase in performance in KIE and VQA tasks. |
WarriorCoder: Learning from Expert Battles to Augment Code Large Language Models (2025.acl-long)
Copied to clipboard
Huawen Feng, Pu Zhao, Qingfeng Sun, Can Xu, Fangkai Yang, Lu Wang, Qianli Ma, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang, Qi Zhang
| Challenge: | Recent code large language models have demonstrated impressive performance on code-related tasks. |
| Approach: | They propose a paradigm that learns from expert battles to address these limitations . they create an arena where leading LLMs challenge each other with evaluations . |
| Outcome: | The proposed model improves on existing models by leveraging expert battles . it achieves state-of-the-art performance even without relying on proprietary models . |
PLAWBENCH: A Rubric-Based Benchmark for Evaluating LLMs in Real-World Legal Practice (2026.acl-long)
Copied to clipboard
Yuzhen Shi, Huanghai Liu, Yiran HU, Song Gaojie, Xu Xinran, Yubo Ma, Tianyi Tang, Li Zhang, Qingjing Chen, Feng Di, Wenbo Lv, Weiheng Wu, Kexin Yang, Sen Yang, Wei Wang, Rongyao Shi, Qiu Yuanyang, Yuemeng Qi, Zhang Jingwen, Sui Xiaoyu, Yifan Chen, Zhang Yi, An Yang, Bowen Yu, Dayiheng Liu, Junyang Lin, Weixing Shen, Bing Zhao, Charles L. A. Clarke, HU Wei
| Challenge: | Existing benchmarks for large language models (LLMs) are coarse, single-dimensional metrics and do not explicitly assess fine-grained legal reasoning. |
| Approach: | They propose a Practical Law Benchmark to evaluate large language models in real-world legal practice scenarios. |
| Outcome: | The proposed model is based on 850 questions and 13 scenarios with expert-designed evaluation rubrics. |
White-box Testing of NLP models with Mask Neuron Coverage (2022.findings-naacl)
Copied to clipboard
| Challenge: | Recent research has shown that black-box testing is not applicable to NLP models. |
| Approach: | They propose a set of white-box testing methods that are customized for transformer-based NLP models and adapt them to a black-box test suite. |
| Outcome: | The proposed methods can reduce testing suites by 60% while retaining failing tests, thereby concentrating faultdetection power of the test suite. |
GTR-LSTM: A Triple Encoder for Sentence Generation from RDF Data (P18-1)
Copied to clipboard
| Challenge: | Knowledge bases are becoming an enabling resource for many applications including Q&A systems, recommender systems, and summarization tools. |
| Approach: | They propose a system to translate RDF triples into natural sentences using an encoder-decoder framework. |
| Outcome: | The proposed model outperforms the baseline model by 17.6%, 6.0%, and 16.4% in terms of BLEU, METEOR, and TER scores. |
Stealthy Jailbreak Attacks on Large Language Models via Benign Data Mirroring (2025.naacl-long)
Copied to clipboard
Honglin Mu, Han He, Yuxin Zhou, Yunlong Feng, Yang Xu, Libo Qin, Xiaoming Shi, Zeming Liu, Xudong Han, Qi Shi, Qingfu Zhu, Wanxiang Che
| Challenge: | Existing black-box jailbreak methods often rely on model feedback . existing methods may be intercepted by content moderators during the search process . |
| Approach: | They propose a method that guides malicious prompt construction by local training a mirror model of the target black-box model through benign data distillation. |
| Outcome: | The proposed method achieves a 92% attack success rate and 80% stealth rate on a subset of AdvBench. |
MulDimIF: A Multi-Dimensional Constraint Framework for Evaluating and Improving Instruction Following in Large Language Models (2026.findings-acl)
Copied to clipboard
Junjie Ye, Caishuang Huang, Zhuohan Chen, Wenjie Fu, Chenyuan Yang, Leyi Yang, Yilong Wu, Peng Wang, Meng Zhou, Xiaolong Yang, Tao Gui, Qi Zhang, Zhongchao Shi, Jianping Fan, Xuanjing Huang
| Challenge: | Existing research has focused on constraint categories, offering little guidance for improving instruction following abilities. |
| Approach: | They propose a multi-dimensional constraint framework that allows for instruction following . they construct 9,106 code-verifiable samples and evaluate 18 LLMs . |
| Outcome: | The proposed framework improves instruction following performance without compromising general performance. |
Fine-Grained Data Ordering Improves Fine-Tuning for Large Language Models (2026.findings-acl)
Copied to clipboard
Xiaomeng Hu, Yixuan Tang, Haoze Li, Hao Chen, Qi Zhang, Zhanming Shen, Yiming Zhang, Haobo Wang, Junbo Zhao
| Challenge: | Prior work focused on data preprocessing, focusing on filtering and cleaning data . a study aimed to improve fine-grained scheduling of data order in epochs . |
| Approach: | They propose a fine-grained scheduling method of data order in epochs to fill this gap . they define data difficulty based on relevance between data and model . |
| Outcome: | The proposed method improves on pre-training and small-scale fine-tuning experiments 2.4% over baselines. |
TestAgent: An Adaptive and Intelligent Expert for Human Assessment (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing adaptive testing methods face several challenges due to mechanized nature of most algorithms and noisy response data. |
| Approach: | They propose to use large language models to enhance adaptive testing through interactive engagement to capture test-takers’ responses and anomalies. |
| Outcome: | The proposed agent achieves more accurate results with 20% fewer questions than state-of-the-art baselines and testers preferred it in speed, smoothness, and other dimensions. |
A Multi-Task Learning Framework for Extracting Bacteria Biotope Information (D19-57)
Copied to clipboard
| Challenge: | Existing methods to extract information from unstructured text are slow or expensive to get. |
| Approach: | They propose a multi-task transfer multi-learning method for Bacteria Biotope rel+ner task . they use BERT and pre-train it using mask language models and next sentence prediction . |
| Outcome: | The proposed method achieves the best performance on all metrics including slot error rate, precision and recall in the Bacteria Biotope rel+ner subtask. |
LongHeads: Multi-Head Attention is Secretly a Long Context Processor (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models struggle to process lengthy inputs due to limited length generalization and attention’s quadratic computational demands. |
| Approach: | They propose a training-free framework that allows each head to attend to important context chunks instead of allowing each head a full sentence . |
| Outcome: | The proposed framework unlocks multi-head attention's untapped potential by allowing each head to attend to important context chunks instead of the full sentence. |
MARS-Bench: A Multi-turn Athletic Real-world Scenario Benchmark for Dialogue Evaluation (2025.findings-emnlp)
Copied to clipboard
Chenghao Yang, Yinbo Luo, Zhoufutu Wen, Qi Chu, Tao Gong, Longxiang Liu, Kaiyuan Zhang, Jianpeng Jiao, Ge Zhang, Wenhao Huang, Nenghai Yu
| Challenge: | Large Language Models (LLMs) have been widely adopted in real-world dialogue applications, but their robustness is criticized all along. |
| Approach: | They propose to use play-by-play text commentary to build a multi-turn athletic real-world scenario dialogue benchmark to evaluate three critical aspects of multi-turned conversations: ultra multi- turn, interactive multi-twist, and cross-turn tasks. |
| Outcome: | The proposed benchmarks outperform open-source LLMs on three critical aspects of multi-turn conversations: ultra multi-turned, interactive multi- turn, and cross-turn tasks. |
Dynamic Curriculum Learning for Low-Resource Neural Machine Translation (2020.coling-main)
Copied to clipboard
| Challenge: | Recent work on neural machine translation (NMT) has demonstrated impressive performance improvements and became the de-facto standard. |
| Approach: | They propose a dynamic curriculum learning method to reorder training samples in training using a Transformer-based system. |
| Outcome: | The proposed method outperforms baselines on three low-resource machine translation benchmarks and different sized data of WMT’16 En-De. |
LLM4Decompile: Decompiling Binary Code with Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Decompilation aims to convert binary code to high-level source code, but traditional tools like Ghidra often produce results that are difficult to read and execute. |
| Approach: | They propose an open-source LLM series trained to decompile binary code . they optimize the LLM training process and introduce the Llm4Decompile-End models . |
| Outcome: | The proposed models outperform GPT-4o and Ghidra on the HumanEval and ExeBench benchmarks by over 100% in terms of re-executability rate. |
Towards Understanding Omission in Dialogue Summarization (2023.acl-long)
Copied to clipboard
| Challenge: | Existing methods for dialogue summarization are far from satisfactory . omission is a major factor in affecting the quality of summarizing, but few studies have explored the problem . |
| Approach: | They propose a dataset that provides high-quality omission labels for dialogue summarization . they propose to use this dataset to detect omitted dialogue utterances . |
| Outcome: | The proposed dataset improves summarization quality by providing ground-truth omission labels . the proposed dataset and codes are publicly available . |
Beyond Quantity: Trajectory Diversity Scaling for Code Agents (2026.findings-acl)
Copied to clipboard
Guhong Chen, Chenghao Sun, Cheng Fu, Qiyao Wang, Zhihong Huang, ChaoPeng Wei, Guangxu Chen, Feiteng Fang, Ahmadreza Argha, Bing Zhao, Xander Xu, Qi Han, Hamid Alinejad-Rokny, Qiang Qu, Binhua Li, Shiwen Ni, Min Yang, HU Wei, Yongbin Li
| Challenge: | Code large language models (LLMs) are becoming tool-interactive agents . quantity-centric scaling exhibits an early bottleneck that underutilizes trajectory data . et al.: a new approach to scale trajectory diversity improves tool-use generalization . |
| Approach: | They propose a Trajectory Diversity Scaling-based data synthesis framework for code agents that scales performance through diversity rather than raw volume. |
| Outcome: | Experiments on general tool-use benchmarks and code agent tasks show that TDScaling improves tool-user generalization and inherent coding proficiency. |
Making Parameter-efficient Tuning More Efficient: A Unified Framework for Classification Tasks (2022.coling-1)
Copied to clipboard
Xin Zhou, Ruotian Ma, Yicheng Zou, Xuanting Chen, Tao Gui, Qi Zhang, Xuanjing Huang, Rui Xie, Wei Wu
| Challenge: | Large pre-trained language models (PLMs) have demonstrated superior performance in industrial applications. |
| Approach: | They propose a framework that re-uses existing parameter-efficient methods with a unified classifier. |
| Outcome: | The proposed framework improves the efficiency of existing parameter-efficient methods with a unified classifier. |
LONGAGENT: Achieving Question Answering for 128k-Token-Long Documents through Multi-Agent Collaboration (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) have been successful in understanding language and processing text, but their cost prohibits their practical applications. |
| Approach: | They propose a multi-agent collaboration method that breaks down lengthy documents into smaller, more manageable chunks and organizes the member agents to read their assigned chunks. |
| Outcome: | The proposed method achieves 16.42% and 1.63% accuracy gains over existing models on single-hop and multi-hop QA settings. |
Distantly Supervised Named Entity Recognition via Confidence-Based Multi-Class Positive and Unlabeled Learning (2022.acl-long)
Copied to clipboard
| Challenge: | Existing methods for named entity recognition suffer from incomplete annotations due to incompleteness of external knowledge bases. |
| Approach: | They propose a method to solve the named entity recognition problem under distant supervision using dictionaries and knowledge bases. |
| Outcome: | The proposed method outperforms existing methods on two benchmark datasets labeled by various knowledge bases. |
WildDoc: How Far Are We from Achieving Comprehensive and Robust Document Understanding in the Wild? (2025.emnlp-main)
Copied to clipboard
An-Lan Wang, Jingqun Tang, Lei Liao, Hao Feng, Qi Liu, Xiang Fei, Jinghui Lu, Han Wang, Hao Liu, Yuliang Liu, Xiang Bai, Can Huang
| Challenge: | Existing benchmarks for document understanding in the wild are based on scanned or digital documents . however, these benchmarks fail to capture the challenges posed by documents in the real world . |
| Approach: | They propose a new benchmark that incorporates a diverse set of manually captured document images reflecting real-world conditions. |
| Outcome: | The proposed model is based on a set of manually captured document images reflecting real-world conditions and is compared with digital or scanned documents. |
Attribution-Based Analysis and Optimization of Modular Agentic Workflows (2026.findings-acl)
Copied to clipboard
Yingxuan Yang, Bo Huang, Siyuan Qi, Chao Feng, Haoyi Hu, Yuxuan Zhu, Jinbo Hu, Haoran Zhao, Ziyi He, Xiao Liu, ZongYu Wang, Muning Wen, Lin Qiu, Xuezhi Cao, Xunliang Cai, Yong Yu, Weinan Zhang
| Challenge: | Large Language Models (LLMs) have driven the rise of agentic workflows . yet, how can we attribute performance gains to individual upgrades and their interactions? |
| Approach: | They propose a game-theoretic framework that models component upgrades as players and evaluates component coalitions to compute Shapley values. |
| Outcome: | The proposed framework provides interaction-aware attribution and recommendation for model allocation under a fixed workflow structure. |
Going “Deeper”: Structured Sememe Prediction via Transformer with Tree Attention (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing studies ignore hierarchical structures of sememes in sememe-based semantic description systems. |
| Approach: | They propose a structured sememe prediction problem to predict a sememes tree with hierarchical structures rather than a set of sememas. |
| Outcome: | The proposed model outperforms baseline models and shows its effectiveness . it predicts a sememe tree with hierarchical structures rather than a set of sememes . |
Auto Search Indexer for End-to-End Document Retrieval (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Generative retrieval heavily relies on the “preprocessed” document identifiers, thus limiting its retrieval performance and ability to retrieve new documents. |
| Approach: | They propose a fully end-to-end retrieval paradigm that can learn the best docids for existing and new documents automatically via a semantic indexing module. |
| Outcome: | The proposed model outperforms baselines on public and industrial datasets and can handle new documents. |
LLMEval-Fair: A Large-Scale Longitudinal Study on Robust and Fair Evaluation of Large Language Models (2026.acl-long)
Copied to clipboard
Ming Zhang, Yujiong Shen, Jingyi Deng, Yuhui Wang, Huayu Sha, Kexin Tan, Qiyuan Peng, Yue Zhang, Junzhe Wang, Shichun Liu, Yueyuan Huang, Jingqi Tong, Changhao Jiang, Yilong Wu, Zhihao Zhang, Mingqi Wu, Mingxu Chai, Zhiheng Xi, Shihan Dou, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing evaluation of Large Language Models on static benchmarks is vulnerable to data contamination and leaderboard overfitting. |
| Approach: | LLMEval-Fair framework provides a framework for dynamic evaluation of Large Language Models . evaluators use a proprietary bank of 220k graduate-level questions to analyze model data . |
| Outcome: | LLMEval-Fair provides robust and credible evaluation framework for Large Language Models . it provides a strong empirical validation for the dynamic evaluation paradigm . |
Design Choices for Extending the Context Length of Visual Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Existing open-source Visual Language Models lack systematic exploration into extending their context length, and commercial models often provide limited details. |
| Approach: | They propose to extend Visual Language Models (VLMs) to 128K lengths and open-source the code, data, and models. |
| Outcome: | The proposed model is based on the Qwen-VL series model and is competitive with commercial model GPT-4V. |
Post-Training Dialogue Summarization using Pseudo-Paraphrasing (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing approaches to dialogue summarization use dialogue-specific features that require additional knowledge to recognize or make the models harder to tune. |
| Approach: | They propose to post-train pretrained language models to rephrase from dialogue to narratives and fine-tune them as usual. |
| Outcome: | The proposed approach outperforms existing models by summary quality and implementation costs. |
Alleviating Exposure Bias via Multi-level Contrastive Learning and Deviation Simulation in Abstractive Summarization (2023.findings-acl)
Copied to clipboard
| Challenge: | Abstractive summarization systems have a severe mismatch between training and inference, i.e., exposure bias. |
| Approach: | They propose a multi-level contrastive learning framework for abstractive summarization and a tailored sparse decoder self-attention pattern to bridge the gap between training and inference. |
| Outcome: | The proposed framework outperforms the state-of-the-art models on two summarization datasets while adding relatively low overhead. |
Open Domain Question Answering with Conflicting Contexts (2025.findings-naacl)
Copied to clipboard
Siyi Liu, Qiang Ning, Kishaloy Halder, Zheng Qi, Wei Xiao, Phu Mon Htut, Yi Zhang, Neha Anna John, Bonan Min, Yassine Benajiba, Dan Roth
| Challenge: | Open domain question answering systems often rely on information retrieved from large collections of text to answer questions. |
| Approach: | They evaluate and benchmark three powerful Large Language Models with a dataset . they find that 25% of unambiguous open domain questions can lead to conflicting contexts . |
| Outcome: | The proposed model can't be used to answer questions with conflicting contexts . it can be fine tuned to provide richer information into the model's training . |
Beyond Boundaries: Learning a Universal Entity Taxonomy across Datasets and Languages for Open Named Entity Recognition (2025.coling-main)
Copied to clipboard
Yuming Yang, Wantong Zhao, Caishuang Huang, Junjie Ye, Xiao Wang, Huiyuan Zheng, Yang Nan, Yuran Wang, Xueying Xu, Kaixin Huang, Yunke Zhang, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Current Large Language Models struggle with complex entity taxonomies in open domains and lack NER capabilities. |
| Approach: | They propose a dataset to guide LLMs' generalization in Open NER under a universal entity taxonomy. |
| Outcome: | The proposed model outperforms GPT-4 in 3 out-of-domain benchmarks across 15 datasets and 6 languages. |
Your Vision-Language Model Itself Is a Strong Filter: Towards High-Quality Instruction Tuning with Data Selection (2024.findings-acl)
Copied to clipboard
Ruibo Chen, Yihan Wu, Lichang Chen, Guodong Liu, Qi He, Tianyi Xiong, Chenxi Liu, Junfeng Guo, Heng Huang
| Challenge: | Existing data selection methods for instruction-following large language models rely on unreliable scores or use downstream tasks for selection. |
| Approach: | They propose a method that utilizes the VLM itself as a filter to select high-quality instruction-tuning data. |
| Outcome: | The proposed method can reach better results compared to full data settings with merely about 15% samples and can achieve superior performance against competitive baselines. |
FacLens: Transferable Probe for Foreseeing Non-Factuality in Fact-Seeking Question Answering of Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing non-factuality detection methods require response generation, which incurs significant computational overhead. |
| Approach: | They propose a lightweight model called Factuality Lens which effectively probes hidden representations of fact-seeking questions for the NFP task. |
| Outcome: | The proposed model is able to probe hidden representations of fact-seeking questions and reduce development costs. |
EnigmaToM: Improve LLMs’ Theory-of-Mind Reasoning Capabilities with Neural Knowledge Base of Entity States (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing ToM reasoning methods rely excessively on off-the-shelf LLMs, reducing their efficiency and limiting their applicability to high-order ToM. |
| Approach: | They propose a neuro-symbolic framework that integrates a Neural Knowledge Base of Entity States and knowledge injection to enhance ToM reasoning. |
| Outcome: | The proposed framework improves ToM reasoning on ToMi, HiToM, and FANToM benchmarks. |
On Large Language Models’ Hallucination with Regard to Known Facts (2024.naacl-long)
Copied to clipboard
Che Jiang, Biqing Qi, Xiangyu Hong, Dayuan Fu, Yang Cheng, Fandong Meng, Mo Yu, Bowen Zhou, Jie Zhou
| Challenge: | Large language models are successful in answering factoid questions but are also prone to hallucination. |
| Approach: | They propose self-reporting to the model when faced with such limitations. |
| Outcome: | The proposed classifier can detect hallucinations with an 88% success rate and can be used to answer factoid questions with correct answer knowledge. |
Mitigating Hallucinations in Large Vision-Language Models by Self-Injecting Hallucinations (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for hallucination mitigation are based on external dependency and require external annotations or auxiliary models for preference data collection. |
| Approach: | a new method is proposed to help model-generated hallucinations without external dependencies. |
| Outcome: | a new method that self-injects hallucinations into a generated response improves halluuutations mitigation. |
RESIN-11: Schema-guided Event Prediction for 11 Newsworthy Scenarios (2022.naacl-demo)
Copied to clipboard
Xinya Du, Zixuan Zhang, Sha Li, Pengfei Yu, Hongwei Wang, Tuan Lai, Xudong Lin, Ziqi Wang, Iris Liu, Ben Zhou, Haoyang Wen, Manling Li, Darryl Hannan, Jie Lei, Hyounghun Kim, Rotem Dror, Haoyu Wang, Michael Regan, Qi Zeng, Qing Lyu, Charles Yu, Carl Edwards, Xiaomeng Jin, Yizhu Jiao, Ghazaleh Kazeminejad, Zhenhailong Wang, Chris Callison-Burch, Mohit Bansal, Carl Vondrick, Jiawei Han, Dan Roth, Shih-Fu Chang, Martha Palmer, Heng Ji
| Challenge: | Existing methods for event prediction are incomplete and noisy. |
| Approach: | They propose to use news-related event schemas to extract newsworthy events . they build a demo website and include a video demonstrating the framework . |
| Outcome: | The proposed framework can be applied to a wide variety of newsworthy scenarios. |
Improving Consistency for Text Summarization with Energy Functions (2023.findings-emnlp)
Copied to clipboard
Qi Zeng, Qingyu Yin, Zheng Li, Yifan Gao, Sreyashi Nag, Zhengyang Wang, Bing Yin, Heng Ji, Chao Zhang
| Challenge: | Current abstractive summarization models generate inconsistent content due to the inherently noisy dataset and the discrepancy between maximum likelihood estimation based training objectives and consistency measurements. |
| Approach: | They propose a new consistency taxonomy that categorizes inconsistent content into faithfulness, factuality, and self-supportiveness. |
| Outcome: | Experiments on XSUM and CNN/DM datasets show that EnergySum mitigates the trade-off between accuracy and consistency. |
UReader: Universal OCR-free Visually-situated Language Understanding with Multimodal Large Language Model (2023.findings-emnlp)
Copied to clipboard
Jiabo Ye, Anwen Hu, Haiyang Xu, Qinghao Ye, Ming Yan, Guohai Xu, Chenliang Li, Junfeng Tian, Qi Qian, Ji Zhang, Qin Jin, Liang He, Xin Lin, Fei Huang
| Challenge: | Existing studies for visually-situated language understanding have shown shallow zero-shot visual text recognition ability when fed a low-resolution image with salient text information. |
| Approach: | They propose a model for universal OCR-free visually-situated language understanding based on the Multimodal Large Language Model (MLLM) their model is jointly finetuned on a wide range of visually situated language understanding tasks via a unified instruction format. |
| Outcome: | The proposed model achieves state-of-the-art ocr-free performance in 8 out of 10 visually-situated language understanding tasks across 5 domains: documents, tables, charts, natural images, and webpage screenshots. |
Detecting Hallucinations in Retrieval-Augmented Generation via Semantic-level Internal Reasoning Graph (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for detecting faithfulness hallucinations are coarse or do not capture the models’ internal reasoning processes, making it difficult to learn. |
| Approach: | They propose a semantic-level internal reasoning graph-based method for detecting faithfulness hallucination using Large language models. |
| Outcome: | The proposed method achieves better overall performance compared to state-of-the-art baselines on RAGTruth and Dolly-15k. |
Reinforcement Learning on Pre-Training Data (2026.acl-long)
Copied to clipboard
Siheng Li, Kejiao Li, Zenan Xu, Guanhua Huang, Kun Li, Haoyuan Wu, null Wujiajia, Zihao Zheng, Chenchen Zhang, Kun Shi, Xue Gong, Qi Yi, Ruibin Xiong, Tingqiang Xu, Yuhao Jiang, Jianfeng Yan, Yuyuan Zeng, Guanghui Xu, Jinbao Xue, Zhijiang xu, Zheng Fang, Shuai LI, Qibin Liu, Xiaoxue Li, Zhuoyu Li, Yangyu Tao, Fei Gao, Cheng Jiang, Bochao Wang, Kai Liu, Jianchen Zhu, Wai Lam, Bo Zhou, Di Wang
| Challenge: | Recent progress in large language models is driven by scaling of training compute through pre-training with nexttoken prediction (NTP) or post-training (RL) Pre-training using NTP enables models to acquire extensive knowledge and skills from general data, but it suffers from data inefficiency and catastrophic forgetting in continual learning settings. |
| Approach: | They propose to scale training compute through pre-training with next-token prediction (NTP) or post-training by scaling reinforcement learning (RL) to improve learning from general data. |
| Outcome: | Experiments on multiple benchmarks and models show that the proposed approach improves continual pre-training and provides a strong foundation for post-training on Qwen3-8B-Base. |
MovieUN: A Dataset for Movie Understanding and Narrating (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Automatic movie narration generation and narration grounding are important to provide a true movie experience for the blind and visually impaired. |
| Approach: | They propose to use movie clips as a benchmark to support automatic movie narration generation and narration grounding tasks. |
| Outcome: | The proposed methods are effective in supporting two movie-based tasks for the blind and visually impaired. |
MindBridge: Scalable and Cross-Model Knowledge Editing via Memory-Augmented Modality (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing knowledge editing methods overfit to specific models, causing edited knowledge to be discarded during each LLM update and requiring frequent re-editing. |
| Approach: | They propose a solution that allows editors to edit knowledge in multiple LLMs at the same time. |
| Outcome: | The proposed solution performs better even in editing tens of thousands of knowledge entries and can adapt to different LLMs. |
Measuring Data Diversity for Instruction Tuning: A Systematic Analysis and A Reliable Metric (2025.acl-long)
Copied to clipboard
Yuming Yang, Yang Nan, Junjie Ye, Shihan Dou, Xiao Wang, Shuo Li, Huijie Lv, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing studies have explored various diversity-aware data selection methods to construct high-quality datasets and enhance model performance. |
| Approach: | They propose to use data diversity to measure instruction tuning of large language models. |
| Outcome: | The proposed diversity metric outperforms existing methods on simulated and real-world data and shows that it captures diversity variations and achieves a 0.97 correlation with instruction tuning. |
Speculating LLMs’ Chinese Training Data Pollution from Their Tokens (2025.emnlp-main)
Copied to clipboard
Qingjie Zhang, Di Wang, Haoting Qian, Liu Yan, Tianwei Zhang, Ke Xu, Qi Li, Minlie Huang, Hewu Li, Han Qiu
| Challenge: | Experiments on GPT and other 23 LLMs indicate that tokens widely exist while GPT’s vocabulary behaves the worst: more than 23% long Chinese tokens (i.e., a token with more than two Chinese characters) are either porn or online gambling. |
| Approach: | They propose to locate Polluted Chinese (PoC) tokens in LLMs and build a PoC token detector to label them in vocabularies by considering each token’s semantics and related contents from the search engines. |
| Outcome: | The proposed method predicts that the ratio of “*” related webpages in GPT-4o's training data is around 0.5%. |
RePair: Automated Program Repair with Process-based Feedback (2024.findings-acl)
Copied to clipboard
| Challenge: | Commercial-scale language models (LMs) have taken APR to unprecedented levels, but they are limited by parameters and humans interact with them through explicit prompts. |
| Approach: | They propose a method that utilizes process supervision to improve program repair by allowing users to input feedback from compilers and test cases. |
| Outcome: | The proposed method outperforms large outcome-based generation methods and is inspired by strategies used in programming competitions. |
CQG: A Simple and Effective Controlled Generation Framework for Multi-hop Question Generation (2022.acl-long)
Copied to clipboard
| Challenge: | Current models can not ensure the complexity of generated questions, so they may generate shallow questions that can be answered without multi-hop reasoning. |
| Approach: | They propose a controlled framework to generate multi-hop questions that contain key entities in multi- hop reasoning chains and a novel Transformer-based decoder to guarantee that key entities appear in the questions. |
| Outcome: | The proposed model outperforms the state-of-the-art model 25% on HotpotQA. |
Structure Regularized Neural Network for Entity Relation Classification for Chinese Literature Text (N18-2)
Copied to clipboard
| Challenge: | Existing methods for relation classification have been used in natural language processing. |
| Approach: | They propose a relation classification task for Chinese literature text using a new dataset. |
| Outcome: | The proposed model outperforms the state-of-the-art methods on Chinese literature text. |
Semi-Supervised Dialogue Policy Learning via Stochastic Reward Estimation (2020.acl-main)
Copied to clipboard
| Challenge: | Existing methods for dialogue policy optimization do not provide sufficient supervision signals at the end of dialogues. |
| Approach: | They propose to learn from state-action pairs of an optimal policy to provide turn-by-turn rewards. |
| Outcome: | The proposed approach outperforms competitive policy learning baselines on a benchmark multi-domain dataset. |
GameTox: A Comprehensive Dataset and Analysis for Enhanced Toxicity Detection in Online Gaming Communities (2025.naacl-short)
Copied to clipboard
| Challenge: | Existing methods to detect toxic behavior in online gaming environments are limited by utterance-level annotation. |
| Approach: | They propose to annotate game chat utterances for toxicity detection through intent classification and slot filling. |
| Outcome: | The proposed model improves the detection of toxic speech in online gaming environments and reveals limitations of current models. |
Evaluating LLMs’ Assessment of Mixed-Context Hallucination Through the Lens of Summarization (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models generate coherent text and follow instructions across diverse tasks, but a critical challenge in scaling LLM applications is hallucination, where the generated content lacks factual grounding or deviates from the intended discourse context. |
| Approach: | They use summarization as a representative task to evaluate LLMs' capability in detecting mixed-context hallucinations, specifically distinguishing between factual and non-factual hallucinos. |
| Outcome: | The proposed model distinguishes between factual and non-factual hallucinations, and their performance bottlenecks. |
Lost in Pronunciation: Detecting Chinese Offensive Language Disguised by Phonetic Cloaking Replacement (2025.emnlp-industry)
Copied to clipboard
Haotan Guo, Jianfei He, Jiayuan Ma, Hongbin Na, Zimu Wang, Haiyang Zhang, Qi Chen, Wei Wang, Zijing Shi, Tao Shen, Ling Chen
| Challenge: | Phonetic Cloaking Replacement (PCR) is a problem in content moderation in China. |
| Approach: | They organize PCR into a four-way surface-form taxonomy and compile PCR-ToxiCN, a dataset of 500 phonetically cloaked offensive posts gathered from the RedNote platform. |
| Outcome: | The proposed model achieves only an F1-score and zero-shot chain-of-thought prompting pushes performance even lower. |
TabPrompt: Graph-based Pre-training and Prompting for Few-shot Table Understanding (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods of Table Understanding (TU) focus on the textual content within the tabular data, disregarding the topological information of the table. |
| Approach: | They propose a framework that uses tabs to understand tabular data without ignoring the topological information of the table. |
| Outcome: | The proposed framework outperforms baselines in few-shot table understanding tasks. |
OneNet: A Fine-Tuning Free Framework for Few-Shot Entity Linking via Large Language Model Prompting (2024.emnlp-main)
Copied to clipboard
| Challenge: | Entity Linking (EL) is the process of associating ambiguous textual mentions to specific entities in a knowledge base. |
| Approach: | They propose a framework that utilizes the few-shot learning capabilities of Large Language Models without the need for fine-tuning to improve the accuracy of EL. |
| Outcome: | The framework outperforms current state-of-the-art methods in a few-shot entity linking task. |
Merge then Realign: Simple and Effective Modality-Incremental Continual Learning for Multimodal LLMs (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in Multimodal Large Language Models (MLLMs) have enhanced their versatility as they integrate a growing number of modalities. |
| Approach: | They propose a simple MCL paradigm that addresses forgetting and misalignment . they propose 'MErge then ReAlign' to extend existing models to more modalities . |
| Outcome: | The proposed paradigm is easy to deploy and highly reusable in the MLLM community. |
LitVISTA: A Benchmark for Narrative Orchestration in Literary Text (2026.acl-long)
Copied to clipboard
Mingzhe Lu, Yiwen Wang, Yanbing Liu, Qi You, Chong Liu, Ruize Qin, Haoyu Dong, Wenyu Zhang, JiaRui Zhang, Yue Hu, Yunpeng Li
| Challenge: | Existing large language models focus on causal coherence, neglecting the complex story arcs and orchestration inherent in human narratives. |
| Approach: | They propose a high-dimensional framework for narrative orchestration that unifies human and model perspectives while jointly characterizing narrative function and structure in a common space. |
| Outcome: | The proposed framework unifies human and model perspectives while jointly characterizing narrative function and structure in a common space. |
PDF-to-Tree: Parsing PDF Text Blocks into a Tree (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies try to extract one universal reading order for PDF files, however, some applications, like Retrieval Augmented Generation, require breaking long articles into sections and subsections for better indexing. |
| Approach: | They propose a new task and dataset, PDF-to-Tree, which organizes the text blocks of a PDF into a tree structure. |
| Outcome: | The proposed parser achieves 93.93% accuracy, surpassing baseline methods by 6.72%. |
CMQCIC-Bench: A Chinese Benchmark for Evaluating Large Language Models in Medical Quality Control Indicator Calculation (2025.findings-acl)
Copied to clipboard
Guangya Yu, Yanhao Li, Zongying Jiang, Yuxiong Jin, Li Dai, Yupian Lin, Ruihui Hou, Weiyan Zhang, Yongqi Fan, Qi Ye, Jingping Liu, Tong Ruan
| Challenge: | Medical quality control indicators are essential to assess the qualifications of healthcare institutions for medical services. |
| Approach: | They propose a Chinese electronic medical records-based dataset for MQCIC and propose CF-IR method that disentangles clinical fact verification and inferential rule reasoning actions. |
| Outcome: | The proposed method outperforms Chain-of-Thought methods on 20 representative LLMs, covering general and medical models. |
Adversarial Knowledge Stimulated Contrastive Prompting for Few-shot Language Learners (2023.findings-acl)
Copied to clipboard
| Challenge: | Prompt-based fine-tuning has boosted performance of Pre-trained language models on few-shot Natural Language Understanding (NLU) tasks by employing task-specific prompts. |
| Approach: | They propose a Cloze-driven prompt framework for prompt tuning that implicitly stimulates knowledge from pre-trained language models. |
| Outcome: | The proposed framework outperforms state-of-the-art for prompt-based fine-tuning on few-shot NLU tasks. |
“Where Does This Strange Smell Come from?”: Enabling Conversational Interfaces for Artificial Olfaction (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing Artificial Olfaction (AO) systems are not compatible with smart home scenarios due to diverse obstacles and the need for natural interaction. |
| Approach: | They propose to use large language models to train a CIAO system for Odor Classification and Odor Source Localization in smart home scenarios. |
| Outcome: | The proposed system outperforms existing systems in indoor event detection scenarios. |
Pre-training Language Model as a Multi-perspective Course Learner (2023.findings-acl)
Copied to clipboard
Beiduo Chen, Shaohan Huang, Zihan Zhang, Wu Guo, Zhenhua Ling, Haizhen Huang, Furu Wei, Weiwei Deng, Qi Zhang
| Challenge: | Experimental results show that our method significantly improves ELECTRA’s average performance by 2.8% and 3.2% absolute points respectively on GLUE and SQuAD 2.0 benchmarks. |
| Approach: | They propose a multi-perspective course learning method to fetch many degrees and visual angles for sample-efficient pre-training and to fully leverage the relationship between generator and discriminator. |
| Outcome: | The proposed method improves ELECTRA's performance on GLUE and SQuAD 2.0 benchmarks and overshadows recent advanced ELECL-style models under the same settings. |
Automatic Construction of Sememe Knowledge Bases via Dictionaries (2021.findings-acl)
Copied to clipboard
| Challenge: | Sememe knowledge bases (SKBs) are used to analyze natural language processing. |
| Approach: | They propose a method to build sememe knowledge bases from an existing dictionary . they propose to use existing dictionaries to build an English and a French SKB . |
| Outcome: | The proposed method is superior to HowNet, the most widely used SKB that takes decades to build manually. |
SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented Generation (2025.acl-long)
Copied to clipboard
| Challenge: | Adaptive Retrieval-Augmented Generation (RAG) is an effective strategy to alleviate hallucination of large language models (LLMs). |
| Approach: | They propose a novel adaptive RAG model that extracts self-aware uncertainty of large language models from their internal states and invokes retrieval accordingly. |
| Outcome: | The proposed model outperforms existing adaptive RAG methods on complex and simple Question Answering datasets. |
HIPO: A Hierarchical Prompt Optimization Framework with Task Awareness and Fine-Grained Debugging (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for prompt optimization apply the same prompt across all samples . existing methods ignore variation in sample difficulty . |
| Approach: | They propose a framework that shifts the paradigm from dataset-level to sample-level optimization. |
| Outcome: | The proposed framework outperforms baselines on 27 tasks and reduces API calls, token consumption and overall cost by 1.2 to 80. |
Toward Secure Tuning: Mitigating Security Risks from Instruction Fine-Tuning (2026.acl-long)
Copied to clipboard
Yanrui Du, Fenglei Fan, Sendong Zhao, Jiawei Cao, Ming Ma, Danyang Zhao, Shuren Qi, Ting Liu, Bing Qin
| Challenge: | Instruction Fine-Tuning (IFT) has emerged as a critical technique for customizing Large Language Models (LLMs) however, recent studies have revealed that IFT can compromise the built-in security mechanisms of LLMs, posing significant security risks. |
| Approach: | They propose a method that shifts learning burden onto security-robust parameters and propose 'warm-up' phase that preferentially trains Mods_Rob to learn low-level features with minimal security risk. |
| Outcome: | The proposed method reduces security risks without sacrificing performance gains across knowledge-intensive datasets. |
MECoT: Markov Emotional Chain-of-Thought for Personality-Consistent Role-Playing (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing Large Language Models struggle to maintain emotionally consistent and psychologically plausible character personalities. |
| Approach: | They propose a framework that enhances LLMs’ ability to generate authentic personality-driven dialogues through stochastic emotional transitions. |
| Outcome: | The proposed framework achieves 93.3% emotional accuracy on the RAPD dataset and significantly outperforms existing approaches. |
Intuitive Fine-Tuning: Towards Simplifying Alignment into a Single Process (2025.acl-long)
Copied to clipboard
| Challenge: | Supervised Fine-Tuning (SFT) and Preference Optimization (PO) are key processes for aligning Language Models with human preferences post pre-training. |
| Approach: | They propose to combine Supervised Fine-Tuning and Preference Optimization (PO) with two sub-processes defined at token level within the Markov Decision Process (MDP) |
| Outcome: | The proposed process performs comparably or even superiorly to SFT and some typical PO methods across several tasks, particularly those requires generation, reasoning, and fact-following abilities. |
When to Trust LLMs: Aligning Confidence with Response Quality (2024.findings-acl)
Copied to clipboard
Shuchang Tao, Liuyi Yao, Hanxing Ding, Yuexiang Xie, Qi Cao, Fei Sun, Jinyang Gao, Huawei Shen, Bolin Ding
| Challenge: | Existing methods express reliability by confidence level, but lack objective guidance . Existing approaches express reliability but lack guidance on when to trust LLMs . |
| Approach: | They propose a reward-based approach to align confidence with quality to ensure reliability . they propose 'conqORD' to help model to verbalize greater confidence for higher quality responses . |
| Outcome: | Experiments show that CONQORD significantly improves confidence and response accuracy . the proposed approach can be used to determine reliability of large language models . |
BloomEval: A Bloom’s Cognitive Taxonomy-Based Benchmark for Evaluating LRMs via Cognitive Hierarchy Trace (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing benchmarks for Large Reasoning Models rely on answer correctness, but fail to assess the structural coherence and cognitive soundness of the reasoning process itself. |
| Approach: | They propose a framework that maps a model's reasoning trajectory onto hierarchical cognitive levels and an annotation pipeline to ensure a scalable yet reliable annotation pipeline. |
| Outcome: | The proposed framework detects hierarchy jumps, breaks, and overthinking errors and enables scalable yet reliable annotation. |
VerIF: Verification Engineering for Reinforcement Learning in Instruction Following (2025.emnlp-main)
Copied to clipboard
| Challenge: | Best practices for RL in instruction following remain underexplored. |
| Approach: | They propose a verification method that combines rule-based code verification with LLM-based verification from a large reasoning model. |
| Outcome: | The proposed method achieves state-of-the-art performance among models of comparable size and generalizes well to unseen constraints. |
A Global Past-Future Early Exit Method for Accelerating Inference of Pre-trained Language Models (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing methods to accelerate inference speed of pre-trained language models are limited to local representations of exit layer . current models are associated with large memory requirement and high computational cost, which slow down inference and further encumber the application of PLMs. |
| Approach: | They propose a method to exit early without passing through all inference layers . they take into consideration all the linguistic information embedded in the past layers a global perspective . |
| Outcome: | The proposed method outperforms existing methods by a large margin . it uses linguistic information embedded in the past layers and future features . the proposed method is scalable and cost-effective . |
Latent Reasoning for Low-Resource Question Generation (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to multihop question generation require extensive data collection and decomposition. |
| Approach: | They propose a generative approach that optimizes the two-phase model without question decomposition data. |
| Outcome: | The proposed approach outperforms baselines on HOTPOTQA, a benchmark multi-hop question answering dataset. |
Graph Ensemble Learning over Multiple Dependency Trees for Aspect-level Sentiment Classification (2021.naacl-main)
Copied to clipboard
| Challenge: | Recent work on aspect-level sentiment classification has shown that syntactic information is effective in capturing long-range syntaktic relations that are obscure from the surface form. |
| Approach: | They propose a graph ensemble technique that integrates syntactic structures with GNNs to better leverage syntaktic information in the face of parsing errors. |
| Outcome: | The proposed model outperforms models with single dependency tree and beats other models without adding model parameters. |
Transferring from Formal Newswire Domain with Hypernet for Twitter POS Tagging (D18-1)
Copied to clipboard
| Challenge: | Existing POS tagging methods for Twitter use labeled newswire text . however, Twitter users tend to mimic formal media expressions and develop linguistically informal styles. |
| Approach: | They propose to use newswire text to learn POS tagging for Twitter while twitter users are developing linguistically informal styles. |
| Outcome: | The proposed method achieves better performance than state-of-the-art methods on three different datasets. |
Improving Relation Extraction with Knowledge-attention (D19-1)
Copied to clipboard
| Challenge: | Existing attention mechanisms are data-driven, but most are data driven. |
| Approach: | They propose a knowledge-attention encoder which integrates prior knowledge from external lexical resources into deep neural networks for relation extraction task. |
| Outcome: | The proposed system outperforms existing CNN, RNN, and self-attention based models on a large-scale relation extraction dataset. |
Causal Intervention for Abstractive Related Work Generation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models ignore the inherent causality during related work generation, leading to spurious correlations which downgrade the models’ generation quality and generalizability. |
| Approach: | They propose a Causal Intervention Module for Related Work Generation (CaM) that captures causal relationships in related work generation and implements causal interventions to mitigate the negative impact of spurious correlations. |
| Outcome: | The proposed framework improves the quality and coherence of generated related work by capturing causalities in the generation process. |
Advancing Fine-Grained Visual Understanding with Multi-Scale Alignment in Multi-Modal Models (2025.emnlp-main)
Copied to clipboard
Wei Wang, Zhaowei Li, Qi Xu, Linfeng Li, YiQing Cai, Botian Jiang, Hang Song, Xingcan Hu, Pengyu Wang, Li Xiao
| Challenge: | Recent advances in multi-modal large language models have demonstrated remarkable capabilities in multimodal understanding, reasoning, and interaction. |
| Approach: | They propose a method that effectively aligns and integrates multi-scale knowledge of objects . they use a pipeline that provides over 300K essential training data to enhance alignment . |
| Outcome: | The proposed method effectively aligns and integrates multi-scale knowledge of objects, including texts, coordinates, and images. |
TEF: Causality-Aware Taxonomy Expansion via Front-Door Criterion (2025.coling-main)
Copied to clipboard
| Challenge: | Existing research still faces spurious query-anchor matching due to unobserved factors. |
| Approach: | They propose a model that uses the front-door criteria to decompose the expansion process into a parser module and a connector to isolate confounding effects. |
| Outcome: | Extensive experiments on three benchmarks validate the effectiveness of the proposed model. |
Learning Domain Representation for Multi-Domain Sentiment Classification (N18-1)
Copied to clipboard
| Challenge: | Training data for sentiment analysis is abundant in multiple domains, yet scarce for other domains. |
| Approach: | They propose to use domain-specific representations of input sentences to improve sentiment classification . they use a descriptor vector to map adversarially trained domain-general Bi-LSTM inputs into domain- specific representations . |
| Outcome: | The proposed model outperforms existing methods on multi-domain sentiment analysis significantly. |
A Partition Filter Network for Joint Entity and Relation Extraction (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to extract entity and relation feature are flawed because they do not consider the intimate connection between NER and RE. |
| Approach: | They propose a partition filter network to model two-way interaction between tasks . they leverage two gates: entity and relation gate, to segment neurons into two task partitions and one shared partition. |
| Outcome: | The proposed model performs significantly better than previous approaches on six public datasets. |
Please refuse to answer me! Mitigating Over-Refusal in Large Language Models via Adaptive Contrastive Decoding (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for mitigating over-refusal can't maintain low refusal ratio for harmless queries while keeping high for malicious queries. |
| Approach: | They propose a model-agnostic approach to mitigate over-refusal in large language models . they propose an adaptive contrastive decoding strategy that incorporates or removes the refusal token distribution . |
| Outcome: | The proposed approach reduces the refusal ratio for over-refusal queries by 10.35% while increasing the refusal rate for malicious queries by 0.13%. |
Beyond the Tip of Efficiency: Uncovering the Submerged Threats of Jailbreak Attacks in Small Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Small language models (SLMs) have become increasingly prominent in the deployment on edge devices due to their high efficiency and low computational cost. |
| Approach: | They evaluate the security performance of 13 state-of-the-art small language models under various jailbreak attacks. |
| Outcome: | The proposed methods demonstrate that SLMs are quite susceptible to jailbreak attacks and some are even vulnerable to harmful prompts. |
TaeBench: Improving Quality of Toxic Adversarial Examples (2025.naacl-industry)
Copied to clipboard
| Challenge: | Existing adversarial examples generate invalid or ambiguous examples that fool the systems into wrong detection. |
| Approach: | They propose an annotation pipeline for quality control of generated toxic adversarial examples (TAE) they use model-based automated annotation and human-based quality verification to assess quality requirements of a TAE dataset. |
| Outcome: | The proposed pipeline can transfer-attack SOTA toxicity content moderation models and services with adversarial training. |
TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP (2020.emnlp-demos)
Copied to clipboard
| Challenge: | TextAttack provides implementations of 16 adversarial attacks from the literature and supports a variety of models and datasets. |
| Approach: | They introduce a Python framework for adversarial attacks, data augmentation, and adversarially training in NLP. |
| Outcome: | This paper introduces a Python framework for adversarial attacks, data augmentation, and adversarially training in NLP. |
GroundingGPT: Language Enhanced Multi-modal Grounding Model (2024.acl-long)
Copied to clipboard
Zhaowei Li, Qi Xu, Dong Zhang, Hang Song, YiQing Cai, Qi Qi, Ran Zhou, Junting Pan, Zefeng Li, Vu Tu, Zhida Huang, Tao Wang
| Challenge: | Existing multi-modal large language models focus on capturing global information while neglecting the fine-grained local information in multimodal inputs. |
| Approach: | They propose an end-to-end language enhanced multi-modal grounding model that performs fine-grained grounding tasks for image, video and audio. |
| Outcome: | The proposed model achieves impressive fine-grained understanding of multi-modal inputs while maintaining or improving its global comprehension capabilities. |
DoG-Instruct: Towards Premium Instruction-Tuning Data via Text-Grounded Instruction Wrapping (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing methods to collect high-quality instruction-response pairs suffer from unaffordable labor costs or severe hallucinations in the self-generation of LLMs. |
| Approach: | They propose a method that trains LLMs to generate instruction-response pairs based on human-written documents rather than relying solely on self-generation without context. |
| Outcome: | The proposed method outperforms existing typical methods on multiple benchmarks and shows that it is 100% scalable. |
Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward (2026.findings-acl)
Copied to clipboard
Guanhua Huang, Tingqiang Xu, Mingze Wang, Qi Yi, Xue Gong, Siheng Li, Ruibin Xiong, Kejiao Li, Yuhao Jiang, Bo Zhou
| Challenge: | Recent studies show that RLVR training is slow and results plateau as policy entropy collapses . low-probability regularization (Lp-Reg) reduces the number of low-quality exploratory tokens induced by RL training . |
| Approach: | They propose a method to reduce RLVR over-penalization by eliminating low-probability exploratory tokens . they propose 'Low-provability Regularization' to reduce the gradual elimination of low-quality exploratory entropy tokens. |
| Outcome: | The proposed method eliminates low-probability exploratory tokens and prevents suppression of potentially valuable low-property candidates. |
PRIME: A Process-Outcome Alignment Benchmark for Verifiable Reasoning in Mathematics and Engineering (2026.acl-long)
Copied to clipboard
Xiangfeng Wang, Hangyu Guo, Yanlin Lai, Mitt Huang, Liang Zhao, Chengyuan Yao, Yinmin Zhang, Qi Han, null Xiaoxiaoren, Chun Yuan, Tong Xu, Zheng Ge, Xiangyu Zhang, Daxin Jiang
| Challenge: | Current outcome-centric verification paradigms neglect potential errors in the derivation process. |
| Approach: | They propose a process-aware RLVR training paradigm utilizing verifiers selected via **PRIME**. |
| Outcome: | The proposed approach outperforms the baseline verification paradigm on AIME24, AIME25, and Beyond-AIME models. |
Knowledge Poisoning Attacks on Medical Multi-Modal Retrieval-Augmented Generation (2026.acl-long)
Copied to clipboard
Peiru Yang, Haoran Zheng, Tong Ju, Shiting Wang, Wanchun Ni, Jiajun Liu, Shangguang Wang, Yongfeng Huang, Tao Qi
| Challenge: | Existing studies have investigated knowledge poisoning attacks in medical RAG systems . knowledge poison attacks can disrupt model outputs and undermine system reliability . |
| Approach: | They propose a knowledge poisoning framework that injects misinformation into textual data . they propose to use paired visual data as a query-agnostic trigger to promote retrieval . |
| Outcome: | The proposed framework produces clinically plausible but incorrect generations on five LLMs and datasets. |
Modeling the Q-Diversity in a Min-max Play Game for Robust Optimization (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for minimizing the worst-case loss of annotated groups are lacking in practice due to expensive annotations and privacy issues. |
| Approach: | They propose a distributionally robust optimization framework that relaxes group identification into direct parameterization by using an interactive training mode. |
| Outcome: | The proposed method outperforms state-of-the-art methods on synthetic and real-world text classification tasks. |
Answering Open-Domain Questions of Varying Reasoning Steps from Text (2021.emnlp-main)
Copied to clipboard
| Challenge: | a new benchmark is developed to answer open-domain questions from text . the system uses a single multi-task transformer model to perform all the necessary subtasks . |
| Approach: | They develop a unified system to answer directly from open-domain questions . they use a single multi-task transformer model to perform all the necessary subtasks . |
| Outcome: | The proposed system can answer open-domain questions on any text collection without prior knowledge of reasoning complexity. |
CA-GAR: Context-Aware Alignment of LLM Generation for Document Retrieval (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent techniques such as Generation-Augmented Retrieval (GAR) and Generative Document Retrieleval (GDR) leverage LLMs to enhance retrieval performance but face key challenges: GAR’s generated content may not always align with the target document corpus, while GDR limits the generative capacity of LLM. |
| Approach: | They propose a Context-Aware Generation-Augmented Retrieval approach which integrates corpus information into their generation process. |
| Outcome: | Experimental results show that CA-GAR outperforms existing methods on seven tasks and four non-English languages. |
A General Framework to Enhance Fine-tuning-based LLM Unlearning (2025.findings-acl)
Copied to clipboard
Jie Ren, Zhenwei Dai, Xianfeng Tang, Hui Liu, Jingying Zeng, Zhen Li, Rahul Goutam, Suhang Wang, Yue Xing, Qi He, Hui Liu
| Challenge: | Existing approaches to remove copyrighted and privacy-sensitive data from Large Language Models (LLMs) have been proposed to remove specific data from LLMs without requiring full retraining. |
| Approach: | They propose a general framework that enhances the utility of fine-tuning-based methods by distinguishing target data and suppressing related generations. |
| Outcome: | The proposed framework improves the unlearning and utility of fine-tuning-based methods by distinguishing the target data and suppressing related generations. |
CrossWOZ: A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset (2020.tacl-1)
Copied to clipboard
| Challenge: | Despite the significant contributions to the community, there is still a gap between existing dialogue corpora and real-life human dialogue data. |
| Approach: | They propose to develop Chinese cross-domain wizard-of-oz task-oriented dataset CrossWOZ with rich annotations of dialogue states and dialogue acts on both user and system sides. |
| Outcome: | The proposed dataset contains 6K dialogue sessions and 102K utterances for 5 domains, including hotel, restaurant, attraction, metro, and taxi. |
DiffZOO: A Purely Query-Based Black-Box Attack for Red-teaming Text-to-Image Generative Model via Zeroth Order Optimization (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing text-to-image (T2I) synthesis diffusion models raise misuse concerns, particularly in creating prohibited or not-safe-for-work (NSFW) images. |
| Approach: | They propose a method which uses zeroth order optimization to procure gradient approximations and harnesses both C-PRV and D-PRv to enhance attack prompts within a discrete prompt space. |
| Outcome: | The proposed method achieves an 8.5% higher average attack success rate than previous works on multiple state-of-the-art safety mechanisms. |
Attentive Pooling with Learnable Norms for Text Representation (2020.acl-main)
Copied to clipboard
| Challenge: | Existing pooling methods that use fixed pooling norms may not be optimal for learning text representations in different tasks. |
| Approach: | They propose to learn pooling norms in an end-to-end manner to automatically find the optimal ones for text representation in different tasks. |
| Outcome: | The proposed approach improves on four benchmark datasets on a neural NLP model. |
Unveiling Linguistic Regions in Large Language Models (2024.acl-long)
Copied to clipboard
| Challenge: | Existing studies on how LLMs achieve cross-lingual alignment and generalization have not explored the intrinsic mechanisms of how they achieve crosslingual alignment. |
| Approach: | They propose to remove a core region that corresponds to linguistic competence and set parameters to zero to reduce performance across 30 different languages. |
| Outcome: | The proposed model can be used to perform tasks requiring abstract knowledge and reasoning in complex languages. |
Anchored Cyclic Generation: A Novel Paradigm for Long-Sequence Symbolic Music Generation (2026.findings-acl)
Copied to clipboard
| Challenge: | Autoregressive sequence modeling has been successful in many domains, but maintaining long-term coherence and structural integrity remains a challenge. |
| Approach: | They propose an ACG paradigm that relies on anchor features from previously generated musical content to guide subsequent generation during the autoregressive process. |
| Outcome: | The proposed framework outperforms existing methods in symbolic music generation tasks. |
Unsupervised Graph-Text Mutual Conversion with a Unified Pretrained Language Model (2023.acl-long)
Copied to clipboard
| Challenge: | Existing unsupervised approaches for learning knowledge graphs require multiple modules and require entity information or relation type for training. |
| Approach: | They propose a method that uses a unified pretrained language model to achieve fully unsupervised graph-text mutual conversion for the first time. |
| Outcome: | The proposed method outperforms state-of-the-art methods for G2T and T2G tasks by fine-tuning only one pretrained model. |
RobustQA: Benchmarking the Robustness of Domain Adaptation for Open-Domain Question Answering (2023.findings-acl)
Copied to clipboard
Rujun Han, Peng Qi, Yuhao Zhang, Lan Liu, Juliette Burger, William Yang Wang, Zhiheng Huang, Bing Xiang, Dan Roth
| Challenge: | Existing ODQA datasets consist mainly of Wikipedia corpus, and are insufficient to study models’ generalizability across diverse domains. |
| Approach: | They propose a benchmark to evaluate ODQA's domain robustness using Wikipedia corpus . they annotate QA pairs in retrieval datasets with rigorous quality control . |
| Outcome: | The proposed benchmark improves model performance on annotated QA pairs in retrieval datasets with rigorous quality control. |
SDAR: A Synergistic Diffusion-AutoRegression Paradigm for Scalable Sequence Generation (2026.findings-acl)
Copied to clipboard
Shuang Cheng, Yihan Bian, Dawei Liu, Yuhua Jiang, Yihao Liu, Linfeng Zhang, Qian Yao, Zhongbo Tian, Wenhai Wang, Qipeng Guo, Kai Chen, Biqing Qi, Bowen Zhou
| Challenge: | Autoregressive (AR) language models are a dominant paradigm in the field of parallelism and non-causal modeling. |
| Approach: | They propose a blockwise discrete diffusion model that preserves AR-compatible serving while enabling parallel intra-block generation. |
| Outcome: | The proposed model achieves theoretical speedups over 5 and wall-clock speedup of 2.3 on H200 GPUs in latency-critical regimes. |
A Structure-Aware Argument Encoder for Literature Discourse Analysis (2022.coling-1)
Copied to clipboard
Yinzi Li, Wei Chen, Zhongyu Wei, Yujun Huang, Chujun Wang, Siyuan Wang, Qi Zhang, Xuanjing Huang, Libo Wu
| Challenge: | Existing research for argument representation learning treats tokens in sentences equally and ignores the implied structure information of argumentative context. |
| Approach: | They propose to separate tokens into two groups to capture structural information of arguments and to incorporate paragraph-level position information into the model. |
| Outcome: | The proposed model captures structural information of arguments and is able to identify arguments automatically. |
Open-World Attribute Mining for E-Commerce Products with Multimodal Self-Correction Instruction Tuning (2025.acl-long)
Copied to clipboard
| Challenge: | Current AM methods focus on extracting attributes from unimodal text, underutilizing multimodal data. |
| Approach: | They propose a framework for multimodal self-correction instruction tuning to extract new attributes from images and text with Multimodal Large Language Models. |
| Outcome: | The proposed framework outperforms state-of-the-art methods on two datasets. |
XAL: EXplainable Active Learning Makes Classifiers Better Low-resource Learners (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing methods for active learning rely on model uncertainty or disagreement to pick unlabeled data, leading to over-confidence in superficial patterns and lack of exploration. |
| Approach: | They propose to use a bi-directional encoder and a uni-directional decoder to generate and score an explanation for low-resource text classification. |
| Outcome: | The proposed model improves on 9 strong baselines on six datasets and can generate explanations for its predictions. |
Modeling and Solving Stable Matching under Probabilistic Preferences with Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have shown strong capability in understanding and simulating humans’ decisions, suggesting a new way to use LLMs as tools to study social systems. |
| Approach: | They propose a Hybrid GS–LLM matching method that integrates Gale–Shapley with probabilistic acceptance decisions. |
| Outcome: | The proposed method outperforms classical baselines in terms of stability and improves robustness under uncertainty. |
An End-to-end Approach for Handling Unknown Slot Values in Dialogue State Tracking (P18-1)
Copied to clipboard
| Challenge: | a dialogue state tracker is a core component in most of today's spoken dialogue systems . slot-filling dialogues are composed of a predefined set of slots that need to be filled through the conversation . |
| Approach: | They propose an E2E architecture that extracts unknown slot values while still achieving state-of-the-art accuracy on the standard DSTC2 benchmark. |
| Outcome: | The proposed architecture achieves state-of-the-art accuracy on the DSTC2 benchmark while retaining predefined slot values. |
Cross-Lingual Consistency of Factual Knowledge in Multilingual Language Models (2023.emnlp-main)
Copied to clipboard
| Challenge: | Multilingual large-scale pretrained language models store factual knowledge, but large variations are observed across languages. |
| Approach: | They propose a ranking-based consistency metric to evaluate cross-lingual consistency of factual knowledge in multilingual PLMs. |
| Outcome: | The proposed metric evaluates cross-lingual consistency of factual knowledge across languages independently from accuracy. |
Cross-lingual Lexical Sememe Prediction (D18-1)
Copied to clipboard
| Challenge: | Sememes are defined as the minimum semantic units of human languages . but most languages do not have sememe-based linguistic knowledge bases . a new framework is proposed to predict sememes for words in other languages based on semems . |
| Approach: | They propose a framework to model correlations between sememes and multi-lingual words in low-dimensional semantic space for sememe prediction. |
| Outcome: | The proposed model improves on baseline methods on real-world datasets. |
Language-Coupled Reinforcement Learning for Multilingual Retrieval-Augmented Generation (2026.findings-acl)
Copied to clipboard
Rui Qi, Fengran Mo, Yufeng Chen, Xue Zhang, Shuo Wang, Hongliang Li, Xu Jinan, Meng Jiang, Jian-Yun Nie, Kaiyu Huang
| Challenge: | Existing approaches to multilingual retrieval-augmented generation (MRAG) use a single-turn retrieval and subsequent optimization to acquire and integrate beneficial external knowledge from multilingual collections. |
| Approach: | They propose a multilingual search-augmented reinforcement learning framework that integrates a language-coupled Group Relative Policy Optimization into the policy and reward models. |
| Outcome: | The proposed framework achieves competitive performance and is appropriate for various practical scenarios such as constrained training data and retrieval over collections encompassing a large number of languages. |
Enhancing Multimodal Large Language Models for Ancient Chinese Character Evolution Analysis via Glyph-Driven Fine-Tuning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing studies have explored the evolutionary analysis of ancient scripts, with particular attention to the transformation of character forms from oracle bone inscriptions to regular script. |
| Approach: | They propose a benchmark framework that leverages MLLMs to analyze the evolution of ancient Chinese scripts. |
| Outcome: | The proposed framework improves performance on core tasks and character recognition and evolutionary reasoning tasks while limiting performance on other tasks. |
HieRec: Hierarchical User Interest Modeling for Personalized News Recommendation (2021.acl-long)
Copied to clipboard
| Challenge: | Existing news recommendation methods learn a single user embedding for each user from their previous behaviors to represent their overall interest. Existing methods only learn 'one' embeddable representation vectors to model user interest. |
| Approach: | They propose a news recommendation method with hierarchical user interest modeling that captures user interest in news rather than a single user embedding. |
| Outcome: | The proposed method can better capture multi-grained user interest in news. |
RethinkingTMSC: An Empirical Study for Target-Oriented Multimodal Sentiment Classification (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Recent studies have shown that current TMSC systems rely on textual information, and the progress in tackling this task has slowed down. |
| Approach: | They propose to integrate both visual and textual information to improve the performance of TMSC by considering multimodal information. |
| Outcome: | The proposed model integrates both visual and textual information to improve performance. |
Tag-grounded Visual Instruction Tuning with Retrieval Augmentation (2024.emnlp-main)
Copied to clipboard
| Challenge: | Multimodal Large Language Models (MLLMs) have seen remarkable progress in providing general instruction-following ability, but struggle with critical problems when required to provide a detailed and accurate response to a visual instruction. |
| Approach: | They propose to enhance the mapping process by using retrieval-augmented tag tokens, which contain rich object-aware information such as object names and attributes. |
| Outcome: | The proposed model outperforms baselines that share the same language model and training data on 12 benchmarks and shows zero-shot capability when provided with specific datastores. |
Hard Sample Aware Prompt-Tuning (2023.acl-long)
Copied to clipboard
| Challenge: | Prompt-tuning based few-shot learning has garnered increasing attention in recent years due to its efficiency and promising capability. |
| Approach: | They propose a framework to distinguish informative hard samples from misleading ones in model training. |
| Outcome: | The proposed framework achieves new SOTA results on a series of NLP tasks pushing the SST-5 accuracy to 49.5% (1.1% point absolute improvement), QNLI accuracy to 74.6% (1.9% absolute improvement) |
PlugAT: A Plug and Play Module to Defend against Textual Adversarial Attack (2022.coling-1)
Copied to clipboard
| Challenge: | Recent studies have shown that adversarial examples can be easily fooled by adversarially perturbed examples. |
| Approach: | They propose a pluggable defense module PlugAT to provide robust predictions by adding a few trainable parameters to the model inputs while keeping the original model frozen. |
| Outcome: | The proposed model improves robustness over several strong baselines whilst training only 9.1% parameters. |
XQuant: Achieving Ultra-Low Bit KV Cache Quantization with Cross-Layer Compression (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse tasks. however, their extensive memory requirements present significant challenges for deployment in resource-constrained environments. |
| Approach: | They propose a training-free framework that achieves ultra-low equivalent bit-width KV cache quantization. |
| Outcome: | The proposed framework outperforms state-of-the-art methods on TruthfulQA and LongBench. |
Subspace Defense: Discarding Adversarial Perturbations by Learning a Subspace for Clean Signals (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing models that extract discrete inputs into fixed-length representations are vulnerable to adversarial attacks that place perturbations on clean inputs to fool DNNs. |
| Approach: | They propose to inspect the subspaces of sample features through spectral analysis to better understand adversarial attacks. |
| Outcome: | The proposed strategy enables the model to inherently suppress adversaries, which boosts model robustness and motivates new directions of effective adversarial defense. |
ClueAnchor: Clue-Anchored Knowledge Reasoning Exploration and Optimization for Retrieval-Augmented Generation (2025.findings-emnlp)
Copied to clipboard
Hao Chen, Yukun Yan, Sen Mei, Wanxiang Che, Zhenghao Liu, Qi Shi, Xinze Li, Yuchun Fan, Pengcheng Huang, Qiushi Xiong, Zhiyuan Liu, Maosong Sun
| Challenge: | Existing RAG systems often underutilize the retrieved documents, authors say . they fail to extract and integrate key clues needed to support faithful and interpretable reasoning . |
| Approach: | a new framework extracts key clues from retrieved content and generates multiple reasoning paths . the framework optimizes the model by selecting the most appropriate reasoning path . |
| Outcome: | Experiments show that ClueAnchor outperforms baseline RAG frameworks in completeness and robustness. |
LLMRouterBench: A Massive Benchmark and Unified Framework for LLM Routing (2026.findings-acl)
Copied to clipboard
Hao Li, Yiqun Zhang, Zhaoyan Guo, Chenxu Wang, Shengji Tang, Qiaosheng Zhang, Yang Chen, Biqing Qi, Peng Ye, Lei Bai, Zhen Wang, Shuyue Hu
| Challenge: | Large language model (LLM) routing assigns each query to the best suitable model from an ensemble. |
| Approach: | They introduce a large-scale benchmark and unified framework for LLM routing . they find that many routing methods exhibit similar performance under unified evaluation . |
| Outcome: | The proposed benchmark provides comprehensive metrics for both performance-oriented and performance-cost trade-off routing. |
Stay Hungry, Stay Focused: Generating Informative and Specific Questions in Information-Seeking Conversations (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing work on question generation assumes knowledge of what the answer might be . instead, questioner must reason pragmatically about how to acquire new information . |
| Approach: | They propose a question generation system that generates pragmatically relevant questions in information-asymmetric conversations. |
| Outcome: | The proposed questioner significantly improves the informativeness and specificity of questions generated over a baseline model as evaluated by metrics as well as humans. |
Detecting Adversarial Samples through Sharpness of Loss Landscape (2023.findings-acl)
Copied to clipboard
Rui Zheng, Shihan Dou, Yuhao Zhou, Qin Liu, Tao Gui, Qi Zhang, Zhongyu Wei, Xuanjing Huang, Menghan Zhang
| Challenge: | Existing studies have shown that adversarial samples are more vulnerable than normal ones to textual adversarials. |
| Approach: | They propose a simple and effective sharpness-based detector that can distinguish adversarial samples by maximizing the loss increment within the region where the inference sample is located. |
| Outcome: | The proposed method outperforms previous detection methods by large margins on three text classification tasks. |
Read Extensively, Focus Smartly: A Cross-document Semantic Enhancement Method for Visual Documents NER (2022.coling-1)
Copied to clipboard
| Challenge: | Existing methods to extract entities from visually-rich documents ignore the inherent multimodality of VRDs and thus the suboptimal results are achieved. |
| Approach: | They propose a multimodal semantic enhancement method that filters redundant information in the current document and a cross-document information awareness technique to enrich the entity-related context. |
| Outcome: | The proposed method outperforms existing methods on two documents understanding benchmarks covering eight languages. |
CARE-CR: Context-Aware Routing and Expert Fusion for Multi-Preference Cognitive Restructuring (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) offer promising avenues for automated cognitive restructuring in mental health settings, but current approaches lack the adaptability to balance conflicting therapeutic dimensions, such as empathy and rationality. |
| Approach: | They propose a decoupled optimization framework that implements a dimension-guided Monte Carlo tree search to train expert policies specialized for distinct therapeutic attributes rather than relying on a monolithic alignment strategy. |
| Outcome: | The proposed framework achieves consistent improvements over baselines across multiple evaluation dimensions, including diagnostic accuracy, contextual appropriateness, task effectiveness, and overall helpfulness, while enabling controllable cognitive restructuring generation. |
Can We Continually Edit Language Models? On the Knowledge Attenuation in Sequential Model Editing (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for model editing suffer from knowledge attenuation due to redundant parameters interference and update weight disentanglement. |
| Approach: | They propose a method to mitigate the problem of knowledge attenuation in sequential editing by analyzing redundant parameters interference and update weight disentanglement. |
| Outcome: | The proposed method mitigates the knowledge attenuation issue and improves on existing benchmarks. |
Emma-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning (2025.acl-long)
Copied to clipboard
| Challenge: | Visual-Language-Action models lack the ability to generate actionable policies tailored to specific robotic embodiments. |
| Approach: | They propose an embodied multimodal action model with Grounded Chain of Thought and Look-ahead Spatial Reasoning that enhances spatial reasoning and task planning. |
| Outcome: | The proposed model improves on existing baselines in tasks requiring spatial reasoning and grounding reasoning. |
Toward Recognizing More Entity Types in NER: An Efficient Implementation using Only Entity Lexicons (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing named entity recognition systems require large scale labeled data to perform, while annotation of NER data is laborious and time-consuming. |
| Approach: | They propose to adjust an existing named entity recognition system to recognize entity types not defined in the system. |
| Outcome: | The proposed method can be quickly adjusted to a named entity recognition system. |
Low-Resource Dialogue Summarization with Domain-Agnostic Multi-Source Pretraining (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for low-resource dialogue summarization neglect the difference between dialogues and conventional articles. |
| Approach: | They propose a multi-source pretraining paradigm to leverage external summary data . they exploit large-scale in-domain non-summary data to separate dialogue encoder and summary decoder . |
| Outcome: | The proposed model can be used to better leverage external summary data. |
Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models (2024.acl-long)
Copied to clipboard
| Challenge: | Mixture-of-Experts (MoE) LLMs achieve higher performance with fewer active parameters, but are still difficult to deploy due to their immense parameter sizes. |
| Approach: | They propose expert-level sparsification techniques to enhance the deployment efficiency of large language models by introducing plug-and-play expert pruning and skipping techniques. |
| Outcome: | The proposed methods reduce model sizes and increase inference speed while maintaining satisfactory performance across a wide range of tasks. |
ALPS: Attention Localization and Pruning Strategy for Efficient Adaptation of Large Language Models (2025.findings-acl)
Copied to clipboard
Hao Chen, Haoze Li, Zhiqing Xiao, Lirong Gao, Qi Zhang, Xiaomeng Hu, Ningtao Wang, Xing Fu, Junbo Zhao
| Challenge: | Prior research has focused on optimizing general-purpose large language models to downstream tasks . however, these approaches inherently introduce data dependency, which hinders generalization and reusability. |
| Approach: | They propose an algorithm that localizes the most task-sensitive attention heads and prunes by restricting attention training updates to these heads, thereby reducing alignment costs. |
| Outcome: | The proposed algorithm achieves 2% performance improvement over baselines on three tasks while localizing the most task-sensitive attention heads. |
Taxonomy-Driven Knowledge Graph Construction for Domain-Specific Scientific Applications (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for constructing domain-specific knowledge graphs neglect curated taxonomies and LLMs fail to extract KGs in specialized domains. |
| Approach: | They propose a taxonomy-driven framework for constructing domain-specific knowledge graphs . they use structured taxonomies, Large Language Models and Retrieval-Augmented Generation . |
| Outcome: | The proposed framework can be adapted for other specialized domains. |
Every Answer Matters: Evaluating Commonsense with Probabilistic Measures (2024.acl-long)
Copied to clipboard
Qi Cheng, Michael Boratko, Pranay Kumar Yelugam, Tim O’Gorman, Nalini Singh, Andrew McCallum, Xiang Li
| Challenge: | Existing commonsense evaluations are often posed as multiple-choice questions, allowing models to exploit systematic biases. |
| Approach: | They propose a generative task that evaluates common sense via multiple open-ended generations and a method that strongly correlates with human judgments. |
| Outcome: | The proposed method outperforms strong language model baselines on a dataset of human and machine common sense. |
Dim-Krum: Backdoor-Resistant Federated Learning for NLP with Dimension-wise Krum-Based Aggregation (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to reduce backdoor risk of federated learning are validated in the CV field. |
| Approach: | They propose a federated aggregation algorithm that detects errors determined by backdoor strengths for NLP attacks. |
| Outcome: | The proposed method is hard to defend against than CV, and the results validate it. |
PKAD: Pretrained Knowledge is All You Need to Detect and Mitigate Textual Backdoor Attacks (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Current defense methods can be classified into inference-time and training-time ones based on their execution phase. |
| Approach: | They propose a two-stage poison detection strategy using pre-trained language models to detect poisoned samples before model training. |
| Outcome: | The proposed method achieves better performance than current methods more quickly and with fewer training costs. |
The Art of SOCRATIC QUESTIONING: Recursive Thinking with Large Language Models (2023.emnlp-main)
Copied to clipboard
| Challenge: | Chain-of-Thought (CoT) prompting relies on the initial decisions, causing errors in early steps to accumulate and impact the final answers. |
| Approach: | They propose a divide-and-conquer style algorithm that leverages large language models to raise and answer sub-questions until collecting enough information to tackle the original one. |
| Outcome: | The proposed algorithm is more robust to errors and errors than CoT prompting and Tree-of-Thought prompting methods. |
InMind: Evaluating LLMs in Capturing and Applying Individual Human Reasoning Styles (2025.emnlp-main)
Copied to clipboard
Zizhen Li, Chuanhao Li, Yibin Wang, Qi Chen, Diping Song, Yukang Feng, Jianwen Sun, Jiaxin Ai, Fanrui Zhang, Mingzhu Sun, Kaipeng Zhang
| Challenge: | Recent large language models (LLMs) have demonstrated strong reasoning abilities across complex mathematical and scientific domains. |
| Approach: | They propose a framework to assess whether LLMs can capture and apply personalized reasoning styles in social deduction games. |
| Outcome: | The proposed framework evaluates LLMs on the game Avalon and shows that they can capture and apply individualized reasoning styles. |
Geo-BERT Pre-training Model for Query Rewriting in POI Search (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to solve the word mismatch between queries and documents are often inadequate to integrate geographic information into the pre-training model. |
| Approach: | They propose to train a pre-training model to integrate semantics and geographic information in the pre-trained representations of POIs. |
| Outcome: | The proposed model achieves excellent accuracy on a wide range of real-world datasets of map services. |
Answer When Needed, Forget When Not: Language Models Pretend to Forget via In-Context Knowledge Unlearning (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) are increasingly required to selectively unlearn specific information. |
| Approach: | They propose a method which fine-tunes pre-trained LLMs to enable prompt unlearning of target knowledge within the context while preserving unrelated information. |
| Outcome: | The proposed method achieves up to 95% forget accuracy while retaining 80% of unrelated knowledge, significantly outperforming baselines in both in-domain and out-of-domain scenarios. |
Stacked Acoustic-and-Textual Encoding: Integrating the Pre-trained Models into Speech Translation Encoders (2021.acl-long)
Copied to clipboard
| Challenge: | End-to-end Speech Translation (E2E ST) encoders lack global context representation, whereas MT encoder lacks it. |
| Approach: | They propose a Stacked Acoustic-and-Textual Encoding method for speech translation . they propose an adaptor module to alleviate representation inconsistency . |
| Outcome: | The proposed method achieves state-of-the-art BLEU scores of 18.3 and 25.2 on two ST tasks. |
Hi-ArG: Exploring the Integration of Hierarchical Argumentation Graphs in Language Pretraining (2023.emnlp-main)
Copied to clipboard
Jingcong Liang, Rong Ye, Meng Han, Qi Zhang, Ruofei Lai, Xinyu Zhang, Zhao Cao, Xuanjing Huang, Zhongyu Wei
| Challenge: | Recent studies have discussed its capability to assist language models for various applications. |
| Approach: | They propose a structure to organize arguments using the **Hi**erarchical **Ar**gumentation **G**raph (Hi-ArG) and propose two approaches to exploit Hi-AarG, including a text-graph multi-modal model GreaseArR and a framework augmented with graph information. |
| Outcome: | The proposed structure supersedes existing language models on two argumentation tasks while incorporating graph information during further training improves vanilla language models. |
P4: Plug-and-Play Discrete Prompting for Large Language Models Personalization (2024.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) exhibit impressive capabilities in following instructions, but manually prompting them to exhibit certain personalities may result in sub-optimal performance. |
| Approach: | They propose a plug-and-play prompting method to manipulate Large Language Models with distinct human-like personality traits by appending discrete personalized suffixes to query or dialog histories and focusing exclusively on influential tokens. |
| Outcome: | The proposed method outperforms other prompting methods and model editing methods on four models ranging from 1.1B to 13B and achieves 79.9% accuracy in customizing LLMs’ personalities. |
AutoReproduce: Automatic AI Experiment Reproduction with Paper Lineage (2026.acl-long)
Copied to clipboard
Xuanle Zhao, Zilin Sang, Yuxuan Li, Qi Shi, Weilun Zhao, Shuo Wang, Duzhen Zhang, Xu Han, Zhiyuan Liu, Maosong Sun
| Challenge: | Efficient reproduction of research papers requires deep domain expertise. |
| Approach: | They propose a framework that systematically mines implicit knowledge from the cited literature to reproduce experimental code in a complete, end-to-end manner. |
| Outcome: | The proposed framework surpasses baselines across all metrics and reproduces experimental code in a complete, end-to-end manner. |
Long-Horizon Dialogue Understanding for Role Identification in the Game of Avalon with Large Language Models (2023.findings-emnlp)
Copied to clipboard
Simon Stepputtis, Joseph Campbell, Yaqi Xie, Zhengyang Qi, Wenxin Zhang, Ruiyi Wang, Sanketh Rangreji, Charles Lewis, Katia Sycara
| Challenge: | Deception and persuasion play a critical role in long-horizon multi-party dialogues, especially when the interests, goals, and motivations of the participants are not aligned. |
| Approach: | They propose a game in which players must determine each other’s hidden identities to complete their team’s objective. |
| Outcome: | The proposed model can be used to determine the true player identities of six human players in a cooperative-competitive game. |
DeMAC: Enhancing Multi-Agent Coordination with Dynamic DAG and Manager-Player Feedback (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Multi-agent systems (MAS) powered by large language models struggle to adapt to evolving task dependencies and to handle uncertainties. |
| Approach: | They propose a Dynamic Environment-Aware Manager-Player Agents Coordination framework that enhances multi-agent coordination through long-term strategic planning. |
| Outcome: | The proposed framework outperforms traditional reinforcement learning and human-agent collaboration in the Overcooked simulation. |
CoRec: An Easy Approach for Coordination Recognition (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing syntactic parsers are slow and suffer from errors, especially for long and complicated sentences. |
| Approach: | They propose a pipeline model COordination RECognizer with coordinator identifier and conjunct boundary detector. |
| Outcome: | The proposed model improves the yield of state-of-the-art Open IE models by reducing errors and slow processing time. |
All Information is Valuable: Question Matching over Full Information Transmission Network (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods for question matching only transmit one kind of information while failing to utilize both kinds of information simultaneously. |
| Approach: | They propose a question matching network that can transmit both representation and interactive information together in a simultaneous fashion. |
| Outcome: | The proposed approach outperforms strong baseline models on two standard benchmarks. |
Review-Driven Multi-Label Music Style Classification by Exploiting Style Correlations (N19-1)
Copied to clipboard
| Challenge: | Several methods have been proposed for automatic music style classification, but they are limited in two aspects. |
| Approach: | They propose a deep learning approach to automatically learn and exploit style correlations by reviewing music reviews on websites. |
| Outcome: | The proposed approach performs well in capturing style correlations. |
Counterfactual Data Augmentation for Neural Machine Translation (2021.naacl-main)
Copied to clipboard
| Challenge: | Neural machine translation models often rely on large-scale parallel corpora for training, exhibiting degraded performance on low-resource languages. |
| Approach: | They propose a method that interprets language models and phrasal alignment causally and generates augmented parallel translation corpora by sampling new source phrases from a masked language model. |
| Outcome: | The proposed method improves translation, backtranslation and translation robustness on IWSLT’15 English Vietnamese, WMT’17 English - German, and WMT'18 English – Turkish. |
LaRS: Latent Reasoning Skills for Chain-of-Thought Reasoning (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods require human experts or pre-trained LLMs to describe the skill to guide the selection. |
| Approach: | They propose a new approach that uses unsupervised learning to create a latent space representation of rationales with a variable called a reasoning skill. |
| Outcome: | Empirical results show that LaRS outperforms SOTA skill-based selection methods . it processes example banks four times faster and reduces LLM inferences by half . |
TRUST-VL: An Explainable News Assistant for General Multimodal Misinformation Detection (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods focus on a single type of distortion and struggle to generalize to unseen scenarios. |
| Approach: | They propose a vision-language model that combines a question-aware visual amplifier module with a large-scale instruction dataset to support training. |
| Outcome: | The proposed model is able to generalize to multiple distortion types while requiring task-specific skills. |
AMoPO: Adaptive Multi-objective Preference Optimization without Reward Models and Reference Models (2025.findings-acl)
Copied to clipboard
Qi Liu, Jingqing Ruan, Hao Li, Haodong Zhao, Desheng Wang, Jiansong Chen, Wan Guanglu, Xunliang Cai, Zhi Zheng, Tong Xu
| Challenge: | Existing multi-objective preference alignment methods for large language models face limitations such as auxiliary reward/reference models and computational complexity. |
| Approach: | They propose a framework that achieves dynamic balance across preference dimensions by using dimension-aware generation metrics as implicit rewards. |
| Outcome: | Empirical results show that AMoPO outperforms state-of-the-art methods by 28.5% . |
OpenAttack: An Open-source Textual Adversarial Attack Toolkit (2021.acl-demo)
Copied to clipboard
Guoyang Zeng, Fanchao Qi, Qianrui Zhou, Tingji Zhang, Zixian Ma, Bairu Hou, Yuan Zang, Zhiyuan Liu, Maosong Sun
| Challenge: | Various attack models are distinct and implemented with different programming frameworks and settings, which hinders quick utilization and fair comparison of attack models. |
| Approach: | They propose an open-source textual adversarial attack toolkit to solve these issues by combining 15 typical attack models into one toolkit. |
| Outcome: | The proposed toolkit supports all attack types, multilinguality, and parallel processing. |
Global Encoding for Abstractive Summarization (P18-2)
Copied to clipboard
| Challenge: | Existing models for abstractive summarization suffer from repetition and semantic irrelevance. |
| Approach: | They propose a global encoding framework which controls the information flow from the encoder to the decoder based on the global information of the source context. |
| Outcome: | The proposed model outperforms baseline models on the LCSTS and English Gigaword and can generate summary of higher quality and reduce repetition. |
Eval-RAR: Evaluation-Driven Retrieval-Augmented Reasoning via Reinforcement Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for retrieval-augmented generation fail to provide explicit supervision for internal reasoning process. |
| Approach: | They propose an Evaluation-driven Retrieval-Augmented Reasoning framework that uses reinforcement learning and a fine-grained evaluation reward to optimize the process. |
| Outcome: | Eval-RAR outperforms existing methods on QA benchmarks on seven single-hop and multi-hop tasks. |
Empirical Study of Zero-Shot NER with ChatGPT (2023.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) have been a key component of natural language processing (NLP) . |
| Approach: | They propose to decompose the NER task into simpler subproblems by labels and propose a syntactic augmentation strategy to stimulate model's intermediate thinking. |
| Outcome: | The proposed methods achieve remarkable improvements for zero-shot NER across seven benchmarks, including Chinese and English datasets. |
Program Translation via Code Distillation (2023.emnlp-main)
Copied to clipboard
| Challenge: | Software version migration and program translation are costly parts of the lifecycle of large codebases. |
| Approach: | They propose a model that captures semantic and structural equivalence of code in a language agnostic intermediate representation. |
| Outcome: | The proposed model achieves state-of-the-art performance on CodeXGLUE and TransCoder GeeksForGeeks translation benchmarks. |
RecStream: Graph-aware Stream Management for Concurrent Recommendation Model Online Serving (2025.coling-industry)
Copied to clipboard
| Challenge: | Existing systems that use recommendation models perform poorly under highly concurrent scenarios. |
| Approach: | They propose a system that optimizes stream configurations based on model characteristics and concurrency levels. |
| Outcome: | The proposed system outperforms existing methods under high concurrency scenarios. |
ProphetNet-X: Large-Scale Pre-training Models for English, Chinese, Multi-lingual, Dialog, and Code Generation (2021.acl-demo)
Copied to clipboard
Weizhen Qi, Yeyun Gong, Yu Yan, Can Xu, Bolun Yao, Bartuer Zhou, Biao Cheng, Daxin Jiang, Jiusheng Chen, Ruofei Zhang, Houqiang Li, Nan Duan
| Challenge: | Existing models for pre-training are not convenient for users to find and set them up. |
| Approach: | They propose to extend ProphetNet into other domains and languages by pre-training models . they pre-train a cross-lingual generation model ProphetNet-Multi and a Chinese generation model . |
| Outcome: | The proposed models achieve new state-of-the-art on 10 benchmarks. |
Connectivity Patterns are Task Embeddings (2023.findings-acl)
Copied to clipboard
Zhiheng Xi, Rui Zheng, Yuansen Zhang, Xuanjing Huang, Zhongyu Wei, Minlong Peng, Mingming Sun, Qi Zhang, Tao Gui
| Challenge: | Existing methods for predicting inter-task transferability are sparse and task-specific. |
| Approach: | They propose a method that uses connectivity patterns of neurons as a unique identifier associated with a task. |
| Outcome: | The proposed method outperforms baselines in predicting inter-task transferability across data regimes and transfer settings while keeping high efficiency in computation and storage. |
EfficientRAG: Efficient Retriever for Multi-Hop Question Answering (2024.emnlp-main)
Copied to clipboard
Ziyuan Zhuang, Zhiyang Zhang, Sitao Cheng, Fangkai Yang, Jia Liu, Shujian Huang, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang, Qi Zhang
| Challenge: | Existing retrieval-augmented generation methods rely on multiple calls of large language models (LLMs) Large-language models lack knowledge underrepresented in training data and still face hallucinations. |
| Approach: | They propose an efficient retriever for multi-hop question answering that generates new queries iteratively without the need for LLM calls. |
| Outcome: | The proposed method surpasses existing methods on three open-domain multi-hop question-answering datasets. |
BabelDOC: Better Layout-Preserving PDF Translation via Intermediate Representation (2026.acl-demo)
Copied to clipboard
| Challenge: | Existing document translation pipelines face a tension between linguistic processing and layout preservation. |
| Approach: | They propose a framework for layout-preserving PDF translation that decouples visual layout metadata from semantic content. |
| Outcome: | The proposed framework improves layout fidelity, visual aesthetics, and terminology consistency over representative baselines while maintaining competitive translation precision. |
Can LLM Agents Simulate Multi-Turn Human Behavior? Evidence from Real Online Customer Behavior Data (2026.acl-long)
Copied to clipboard
Yuxuan Lu, Jing Huang, Yan Han, Bingsheng Yao, Sisong Bei, Yaochen Xie, Yisi Sang, Qi He, Dakuo Wang
| Challenge: | Recent research shows that LLM Agents can generate “believable” human behaviors via prompt-only methods, leaving open questions of whether they can accurately generate step-by-step actions in multi-turn interaction tasks. |
| Approach: | They propose to use shopping data to evaluate LLMs' ability to accurately generate step-by-step actions in a multi-turn interaction task. |
| Outcome: | The proposed model achieves 17.26% action generation accuracy and 33.86% F1 score on final purchase prediction, representing improvements of 5.4% and 13.85% over baselines. |
Diagnosing Moral Reasoning Acquisition in Language Models: Pragmatics and Generalization (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Prior research has shown that LLMs fail to perform satisfactorily on moral cognizance tasks . |
| Approach: | They propose to use curated datasets to improve LLMs' moral cognizance . they find pragmatic dilemma constrains generalization ability of current learning paradigms . |
| Outcome: | The proposed learning paradigms fail to perform on moral cognizance tasks, the authors show . they show that the pragmatic dilemma is the primary bottleneck for moral reasoning acquisition . |
Connecting the Dots: Event Graph Schema Induction with Path Language Modeling (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to automate event extraction focus on uncertainty, re-occurring events and multiple hypotheses. |
| Approach: | They propose a new Event Graph Schema where two event types are connected through multiple paths involving entities that fill important roles in a coherent story. |
| Outcome: | The proposed model is highly effective at inducing salient and coherent schemas. |
Reward Modeling Requires Automatic Adjustment Based on Data Quality (2024.findings-emnlp)
Copied to clipboard
Binghai Wang, Rui Zheng, Lu Chen, Zhiheng Xi, Wei Shen, Yuhao Zhou, Dong Yan, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Reinforcement Learning from Human Feedback (RLHF) is a method for aligning language models with human values. |
| Approach: | They propose a method that automatically adjusts reward modeling based on data quality . they use preference data to train a reward model that is more aligned with human values . |
| Outcome: | The proposed method stabilizes reward model training and significantly improves alignment performance on human preference datasets. |
MinosEval: Distinguishing Factoid and Non-Factoid for Tailored Open-Ended QA Evaluation with LLMs (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing evaluation methods overlook the distinction between factoid and non-factoidic questions. |
| Approach: | They propose a method that distinguishes open-ended questions and ranks candidate answers . they propose QA requires longer answer statements and nuanced reasoning processes . |
| Outcome: | The proposed method better aligns with human annotations and offers more interpretable results. |
One-Model-Connects-All: A Unified Graph Pre-Training Model for Online Community Modeling (2023.findings-emnlp)
Copied to clipboard
Ruoxue Ma, Jiarong Xu, Xinnong Zhang, Haozhe Zhang, Zuyu Zhao, Qi Zhang, Xuanjing Huang, Zhongyu Wei
| Challenge: | Existing studies on integrating online community to solve social problems have not fully utilized these three components and the relationship among them. |
| Approach: | They propose a framework that simultaneously considers communities, users, and texts and can easily connect with a variety of downstream tasks related to social media. |
| Outcome: | The proposed model can be used to perform violation detection, sentiment analysis, and community recommendation across multiple tasks. |
PILLOW: Enhancing Efficient Instruction Fine-tuning via Prompt Matching (2023.emnlp-industry)
Copied to clipboard
| Challenge: | Low-Rank Adaptation (LoRA) has been used to adapt Large Language Models to a variety of tasks, but it requires substantial computational resources to perform. |
| Approach: | They propose a low-rank adaptive learning approach that leverages LoRA's in-context learning capability through prompt matching via reinforcement learning in resource-constrained environments. |
| Outcome: | The proposed model improves LoRA performance on evaluation metrics and utilises consumer-grade GPU resources. |
MEAV: Model Editing with Alignment Vectors for inference time LLM alignment in single and multidomain preference spectrum (2026.findings-acl)
Copied to clipboard
Sadat Shahriar, Zheng Qi, Nikolaos Pappas, Srikanth Doss, Kishaloy Halder, Monica Sunkara, Manuel Mager, Yassine Benajiba
| Challenge: | Existing training-time alignment methods require full retraining when a change is needed. |
| Approach: | They propose an inference-time model-editing-based alignment method that learns encoded representations of preference dimensions and allows dynamic adjusting of the model behavior. |
| Outcome: | The proposed method can be used to align large language models to human preferences . it reduces the cost of inference by half compared to the prompt engineering approach . |
Characterizing the Impacts of Instances on Robustness (2023.findings-acl)
Copied to clipboard
Rui Zheng, Zhiheng Xi, Qin Liu, Wenbin Lai, Tao Gui, Qi Zhang, Xuanjing Huang, Jin Ma, Ying Shan, Weifeng Ge
| Challenge: | Existing defense approaches focus on developing new model structures or training algorithms, but they do little to tap the potential of training instances. |
| Approach: | They propose a method that can distinguish between robust and non-robust instances according to the model’s sensitivity to perturbations on individual instances during training. |
| Outcome: | The proposed method can distinguish between robust and non-robust instances according to the model’s sensitivity to perturbations on individual instances during training. |
Open Set Relation Extraction via Unknown-Aware Training (2023.acl-long)
Copied to clipboard
Jun Zhao, Xin Zhao, WenYu Zhan, Qi Zhang, Tao Gui, Zhongyu Wei, Yun Wen Chen, Xiang Gao, Xuanjing Huang
| Challenge: | Existing supervised relation extraction methods can still misclassify unknown relations into known relations due to the lack of supervision signals. |
| Approach: | They propose a method that regularizes the model by dynamically synthesizing negative instances that can provide the missing supervision signals. |
| Outcome: | The proposed method achieves SOTA unknown relation detection without compromising the classification of known relations. |
AutoRAG-HP: Automatic Online Hyper-Parameter Tuning for Retrieval-Augmented Generation (2024.findings-emnlp)
Copied to clipboard
Jia Fu, Xiaoting Qin, Fangkai Yang, Lu Wang, Jue Zhang, Qingwei Lin, Yubo Chen, Dongmei Zhang, Saravan Rajmohan, Qi Zhang
| Challenge: | Recent advances in Large Language Models have transformed ML/AI development . a reevaluation of AutoML principles for Retrieval-Augmented Generation (RAG) systems is needed. |
| Approach: | They propose a framework for hyper-parameter tuning and a hierarchical MAB method for efficient exploration of large search spaces. |
| Outcome: | The proposed framework outperforms baseline methods in more challenging optimization scenarios. |
Seeing is Believing, but How Much? A Comprehensive Analysis of Verbalized Calibration in Vision-Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to quantify uncertainty are limited in vision-language models . however, current models display notable miscalibration across diverse tasks and settings . |
| Approach: | They evaluate verbalized confidence in vision-language models using visual reasoning . they propose a prompting strategy that improves confidence alignment in multimodal settings . |
| Outcome: | The proposed method improves confidence alignment across multimodal settings. |
Discrete Argument Representation Learning for Interactive Argument Pair Identification (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing research on monological argumentation covers claims generation, argument structure prediction, and essay scoring. |
| Approach: | They propose to identify argument pairs from two posts with opposite stances to a certain topic. |
| Outcome: | The proposed framework outperforms competing models on a large-scale dataset . it also proves that it is useful for analyzing argument pairs from two posts . |
Controllable Contamination Detection for Reliable LLM Evaluation with Statistical Guarantees (2026.acl-long)
Copied to clipboard
Zheng Zhang, Qi Liu, Siyuan Liang, Ning Li, Zirui Hu, Weibo Gao, Rui Li, Zhenya Huang, Leszek Rutkowski, Baosheng Yu, Dacheng Tao
| Challenge: | Existing training data detectors fail to detect clean samples from contaminated test sets . existing methods fail to identify clean samples due to black-box nature of LLMs . |
| Approach: | They propose a framework that detects and filters contaminated evaluation data . they propose 'failure detection' to reduce the proportion of contaminated samples mistakenly retained . |
| Outcome: | The proposed framework reduces false discovery rate (FDR) under valid FDR control while maintaining evaluation consistency. |
ConvLab-3: A Flexible Dialogue System Toolkit Based on a Unified Data Format (2023.emnlp-demo)
Copied to clipboard
Qi Zhu, Christian Geishauser, Hsien-chin Lin, Carel van Niekerk, Baolin Peng, Zheng Zhang, Shutong Feng, Michael Heck, Nurul Lubis, Dazhen Wan, Xiaochen Zhu, Jianfeng Gao, Milica Gasic, Minlie Huang
| Challenge: | Existing tools for building TOD systems often lack a user-friendly interface . a toolkit with advanced, easily integrable modules is needed to bridge this gap . |
| Approach: | They propose a multifaceted dialogue system toolkit that integrates diverse datasets and models with a streamlined training process and in-depth evaluation tools. |
| Outcome: | The proposed toolkit combines RL and transfer learning to support the rapid development and evaluation of robust dialogue policies. |
AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corpora (2026.acl-long)
Copied to clipboard
Jiaxin Bai, Wei Fan, Qi Hu, Qing Zong, Chunyang Li, Hong Ting Tsang, Hongyu Luo, Yauwai Yim, Haoyu Huang, Xiao Zhou, Feng Qin, Tianshi Zheng, Xi Peng, Xin Yao, Huiwen Yang, Leijie Wu, JI Yi, Gong Zhang, Renhai Chen, Yangqiu Song
| Challenge: | Existing knowledge graph construction frameworks require predefined schemas, limiting their scalability and domain coverage. |
| Approach: | They propose a framework for fully autonomous knowledge graph construction that eliminates the need for predefined schemas. |
| Outcome: | The proposed framework outperforms state-of-the-art models on multi-hop QA tasks and enhances LLM factuality. |
Thought-Action Graph Reasoning: Faithful and Efficient Reasoning of Large Language Models via Reusing Past Experience (2026.findings-acl)
Copied to clipboard
Zhixiao Qi, Feng Huang, Yunqi Zhang, Shijie Zhang, Qingqing Sun, Yongfeng Huang, Minghu Jiang, Shuai Chen, Tianyi Zhang
| Challenge: | Existing methods for integrating knowledge graphs with LLMs suffer from poor generalization or low reasoning efficiency. |
| Approach: | They propose a thought-action Graph (TAG) that decomposes LLM-KG interaction trajectories into fine-grained semantic operators and guides LLM to execute on them. |
| Outcome: | The proposed paradigm outperforms state-of-the-art methods on KGQA benchmarks while reducing the number of LLM calls and generated tokens. |
Efficient Integration of External Knowledge to LLM-based World Models via Retrieval-Augmented Generation and Reinforcement Learning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing attempts to enhance LLM-based world models through prompting or fine-tuning approaches are either requiring human knowledge or computationally extensive. |
| Approach: | They propose a framework that leverages retrieval-augmented generation to integrate external knowledge to LLM-based world models. |
| Outcome: | The proposed framework outperforms baseline models and exhibits strong generalizability. |
NL2Lean: Translating Natural Language into Lean 4 through Multi-Aspect Reinforcement Learning (2025.emnlp-main)
Copied to clipboard
Yue Fang, Shaohan Huang, Xin Yu, Haizhen Huang, Zihan Zhang, Weiwei Deng, Furu Wei, Feng Sun, Qi Zhang, Zhi Jin
| Challenge: | Existing formal proof assistants rely on instruction tuning and lack fine-grained structural and semantic alignment. |
| Approach: | They propose a reinforcement learning framework that enables LLMs to translate natural language into formal language such as Lean 4 . they use a model with basic translation ability to refine the model's reinforcement learning . |
| Outcome: | The proposed method outperforms baseline models on NL-to-Lean 4 tasks. |
CausalMACE: Causality Empowered Multi-Agents in Minecraft Cooperative Tasks (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing work on multi-agent collaborative tasks in Minecraft is limited due to inefficiency and limited fault tolerance. |
| Approach: | They propose a framework that incorporates causality to manage dependencies among subtasks. |
| Outcome: | The proposed framework achieves state-of-the-art performance in multi-agent cooperative tasks of Minecraft. |
ChemAmp: Amplified Chemistry Tools via Composable Agents (2026.findings-acl)
Copied to clipboard
Zhucong Li, Powei Chang, Jin Xiao, Zhijian Zhou, Qianyu He, Jiaqing Liang, Fenglei Cao, Xu Yinghui, Yuan Qi
| Challenge: | LLM-based agents are powerful tools for automating complex scientific workflows, especially in chemistry, but their single-task performance is limited by tool constraints. |
| Approach: | They propose a framework that optimizes the collective capabilities of specialized tools by dynamic coordination within individual tasks. |
| Outcome: | The proposed framework outperforms chemistry-specialized models, generalist LLMs, and agent systems with tool orchestration. |
LM-Searcher: Cross-domain Neural Architecture Search with LLMs via Unified Numerical Encoding (2025.emnlp-main)
Copied to clipboard
Yuxuan Hu, Jihao Liu, Ke Wang, Jinliang Zheng, Weikang Shi, Manyuan Zhang, Qi Dou, Rui Liu, Aojun Zhou, Hongsheng Li
| Challenge: | Recent advances in Large Language Models have opened new avenues for solving complex optimization problems, including Neural Architecture Search (NAS). |
| Approach: | They propose a framework that leverages LLMs for cross-domain neural architecture optimization without extensive domain-specific tuning. |
| Outcome: | The proposed framework achieves competitive performance in both in-domain and out-of-domain tasks. |
DAC: A Dynamic Attention-aware Approach for Task-Agnostic Prompt Compression (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods rely on information entropy as the metric to compress lexical units, but ignore attention-critical tokens and information . recent advent of In-Context Learning (ICL), Chain-of-Thought (CoT), and Retrieval Augmented Generation (RAG) technologies has significantly invigorated the landscape of applications based on Large Language Models (LLMs). |
| Approach: | They propose a dynamic attention-aware approach to task-agnostic prompt compression . they integrate entropy and attention information to achieve fine-grained prompt compression. |
| Outcome: | Experiments show that the proposed approach improves across tasks and LLMs. |
Multi-stage Distillation Framework for Cross-Lingual Semantic Similarity Matching (2022.findings-naacl)
Copied to clipboard
Kunbo Ding, Weijie Liu, Yuejian Fang, Zhe Zhao, Qi Ju, Xuefeng Yang, Rong Tian, Zhu Tao, Haoyan Liu, Han Guo, Xingyu Bai, Weiquan Mao, Yudong Li, Weigang Guo, Taiqiang Wu, Ningyuan Sun
| Challenge: | Existing studies have shown that cross-lingual knowledge distillation can improve the performance of pre-trained models for cross-linguistic similarity matching tasks. |
| Approach: | They propose a multi-stage distillation framework for constructing a small-size but high-performance cross-lingual model using contrastive learning, bottleneck, and parameter recurrent strategies. |
| Outcome: | The proposed model can compress the size of XLM-R and MiniLM by more than 50% while the performance is only reduced by about 1%. |
DUET: Joint Exploration of User–Item Profiles in Recommendation System (2026.findings-acl)
Copied to clipboard
Yue Chen, Yifei Sun, Lu Wang, Fangkai Yang, Pu Zhao, Minjie Hong, Yifei Dong, Minghua He, Nan Hu, Jianjin Zhang, Zhiwei Dai, Yuefeng Zhan, Weihao Han, Hao Sun, Qingwei Lin, Weiwei Deng, Feng Sun, Qi Zhang, Saravan Rajmohan, Dongmei Zhang
| Challenge: | Existing LLMs are opaque and difficult to interpret, resulting in limited interpretability. |
| Approach: | They propose an interaction-aware profile generator that jointly produces user and item profiles conditioned on both user history and item evidence. |
| Outcome: | The proposed model outperforms baselines on three real-world datasets. |
SciCustom: A Framework for Custom Evaluation of Scientific Capabilities in Large Language Models (2026.acl-long)
Copied to clipboard
Yiyang Gu, Junwei Yang, Junyu Luo, Ye Yuan, Bin Feng, Yingce Xia, Shufang Xie, Kaili Liu, Bohan Wu, Qi Shi, Haoran Li, Beier Xiao, Zhiping Xiao, Xiao Luo, Weizhi Zhang, Philip S. Yu, Zequn Liu, Ming Zhang
| Challenge: | Existing evaluations of large language models fail to reflect fine-grained capabilities . existing benchmarks are manually curated or domain-generic, limiting scalability and alignment with real use cases. |
| Approach: | They propose a framework that allows custom construction of benchmarks from large-scale scientific data to evaluate application-specific scientific capabilities in LLMs. |
| Outcome: | The proposed framework reveals fine-grained differences in scientific capabilities that standard benchmarks overlook . it allows custom construction of benchmarks from large-scale scientific data to evaluate application-specific capabilities in LLMs. |
Generalizable and Explainable Dialogue Generation via Explicit Action Learning (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Conditioned response generation for task-oriented dialogues implicitly optimizes task completion and language quality. |
| Approach: | They propose to learn natural language actions that represent utterances as a span of words. |
| Outcome: | The proposed approach outperforms latent action baselines on a multi-domain dataset. |
WIST: Web-Grounded Iterative Self-Play Tree for Domain-Targeted Reasoning Improvement (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for self-improvement of large language models with verifiable rewards (RLVR) can drift over iterations, while corpus-grounded approaches rely on curated data environments. |
| Approach: | They propose a Web-grounded Iterative Self-play Tree framework for domain-targeted reasoning improvement that learns directly from the open-web without requiring any pre-arranged domain corpus. |
| Outcome: | The proposed framework outperforms both purely endogenous self-evolution and corpus-grounded self-play baselines and is domain-steerable. |
ADELIE: Aligning Large Language Models on Information Extraction (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) struggle to follow complex instructions of IE tasks due to not being aligned with humans. |
| Approach: | They propose an aligned large language moDEL that effectively solves various IE tasks including closed IE, open IE and on-demand IE. |
| Outcome: | The proposed model achieves state-of-the-art (SoTA) performance among open-source models. |
ToolSword: Unveiling Safety Issues of Large Language Models in Tool Learning Across Three Stages (2024.acl-long)
Copied to clipboard
Junjie Ye, Sixian Li, Guanyu Li, Caishuang Huang, Songyang Gao, Yilong Wu, Qi Zhang, Tao Gui, Xuanjing Huang
| Challenge: | Existing research focuses on enhancing LLMs capabilities through tool utilization. |
| Approach: | They propose a framework to investigate safety issues in large language models in tool learning . they propose malicious queries and jailbreak attacks in the input stage . |
| Outcome: | The proposed framework investigates six safety scenarios for LLMs in tool learning . the data will be released upon acceptance of the proposed framework . |
PragmatiCQA: A Dataset for Pragmatic Question Answering in Conversations (2023.findings-acl)
Copied to clipboard
| Challenge: | Mars? - PragmatiCQA |
| Approach: | Mars? - The Paper . |
| Outcome: | The proposed dataset features 6873 QA pairs that explores pragmatic reasoning in conversations over a diverse set of topics. |
Using the Past Knowledge to Improve Sentiment Classification (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing model retains knowledge learned from past tasks and selectively transfers it to new task to help it learn better. |
| Approach: | They propose a lifelong learning model that can retain and selectively transfer the knowledge learned in the past to help learn the new task. |
| Outcome: | The proposed model outperforms strong baselines, including even multiple task learning. |
Can LLMs Simulate L2-English Dialogue? An Information-Theoretic Analysis of L1-Dependent Biases (2025.acl-long)
Copied to clipboard
Rena Wei Gao, Xuetong Wu, Tatsuki Kuribayashi, Mingrui Ye, Siya Qi, Carsten Roever, Yuanxing Liu, Zheng Yuan, Jey Han Lau
| Challenge: | Large Language Models (LLMs) can simulate non-native-like English use observed in human second language (L2) learners interfered with by their native first language (N1) knowledge. |
| Approach: | They use large language models to simulate non-native-like English use observed in human second language (L2) learners, and then compare their outputs to real L2 learner data. |
| Outcome: | The proposed models replicate L1-dependent patterns observed in human second language (L2) learners, with distinct influences from various languages. |
SimRAG: Self-Improving Retrieval-Augmented Generation for Adapting Large Language Models to Specialized Domains (2025.naacl-long)
Copied to clipboard
Ran Xu, Hui Liu, Sreyashi Nag, Zhenwei Dai, Yaochen Xie, Xianfeng Tang, Chen Luo, Yang Li, Joyce C. Ho, Carl Yang, Qi He
| Challenge: | Retrieval-augmented generation (RAG) enhances the question answering abilities of large language models (LLMs) however, adapting general-purpose RAG systems to specialized fields poses unique challenges due to distribution shifts and limited access to domain-specific data. |
| Approach: | They propose a method that equips large language models with joint capabilities of question answering and question generation for domain adaptation. |
| Outcome: | Experiments on 11 datasets across three different domains verify the efficacy of SimRAG over baselines by 1.2%–8.6%. |
MMoE: Enhancing Multimodal Models with Mixtures of Multimodal Interaction Experts (2024.emnlp-main)
Copied to clipboard
| Challenge: | Multimodal models focus on the correspondence between images and text, but this only covers a subset of real-world interactions. |
| Approach: | They propose an approach to enhance multimodal models by training separate expert models for each type of interaction, such as redundancy present in both modalities, uniqueness in one modality, or synergy that emerges when both . modality is used to capture overlaps in semantic content between images and text, making a strong multi-view redundancies assumption. |
| Outcome: | The proposed approach improves on a sarcasm detection and humor detection task. |
PromptBERT: Improving BERT Sentence Embeddings with Prompts (2022.emnlp-main)
Copied to clipboard
Ting Jiang, Jian Jiao, Shaohan Huang, Zihan Zhang, Deqing Wang, Fuzhen Zhuang, Furu Wei, Haizhen Huang, Denvy Deng, Qi Zhang
| Challenge: | Existing research shows that BERT and RoBERTa are poor in sentence embeddings due to static token embeddable bias and ineffective BERT layers. |
| Approach: | They propose a novel contrastive learning method for better sentence embeddings by using a template denoising technique. |
| Outcome: | The proposed method achieves 2.29 and 2.58 points of improvement compared to SimCSE and RoBERTa in the unsupervised setting. |
ChartEdit: How Far Are MLLMs From Automating Chart Analysis? Evaluating MLLMs’ Capability via Chart Editing (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing evaluations of multimodal large language models rely on limited case studies . however, they lack the ability to generate accurate edits according to the instructions . |
| Approach: | They propose a benchmark for chart editing that includes 1,405 edit instructions applied to 233 real-world charts. |
| Outcome: | The proposed benchmark includes 1,405 diverse editing instructions applied to 233 real-world charts. |
Evaluating Document Coherence Modeling (2021.tacl-1)
Copied to clipboard
| Challenge: | a new study examines pretrained language models' ability to model discourse and pragmatic phenomena. |
| Approach: | They propose a sentence intrusion detection task using a dictionary dataset . they show that pretrained LMs perform impressively in in-domain evaluation . |
| Outcome: | The proposed dataset shows that pretrained LMs perform impressively in in-domain evaluation, but experience a substantial drop in the cross-domain setting, indicating limited generalization capacity. |
Mnemis: Dual-Route Retrieval on Hierarchical Graphs for Long-Term LLM Memory (2026.acl-long)
Copied to clipboard
Zihao Tang, Xin Yu, Ziyu Xiao, Zengxuan Wen, Zelin Li, Jiaxi Zhou, Hualei Wang, Haohua Wang, Haizhen Huang, Weiwei Deng, Feng Sun, Qi Zhang
| Challenge: | Existing methods for retrieving historical messages are based on similarity-based mechanisms. |
| Approach: | They propose a system that integrates System-1 similarity search with a complementary System-2 mechanism, termed Global Selection. |
| Outcome: | The proposed framework achieves state-of-the-art on long-term memory benchmarks and 93.9 on LoCoMo and 91.6 on LongMemEval-S. |
GEMv2: Multilingual NLG Benchmarking in a Single Line of Code (2022.emnlp-demos)
Copied to clipboard
Sebastian Gehrmann, Abhik Bhattacharjee, Abinaya Mahendiran, Alex Wang, Alexandros Papangelis, Aman Madaan, Angelina Mcmillan-major, Anna Shvets, Ashish Upadhyay, Bernd Bohnet, Bingsheng Yao, Bryan Wilie, Chandra Bhagavatula, Chaobin You, Craig Thomson, Cristina Garbacea, Dakuo Wang, Daniel Deutsch, Deyi Xiong, Di Jin, Dimitra Gkatzia, Dragomir Radev, Elizabeth Clark, Esin Durmus, Faisal Ladhak, Filip Ginter, Genta Indra Winata, Hendrik Strobelt, Hiroaki Hayashi, Jekaterina Novikova, Jenna Kanerva, Jenny Chim, Jiawei Zhou, Jordan Clive, Joshua Maynez, João Sedoc, Juraj Juraska, Kaustubh Dhole, Khyathi Raghavi Chandu, Laura Perez Beltrachini, Leonardo F . R. Ribeiro, Lewis Tunstall, Li Zhang, Mahim Pushkarna, Mathias Creutz, Michael White, Mihir Sanjay Kale, Moussa Kamal Eddine, Nico Daheim, Nishant Subramani, Ondrej Dusek, Paul Pu Liang, Pawan Sasanka Ammanamanchi, Qi Zhu, Ratish Puduppully, Reno Kriz, Rifat Shahriyar, Ronald Cardenas, Saad Mahamood, Salomey Osei, Samuel Cahyawijaya, Sanja Štajner, Sebastien Montella, Shailza Jolly, Simon Mille, Tahmid Hasan, Tianhao Shen, Tosin Adewumi, Vikas Raunak, Vipul Raheja, Vitaly Nikolaev, Vivian Tsai, Yacine Jernite, Ying Xu, Yisi Sang, Yixin Liu, Yufang Hou
| Challenge: | Evaluations in machine learning rarely use the latest metrics, datasets, or human evaluation in favor of remaining compatible with prior work. |
| Approach: | They propose to use the Generation, Evaluation, and Metrics Benchmark to integrate new evaluation methods into existing evaluations. |
| Outcome: | The proposed evaluation infrastructure bridges the gap between the advantages of leaderboards and in-depth and evolving evaluations by allowing model developers to benefit from each other's work. |
QuoteR: A Benchmark of Quote Recommendation for Writing (2022.acl-long)
Copied to clipboard
| Challenge: | Existing methods to recommend quotes are evaluated on unpublished datasets . |
| Approach: | They propose to build a dataset that is open and contains three parts including English, standard Chinese and classical Chinese. |
| Outcome: | The proposed model outperforms existing methods on all three parts of QuoteR. |
Reasoning over Hierarchical Question Decomposition Tree for Explainable Question Answering (2023.acl-long)
Copied to clipboard
| Challenge: | Existing XQA methods focus on reasoning on a single knowledge source, e.g., structured knowledge bases, unstructured corpora, etc. Existing work in XQA focuses on integrating information from heterogeneous knowledge sources. |
| Approach: | They propose to leverage question decomposing for heterogeneous knowledge integration by breaking down a complex question into simpler ones and selecting the appropriate knowledge source for each sub-question. |
| Outcome: | The proposed framework outperforms SOTA methods on complex QA datasets. |
RobuT: A Systematic Study of Table QA Robustness Against Human-Annotated Adversarial Perturbations (2023.acl-long)
Copied to clipboard
Yilun Zhao, Chen Zhao, Linyong Nan, Zhenting Qi, Wenlin Zhang, Xiangru Tang, Boyu Mi, Dragomir Radev
| Challenge: | Existing Table QA models are vulnerable to task-specific perturbations, such as replacing key question entities or shuffling table columns. |
| Approach: | They propose to use large language models to generate adversarial examples to enhance training, which significantly improves the robustness of Table QA models. |
| Outcome: | The proposed model significantly improves on existing Table QA models against human-annotated adversarial perturbations. |
Black-Box Membership Inference Attacks for Video Training Data in Multimodal Large Language Models (2026.acl-long)
Copied to clipboard
Jinrui Wang, Zhenfeng Gao, Wendan Wang, Huili Wang, Zichen Qin, Linjie Zhu, Hongke Fu, Shangguang Wang, Tao Qi
| Challenge: | Existing methods assess model memorization of key semantic concepts within a video but do not provide reliable evidence that a specific video was used during training. |
| Approach: | They propose a black-box MIA framework that can provide reliable evidence of specific video data usage for training multimodal large language models. |
| Outcome: | The proposed framework can provide reliable evidence of specific video data usage for training multimodal large language models. |
Towards Identification and Intervention of Safety-Critical Parameters in Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing safety-related methodologies for large language models are lacking . despite advances in safety alignment techniques, safeguarding LLMs during adaptation to various tasks remains a challenge. |
| Approach: | They propose a framework to quantify how different parameters affect LLM safety . they propose two targeted intervention paradigms for safety enhancement and preservation . |
| Outcome: | The proposed framework reveals safety-critical patterns across different LLM architectures. |
Sememe Prediction for BabelNet Synsets using Multilingual and Multimodal Information (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing sememe KBs only cover a few languages, which hinders the wide utilization of sememes. |
| Approach: | They propose to build a multilingual sememe KB based on a dictionary called BabelNet . they use multilingual synonyms, multilingual glosses and images to encode sememes . |
| Outcome: | The proposed model outperforms previous methods in terms of MAP and F1 scores. |
End-to-end Learning of Logical Rules for Enhancing Document-level Relation Extraction (2024.acl-long)
Copied to clipboard
| Challenge: | Document-level relation extraction (DocRE) aims to extract relations between entities in a document. |
| Approach: | They propose a rule-based framework that jointly learns DocRE and logical rules . they parameterize a Rule reasoning module to simulate the inference of logical rule . |
| Outcome: | The proposed framework improves DocRE models by a significant margin on four benchmark datasets. |
MASFactory: A Graph-centric Framework for Orchestrating LLM-Based Multi-Agent Systems with Vibe Graphing (2026.acl-demo)
Copied to clipboard
| Challenge: | Large language model-based multi-agent systems (MAS) are increasingly used to extend agentic problem solving via role specialization and collaboration. |
| Approach: | They propose a graph-centric framework for orchestrating large language model-based multi-agent systems . they compile a user's natural-language intent into an editable workflow specification and then into an executable graph . |
| Outcome: | The proposed framework compiles natural-language intent into an executable graph and then compile and executes it at runtime. |
DiffuVST: Narrating Fictional Scenes with Global-History-Guided Denoising Models (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for visual storytelling suffer from low inference speed and are not well-suited for synthetic scenes. |
| Approach: | They propose a diffusion-based system that generates visual descriptions as a single conditional denoising process. |
| Outcome: | The proposed system improves inter-sentence coherence and image-to-text fidelity. |
TSGP: Two-Stage Generative Prompting for Unsupervised Commonsense Question Answering (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies focus on acquiring relevant knowledge by retrieving external knowledge bases and fine-tuning pre-trained models. |
| Approach: | They propose a two-stage prompt-based unsupervised commonsense question answering framework that leverages implicit knowledge stored in PrLMs to generate knowledge for questions with unlimited types and possible candidate answers independent of specified choices. |
| Outcome: | The proposed framework significantly improves the reasoning ability of language models in unsupervised settings. |
OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems (2024.acl-long)
Copied to clipboard
Chaoqun He, Renjie Luo, Yuzhuo Bai, Shengding Hu, Zhen Thai, Junhao Shen, Jinyi Hu, Xu Han, Yujie Huang, Yuxiang Zhang, Jie Liu, Lei Qi, Zhiyuan Liu, Maosong Sun
| Challenge: | Large Language Models (LLMs) and Large Multimodal Models have exceeded general human capabilities in various tasks. |
| Approach: | They present an Olympiad-level bilingual multimodal scientific benchmark featuring 8,476 problems from Olympiad level mathematics and physics competitions. |
| Outcome: | The best performing model, GPT-4V, attains an average score of 17.97% on OlympiadBench, with a mere 10.74% in physics, highlighting the benchmark rigor and the intricacy of physical reasoning. |
Improving the Language Understanding Capabilities of Large Language Models Using Reinforcement Learning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Instruction-fine-tuned large language models (LLMs) under 14B parameters underperform on NLU tasks . we explore a framework to improve the NLU capabilities of LLMs . |
| Approach: | They propose to use Proximal Policy Optimization to improve NLU capabilities . they frame NLU as a reinforcement learning environment and optimize for reward signals . |
| Outcome: | The proposed framework outperforms supervised fine-tuning on GLUE and superGLUE tasks. |
Too Consistent to Detect: A Study of Self-Consistent Errors in LLMs (2025.emnlp-main)
Copied to clipboard
Hexiang Tan, Fei Sun, Sha Liu, Du Su, Qi Cao, Xin Chen, Jingang Wang, Xunliang Cai, Yuanzhuo Wang, Huawei Shen, Xueqi Cheng
| Challenge: | Existing detection methods fail to account for **self-consistent error** . study identifies self-consistency errors and evaluates them . |
| Approach: | They propose a method that fuses hidden state evidence from an external verifier LLM to detect self-consistent errors. |
| Outcome: | The proposed method significantly enhances performance on self-consistent errors across three LLM families. |
Robust Lottery Tickets for Pre-trained Language Models (2022.acl-long)
Copied to clipboard
| Challenge: | Recent studies have shown that pre-trained language models contain smaller matching subnetworks that are not robust to adversarial examples. |
| Approach: | They propose a method to find robust tickets hidden in pre-trained language models by learning binary weight masks and an adversarial loss objective to guide the search. |
| Outcome: | The proposed method improves on previous work on adversarial robustness evaluation. |
Specificity-Driven Cascading Approach for Unsupervised Sentiment Modification (D19-1)
Copied to clipboard
| Challenge: | Existing methods for unsupervised sentiment modification lack specific information in text generated without parallel data . specificity-driven cascading approach can improve specificity of generated text and content preservation . |
| Approach: | They propose a specificity-driven cascading approach for unsupervised sentiment modification . the method performs target sentiment addition and content reconstruction independently . |
| Outcome: | The proposed method outperforms competitive systems by a large margin on Yelp and Amazon datasets. |
Semantically Comprehensive Token Pruning in LVLMs via Maximizing Concept Coverage (2026.acl-long)
Copied to clipboard
| Challenge: | Existing visual token pruning methods leverage simple metrics derived from human experience, such as attention or similarity, to rank and select tokens within a highly entangled feature space. |
| Approach: | They propose a novel visual token pruning method that uses a concept-driven paradigm to quantify the Marginal Semantic Gain of each token's contribution to uncovered concepts. |
| Outcome: | The proposed method outperforms state-of-the-art methods in a concept-driven model while maintaining semantic completeness. |
SDAR-VL: Stable and Efficient Block-wise Diffusion for Vision-Language Understanding (2026.acl-long)
Copied to clipboard
| Challenge: | Existing block-wise discrete diffusion models lack robust autoregressive (AR) decoders. |
| Approach: | They propose a block-wise discrete diffusion framework for large-scale vision-language understanding with a progressive beta noise curriculum. |
| Outcome: | The proposed framework improves training efficiency, convergence stability, and task performance over conventional block diffusion. |
Blinded by Generated Contexts: How Language Models Merge Generated and Retrieved Contexts When Knowledge Conflicts? (2024.acl-long)
Copied to clipboard
| Challenge: | Recent advances in augmenting Large Language Models (LLMs) with auxiliary information have significantly revolutionized their efficacy in knowledge-intensive tasks. |
| Approach: | They propose a systematic framework to identify whether LLMs’ responses are attributed to either generated or retrieved contexts. |
| Outcome: | The proposed framework identifies whether LLMs’ responses are attributed to either generated or retrieved contexts. |
RLSeek: Evidence-Grounded Reasoning for RAG Hallucination Detection (2026.acl-long)
Copied to clipboard
Zhaoheng Huang, Dacheng Wen, Yutao Zhu, Xiaoying Lian, Yushi Liang, Kai Hao, Nan Li, Liangjie Zhang, Qi Zhang, Ji-Rong Wen, Zhicheng Dou, Fangzhao Wu
| Challenge: | Recent work addresses this problem by training span-level hallucination detectors using reinforcement learning and chain-of-thought reasoning. |
| Approach: | They propose a framework that explicitly enforces active evidence seeking during CoT reasoning by requiring quotation of relevant source segments at each verification step. |
| Outcome: | The proposed framework improves hallucination span detection performance with limited reasoning overhead and improved robustness in out-of-domain settings. |
MMCLIP: Cross-Modal Attention Masked Modelling for Medical Language-Image Pre-Training (2026.acl-long)
Copied to clipboard
| Challenge: | Existing vision-and-language pretraining methods face challenges in reconstructing pathological features due to limited data. |
| Approach: | They propose a method that uses masked modeling to enhance visual and linguistic learning. |
| Outcome: | MMCLIP integrates unpaired data through disease-kind prompts to achieve state-of-the-art performance in zero-shot and fine-tuning across five benchmarks. |
Dual-Alignment Pre-training for Cross-lingual Sentence Embedding (2023.acl-long)
Copied to clipboard
Ziheng Li, Shaohan Huang, Zihan Zhang, Zhi-Hong Deng, Qiang Lou, Haizhen Huang, Jian Jiao, Furu Wei, Weiwei Deng, Qi Zhang
| Challenge: | Recent studies have shown that dual encoder models trained with the sentence-level translation ranking task are effective methods for cross-lingual sentence embedding. |
| Approach: | They propose a dual-alignment pre-training framework that incorporates both sentence-level and token-level alignment. |
| Outcome: | The proposed framework improves cross-lingual sentence embedding on three cross-linguistic benchmarks. |
VLN-MME: Diagnosing MLLMs as Language-guided Visual Navigation Agents (2026.acl-long)
Copied to clipboard
| Challenge: | Multimodal Large Language Models have demonstrated remarkable capabilities across vision-language tasks, but their performance as embodied agents needs further exploration. |
| Approach: | They propose a framework to evaluate multimodal large language models as zero-shot agents . they find that enhancing prevalent agents with Chain-of-Thought reasoning and self-reflection leads to an unexpected performance decrease. |
| Outcome: | The proposed framework enables comparisons and component-level ablations across diverse MLLM architectures, agent designs, and navigation tasks. |
GA-SAM: Gradient-Strength based Adaptive Sharpness-Aware Minimization for Improved Generalization (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies show flat minima tend to imply better generalization abilities . however, it has some difficulty implying SAM to some natural language tasks . |
| Approach: | They propose a flatness-aware minimization algorithm that can be applied to natural language tasks . they propose to use parameter corruptions to explain why flat minima generalize better . |
| Outcome: | The proposed algorithm can generalize better for flat minima that are robust against corruptions or perturbations. |
GLGE: A New General Language Generation Evaluation Benchmark (2021.findings-acl)
Copied to clipboard
Dayiheng Liu, Yu Yan, Yeyun Gong, Weizhen Qi, Hang Zhang, Jian Jiao, Weizhu Chen, Jie Fu, Linjun Shou, Ming Gong, Pengcheng Wang, Jiusheng Chen, Daxin Jiang, Jiancheng Lv, Ruofei Zhang, Winnie Wu, Ming Zhou, Nan Duan
| Challenge: | Multi-task benchmarks focus on a range of Natural Language Understanding (NLU) tasks without considering the Natural Language Generation (NLG) models. |
| Approach: | They propose a multi-task benchmark for evaluating the generalization capabilities of NLG models across eight language generation tasks. |
| Outcome: | The proposed benchmarks are based on GLUE and Su-perGLUE for English and several other languages. |
Distinguish Sense from Nonsense: Out-of-Scope Detection for Virtual Assistants (2022.emnlp-industry)
Copied to clipboard
| Challenge: | Out of Scope (OOS) detection is a problem with chatbots that cannot make sense of a query . a real-world solution to this problem is to identify out-of-domain queries . |
| Approach: | They propose a simple yet effective OOS detection method that outperforms standard methods . they propose analyzing data from an enterprise virtual assistant platform to test the method . |
| Outcome: | The proposed method outperforms standard OOS detection methods in a real-world deployment of virtual assistants. |
Simple or Complex? Complexity-controllable Question Generation with Soft Templates and Deep Mixture of Experts Model (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing work on complex questions does not consider controlling complexity of generated questions. |
| Approach: | They propose an end-to-end neural complexity-controllable question generation model that incorporates a mixture of experts as the selector of soft templates to capture question similarity while avoiding the expensive construction of actual templates. |
| Outcome: | The proposed model is superior to state-of-the-art methods in both automatic and manual evaluations on two benchmark QA datasets. |
LexicalAT: Lexical-Based Adversarial Reinforcement Training for Robust Sentiment Classification (D19-1)
Copied to clipboard
| Challenge: | Existing text classification models are fragile and sensitive to simple perturbations. |
| Approach: | They propose a generator-classifier adversarial training approach to improve classification models . they use a large-scale lexical knowledge base to generate attacking examples . |
| Outcome: | The proposed approach outperforms strong baselines and reduces test errors on neural networks. |
Clustered Self-Assessment: A Simple yet Effective Method for Uncertainty Quantification in Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for uncertainty quantification in large language models rely on indirect signals, such as entropy across sampled generations, which can be difficult to interpret and do not fully leverage the model’s ability to assess its own uncertainty. |
| Approach: | They propose a method that groups sampled generations into semantically distinct clusters and uses the probability assigned by the LLM to each option as a confidence estimate. |
| Outcome: | The proposed method outperforms baseline methods and achieves competitive performance with as few as two additional samples. |
For-Value: Efficient Forward-Only Data Valuation for finetuning LLMs and VLMs (2026.acl-long)
Copied to clipboard
Wenlong Deng, Qi Zeng, Jiaming Zhang, Minghui Chen, Zixin Ding, Christos Thrampoulidis, Boying Gong, Xiaoxiao Li
| Challenge: | Existing methods for data valuation rely on gradient computations, making them prohibitive for billion-parameter models. |
| Approach: | They propose a forward-only data valuation framework that enables efficient batch-scalable value estimation while maintaining effectiveness. |
| Outcome: | The proposed framework matches or outperforms gradient-based baselines in detecting influential data and mislabeled data while achieving significant efficiency improvements. |
QiMeng-Attention: SOTA Attention Operator is generated by SOTA Attention Algorithm (2025.findings-acl)
Copied to clipboard
Qirui Zhou, Shaohui Peng, Weiqiang Xiong, Haixin Chen, Yuanbo Wen, Haochen Li, Ling Li, Qi Guo, Yongwei Zhao, Ke Gao, Ruizhi Chen, Yanjun Wu, Zhao Chen, Yunji Chen
| Challenge: | Existing LLMs cannot comprehend the complex data flow and computation process of the attention operator and utilize low-level primitive to exploit GPU performance. |
| Approach: | They propose an LLM-friendly Thinking Language (LLM-TL) that can decouple the generation of high-level optimization logic and low-level implementation on GPU and enhance LLMs’ understanding of attention operator. |
| Outcome: | The proposed method outshines existing LLMs on A100, RTX8000, and T4 GPUs, achieving a speed-up of up to 35.16. |
ORTicket: Let One Robust BERT Ticket Transfer across Different Tasks (2024.lrec-main)
Copied to clipboard
| Challenge: | Pretrained language models are susceptible to subtle perturbations and require multiple adversarial training during fine-tuning to improve their robustness. |
| Approach: | They propose a novel adversarial defense method ORTicket that fine-tunes a model for downstream tasks. |
| Outcome: | The proposed method achieves comparable robustness to other defense methods while maintaining the efficiency of fine-tuning. |
TextFusion: Privacy-Preserving Pre-trained Model Inference via Token Fusion (2022.emnlp-main)
Copied to clipboard
Xin Zhou, Jinzhu Lu, Tao Gui, Ruotian Ma, Zichu Fei, Yuran Wang, Yong Ding, Yibo Cheung, Qi Zhang, Xuanjing Huang
| Challenge: | Existing methods to preserve inference privacy are available as cloud services . however, the risk of privacy leakage remains, according to recent studies . |
| Approach: | They propose a method to preserve inference privacy by fusing token representations in the cloud. |
| Outcome: | The proposed method preserves inference privacy without sacrificing performance on different scenarios. |
Toward Optimal LLM Alignments Using Two-Player Games (2025.findings-emnlp)
Copied to clipboard
Rui Zheng, Hongyi Guo, Zhihan Liu, Xiaoying Zhang, Yuanshun Yao, Xiaojun Xu, Zhaoran Wang, Zhiheng Xi, Tao Gui, Qi Zhang, Xuanjing Huang, Yang Liu, Hang Li
| Challenge: | Alignment of large language models (LLM) is a process that ensures the model’s responses to user prompts align with human intentions and social values. |
| Approach: | They propose an alignment method based on a two-agent game consisting of an adversarial agent and a defensive agent. |
| Outcome: | The proposed method improves on a two-agent game with an adversarial agent and a defensive agent. |
Retrieval, Reasoning, Re-ranking: A Context-Enriched Framework for Knowledge Graph Completion (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing embedding-based methods rely on triples in the KG, which is vulnerable to specious relation patterns and long-tail entities. |
| Approach: | They propose a context-enriched framework for KGC that uses a large language model to generate potential answers for each query triple. |
| Outcome: | The proposed framework improves on FB15k237 and WN18RR datasets. |
That Slepen Al the Nyght with Open Ye! Cross-era Sequence Segmentation with Switch-memory (2022.acl-long)
Copied to clipboard
| Challenge: | Grammar, vocabulary, and lexical semantic shifts take place over time, creating diachronic linguistic gap. |
| Approach: | a Chinese cross-era learning framework incorporates era-specific linguistic knowledge into a neural network. |
| Outcome: | a new learning framework for Chinese word segmentation improves on four corpora from different eras. |
SoT: Structured-of-Thought Prompting Guides Multilingual Reasoning in Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models struggle with multilingual reasoning tasks due to resource constraints . a training-free method improves performance on multilingual thinking tasks . |
| Approach: | They propose a training-free method that transforms language-specific semantic information into language-agnostic structured representations. |
| Outcome: | The proposed method outperforms strong baselines on multilingual reasoning tasks. |
SAM3-I: Segment Anything with Instructions (2026.acl-long)
Copied to clipboard
Jingjing Li, Yue Feng, Yuchen Guo, Jincai Huang, Wei Ji, Qi Bi, Yongri Piao, Miao Zhang, Xiaoqi Zhao, Qiang Chen, Shihao Zou, Huchuan Lu, Li Cheng
| Challenge: | Existing methods for concept-level grounding and instruction-level reasoning use coarse representations and iterative mask filtering. |
| Approach: | They propose an instruction-following extension of the Segment Anything Model 3 family that unifies concept-level grounding and instruction-level reasoning within a single segmentation framework. |
| Outcome: | Experiments show that SAM3-I achieves appealing performance across referring and reasoning-based segmentation while maintaining its strong concept recall ability. |
Learning “O” Helps for Learning More: Handling the Unlabeled Entity Problem for Class-incremental NER (2023.acl-long)
Copied to clipboard
Ruotian Ma, Xuanting Chen, Zhang Lin, Xin Zhou, Junzhe Wang, Tao Gui, Qi Zhang, Xiang Gao, Yun Wen Chen
| Challenge: | Existing Named Entity Recognition systems are typically trained on a large-scale dataset with predefined entity classes, then deployed for entity recognition on the test data without further adaptation or refinement. |
| Approach: | They propose a representation learning method that adaptively detects entity clusters in "O" and two effective distance-based relabeling strategies for better learning the old classes. |
| Outcome: | The proposed method achieves 10.62% improvement over the baseline methods. |
AJ-Bench: Benchmarking Agent-as-a-Judge for Environment-Aware Evaluation (2026.findings-acl)
Copied to clipboard
Wentao Shi, Yu Wang, Yuyang Zhao, Yuxin Chen, Fuli Feng, Xueyuan Hao, Xi Su, Qi GU, Hui Su, Xunliang Cai, Xiangnan He
| Challenge: | Existing approaches to verify agent behaviors in complex environments rely on rule-based verifiers or LLM-as-a-Judge models. |
| Approach: | They propose a benchmark to evaluate Agent-as-a-Judge across three domains . the benchmark covers search, data systems, and graphical user interfaces - with 155 tasks and 516 trajectories . |
| Outcome: | The proposed benchmark outperforms existing benchmarks in search, data systems, and GUI domains while revealing open challenges in agent-based verification. |
Text Anomaly Detection with Simplified Isolation Kernel (2025.findings-emnlp)
Copied to clipboard
| Challenge: | High-dimensional dense embeddings extracted by large language models pose memory requirements and high computation time. |
| Approach: | They propose a method that maps high-dimensional dense embeddings to lower-dimensional sparse representations while preserving crucial anomaly characteristics. |
| Outcome: | The proposed method achieves better detection performance than 11 SOTA anomaly detection algorithms while maintaining computational efficiency and low memory cost. |
GRIT: A Dataset of Group Reference Recognition in Italian (2024.lrec-main)
Copied to clipboard
| Challenge: | a task of automatically recognizing group references has not yet gained much attention within NLP. |
| Approach: | They propose a large-scale dataset for automatic group reference recognition in italian . they verify the validity of the task using a fine-tuned BERT model . |
| Outcome: | The proposed dataset proves that it can be applied to political text analysis and social media analysis. |
Hi-Transformer: Hierarchical Interactive Transformer for Efficient and Effective Long Document Modeling (2021.acl-short)
Copied to clipboard
| Challenge: | Existing approaches to model long documents are difficult due to the quadratic complexity of text length. |
| Approach: | They propose a hierarchical interactive Transformer for efficient long document modeling. |
| Outcome: | Extensive experiments on three benchmark datasets validate the efficiency and effectiveness of Hi-Transformer in long document modeling. |
The Subtle Art of Defection: Understanding Uncooperative Behaviors in LLM based Multi-Agent Systems (2026.eacl-industry)
Copied to clipboard
| Challenge: | Existing literature on uncooperative behavior degrades collective outcomes and requires more resilient multi-agent systems. |
| Approach: | They propose a game theory-based taxonomy of uncooperative agent behaviors and a structured, multi-stage simulation pipeline that dynamically generates and refines uncooperation behaviors as agents’ states evolve. |
| Outcome: | The proposed framework achieves 96.7% accuracy in generating realistic uncooperative behaviors, validated by human evaluations. |
On the token distance modeling ability of higher RoPE attention dimension (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing work on extending the context length of language models based on Rotary position embedding (RoPE) has shown promising results in capturing longer-range contextual information. |
| Approach: | They propose to use a hidden dimension of an attention head to investigate its contribution to capturing long-distance dependencies. |
| Outcome: | The proposed model can capture long-distance dependencies by extending the attention of a particular dimension of an attention head. |
Beyond Seen Data: Improving KBQA Generalization Through Schema-Guided Logical Form Generation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Knowledge base question answering (KBQA) aims to answer user questions in natural language using rich human knowledge stored in large KBs. |
| Approach: | They propose a model that injects schema contexts into entity retrieval and logical form generation to enhance generalizability. |
| Outcome: | The proposed model outperforms state-of-the-art models on two commonly used benchmark datasets across a variety of test settings. |
GEM: Gestalt Enhanced Markup Language Model for Web Understanding via Render Tree (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing models that use plain HTMLs do not include crucial visual information in the rendered web. |
| Approach: | They propose a Gestalt Enhanced Markup Language Model for hosting visual information without visual input. |
| Outcome: | The proposed model can handle multiple downstream tasks without visual input. |
TP-Detector: Detecting Turning Points in the Engineering Process of Large-scale Projects (2023.emnlp-demo)
Copied to clipboard
| Challenge: | Extensive experiments demonstrate the effectiveness of our proposed method on a constructed dataset compared to baseline methods. |
| Approach: | They propose a novel task of detecting turning points in the engineering process of large-scale projects by treating news streams as a window with multiple instances. |
| Outcome: | The proposed mode is able to detect transitions in news streams with multiple instances. |
CASN:Class-Aware Score Network for Textual Adversarial Detection (2023.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to counteract adversarial attacks can be divided into two directions, adversarials defense and adversarially detection. |
| Approach: | They propose a score-based generative method to implicitly model the data distribution using a log-density distribution and supervised contrastive learning to guide the estimation using label information. |
| Outcome: | The proposed method improves on three text classification tasks on four advanced attack algorithms. |
Unified Dual-view Cognitive Model for Interpretable Claim Verification (2021.acl-long)
Copied to clipboard
| Challenge: | Existing studies constructing direct interactions between the claim and each single user response to capture evidence have shown remarkable success in interpretable claim verification. |
| Approach: | They propose a Dual-view model based on the views of Collective and Individual Cognition (CICD) that captures word-level semantics based . on individual cognition, they adjust the proportion between them to generate global evidence. |
| Outcome: | The proposed model is based on the views of collective and individual cognition and achieves state-of-the-art performance on three benchmark datasets. |
Enhancing Large Vision-Language Models with Ultra-Detailed Image Caption Generation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing pipelines for generating high-quality, ultra-detailed image captions are limited by the scarcity of image caption data. |
| Approach: | They propose a pipeline for generating high-quality, ultra-detailed image captions that integrates both pre-processing and post-processor stages. |
| Outcome: | The proposed pipeline improves LVLMs' perception and cognitive abilities across multiple vision-language benchmarks. |
STReasoner: Empowering LLMs for Spatio-Temporal Reasoning in Time Series via Spatial-Aware Reinforcement Learning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing models focus on predictive accuracy over reasoning, a gap exists . time series data are ubiquitous in real-world systems and exhibit complex spatio-temporal structures. |
| Approach: | They propose a time series reasoning model that integrates time series, graph structure, and text for explicit reasoning. |
| Outcome: | The proposed model achieves average accuracy gains between 17% and 135% at 0.004x the cost of proprietary models and generalizes robustly to real-world data. |
RouterHGC: Optimized Router for LLM-based Multi-Agent Systems via Heterogeneous Graph Contrastive Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs)-driven Multi-Agent Systems (MAS) have demonstrated remarkable scalability and generalizability across complex tasks. |
| Approach: | They propose a new framework for routing using large language models . they formalize routing as node selection through edge-weight prediction . |
| Outcome: | The proposed framework outperforms the best single LLM and baselines on five datasets . it achieves 0.80%–6.17% accuracy gains on MATH and HotpotQA while reducing inference cost by 27.40%. |
Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods for textual backdoor attacks insert additional contents into normal samples as triggers, causing detection and blocking of backdoors. |
| Approach: | They propose to use syntactic structure as trigger in textual backdoor attacks . they propose to achieve similar attack performance but have higher invisibility . |
| Outcome: | The proposed method achieves almost 100% success rate but has higher invisibility and stronger resistance to defenses than the insertion-based methods. |
Enhancing LLM-based Search Agents via Contribution Weighted Group Relative Policy Optimization (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to training large language models suffer from unstable value estimation, whereas outcome supervision struggles with credit assignment due to sparse, trajectory-level rewards. |
| Approach: | They propose a framework that integrates process supervision into group relative policy optimization. |
| Outcome: | The proposed framework outperforms standard GRPO on knowledge-intensive benchmarks by 5.0% and 6.3% on Qwen3-1.7B. |
OptSLA: an Optimization-Based Approach for Sequential Label Aggregation (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to annotate data are based on binary and multi-choice problems, but little work has been done on complex tasks such as sequence labeling with imbalanced classes. |
| Approach: | They propose an optimization-based Sequential Label Aggregation method that integrates worker reliabilities and advanced deep learning techniques to conquer the challenge. |
| Outcome: | The proposed method outperforms state-of-the-art methods and is easier to interpret. |
Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer (2021.emnlp-main)
Copied to clipboard
| Challenge: | Experimental results show that popular NLP models are vulnerable to both adversarial and backdoor attacks based on text style transfer. |
| Approach: | They propose to conduct adversarial and backdoor attacks based on text style transfer . the authors propose to use text style to alter the style of a sentence . |
| Outcome: | The proposed methods show that popular models are vulnerable to both attacks based on text style transfer . the results show that the proposed methods perform better than baselines in many aspects . |
Question Directed Graph Attention Network for Numerical Reasoning over Text (2020.emnlp-main)
Copied to clipboard
Kunlong Chen, Weidi Xu, Xingyi Cheng, Zou Xiaochuan, Yuyu Zhang, Le Song, Taifeng Wang, Yuan Qi, Wei Chu
| Challenge: | Numerical reasoning requires both natural language understanding and arithmetic computation. |
| Approach: | They propose a graph representation for the context of the passage and question needed for numerical reasoning. |
| Outcome: | The proposed model achieves remarkable results in benchmark datasets such as DROP. |
The Threat of PROMPTS in Large Language Models: A System and User Prompt Perspective (2025.findings-acl)
Copied to clipboard
| Challenge: | Prompts are essential for guiding model output and influencing content generation. |
| Approach: | They propose to attack models with prompt leakage and prompt jailbreak attacks . they summarize the experimental setups of these methods and explore the relationship between prompt threats and prompt injection attacks. |
| Outcome: | The proposed methods summarize the experimental setups and examine the relationship between prompt threats and prompt injection attacks. |
Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Alignment (2026.acl-long)
Copied to clipboard
Yuming Yang, Mingyoung Lai, Wanxu Zhao, Xiaoran Fan, Zhiheng Xi, Mingqi Wu, Chiyue Huang, Jun Zhao, Haijun Lv, Jian Tong, Yunhua Zhou, Yicheng Zou, Qipeng Guo, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing methods assess suitability primarily through student likelihood, favoring trajectories that align closely with the student model’s current behavior but overlooking more informative ones. |
| Approach: | They propose a Rank–Surprisal Ratio metric that captures both alignment and informativeness to assess the suitability of a reasoning trajectory. |
| Outcome: | The proposed metric captures both alignment and informativeness to assess the suitability of a reasoning trajectory. |
ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization (2025.findings-emnlp)
Copied to clipboard
Zhensheng Jin, Xinze Li, Yifan Ji, Chunyi Peng, Zhenghao Liu, Qi Shi, Yukun Yan, Shuo Wang, Furong Peng, Ge Yu
| Challenge: | Existing methods to train LLMs suffer from overthinking, leading to lengthy reasoning traces . Existing approaches to train large language models suffer from this problem . |
| Approach: | They propose a method to combine multiple reasoning chains for training LLMs . they use stepwise exploration and long-short switched sampling to evaluate reasoning paths . |
| Outcome: | The proposed method reduces reasoning lengths by approximately 30-50% . it also maintains or improves reasoning accuracy compared to baselines . |
Two Birds with One Stone: Unified Model Learning for Both Recall and Ranking in News Recommendation (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing news recommender systems conduct news recall and ranking separately with different models, but maintaining multiple models leads to high computational cost and high latency. |
| Approach: | They propose a unified method for recall and ranking in news recommendation that uses historical news click behaviors to extract user embeddings for ranking from the user's attention query. |
| Outcome: | The proposed method improves recall and ranking efficiency and effectiveness on a benchmark dataset. |
Thinking Clearly, Talking Fast: Concept-Guided Non-Autoregressive Generation for Open-Domain Dialogue Systems (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing models with seq2seq framework lack ability to effectively manage concept transitions . lack of concept management strategies might lead to incoherent dialogue due to loosely connected concepts . |
| Approach: | They propose a concept-guided non-autoregressive model for open-domain dialogue generation that learns to identify multiple associated concepts from a conceptual graph and a customized Insertion Transformer to perform concept-directed generation to complete a response. |
| Outcome: | The proposed model outperforms state-of-the-art models in automatic and human evaluations with substantially faster inference speed. |
UniHGKR: Unified Instruction-aware Heterogeneous Knowledge Retrievers (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing information retrieval models assume a homogeneous structure for knowledge sources and user queries, limiting their applicability in real-world settings. |
| Approach: | They propose a unified instruction-aware heterogeneous knowledge retriever that builds a heterogenous retrieval space for heterogenized knowledge and follows diverse user instructions to retrieve knowledge in specified types. |
| Outcome: | The proposed framework outperforms state-of-the-art methods on CompMix-IR . it achieves 6.36% relative improvements and 54.23% relative improvements . |
Investigating Context Faithfulness in Large Language Models: The Roles of Memory Strength and Evidence Style (2025.findings-acl)
Copied to clipboard
| Challenge: | Retrieval-augmented generation improves Large Language Models (LLMs) by integrating external information into the response generation process. |
| Approach: | They investigate the impact of memory strength and evidence presentation on LLMs’ receptiveness to external evidence by measuring the divergence in LLM responses to different paraphrases of the same question. |
| Outcome: | The proposed method improves Large Language Models (LLMs) by integrating external information into the response generation process. |
V-VAE: A Variational Auto Encoding Framework Towards Fine-Grained Control over Human-Like Chat (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing role-play and persona-based chat approaches rely on static role descriptions, coarse-grained signal space, and low-quality synthetic data. |
| Approach: | They propose a Verbal Variational Auto-Encoding framework which dynamically adapts dialogue behaviour based on latent variables across talking style, interaction patterns, and personal attributes. |
| Outcome: | The proposed framework outperforms baselines on HumanChatBench and DialogBench to address the scarcity of high-quality data in the human-like domain. |
TASO: Task-Aligned Sparse Optimization for Parameter-Efficient Model Adaptation (2025.emnlp-main)
Copied to clipboard
Daiye Miao, Yufang Liu, Jie Wang, Changzhi Sun, Yunke Zhang, Demei Yan, Shaokang Dong, Qi Zhang, Yuanbin Wu
| Challenge: | Existing studies have shown that LoRA introduces substantial parameter redundancy, which not only increases the number of trainable parameters but also hinders the effectiveness of fine-tuning. |
| Approach: | They propose a method that leverages importance information from the pretrained model’s weights to mitigate LoRA redundancy. |
| Outcome: | The proposed method significantly reduces the number of trainable parameters required for task adaptation while providing a task-aligned perspective for LoRA redundancy reduction. |
Distantly Supervised Named Entity Recognition using Positive-Unlabeled Learning (P19-1)
Copied to clipboard
| Challenge: | Empirical studies on four public NER datasets demonstrate the effectiveness of our proposed method. |
| Approach: | They propose a method to perform named entity recognition using unlabeled data and named entity dictionaries. |
| Outcome: | The proposed method can estimate task loss as if there is fully labeled data. |
Incorporating Dynamic Semantics into Pre-Trained Language Model for Aspect-based Sentiment Analysis (2022.findings-acl)
Copied to clipboard
| Challenge: | Aspect-based sentiment analysis (ABSA) predicts sentiment polarity towards a specific aspect in a sentence. |
| Approach: | They propose to use a dynamic aspect-oriented semantics-based method to learn ABSA. |
| Outcome: | The proposed method can learn dynamic aspect-oriented semantics for ABSA on three benchmark datasets. |
Divide and Conquer: Legal Concept-guided Criminal Court View Generation (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for creating rationales for criminal cases do not pay enough attention to the important legal concepts. |
| Approach: | They propose a legal concept-guided court view generation framework that generates rationales based on predicted legal concepts . they first divide the court view into sub-views, then employ a solver and verifier to generate and select rationale. |
| Outcome: | The proposed model generates coherent and coherent court views on a real-world criminal case dataset. |
Heterogeneous Graph Neural Networks for Keyphrase Generation (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches for keyphrase generation generate uncontrollable and inaccurate absent keyphrases. |
| Approach: | They propose a graph-based method that captures explicit knowledge from related references. |
| Outcome: | The proposed model improves on baseline keyphrase generation models on multiple benchmarks. |
Generalizing Trust: Weak-to-Strong Trustworthiness in Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Recent studies have highlighted weak-to-strong generalization, where a strong model trained only on a weak model’s labels surpasses the weak model in task performance. |
| Approach: | They propose two fundamental fine-tuning strategies that leverage trustworthiness regularization during the fine-uning of the weak model and the weak-to-strong transfer to improve trustworthy. |
| Outcome: | The proposed models show that they can generalize robustness, fairness, and privacy better when trained on weak models than models trained on strong models. |
Interpretable Automatic Fine-grained Inconsistency Detection in Text Summarization (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing factual consistency evaluation approaches for text summarization provide binary predictions and limited insights into the weakness of summarizing systems. |
| Approach: | They propose a task of fine-grained inconsistency detection to detect inconsistent summaries . they represent facts with semantic frames extracted by semantic role labeling and highlight related semantic frames to predict inconsistance . |
| Outcome: | The proposed model outperforms baseline models and provides evidence to support or refute the summary. |
Efficient Adversarial Training with Robust Early-Bird Tickets (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to improve the robustness of pre-trained language models are expensive because of the need to generate adversarial examples via gradient descent. |
| Approach: | They propose an adversarial optimization method that searches for robust tickets with structured sparsity in the early stage and fine-tunes tickets in the remaining time. |
| Outcome: | The proposed method achieves up to 7 13 training speedups while maintaining comparable or even better robustness compared to the most competitive state-of-the-art methods. |
TEACH: A Contrastive Knowledge Adaptive Distillation Framework for Classical Chinese Understanding (2025.acl-long)
Copied to clipboard
| Challenge: | Traditional methods for processing classical Chinese segment language understanding into discrete tasks, which overlook crucial background information and reduce user engagement. |
| Approach: | They propose a framework that integrates word sense disambiguation with sentence translation to minimize hallucinations and improve semantic analysis. |
| Outcome: | The proposed framework integrates word sense disambiguation with sentence translation to minimize hallucinations and improve semantic analysis. |
EgoMemory: Memory-Augmented Personalized Retrieval for Long-Context Egocentric Video (2026.findings-acl)
Copied to clipboard
Yuanmin Tang, Jue Zhang, Xiaoting Qin, Jing Yu, Meikang Qiu, Gaopeng Gou, Gang Xiong, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang, Qi Wu
| Challenge: | Existing egocentric video datasets do not support the personalization and long-context reasoning required for episodic memory retrieval. |
| Approach: | They propose a benchmark framework that uses MLLMs and reflective Chain-of-Thought to ground user queries in personal memory explicitly. |
| Outcome: | The proposed framework outperforms state-of-the-art benchmarks on three benchmarks . it can be used to generate detailed target video descriptions in long-context contexts based on user-specific object annotations enriched with user-specified object annotation data . |
UER: An Open-Source Toolkit for Pre-training Models (D19-3)
Copied to clipboard
Zhe Zhao, Hui Chen, Jinbin Zhang, Xin Zhao, Tao Liu, Wei Lu, Xi Chen, Haotang Deng, Qi Ju, Xiaoyong Du
| Challenge: | Existing work on pre-training models have shown that it is important to use a framework to deploy various pre- training models efficiently. |
| Approach: | They propose an assemble-on-demand pre-training toolkit that assembles pre-trained models on demand and encapsulates them with rich modules. |
| Outcome: | The proposed framework can reproduce state-of-the-art models or develop models that remain unexplored. |
Locate Then Ask: Interpretable Stepwise Reasoning for Multi-hop Question Answering (2022.coling-1)
Copied to clipboard
| Challenge: | Existing methods for multi-hop reasoning ignore grounding on supporting facts of each step, which tends to generate inaccurate decompositions. |
| Approach: | They propose an interpretable stepwise reasoning framework that incorporates supporting sentences and questions at each intermediate step and utilizes the inference of the current hop for the next until reasoning out the final result. |
| Outcome: | The proposed model can boost performance and yield a better interpretable reasoning process without decomposition supervision. |
Do LLMs Overcome Shortcut Learning? An Evaluation of Shortcut Challenges in Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have shown remarkable capabilities in various tasks, but may rely on dataset biases as shortcuts for prediction. |
| Approach: | They propose to use a test suite to evaluate the impact of shortcuts on LLMs' performance. |
| Outcome: | The proposed test suite incorporates six shortcut types, five evaluation metrics, and four prompting strategies. |
Pretrain-KGE: Learning Knowledge Representation from Pretrained Language Models (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing knowledge graph embedding models suffer from limited knowledge representation due to sparse and noisy dataset annotations. |
| Approach: | They propose to use pretrained language models to enhance knowledge representation by leveraging world knowledge from pretrained models. |
| Outcome: | Extensive experiments show that the proposed framework can improve results over existing models. |
Long-context Language Models Fail in Basic Retrieval Tasks Without Sufficient Reasoning Steps (2025.findings-emnlp)
Copied to clipboard
| Challenge: | despite their extensive context window, long-context language models fail in some basic cases . a recent study shows that long-cot methods are not necessary for long-constituency tasks . |
| Approach: | a new study evaluates long-context language models with a large context window . the authors propose a method that can be well addressed with arbitrary reasoning steps . |
| Outcome: | The proposed methods are well addressed with a sufficient number of reasoning steps, guided by specific CoT prompts. |
MSI-Agent: Incorporating Multi-Scale Insight into Embodied Agents for Superior Planning and Decision-Making (2024.emnlp-main)
Copied to clipboard
| Challenge: | Insight is a form of long-term memory for an agent but lack of general insight can undermine its effectiveness. |
| Approach: | They propose an embodied agent that summarises and utilizes insight effectively across different scales and generates task-specific and high-level insight, stores it in a database, and then uses relevant insight from it. |
| Outcome: | The proposed agent outperforms a similar agent when planning by GPT3.5 and is more robust when faced with domain-shifting scenarios. |
Orca: A Few-shot Benchmark for Chinese Conversational Machine Reading Comprehension (2023.findings-emnlp)
Copied to clipboard
Nuo Chen, Hongguang Li, Junqing He, Yinan Bao, Xinshi Lin, Qi Yang, Jianfeng Liu, Ruyi Gan, Jiaxing Zhang, Baoyuan Wang, Jia Li
| Challenge: | Existing benchmarks for conversational machine reading comprehension are inconsistent with real scenarios. |
| Approach: | They propose to use a Chinese CMRC benchmark to evaluate model's generalization ability towards diverse domains by using zero-shot/few-shot settings. |
| Outcome: | The proposed benchmarks are based on 831 hot-topic driven conversations with 4,742 turns and cover 33 domains. |
Neural Network Surgery: Injecting Data Patterns into Pre-trained Models with Minimal Instance-wise Side Effects (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing neural network tuning methods cause instance-wise side effects . et al., 2018: a new approach to perform neural network surgery . |
| Approach: | They propose to perform neural network surgery by only changing 10-5 parameters . they propose to use a dynamic selecting method to achieve the best overall performance . |
| Outcome: | The proposed method achieves the best overall performance and induces fewer instance-wise side effects by changing only 10-5 of the parameters. |
Movie101: A New Movie Understanding Benchmark (2023.acl-long)
Copied to clipboard
| Challenge: | Existing methods to narrate movies with no actors are difficult to implement in real situations . a new metric is proposed to provide the best correlation with human evaluation . |
| Approach: | They propose a large-scale Chinese movie benchmark to help visually impaired enjoy movies . they propose metric called Movie Narration Score (MNScore) which achieves best correlation with human evaluation. |
| Outcome: | The proposed method outperforms baselines and the existing methods. |
Retrieved Sequence Augmentation for Protein Representation Learning (2024.emnlp-main)
Copied to clipboard
Chang Ma, Haiteng Zhao, Lin Zheng, Jiayi Xin, Qintong Li, Lijun Wu, Zhihong Deng, Yang Lu, Qi Liu, Sheng Wang, Lingpeng Kong
| Challenge: | Using multiple sequence alignments (MSA) to extract evolutionary knowledge is limited. |
| Approach: | They propose to use multiple sequence alignments to augment protein representations . they propose to employ Retrieved Sequence Augmentation to enhance protein representation learning . |
| Outcome: | The proposed method surpasses MSA Transformer by 5% in structural and property prediction tasks while being 373 times faster. |
Distantly Supervised Contrastive Learning for Low-Resource Scripting Language Summarization (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods for code summarization are limited in resources and require atomic commands and category constraints to enhance code representations. |
| Approach: | They propose a framework that leverages limited atomic commands and category constraints to enhance code representations. |
| Outcome: | The proposed framework outperforms baseline methods in a number of domains and demonstrates superiority over competing frameworks. |
Pretraining the Noisy Channel Model for Task-Oriented Dialogue (2021.tacl-1)
Copied to clipboard
| Challenge: | Current research on task-oriented dialogue models suffers from the explaining-away effect, manifested in models that favor short and generic responses. |
| Approach: | They propose to factorize the dialogue task into two models, the distribution of the context given the response, and the prior for the response itself, using Bayes' theorem. |
| Outcome: | The proposed model mitigates the explaining-away effect and allows the principled incorporation of large pretrained models for the response prior. |
R3-RAG: Learning Step-by-Step Reasoning and Retrieval for LLMs via Reinforcement Learning (2025.findings-emnlp)
Copied to clipboard
Yuan Li, Qi Luo, Xiaonan Li, Bufan Li, Qinyuan Cheng, Bo Wang, Yining Zheng, Yuxin Wang, Zhangyue Yin, Xipeng Qiu
| Challenge: | RAG systems that integrate external knowledge with Large Language Models often become bottlenecks due to their limited parameters compared to LLMs and their inability to perform step-by-step reasoning. |
| Approach: | They propose a model that integrates external knowledge with Large Language Models to enhance factual correctness and mitigate hallucination. |
| Outcome: | The proposed model outperforms baselines and can transfer well to different retrievers. |
Unveiling the Deficiencies of Pre-trained Text-and-Layout Models in Real-world Visually-rich Document Information Extraction (2026.findings-eacl)
Copied to clipboard
Chong Zhang, Yixi Zhao, Yulu Xie, Chenshu Yuan, Yi Tu, Ya Guo, Mingxu Chai, Ziyu Shen, Yue Zhang, Qi Zhang
| Challenge: | PTLMs have shown remarkable success in multiple information extraction tasks . however, their performance in real-world scenarios falls short of expectations . |
| Approach: | They propose to use an entity-centric dataset to evaluate PTLMs' performance . they find that inadequate annotations in benchmark datasets lead to spurious correlations . |
| Outcome: | The proposed dataset disentangles the falsely-coupled segment and entity annotations that arises from the block-level annotation of FUNSD. |
CoMave: Contrastive Pre-training with Multi-scale Masking for Attribute Value Extraction (2023.findings-acl)
Copied to clipboard
Xinnan Guo, Wentao Deng, Yongrui Chen, Yang Li, Mengdi Zhou, Guilin Qi, Tianxing Wu, Dong Yang, Liubin Wang, Yong Pan
| Challenge: | Existing methods to extract product features from unstructured text still suffer from problems . e-commerce platforms are focusing on multi-scale values, which can be confusing . |
| Approach: | They propose a pre-training technique to automatically obtain attribute value pairs from product descriptions to aid e-commerce. |
| Outcome: | The proposed method improves on the existing token-level masking strategy and achieves state-of-the-art on four benchmarks. |
EVIDENCEMINER: Textual Evidence Discovery for Life Sciences (2020.acl-demos)
Copied to clipboard
Xuan Wang, Yingjun Guan, Weili Liu, Aabhas Chauhan, Enyi Jiang, Qi Li, David Liem, Dibakar Sigdel, John Caufield, Peipei Ping, Jiawei Han
| Challenge: | EVIDENCEMINER is a web-based system that allows users to query a natural language statement and retrieve textual evidence from a background corpora for life sciences. |
| Approach: | They propose a web-based system that lets users query a natural language statement and automatically retrieves textual evidence from a background corpora for life sciences. |
| Outcome: | EVIDENCEMINER is a web-based system that lets users query a natural language statement and automatically retrieves textual evidence from a background corpora for life sciences. |
LoFT: Enhancing Faithfulness and Diversity for Table-to-Text Generation via Logic Form Control (2023.eacl-main)
Copied to clipboard
| Challenge: | Existing models for LT2T generation focus on surface-level realizations without much logical inference. |
| Approach: | They propose a model that uses logic forms as fact verifiers and content planners to control LT2T generation. |
| Outcome: | Experimental results show that the proposed model addresses unfaithfulness and diversity issues simultaneously. |
Learning with Less: Knowledge Distillation from Large Language Models via Unlabeled Data (2025.findings-naacl)
Copied to clipboard
Juanhui Li, Sreyashi Nag, Hui Liu, Xianfeng Tang, Sheikh Muhammad Sarwar, Limeng Cui, Hansu Gu, Suhang Wang, Qi He, Jiliang Tang
| Challenge: | Large Language Models (LLMs) have demonstrated superior language understanding abilities in many real-world NLP applications. |
| Approach: | They propose a learning-based sample selection method that incorporates signals from both teacher and student to enhance model performance. |
| Outcome: | The proposed method improves model performance across datasets with higher data efficiency. |
FinMRAGBench: A Realistic and Complex Benchmark for Multi-Modal RAG in Financial Document Analysis (2026.findings-acl)
Copied to clipboard
Shouqing Yang, Qi Zhang, Yuhang Yang, Ruikang Xu, Yuwei Hou, Zhulin Jia, Lirong Gao, Haobo Wang, Jinglei Chen, Jiexiang Wang, Sheng Guo, Bo Zheng, Gang Chen
| Challenge: | Existing benchmarks for realistic financial analysis fail to capture realistic financial situations involving cross-document retrieval, multi-page evidence integration, and diverse analytical tasks. |
| Approach: | They propose a multi-modal financial RAG benchmark that evaluates large language models in realistic financial analysis settings. |
| Outcome: | The proposed framework achieves the strongest overall performance across all models. |
WebCPM: Interactive Web Search for Chinese Long-form Question Answering (2023.acl-long)
Copied to clipboard
Yujia Qin, Zihan Cai, Dian Jin, Lan Yan, Shihao Liang, Kunlun Zhu, Yankai Lin, Xu Han, Ning Ding, Huadong Wang, Ruobing Xie, Fanchao Qi, Zhiyuan Liu, Maosong Sun, Jie Zhou
| Challenge: | Long-form question answering requires two procedures: information retrieval and information synthesis. |
| Approach: | They propose a Chinese long-form question answering dataset called WebCPM . the dataset is based on a web search interface that engages with a search engine in real time . |
| Outcome: | The proposed dataset generates answers that are no worse than human-written ones . the dataset is the first Chinese LFQA dataset . |
MPII: Multi-Level Mutual Promotion for Inference and Interpretation (2022.acl-long)
Copied to clipboard
| Challenge: | Existing methods for providing interpretations provide human-unfriendly interpretations, resulting in sub-optimal performance. |
| Approach: | They propose a multi-level Mutual Promotion mechanism for self-evolved inference and sentence-level interpretation that integrates inference with interpretation in an autoregressive manner. |
| Outcome: | The proposed approach outperforms baseline models on NLI and CQA tasks for both inference performance and interpretation quality. |
Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding (2024.emnlp-main)
Copied to clipboard
Chong Zhang, Yi Tu, Yixi Zhao, Chenshu Yuan, Huan Chen, Yue Zhang, Mingxu Chai, Ya Guo, Huijia Zhu, Qi Zhang, Tao Gui
| Challenge: | Existing models of layout reading order do not convey the complete reading order information in the layout. |
| Approach: | They propose to model layout reading order as ordering relations over layout elements . they propose a reading-order-relation-enhancing pipeline to improve model performance . |
| Outcome: | The proposed model outperforms existing models on a visual-rich document dataset and on eight cross-domain VrD-IE/QA tasks without targeted optimization. |
Defensive Prompt Patch: A Robust and Generalizable Defense of Large Language Models against Jailbreak Attacks (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have showcased their ability to understand and generate text akin to human interaction. |
| Approach: | They propose a prompt-based defense mechanism specifically designed to protect LLMs against jailbreak attacks by introducing jailbreak prompts into malicious queries. |
| Outcome: | Empirical results show that the proposed defense outperforms existing defense strategies in balancing safety and utility while maintaining high utility. |
Dynamic Multi-granularity Attribution Network for Aspect-based Sentiment Analysis (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for predicting sentiment polarity of aspects are susceptible to interference caused by irrelevant contexts and lack sentiment knowledge at a data-specific level. |
| Approach: | They propose a novel Aspect-based sentiment analysis method that leverages attention scores to model the relationships between aspects and contexts. |
| Outcome: | The proposed method is able to predict sentiments from a set of five benchmark datasets. |
SUA: Stealthy Multimodal Large Language Model Unlearning Attack (2025.emnlp-main)
Copied to clipboard
| Challenge: | Multimodal Large Language Models (MLLMs) trained on massive data may memorize sensitive personal information and photos, posing privacy and copyright concerns. |
| Approach: | They propose a framework that learns a universal noise pattern to recover unlearned information from MLLMs. |
| Outcome: | The proposed framework learns a universal noise pattern and can reveal unlearned content when applied to images. |
CoTKR: Chain-of-Thought Enhanced Knowledge Rewriting for Complex Knowledge Graph Question Answering (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing knowledge rewriting methods may include irrelevant information, omit crucial details, or fail to align with the question’s semantics. |
| Approach: | They propose a new rewriting method CoTKR for generating reasoning traces and corresponding knowledge in an interleaved manner, thereby mitigating the limitations of single-step knowledge rewrite. |
| Outcome: | The proposed method mitigates the limitations of single-step knowledge rewriting and bridges the preference gap between the knowledge reactor and the question answering (QA) model. |
Towards Long Context Hallucination Detection (2025.findings-naacl)
Copied to clipboard
Siyi Liu, Kishaloy Halder, Zheng Qi, Wei Xiao, Nikolaos Pappas, Phu Mon Htut, Neha Anna John, Yassine Benajiba, Dan Roth
| Challenge: | Large language models are prone to contextual hallucination, generating information that is either unsubstantiated or contradictory to the given context. |
| Approach: | They propose a dataset specifically designed for long-context hallucination detection. |
| Outcome: | The proposed architecture outperforms existing models while providing faster inference. |
MM-Doc-R1: Training Agents for Long Document Visual Question Answering through Multi-turn Reinforcement Learning (2026.findings-acl)
Copied to clipboard
Jiahang Lin, Kai Hu, Binghai Wang, Yuhao Zhou, Zhiheng Xi, Honglin Guo, Shichun Liu, Junzhe Wang, Shihan Dou, Enyu Zhou, Hang Yan, Zhenhua Han, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing work on long document visual question answering is based on Retrieval-Augmented Generation (RAG) where textual or visual content is encoded into embeddings and relevance is determined by similarity scores with respect to the original query. |
| Approach: | They propose a framework that employs an agentic, vision-aware workflow to address long document visual question answering through iterative information discovery and synthesis. |
| Outcome: | The proposed framework outperforms existing RL systems by 10.4% on the MMLongbench-Doc benchmark and demonstrates superior training performance over GRPO. |
Self-Improving for Zero-Shot Named Entity Recognition with Large Language Models (2024.naacl-short)
Copied to clipboard
| Challenge: | Existing studies exploring the performance of large language models on named entity recognition tasks have focused on training task-specific LLMs for NER. |
| Approach: | They propose a training-free self-improving framework that utilizes an unlabeled corpus to stimulate the self-learning ability of LLMs. |
| Outcome: | The proposed framework improves performance on the named entity recognition task by using an unlabeled corpus. |
Enhancing Cross-lingual Natural Language Inference by Prompt-learning from Cross-lingual Templates (2022.acl-long)
Copied to clipboard
| Challenge: | Existing methods for enhancing pre-trained cross-lingual language models with additional data are rare in practice, especially for low-resource languages. |
| Approach: | They propose a prompt-learning framework for enhancing cross-lingual natural language inference by constructing cloze-style questions through cross-linguistic templates. |
| Outcome: | The proposed framework significantly outperforms existing models under cross-lingual transfer settings. |
SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers (2025.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have impressive capabilities across various fields, but their widespread use is facing a severe and realistic challenge, which is their high demand for GPU memory. |
| Approach: | They propose a KV cache reduction method which balances both shallow and deep layers by using an attention weight based eviction method and a codebook based replacement approach. |
| Outcome: | The proposed method reduces the KV cache for shallower layers while preserving similar or even better model performance. |
Pointwise Mutual Information as a Performance Gauge for Retrieval-Augmented Generation (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing methods to improve language models' performance do not exploit this phenomenon . |
| Approach: | They propose to use contextual information to select and construct prompts that improve model performance. |
| Outcome: | The proposed methods show that the mutual information between a context and a question is an effective gauge for language model performance. |
Aligning Large Language Models to Follow Instructions and Hallucinate Less via Effective Data Filtering (2025.acl-long)
Copied to clipboard
Shuzheng Si, Haozhe Zhao, Gang Chen, Cheng Gao, Yuzhuo Bai, Zhitong Wang, Kaikai An, Kangyang Luo, Chen Qian, Fanchao Qi, Baobao Chang, Maosong Sun
| Challenge: | Existing studies show that training LLMs on data containing unfamiliar knowledge during instruction tuning can encourage hallucinations. |
| Approach: | They propose a framework that measures how familiar the LLM is with instruction data and introduce an expert-aligned reward model to ensure the quality of selected samples. |
| Outcome: | The proposed framework reduces hallucinations while maintaining a competitive ability to follow instructions. |
Diversify Question Generation with Retrieval-Augmented Style Transfer (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing question generation systems focus on the internal knowledge within the textual passage or the semantic word space for diverse content planning. Existing solutions focus on relying on the knowledge of the text and the semantic words, but have not considered the potential of external knowledge for expression diversity. |
| Approach: | They propose a framework for Retrieval-Augmented Style Transfer that utilizes the style of diverse templates for question generation. |
| Outcome: | The proposed framework outperforms baselines on diversity while being comparable in terms of consistency scores. |
ResLoRA: Identity Residual Mapping in Low-Rank Adaption (2024.findings-acl)
Copied to clipboard
Shuhua Shi, Shaohan Huang, Minghui Song, Zhoujun Li, Zihan Zhang, Haizhen Huang, Furu Wei, Weiwei Deng, Feng Sun, Qi Zhang
| Challenge: | Low-rank adaptation (LoRA) is one of the most popular parameter-efficient fine-tuning methods. |
| Approach: | They propose a low-rank adaptation method that adds residual paths during training and merges them together during inference to achieve better results. |
| Outcome: | The proposed method achieves 2.5x faster convergence speed and improves performance by 14.3% on NLG, NLU, and text-to-image tasks. |
Semantic-Unit-Based Dilated Convolution for Multi-Label Text Classification (D18-1)
Copied to clipboard
| Challenge: | a novel model for multi-label text classification is proposed for the task of assigning multiple labels for a given text. |
| Approach: | They propose a novel model for multi-label text classification based on sequence-to-sequence learning and a hybrid attention mechanism that extracts both the word-level and the semantic unit. |
| Outcome: | The proposed model is competitive to the baseline models and more robust to classifying low-frequency labels. |
LLMEval-Med: A Real-world Clinical Benchmark for Medical LLMs with Physician Validation (2025.findings-emnlp)
Copied to clipboard
Ming Zhang, Yujiong Shen, Zelin Li, Huayu Sha, Binze Hu, Yuhui Wang, Chenhao Huang, Shichun Liu, Jingqi Tong, Changhao Jiang, Mingxu Chai, Zhiheng Xi, Shihan Dou, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Current medical benchmarks have limitations in question design, data sources and evaluation methods. |
| Approach: | They propose a new benchmark covering five core medical areas . it includes 2,996 questions created from real-world electronic health records . |
| Outcome: | The proposed model covers five core medical areas and includes 2,996 questions created from real-world electronic health records and expert-designed clinical scenarios. |
TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use (2025.findings-emnlp)
Copied to clipboard
Junjie Ye, Yilong Wu, Sixian Li, Yuming Yang, Zhiheng Xi, Tao Gui, Qi Zhang, Xuanjing Huang, Peng Wang, Zhongchao Shi, Jianping Fan, Zhengyin Du
| Challenge: | a new approach to training large language models (LLMs) overlooks task-specific characteristics in tool use, leading to performance bottlenecks. |
| Approach: | They propose a task-feature-based framework that mitigates the effects of suboptimal training data . they use a dataset to train large-scale LLMs and a reward mechanism tailored to error categories . |
| Outcome: | The proposed framework matches or surpasses open- and closed-source LLMs in tool-use performance using only 1,217 training data points. |
LCAN: A Label-Aware Contrastive Attention Network for Multi-Intent Recognition and Slot Filling in Task-Oriented Dialogue Systems (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Multi-intent utterances processing remains a persistent challenge due to intricate intent-slot dependencies and semantic ambiguities. |
| Approach: | They propose a label-aware contrastive attention network (LCAN) that integrates label-based attention and contrastive learning strategies to improve semantic understanding and generalization in multi-intent scenarios. |
| Outcome: | The proposed model improves intent recognition and slot filling performance in multi-intent dialogue systems. |
MCP-Guard: A Multi-Stage Defense-in-Depth Framework for Securing Model Context Protocol in Agentic AI (2026.findings-acl)
Copied to clipboard
Wenpeng Xing, Zhonghao Qi, Yupeng Qin, Yilin Li, Caini Chang, Jiahui Yu, Changting Lin, Zhenzhen Xie, Meng Han
| Challenge: | Large Language Models (LLMs) are vulnerable to jailbreak, authors say . authors propose a robust, layered defense architecture designed for LLM–tool interactions . |
| Approach: | They propose a robust, layered defense architecture designed for LLM–tool interactions . they propose XCP-Guard, which employs a three-stage detection pipeline . |
| Outcome: | The proposed model achieves 96.01% accuracy in identifying adversarial prompts . the model is based on a three-stage detection pipeline that balances efficiency with accuracy . |
Can LLMs Understand Unvoiced Speech? Exploring EMG-to-Text Conversion with LLMs (2025.acl-short)
Copied to clipboard
| Challenge: | Unvoiced electromyography (EMG) is an effective communication tool for individuals unable to produce vocal speech. |
| Approach: | They propose an EMG adaptor module that maps EMG features to an LLM's input space and achieves an average word error rate of 0.49 on a closed-vocabulary unvoiced EMG-to-text task. |
| Outcome: | The proposed module achieves an average word error rate of 0.49 on a closed-vocabulary unvoiced EMG-to-text task. |
From Query to Logic: Ontology-Driven Multi-Hop Reasoning in LLMs (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) exhibit limitations in complex multi-hop question answering tasks that necessitate non-linear, structured reasoning. |
| Approach: | They propose an ontology-driven reasoning and chain framework that combines LLMs’ generative capabilities with the structural benefits of knowledge graphs. |
| Outcome: | Extensive experiments across a diverse set of models and standard MQA benchmarks demonstrate that the proposed framework achieves competitive performance while producing more interpretable reasoning chains. |
Zero-shot Faithfulness Evaluation for Text Summarization with Foundation Language Model (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing work evaluates faithfulness using models trained on related tasks or in-domain synthetic data. |
| Approach: | They propose to do zero-shot faithfulness evaluation with a foundation language model. |
| Outcome: | The proposed model outperforms ChatGPT on faithfulness and inconsistency detection with 24x fewer parameters and is competitive with existing models. |
MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation (2025.emnlp-main)
Copied to clipboard
Weihao Xuan, Rui Yang, Heli Qi, Qingcheng Zeng, Yunze Xiao, Aosong Feng, Dairui Liu, Yun Xing, Junjue Wang, Fan Gao, Jinghui Lu, Yuang Jiang, Huitao Li, Xin Li, Kunyu Yu, Ruihai Dong, Shangding Gu, Yuekang Li, Xiaofei Xie, Felix Juefei-Xu, Foutse Khomh, Osamu Yoshie, Qingyu Chen, Douglas Teodoro, Nan Liu, Randy Goebel, Lei Ma, Edison Marrese-Taylor, Shijian Lu, Yusuke Iwasawa, Yutaka Matsuo, Irene Li
| Challenge: | Existing large language model evaluation benchmarks focus on English, while current multilingual tasks lack parallel questions that specifically assess cross-lingual reasoning abilities. |
| Approach: | They propose a comprehensive benchmark covering 29 languages, built on an English benchmark. |
| Outcome: | The MMLU-ProX is a comprehensive benchmark covering 29 languages, built on an English benchmark. |
PTUM: Pre-training User Model from Unlabeled User Behaviors via Self-supervision (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for user modeling cannot exploit useful information in unlabeled data . Existing models only model task-specific user information and do not exploit universal user information encoded in user behaviors. |
| Approach: | They propose to pre-train user models from large-scale unlabeled user behavior data. |
| Outcome: | The proposed method can model relatedness between historical and future behaviors on two real-world datasets. |
When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errors (2026.acl-long)
Copied to clipboard
Yuqing Yang, Qi Zhu, Zhen Han, Boran Han, Zhengyuan Shen, Shuai Wang, Vassilis N. Ioannidis, Huzefa Rangwala
| Challenge: | Large language models (LLMs) perform well on table tasks, but they still make data referencing errors (DREs) prior studies have only offered limited, small-scale analyses. |
| Approach: | They propose inference-time strategies and lightweight critics to mitigate data referencing errors. |
| Outcome: | The proposed model achieves an average F1 score of 78.2% in detecting both in-distribution and out-of-difference DREs and assists inference for larger models. |
GraphQ IR: Unifying the Semantic Parsing of Graph Query Languages with One Intermediate Representation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to neural semantic parsing are limited by the semantic gap between natural and formal languages. |
| Approach: | They propose a unified intermediate representation for graph query languages, named GraphQ IR, which has a natural-language-like expression that bridges the semantic gap and formally defined syntax that maintains the graph structure. |
| Outcome: | The proposed representation can convert user queries into graphQ IR, which can later be losslessly compiled into various downstream graph query languages. |
Parameter-Aware Contrastive Knowledge Editing: Tracing and Rectifying based on Critical Transmission Paths (2025.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) encode vast amounts of knowledge in their parameters, but the acquired knowledge can be incorrect or outdated over time, necessitating rectification after pre-training. |
| Approach: | They propose a method that captures key information flows that influence model predictions . they propose 'critical transmission paths' to improve model editing . |
| Outcome: | The proposed method improves on two prominent datasets and three widely used LLMs. |
Metric-guided Distillation: Distilling Knowledge from the Metric to Ranker and Retriever for Generative Commonsense Reasoning (2022.emnlp-main)
Copied to clipboard
Xingwei He, Yeyun Gong, A-Long Jin, Weizhen Qi, Hang Zhang, Jian Jiao, Bartuer Zhou, Biao Cheng, Sm Yiu, Nan Duan
| Challenge: | Existing work on commonsense generation requires models to have relational reasoning and compositional generalization capabilities. |
| Approach: | They propose a metric distillation rule to distill knowledge from a standard metric to a ranker and transfer it to re-ranking a retriever. |
| Outcome: | The proposed method surpasses the previous SOTA. |
Augmented Adversarial Trigger Learning (2025.findings-naacl)
Copied to clipboard
| Challenge: | Gradient optimization-based adversarial attack methods can generate jailbreak prompts or leak system prompts. |
| Approach: | They propose an algorithm that enhances negative log-likelihood loss and augments it with auxiliary loss. |
| Outcome: | The proposed approach outperforms current state-of-the-art techniques in nearly 100% of attacks while requiring 80% fewer queries. |
TRAC: Teacher-Guided Token Reward with Adaptive Calibration for Robust Policy Optimization (2026.acl-long)
Copied to clipboard
| Challenge: | Current reward models for reinforcement learning (RL) rely on outcome rewards that propagate a single scalar value across all tokens based on final correctness. |
| Approach: | They propose a framework that derives dense token-level supervision from LLMs . they use a multi-granularity calibration mechanism to modulate teacher influence . |
| Outcome: | The proposed framework evaluates teacher reliability across problem-level expertise, trajectory-level discrimination, and token-level confidence. |
XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generation (2020.emnlp-main)
Copied to clipboard
Yaobo Liang, Nan Duan, Yeyun Gong, Ning Wu, Fenfei Guo, Weizhen Qi, Ming Gong, Linjun Shou, Daxin Jiang, Guihong Cao, Xiaodong Fan, Ruofei Zhang, Rahul Agrawal, Edward Cui, Sining Wei, Taroon Bharti, Ying Qiao, Jiun-Hung Chen, Winnie Wu, Shuguang Liu, Fan Yang, Daniel Campos, Rangan Majumder, Ming Zhou
| Challenge: | XGLUE provides a benchmark dataset to train large-scale cross-lingual pre-trained models . XCLUE provides 11 diversified tasks that cover both understanding and generation scenarios . |
| Approach: | They introduce a new benchmark dataset to train large-scale cross-lingual pre-trained models using multilingual and bilingual corpora. |
| Outcome: | The proposed dataset is labeled in English and includes only natural language understanding tasks. |
Language Agnostic Multilingual Information Retrieval with Contrastive Learning (2023.findings-acl)
Copied to clipboard
| Challenge: | Annotated training data is costly to obtain in many languages . |
| Approach: | They propose a semantic contrastive loss to align parallel sentences that share the same semantics in different languages and a language contrastive gain to leverage parallel sentence pairs to remove language-specific information from non-parallel corpora. |
| Outcome: | The proposed model improves retrieval performance while requiring less computational effort. |
SimRPD: Optimizing Recruitment Proactive Dialogue Agents through Simulator-Based Data Evaluation and Selection (2026.acl-industry)
Copied to clipboard
Zhiyong Cao, Dunqiang Liu, Qi Dai, Haojun Xu, Huai Yuen Khor, Hao Wang, Huan He, Yafei Liu, Ke Ma, Ruqian Shi, Sicheng Zhou, Sijia Yao
| Challenge: | High-quality data in training proactive dialogue agents is scarce, despite fine-tuning and reinforcement learning . a recent study has shown that the effectiveness of supervised fine-touring is limited by the lack of high-quality, domain-specific training data. |
| Approach: | They propose a framework for training recruitment proactive dialogue agents using a high-fidelity user simulator and a multi-dimensional evaluation framework based on Chain-of-Intention. |
| Outcome: | The proposed framework outperforms existing simulator-based data selection strategies in a real-world recruitment scenario. |
Interventional Rationalization (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for rationalization use spurious correlations in data to compose rationales and make predictions. |
| Approach: | They propose a method to discover the causal rationales by using a structural causal model. |
| Outcome: | The proposed method is based on the causal theory and validates on three real-world datasets. |
XMoE: Sparse Models with Fine-grained and Adaptive Expert Selection (2024.findings-acl)
Copied to clipboard
| Challenge: | XMoE leverages small experts and a threshold-based router to selectively engage only essential parameters. |
| Approach: | They propose a novel MoE that leverages small experts to selectively engage only essential parameters. |
| Outcome: | The proposed model can reduce computation load at MoE layers by over 50% without sacrificing performance. |
ToolEyes: Fine-Grained Evaluation for Tool Learning Capabilities of Large Language Models in Real-world Scenarios (2025.coling-main)
Copied to clipboard
Junjie Ye, Guanyu Li, SongYang Gao, Caishuang Huang, Yilong Wu, Sixian Li, Xiaoran Fan, Shihan Dou, Tao Ji, Qi Zhang, Tao Gui, Xuanjing Huang
| Challenge: | Existing evaluations of tool learning focus on validation of tools for large language models with expected outcomes, but this focus ignores the complex capabilities required for LLMs to effectively use tools. |
| Approach: | They propose a fine-grained system for evaluation of large language models’ tool learning capabilities in authentic scenarios. |
| Outcome: | The proposed system examines seven real-world scenarios, analyzing five dimensions crucial to LLMs in tool learning: format alignment, intent comprehension, behavior planning, tool selection, and answer organization. |
TIGER: Text-Informed Generalized Enzyme-Reaction Retrieval (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to enzyme–reaction retrieval suffer from poor generalization across tasks and distributions . TIGER is a text-informed generalized enzyme-reaction retrieval framework that bridges enzymes and biochemical reactions. |
| Approach: | They propose a text-informed generalized enzyme-reaction retrieval framework that leverages protein-to-text generation models to distill textual knowledge from enzyme sequences. |
| Outcome: | The proposed framework outperforms state-of-the-art methods in enzyme–reaction retrieval tasks and distributions. |
Red Teaming Visual Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | VLMs (Vision-Language Models) can be induced to generate harmful or inaccurate content through specific test cases. |
| Approach: | They propose a red teaming dataset which encompasses 12 subtasks under 4 primary aspects (faithfulness, privacy, safety, fairness) this dataset is the first to benchmark current VLMs in terms of these 4 aspects . |
| Outcome: | The proposed dataset shows that 10 open-source VLMs struggle with red teaming in different degrees and have up to 31% performance gap with GPT-4V. |
RAG-QA Arena: Evaluating Domain Robustness for Long-form Retrieval Augmented Question Answering (2024.emnlp-main)
Copied to clipboard
Rujun Han, Yuhao Zhang, Peng Qi, Yumo Xu, Jenyuan Wang, Lan Liu, William Yang Wang, Bonan Min, Vittorio Castelli
| Challenge: | Existing datasets for question answering based on retrieval augmented generation (RAG-QA) are either constructed using a single source corpus or consist of short extractive answers, which fall short of evaluating large language model (LLM) based RAG-QA systems on cross-domain generalization. |
| Approach: | They propose a dataset that integrates short extractive answers from multiple documents into a single coherent narrative. |
| Outcome: | The proposed dataset integrates short extractive answers from multiple documents into a single coherent narrative, covering 26K queries and large corpora across seven different domains. |
Semantic Token Clustering for Efficient Uncertainty Quantification in Large Language Models (2026.eacl-short)
Copied to clipboard
| Challenge: | Large language models have limited truthfulness and tendency toward overconfidence constrain reliability in factual tasks. |
| Approach: | They propose an efficient method that leverages semantic information encoded in LLMs to quantify uncertainty. |
| Outcome: | The proposed method achieves comparable performance to baselines while significantly reducing computational overhead. |
SUT: Active Defects Probing for Transcompiler Models (2023.emnlp-main)
Copied to clipboard
Mengnan Qi, Yufan Huang, Maoquan Wang, Yongqiang Yao, Zihan Liu, Bin Gu, Colin Clement, Neel Sundaresan
| Challenge: | Existing datasets are often criticized for their lack of granularity, which can mask deficiencies in basic syntactic elements that humans care about. |
| Approach: | They propose a new program translation metrics that address basic syntax errors . they propose BLUE, CodeBLUE and computation accuracy metrics which address these errors based on a highly interpretable evaluation harness. |
| Outcome: | The proposed model passes the unit tests with a 26.15% pass rate compared to previous models . |
Fin-STAR: Structure-as-Semantics to Resolve Implicitness in Financial Retrieval (2026.findings-acl)
Copied to clipboard
Yu Zou, Yan Chen, Lida He, Qi Zhou, Xiaorui Zhou, Aixi Zhong, Yi Wang, Wei Li, Qingyu Wang, Jiatao Li, Wei Gong, Jialei Zeng, Jingmei Zhao, Ke Jiang, Qing Li
| Challenge: | Existing Retrieval-Augmented Generation systems treat structure as a physical navigational skeleton rather than intrinsic semantic knowledge. |
| Approach: | They propose a framework that redefining hierarchy as intrinsic semantics and uses snippets to enrich hierarchical lineage. |
| Outcome: | The proposed framework outperforms state-of-the-art hierarchical and graph-based benchmarks on FinTierQA Gold. |
Towards Harmonized Uncertainty Estimation for Large Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated exceptional capabilities in handling a wide range of downstream tasks. |
| Approach: | They propose a method that employs a lightweight model trained on data aligned with the target LLM’s performance to adjust uncertainty scores. |
| Outcome: | The proposed method achieves improvements of up to 60% over existing methods. |
Digging out Discrimination Information from Generated Samples for Robust Visual Question Answering (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to solve this problem rely on additional annotations and generate negative samples . |
| Approach: | They propose a method to Dig out Discrimination information from Generated samples to address these limitations. |
| Outcome: | The proposed method improves on the visual question-answering datasets. |
Few-Shot Complex Knowledge Base Question Answering via Meta Reinforcement Learning (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to complex question-answering (CQA) exhibit uneven performance when questions have different types, harboring inherently different characteristics, e.g., difficulty level. |
| Approach: | They propose a meta-reinforcement learning approach to program induction in CQA to tackle the potential distributional bias in questions. |
| Outcome: | The proposed method achieves state-of-the-art performance on the CQA dataset while using only five trial trajectories for the top-5 retrieved questions in each support set. |
CENTAUR: Bridging the Impossible Trinity of Privacy, Efficiency, and Performance in Privacy-Preserving Transformer Inference (2025.acl-long)
Copied to clipboard
Jinglong Luo, Guanzhong Chen, Yehong Zhang, Shiyu Liu, Hui Wang, Yue Yu, Xun Zhou, Yuan Qi, Zenglin Xu
| Challenge: | Existing privacy-preserving Transformer Inference frameworks suffer from high computational overhead and performance losses. |
| Approach: | They propose a framework that integrates random permutations and SMPC to address the "impossible trinity" CENTAUR resists diverse data reconstruction attacks and boosts inference speed by 5.030.4 times . |
| Outcome: | CENTAUR achieves an unprecedented balance between privacy, efficiency, and performance. |
The Impact of Language Mixing on Bilingual LLM Reasoning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies show multilingual speakers intentionally switch languages during reasoning . enforcing monolingual decoding reduces accuracy by 5.6 percentage points . |
| Approach: | They find that multilingual speakers intentionally switch languages during reasoning . enforcing monolingual decoding reduces accuracy by 5.6 percentage points . authors suggest that language mixing is not merely a byproduct of multilingual training . |
| Outcome: | The proposed model can be used to predict whether a language switch would benefit or harm reasoning. |
Inverse-Q*: Token Level Reinforcement Learning for Aligning Large Language Models Without Preference Data (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Reinforcement Learning from Human Feedback (RLHF) relies on complex methodologies like Proximal Policy Optimization (PPO) that require extensive hyper-parameter tuning and pose challenges in sample efficiency and stability. |
| Approach: | They propose an innovative framework that leverages direct preference optimization techniques but extends them by estimating the conditionally optimal policy directly from the model’s responses. |
| Outcome: | The proposed framework matches and exceeds the effectiveness of Proximal Policy Optimization (PPO) in terms of convergence speed and alignment of model responses with human preferences. |
EcomScriptBench: A Multi-task Benchmark for E-commerce Script Planning via Step-wise Intention-Driven Product Association (2025.acl-long)
Copied to clipboard
Weiqi Wang, Limeng Cui, Xin Liu, Sreyashi Nag, Wenju Xu, Chen Luo, Sheikh Muhammad Sarwar, Yang Li, Hansu Gu, Hui Liu, Changlong Yu, Jiaxin Bai, Yifan Gao, Haiyang Zhang, Qi He, Shuiwang Ji, Yangqiu Song
| Challenge: | Goal-oriented script planning is used by humans to plan for typical activities . however, this capability remains underexplored due to several challenges . |
| Approach: | They propose a framework that enables product-enriched scripts by associating products with each step based on the semantic similarity between the actions and their purchase intentions. |
| Outcome: | The proposed framework can generate product-enriched scripts from 2.4 million scripts . human annotations are conducted to provide gold labels for a sampled subset . |
NaturalCodeBench: Examining Coding Performance Mismatch on HumanEval and Natural User Queries (2024.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) generate code for productive activities, but current benchmarks for code synthesis are oriented towards introductory tasks on algorithm and data science. |
| Approach: | They propose a code benchmark to mirror the complexity and variety of scenarios in real-world coding tasks. |
| Outcome: | The proposed benchmark improves on 39 large language models with close HumanEval scores and achieves an efficiency increase of more than 4 times. |
RIVAL: Reinforcement Learning with Iterative and Adversarial Optimization for Machine Translation (2025.findings-emnlp)
Copied to clipboard
Tianjiao Li, Mengran Yu, Chenyu Shi, Yanjun Zhao, Xiaojing Liu, Qi Zhang, Xuanjing Huang, Qiang Zhang, Jiayin Wang
| Challenge: | Using reinforcement learning from human feedback, large language models perform poorly when applied to colloquial subtitle translation tasks. |
| Approach: | They propose an adversarial training framework that iteratively updates the offline reward model and the online LLM to improve training outcomes. |
| Outcome: | The proposed training framework significantly improves upon translation baselines. |
SciDMT: A Large-Scale Corpus for Detecting Scientific Mentions (2024.lrec-main)
Copied to clipboard
| Challenge: | SciDMT is an enhanced and expanded corpus for scientific mention detection . existing corpora are limited by their small volume and entity linking capabilities . |
| Approach: | They propose to enhance SciDMT, an annotated scientific corpus for scientific mention detection. |
| Outcome: | The proposed corpus is the largest for scientific entity mention detection . it is based on deep learning architectures like SciBERT and GPT-3.5 . |
Think and Recall: Layer-Level Prompting for Lifelong Model Editing (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for lifelong model editing suffer from limitations in usability, such as requiring additional training corpora or lacking support for reversible and detachable edits. |
| Approach: | They propose a plug-and-play method for knowledge retrieval and storage, i.e., Layer-Level Prompting, which enables seamless and efficient lifelong model editing. |
| Outcome: | The proposed method outperforms existing methods on question answering and hallucination benchmarks across different LLMs. |
Syntactically Robust Training on Partially-Observed Data for Open Information Extraction (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Open Information Extraction models have shown promising results with sufficient supervision, but the syntactic distribution of training data is partially observable in comparison to the real world. |
| Approach: | They propose a syntactically robust training framework that enables models to be trained on a multi-paraphrase distribution based on diverse paraphrase generation. |
| Outcome: | The proposed framework can be applied to other syntactic partial observable domains. |
Knowledge Conflicts for LLMs: A Survey (2024.emnlp-main)
Copied to clipboard
| Challenge: | This survey examines knowledge conflicts for large language models (LLMs) this survey aims to shed light on strategies for improving the robustness of LLMs . |
| Approach: | They focus on three categories of knowledge conflicts: context-memory, inter-context, and intra-membry conflict. |
| Outcome: | The findings highlight the challenges faced by large language models when blending contextual and parametric knowledge. |
Sketching as a Tool for Understanding and Accelerating Self-attention for Long Sequences (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing models for long sequences are not efficient due to the quadratic space and time complexity of the self-attention modules. |
| Approach: | They propose to reduce the quadratic complexity to linear (modulo logarithmic factors) by low-dimensional projection and row selection. |
| Outcome: | The proposed methods outperform transformer-based models with smaller time/space footprint on the Long Range Arena benchmark. |
Keep it Consistent: Topic-Aware Storytelling from an Image Stream via Iterative Multi-agent Communication (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods for visual storytelling construct text description independently for each image and roughly concatenate them as a story, which leads to the problem of generating semantically incoherent content. |
| Approach: | They propose a topic description task to detect the global semantic context of an image stream and a story is then constructed with the guidance of the topic description. |
| Outcome: | The proposed framework can generate stories with higher quality compared to state-of-the-art methods on a VIST dataset. |
VisFinEval: A Scenario-Driven Chinese Multimodal Benchmark for Holistic Financial Understanding (2025.emnlp-main)
Copied to clipboard
Zhaowei Liu, Xin Guo, Haotian Xia, Lingfeng Zeng, Fangqi Lou, Jinyi Niu, Mengping Li, Qi Qi, Jiahuan Li, Wei Zhang, Yinglong Wang, Weige Cai, Weining Shen, Liwen Zhang
| Challenge: | Existing benchmarks focus on text comprehension, but MLLMs lack the ability to integrate visual data over financial visuals. |
| Approach: | They evaluate 21 state-of-the-art multimodal large language models in a zero-shot setting . they use an annotated question–answer pair from eight common financial image modalities . |
| Outcome: | The new benchmark outperforms existing models but trailed financial experts by 14 percentage points. |
DMDD: A Large-Scale Dataset for Dataset Mentions Detection (2023.tacl-1)
Copied to clipboard
| Challenge: | Existing corpora for dataset mention detection are limited in size and naming diversity. |
| Approach: | They propose a dataset for dataset mention detection that is the largest publicly available corpus for this task. |
| Outcome: | The proposed dataset is the largest publicly available corpus for dataset mention detection . it identifies open problems in dataset mention recognition and linking . |
OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows (2026.acl-long)
Copied to clipboard
Qiushi Sun, Mukai Li, Zhoumianze Liu, Zhihui Xie, Fangzhi Xu, Zhangyue Yin, Kanzhi Cheng, Zehao Li, Zichen Ding, Qi Liu, Zhiyong Wu, Zhuosheng Zhang, Ben Kao, Lingpeng Kong
| Challenge: | Existing methods for detecting unsafe mobile GUI agents are underexplored. |
| Approach: | They propose a mobile agent safety detection framework that integrates a formal verifier and a VLM-based contextual judge to detect system-level violations. |
| Outcome: | The proposed framework achieves 10%–30% improvements over existing approaches across multiple metrics. |
A Survey on Proactive Defense Strategies Against Misinformation in Large Language Models (2025.findings-acl)
Copied to clipboard
Shuliang Liu, Hongyi Liu, Aiwei Liu, Duan Bingchen, Zheng Qi, Yibo Yan, He Geng, Peijie Jiang, Jia Liu, Xuming Hu
| Challenge: | Existing methods for detection of misinformation generated by large language models fail to mitigate societal risks . authors propose a paradigm shift from passive detection to anticipatory mitigation strategies . existing defenses remain reactionary in an era demanding proactive defense, authors say . |
| Approach: | They propose a three-pillar approach to prevent misinformation by fortifying integrity of training data and inference reliability by embedding self-corrective mechanisms during reasoning. |
| Outcome: | The proposed framework improves existing methods in misinformation prevention by 63% . it demonstrates that existing methods exhibit false negative rates against misinformation . |
Robust Membership Inference for Large Language Models under Adversarial Generative Corruption (2026.acl-long)
Copied to clipboard
Yuanhong Huang, Huili Wang, Xueying Bai, Jinrui Wang, Jiajun Liu, Ziqin Wang, Wanchun Ni, Shangguang Wang, Tao Qi
| Challenge: | Membership inference attacks are a promising tool for auditing training data of LLMs . existing methods rely on the assumption that LLM's assign higher confidence scores to training samples than to non-training ones. |
| Approach: | They propose a membership inference framework that can be robust against adversarial MIAs. |
| Outcome: | The proposed framework can be robust against adversarial MIA methods and AIGT detectors while maintaining the performance of baselines. |
Learning Implicit Sentiment in Aspect-based Sentiment Analysis with Supervised Contrastive Pre-Training (2021.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies have focused on identifying the sentiment polarity of aspects in product reviews. |
| Approach: | They propose to use supervised Contrastive Pre-Training to learn implicit sentiment . they propose to train large-scale sentiment-annotated corpora from in-domain language resources . |
| Outcome: | The proposed model achieves state-of-the-art performance on SemEval2014 benchmarks and comprehensively validates its effectiveness on learning implicit sentiment. |
Boosting LLM Agents with Recursive Contemplation for Effective Deception Handling (2024.findings-acl)
Copied to clipboard
Shenzhi Wang, Chang Liu, Zilong Zheng, Siyuan Qi, Shuo Chen, Qisen Yang, Andrew Zhao, Chaofei Wang, Shiji Song, Gao Huang
| Challenge: | Recent advances in large language models (LLMs) have led to significant success in using LLMs as agents. |
| Approach: | They propose a cognitive framework that incorporates first-order and second-order perspective transitions into LLMs to enhance their ability to identify and counteract deceptive information. |
| Outcome: | The proposed framework enhances LLMs’ ability to identify and counteract deceptive information without extra fine-tuning and data. |
Improving Abstractive Dialogue Summarization with Hierarchical Pretraining and Topic Segment (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for meeting summary have limited the ability to deal with long-term dependency. |
| Approach: | They propose a hierarchical transformer encoder-decoder network with multi-task pre-training to capture key sentences at word level and generate them at word-level. |
| Outcome: | The proposed model is superior to the previous methods in meeting summary datasets AMI and ICSI. |
Cross-Domain Sentiment Classification with Target Domain Specific Information (P18-1)
Copied to clipboard
| Challenge: | Existing methods for sentiment classification focus on learning domain-invariant representations . few of them pay attention to domain-specific information, which should also be informative. |
| Approach: | They propose a method to extract domain specific and invariant representations and train a classifier on each of them. |
| Outcome: | The proposed model can achieve better performance than state-of-the-art methods. |
PP-Rec: News Recommendation with Personalized User Interest and Time-aware News Popularity (2021.acl-long)
Copied to clipboard
| Challenge: | Existing personalized news recommendation methods have difficulties in making accurate recommendations to cold-start users. |
| Approach: | They propose to incorporate news popularity information to improve cold-start recommendations . they propose to use a popularity-aware user encoder to eliminate popularity bias . |
| Outcome: | The proposed method improves accuracy and diversity of personalized news recommendation on two real-world datasets. |
UniRAG: Unified Query Understanding Method for Retrieval Augmented Generation (2025.acl-long)
Copied to clipboard
| Challenge: | Existing query augmentation methods face knowledge update lag and hallucinations in large language models (LLMs) Existing methods face two key challenges: (1) separation of query augmented and encoding tasks, which hinders information sharing and introduces cumulative errors; (2) difficulty of selecting optimal augmentation strategy for different scenarios. |
| Approach: | They propose a unified framework for query understanding in RAG that integrates internal and external knowledge to enhance query augmentation and encoding tasks. |
| Outcome: | The proposed framework outperforms traditional query augmentation methods in five knowledge-intensive benchmark tasks in both closed and open domain question answering. |
SentiRec: Sentiment Diversity-aware Neural News Recommendation (2020.aacl-main)
Copied to clipboard
| Challenge: | Existing news recommendation methods rank candidate news based on relevance to users’ historical browsed news, but if browsed data is dominated by certain kinds of sentiment, the model may recommend news with the same sentiment. |
| Approach: | They propose a sentiment diversity-aware neural news recommendation approach which can recommend news with more diverse sentiment without performance sacrifices. |
| Outcome: | The proposed approach can improve the sentiment diversity in news recommendation without performance sacrifice. |
Low-Entropy Watermark Detection via Bayes’ Rule Derived Detector (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for text watermarking ignore strong evidences embedded in low-entropy tokens, causing statistical measures to falsely indicate the absence of a watermark. |
| Approach: | They propose a Bayes' Rule derived watermark Detector which exploits watermark information from every token by leveraging the posterior probability of watermark’s presence. |
| Outcome: | The proposed method achieves 50% and 70% relative improvements over baselines in code generation and math problem-solving tasks. |
Implicit Personalization in Language Models: A Systematic Study (2024.findings-emnlp)
Copied to clipboard
Zhijing Jin, Nils Heil, Jiarui Liu, Shehzaad Dhuliawala, Yahang Qi, Bernhard Schölkopf, Rada Mihalcea, Mrinmaya Sachan
| Challenge: | Existing studies have focused on the implicit personalization problem, but no unified framework exists to study it. |
| Approach: | They propose a mathematical formulation and a moral reasoning framework to study the phenomenon of Implicit Personalization (IP) they propose 'direct intervention' to estimate causal effect of mediator variable that cannot be directly intervened upon. |
| Outcome: | The proposed method estimates the causal effect of a mediator variable that cannot be directly intervened upon. |
RAPO: An Adaptive Ranking Paradigm for Bilingual Lexicon Induction (2022.emnlp-main)
Copied to clipboard
Zhoujin Tian, Chaozhuo Li, Shuo Ren, Zhiqiang Zuo, Zengxuan Wen, Xinyue Hu, Xiao Han, Haizhen Huang, Denvy Deng, Qi Zhang, Xing Xie
| Challenge: | Existing approaches focus on minimizing distances between words in aligned pairs, while suffering from low discriminative capability to distinguish the relative orders between positive and negative candidates. |
| Approach: | They propose a ranking-oriented induction model to learn personalized mapping function for each word. |
| Outcome: | The proposed model can learn personalized mapping function for each word on public datasets including rich-resource and low-resourced languages. |
EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have recently advanced the field of Automated Theorem Proving (ATP) Existing cost analyses regulate only the number of sampling passes, ignoring the substantial disparities in sampling costs. |
| Approach: | They propose to integrate two complementary methods into a unified EconRL pipeline to increase pass rates under constrained sampling passes. |
| Outcome: | The proposed method reduces token usage and sample passes while maintaining the original performance. |
MM-MATH: Advancing Multimodal Math Evaluation with Process Evaluation and Fine-grained Classification (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing benchmarks for multimodal reasoning in large multimodal models are underperforming on multimodal tasks. |
| Approach: | They propose a benchmark for multimodal reasoning in large multimodal models, MM-MATH . MM's process evaluation employs LMM-as-a-judge to automatically analyze solution steps . diagram misinterpretation is the most common error, they find . |
| Outcome: | The proposed model achieves only 31% accuracy, compared to 82% for humans. |
Grammar-Based Code Representation: Is It a Worthy Pursuit for LLMs? (2025.findings-acl)
Copied to clipboard
Qingyuan Liang, Zhao Zhang, Zeyu Sun, Zheng Lin, Qi Luo, Xiao Yueyi, Yizhou Chen, Yuqun Zhang, Haotian Zhang, Lu Zhang, Chenbin Chenbin, Yingfei Xiong
| Challenge: | Existing research demonstrates the effectiveness of grammar-based code representations in small-scale models, showing their ability to reduce syntax errors and enhance performance. |
| Approach: | They develop a series of billion-scale grammar-based code representations that incorporate grammar rules into the code generation process. |
| Outcome: | Experiments on HumanEval and MBPP show that grammar-based representations reduce syntax errors and improve performance even in billion-scale models. |
Tiny Scales, Great Challenges: The Limits of Multimodal LLMs in Scale Recognition (2026.acl-long)
Copied to clipboard
| Challenge: | Existing benchmarks focus on a single type of quantity or a specific format, lacking a comprehensive evaluation of scale recognition capabilities. |
| Approach: | They propose a visual scale recognition benchmark built using images from COCO, Open Images, and Flickr to evaluate scale recognition capabilities of multimodal large language models. |
| Outcome: | The proposed model achieves 42.60% accuracy, lower than the 97.40% of humans. |
Neural News Recommendation with Multi-Head Self-Attention (D19-1)
Copied to clipboard
| Challenge: | Precisely modeling news and users is critical for news recommendation, and capturing the contexts of words and news is important to learn news and user representations. |
| Approach: | They propose a neural news recommendation approach with multi-head self-attention to model the interactions between words and news and use multi-headed self- attention to capture relatedness between the news. |
| Outcome: | The proposed approach can learn representations from news titles by modeling the interactions between words and users and capture relatedness between the news. |
Larger-Context Tagging: When and Why Does It Work? (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing tagging systems that use sentence-level data are not well understood. |
| Approach: | They propose a larger-context approach to tagging tasks that incorporates contextual information into existing tapping systems. |
| Outcome: | The proposed aggregators improve on four tagging tasks and 13 datasets. |
MCIP: Protecting MCP Safety via Model Contextual Integrity Protocol (2025.emnlp-main)
Copied to clipboard
| Challenge: | Model Context Protocol (MCP) introduces an easy-to-use ecosystem for users and developers, but it also brings underexplored safety risks. |
| Approach: | They propose a framework that addresses the missing safety mechanisms in MCP and a taxonomy that captures diverse range of unsafe behaviors observed in MMP scenarios. |
| Outcome: | The proposed framework improves safety performance on state-of-the-art LLMs by capturing unsafe behaviors and analyzing the results. |
Efficient Sequential Decision Making with Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to retrain or finetune large language models (LLMs) for decision making suffer from computational burden of gradient updates. |
| Approach: | They propose a model selection algorithm that leverages online model selection algorithms to efficiently incorporate LLMs agents into sequential decision making. |
| Outcome: | The proposed approach outperforms both traditional decision making algorithms and vanilla LLM agents on a large-scale Amazon dataset. |
SQL-Trail: Multi-Turn Reinforcement Learning with Interleaved Feedback for Text-to-SQL (2026.acl-long)
Copied to clipboard
Harper Hua, Zhen Han, Zhengyuan Shen, Meng-Chieh Lee, Sheng Guan, Qi Zhu, Sullam Jeoung, Yueyan Chen, Yunfei Bai, Shuai Wang, Vassilis N. Ioannidis, Huzefa Rangwala
| Challenge: | Recent large language models (LLMs) have significantly improved Text-to-SQL generation, but a gap remains between AI systems and human experts on challenging benchmarks such as BIRD-Sql. |
| Approach: | They propose a multi-turn reinforcement learning agentic framework for Text-to-SQL that uses execution feedback to iteratively refine its predictions. |
| Outcome: | The proposed framework outperforms proprietary systems on 7B and 14B models by **5% on average, underscoring the effectiveness of interactive, agentic workflows for robust Text-to-SQL generation. |
RJE: A Retrieval-Judgment-Exploration Framework for Efficient Knowledge Graph Question Answering with LLMs (2025.emnlp-main)
Copied to clipboard
| Challenge: | Knowledge graph question answering (KGQA) aims to answer natural language questions using knowledge graphs. |
| Approach: | They propose a framework that retrieves refined reasoning paths and evaluates their sufficiency. |
| Outcome: | The proposed framework outperforms existing baselines while enabling small open-source LLMs to achieve competitive results without fine-tuning LLM. |
Exploring Question Guidance and Answer Calibration for Visually Grounded Video Question Answering (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for videoQA lack temporal localization labels, leading to inaccurate localization. |
| Approach: | They propose a Question-Guided and Answer-Calibrated TRansformer which guides and calibrates localization using question and option texts without localization labels. |
| Outcome: | The proposed model achieves comparable accuracy to large-scale pretrained models and leads in localization aspects. |
E-ViC: Reasoning Beyond Text via Embodied Visual Chain for Spatial Intelligence (2026.acl-long)
Copied to clipboard
Junbo Qi, Yi Zhang, Hanchu Ni, Che Liu, Zhimin Yao, Ruilin Yang, Xiancong Ren, Liangjian Wen, Wei Ge, Yuya Ieiri, Osamu Yoshie, Yong Dai, Xiaozhu Ju
| Challenge: | Existing Vision-Language Models (VLMs) lack spatial reasoning, despite text-based CoTs . e-ViC reframes spatial intelligence as a verifiable, tool-using capability, argues a new study. |
| Approach: | They propose a framework that moves reasoning beyond text into the visual domain . they ground reasoning in pixel-level interactions to enable human-like "look-and-confirm" strategies . |
| Outcome: | The proposed framework outperforms existing Vision-Language Models with an average gain of 10.1%. |
Parrot: A Training Pipeline Enhances Both Program CoT and Natural Language CoT for Reasoning (2025.emnlp-main)
Copied to clipboard
Senjie Jin, Lu Chen, Zhiheng Xi, Yuhui Wang, Sirui Song, Yuhao Zhou, Xinbo Zhang, Peng Sun, Hong Lu, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing work focuses on enabling models to generate natural language chain-of-thought rationales or leverage executable and verifiable code, such as Python. |
| Approach: | They propose a novel training pipeline that integrates sequential P-CoT and N-Co T generation and a subtask hybrid training strategy to facilitate natural language transferability. |
| Outcome: | The proposed training pipeline improves both N-CoT and P-Co T performance over the RL baseline. |
RoTBench: A Multi-Level Benchmark for Evaluating the Robustness of Large Language Models in Tool Learning (2024.emnlp-main)
Copied to clipboard
Junjie Ye, Yilong Wu, Songyang Gao, Caishuang Huang, Sixian Li, Guanyu Li, Xiaoran Fan, Qi Zhang, Tao Gui, Xuanjing Huang
| Challenge: | Current research emphasizes LLMs’ capacity to utilize tools in well-structured environments while overlooking their stability when confronted with the inevitable noise of the real world. |
| Approach: | They propose a multi-level benchmark to evaluate the robustness of large language models in tool learning by establishing five external environments with varying levels of noise. |
| Outcome: | The proposed model outperforms the GPT-4 model in tool learning in three critical phases: tool selection, parameter identification, and content filling. |
Explanation Graph Generation via Generative Pre-training over Synthetic Graphs (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing frameworks for explanation graph generation are limited due to the large number of datasets available. |
| Approach: | They propose a text-to-graph generative task to pre-train a model to bridge the text-graph gap. |
| Outcome: | The proposed framework surpasses all baseline systems with remarkable margins on ExplaGraphs and CommonsenseQA. |
CoRAG: Enhancing Hybrid Retrieval-Augmented Generation through a Cooperative Retriever Architecture (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods only retrieve related documents from local neighbors or subgraphs in the knowledge base, which often miss relevant information located further away from a global view. |
| Approach: | Hybrid-RAG combines textual documents and graph-structured relational information for RAG . existing methods only retrieve related documents from local neighbors or subgraphs in the knowledge base . |
| Outcome: | Hybrid-RAG combines textual documents and graph-structured relational information . existing methods only retrieve related documents from local neighbors or subgraphs in the knowledge base . |
Incorporating Argument-Level Interactions for Persuasion Comments Evaluation using Co-attention Model (C18-1)
Copied to clipboard
| Challenge: | Existing research explores different text features of reply comments on word level and ignores interactions between participants. |
| Approach: | They propose a co-attention mechanism based neural network to capture interactions between participants on argument level to better model dialogical argumentation. |
| Outcome: | The proposed model outperforms state-of-the-art methods on a publicly available dataset showing that it extracts interactive argument pairs from the original post and the reply. |
Zero-shot Approach to Overcome Perturbation Sensitivity of Prompts (2023.acl-long)
Copied to clipboard
| Challenge: | Recent studies have demonstrated that natural-language prompts can help to leverage the knowledge learned by pre-trained language models for the binary sentence-level sentiment classification task. |
| Approach: | They propose to use few-shot learning settings to fine-tune the sentiment classification model using manual or automatically generated prompts. |
| Outcome: | The proposed method outperforms the base prompt and the prompts generated using few-shot learning for the binary sentence-level sentiment classification task. |
Event Causality Identification via Derivative Prompt Joint Learning (2022.coling-1)
Copied to clipboard
| Challenge: | Existing methods for event causality identification lack annotated data, and they lack the ability to identify explicit and implicit causality. |
| Approach: | They propose a derivative prompt joint learning model which leverages potential causal knowledge in the pre-trained language model to tackle the data scarcity problem. |
| Outcome: | The proposed model can identify explicit and implicit causality on two benchmark datasets and it has great advantages over previous methods. |
ESF: Efficient Sensitive Fingerprinting for Black-Box Tamper Detection of Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) are increasingly utilized in diverse applications, including code generation, legal document analysis, medical diagnosis, and decision-making. |
| Approach: | They propose a fingerprinting method tailored for black-box tamper detection of large language models. |
| Outcome: | The proposed method detects tampering with a 99.2% detection rate using 5 fingerprint samples across state-of-the-art LLMs. |
Actively Supervised Clustering for Open Relation Extraction (2023.acl-long)
Copied to clipboard
| Challenge: | Existing methods for Open Relation Extraction (OpenRE) use a two-stage pipeline, which learns relation representations and assignments in the first stage, then manually labels relation for each cluster. |
| Approach: | They propose a method that performs relation learning and relation labeling simultaneously without a significant increase in human effort. |
| Outcome: | The proposed method improves existing SOTA methods by 13.8% and 10.6% on two datasets. |
Graph Counselor: Adaptive Graph Exploration via Multi-Agent Synergy to Enhance LLM Reasoning (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for enhancing LLM reliability suffer from inefficient information aggregation and rigid reasoning schemes. |
| Approach: | They propose a method that explicitly models external knowledge integration capabilities by explicitly modeling knowledge relationships. |
| Outcome: | The proposed method outperforms existing methods in multiple graph reasoning tasks. |
H-MAS: Hierarchical Multi-Agent Scheduling for Multi-Tenant LLM Serving (2026.findings-acl)
Copied to clipboard
Yuhan Liu, Cong Xu, Qi Jia, Yihua Wang, Feiyu Chen, Liang Jin, Lu Liu, Yaqian Zhao, Yuting Ding, Xiang Li
| Challenge: | Multi-tenant Model-as-a-Service (MaaS) workloads exhibit non-stationarity across multiple time scales . existing request schedulers often rely on a fixed policy that remains unchanged at runtime . |
| Approach: | They propose a hierarchical multi-agent scheduler that operates in a layered closed loop . they propose to maintain 1.2–3.0 higher Goodput than SGLang and vLLM . |
| Outcome: | Experiments show that H-MAS achieves 1.2–3.0 higher Goodput than SGLang and vLLM . it maintains more stable QoS under diverse request lengths and heterogeneous SLO targets . |
SaFER: A Robust and Efficient Framework for Fine-tuning BERT-based Classifier with Noisy Labels (2023.acl-industry)
Copied to clipboard
| Challenge: | Existing noise-handling methods could not improve performance of BERT on noisy datasets . existing methods could only improve performance on noisy data, authors say . |
| Approach: | They propose a fine-tuning framework for BERT-based text classifiers that combats label noises without access to clean data for training or validation. |
| Outcome: | The proposed framework achieves superior performance on multiple text classification benchmarks. |
Incremental Transformer: Efficient Encoder for Incremented Text Over MRC and Conversation Tasks (2025.coling-main)
Copied to clipboard
| Challenge: | Existing encoders that encode incremented inputs have to re-encode the whole text to obtain the encoding of the extended input. |
| Approach: | They propose an efficient encoder dedicated for faster encoding of incremented input . it takes only added input as input but attends to cached representations of original input a lower layer . |
| Outcome: | The proposed encoder achieves 6.2x speedup over current encoders . it takes only added input as input but attends to cached representations of original input . |
Neuro-Symbolic Query Compiler (2025.findings-acl)
Copied to clipboard
| Challenge: | Retrieval-Augmented Generation (RAG) systems are limited in their ability to process information in open-source environments. |
| Approach: | They propose a neuro-symbolic framework inspired by linguistic grammar rules and compiler design to formalize complex queries using a minimal yet sufficient Backus-Naur Form grammar. |
| Outcome: | The proposed framework is based on a backus-naur form grammar and compiler design that maintains completeness while minimizing redundancy. |
Three Stream Based Multi-level Event Contrastive Learning for Text-Video Event Extraction (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for event extraction ignore motion representations in videos and are misguided by background noise. |
| Approach: | They propose a text-video based multimodal event extraction framework that integrates video appearance features and motion representations with video appearance. |
| Outcome: | The proposed framework outperforms the state-of-the-art methods in the event extraction field. |
Lost in the Context: Insufficient and Distracted Attention to Contexts in Preference Modeling (2025.acl-long)
Copied to clipboard
Shihan Dou, Jiayi Chen, Chenhao Huang, Feng Chen, Wei Chengzhi, Huiyuan Zheng, Shichun Liu, Yan Liu, Chenxiao Liu, Chao Xin, Lin Yan, Zongzhang Zhang, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing reward models concatenate contexts and responses, but they often ignore crucial segments of the context that are important for evaluating the response quality. |
| Approach: | They propose a reward model that evaluates the response quality based on a given context and assigns a rewards reward. |
| Outcome: | The proposed framework significantly improves preference modeling by increasing attention to relevant information within the context and achieves better generalizability. |
From Grounding to Manipulation: Case Studies of Foundation Model Integration in Embodied Robotic Systems (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a new study examines the operational characteristics of different integration strategies for robotics . end-to-end vision-language-action models implicitly unify perception and planning . |
| Approach: | They propose end-to-end vision-language-action models that implicitly unify perception and planning . they also propose modular pipelines using either vision-linguistic models or MLLMs . |
| Outcome: | The proposed frameworks implicitly unify perception and planning, and modular pipelines using either vision-language models or multimodal large language models. |
Memory-efficient Temporal Moment Localization in Long Videos (2023.eacl-main)
Copied to clipboard
| Challenge: | Temporal Moment Localization is a multi-modal task that requires understanding the temporal relationships in the entire input video. |
| Approach: | They propose a stochastic sampling module that can process long videos at a constant memory footprint. |
| Outcome: | The proposed model can process videos as long as 18 minutes at a constant memory footprint and achieves faster and faster results than competing models. |
Towards a More Generalized Approach in Open Relation Extraction (2025.acl-long)
Copied to clipboard
| Challenge: | Existing OpenRE methods assume unlabeled data is a mixture of known and novel instances. |
| Approach: | They propose a generalized OpenRE setting that considers unlabeled data as a mixture of known and novel instances. |
| Outcome: | The proposed framework outperforms baselines in relation classification and clustering on three benchmark datasets. |
Logic-level Evidence Retrieval and Graph-based Verification Network for Table-based Fact Verification (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods leverage programs that contain rich logical information to enhance the verification process. |
| Approach: | They propose a table-based fact verification task as an evidence retrieval framework . they retrieve logic-level program-like evidence from the given table and a statement as supplementary evidence for the table . |
| Outcome: | The proposed method is able to retrieve logic-level program-like evidence from a table and a statement as supplementary evidence for the table. |
On the Universal Adversarial Perturbations for Efficient Data-free Adversarial Detection (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing adversarial detection methods require access to training data, which brings noteworthy concerns regarding privacy leakage and generalizability. |
| Approach: | They propose a data-agnostic adversarial detection framework which induces different responses between normal and adversarials to UAPs. |
| Outcome: | The proposed framework achieves competitive detection performance on various text classification tasks, and maintains equivalent time consumption to normal inference. |
Fine-grained Medical Vision-Language Representation Learning for Radiology Report Generation (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to learn medical vision-language representations by contrasting images with entire reports are not effective. |
| Approach: | They propose a phenotype-driven medical vision-language representation learning framework to bridge the gap between visual and textual modalities for improved text-oriented generation. |
| Outcome: | The proposed framework bridges the gap between visual and textual modalities for improved radiology report generation. |
Prompt-based Conservation Learning for Multi-hop Question Answering (2022.coling-1)
Copied to clipboard
| Challenge: | Existing multi-hop QA methods fail to answer a large fraction of sub-questions even if their parent questions are answered correctly. |
| Approach: | They propose a Prompt-based Conservation Learning framework that acquires new knowledge from multi-hop QA tasks while conserving old knowledge learned on single-hop tasks. |
| Outcome: | The proposed framework acquires new knowledge from multi-hop QA tasks while conserving old knowledge learned on single-hop tasks, mitigating forgetting. |
Adversarial and Domain-Aware BERT for Cross-Domain Sentiment Analysis (2020.acl-main)
Copied to clipboard
| Challenge: | Cross-domain sentiment classification requires large amounts of labeled data. |
| Approach: | They propose to apply a pre-training language model BERT on unsupervised domain adaptation . they propose to distill domain-specific features in a self-supervised way . |
| Outcome: | The proposed model outperforms state-of-the-art methods on Amazon dataset . it can be applied to the unsupervised domain adaptation task without domain awareness . |
A Class-Rebalancing Self-Training Framework for Distantly-Supervised Named Entity Recognition (2023.findings-acl)
Copied to clipboard
| Challenge: | Distant supervision reduces the reliance on human annotation in named entity recognition tasks. |
| Approach: | They propose a class-rebalancing self-training framework for improving distantly-supervised named entity recognition by using a flexible threshold and a hybrid pseudo label. |
| Outcome: | The proposed model achieves state-of-the-art on five flat and two nested datasets and compares with other methods on the same dataset. |
Learning to Instruct: Fine-Tuning a Task-Aware Instruction Optimizer for Black-Box LLMs (2025.findings-emnlp)
Copied to clipboard
Yunzhe Qi, Jinjin Tian, Tianci Liu, Ruirui Li, Tianxin Wei, Hui Liu, Xianfeng Tang, Monica Xiao Cheng, Jingrui He
| Challenge: | Learning to Instruct is a new paradigm for black-box LLMs with inaccessible internal states. |
| Approach: | They propose a new paradigm that formulates instruction optimization as an LLM fine-tuning objective for a white-box “instruction engineer” LLM. |
| Outcome: | The proposed framework outperforms strong baselines in performance and efficiency. |
Cognitive Alpha Mining via LLM-Driven Code-Based Evolution (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to finding effective predictive signals from financial data are limited by their complexity and low signal-to-noise ratio. |
| Approach: | They propose a framework that combines code-level alpha representation with LLM-driven reasoning and evolutionary search. |
| Outcome: | The proposed framework combines code-level alpha representation with LLM-driven reasoning and evolutionary search. |
RoCoIns: Enhancing Robustness of Large Language Models through Code-Style Instructions (2024.lrec-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have shown remarkable capabilities in following human instructions and solving NLU tasks. |
| Approach: | They propose to use code style instructions to replace typically natural language instructions to provide more precise instructions and strengthen the robustness of LLMs. |
| Outcome: | The proposed method outperforms natural language models on eight robustness datasets and achieves an improvement of 5.68% in test set accuracy and a reduction of 5.66 points in Attack Success Rate (ASR). |
metaCAT: A Metadata-based Task-oriented Chatbot Annotation Tool (2020.aacl-demo)
Copied to clipboard
| Challenge: | Creating high-quality annotated dialogue corpora necessitates a high level of human engagements. |
| Approach: | They propose to develop an annotation tool specifically for developing task-oriented dialogue data that provides comprehensive metadata annotation coverage to the domain, intent, and span information. |
| Outcome: | The tool provides comprehensive metadata annotation coverage to domain, intent, and span information. |
ChartMind: A Comprehensive Benchmark for Complex Real-world Multimodal Chart Question Answering (2025.emnlp-main)
Copied to clipboard
| Challenge: | Chart question answering (CQA) is a multimodal task for evaluating the reasoning capabilities of vision-language models. |
| Approach: | They propose a chart question answering benchmark that incorporates multilingual contexts and supports open-domain textual outputs. |
| Outcome: | The proposed framework outperforms the previous three common CQA paradigms: instruction-following, OCR-enhanced, and chain-of-thought. |
OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models (2025.acl-long)
Copied to clipboard
Siming Huang, Tianhao Cheng, Jason Klein Liu, Weidi Xu, Jiaran Hao, Liuyihan Song, Yang Xu, Jian Yang, Jiaheng Liu, Chenchen Zhang, Linzheng Chai, Ruifeng Yuan, Xianzhen Luo, Qiufeng Wang, YuanTao Fan, Qingfu Zhu, Zhaoxiang Zhang, Yang Gao, Jie Fu, Qian Liu, Houyi Li, Ge Zhang, Yuan Qi, Xu Yinghui, Wei Chu, Zili Wang
| Challenge: | Code LLMs lack reproducible data pipelines and training protocols for reproducible advancements in code intelligence. |
| Approach: | They propose a top-tier code LLM that releases model weights and inference code . reproducible data pipelines, rigorous experimental ablation results and training protocols are included . |
| Outcome: | The proposed model achieves comparable performance to leading models and serves as an "open cookbook" reproducible training data, rigorous experimental ablation results, and detailed training protocols are also included in the model. |
A Knowledge-Aware Sequence-to-Tree Network for Math Word Problem Solving (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for solving math word problems ignore background common-sense knowledge . a novel knowledge-aware sequence-to-tree (KA-S2T) network incorporates external knowledge and global expression information. |
| Approach: | They propose a knowledge-aware sequence-to-tree network that incorporates external knowledge and global expression information into the problem. |
| Outcome: | The proposed model can achieve better performance than previous models on a Math23K dataset. |
Chinese MentalBERT: Domain-Adaptive Pre-training on Social Media for Chinese Mental Health Text Analysis (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing models for language analysis are inadequate for specialized domains like psychology. |
| Approach: | They have enriched a Chinese social media database with psychological lexicons to enhance its applicability to psychological text analysis. |
| Outcome: | The proposed model performed better on six public datasets and provided relevant predictions given the masked sentences. |
In-sample Curriculum Learning by Sequence Completion for Natural Language Generation (2023.acl-long)
Copied to clipboard
| Challenge: | Existing work on curriculum learning rely on task-specific expertise and cannot generalize to different tasks. |
| Approach: | They propose to do in-sample curriculum learning for natural language generation tasks using human-crafted rules and a numeric score for each sample based on domain expertise to rank the model. |
| Outcome: | The proposed learning strategy generalizes well to different tasks and achieves significant improvements over baselines. |
CL2GEC: A Multi-Discipline Benchmark for Continual Learning in Chinese Literature Grammatical Error Correction (2026.acl-long)
Copied to clipboard
| Challenge: | Existing CGEC benchmarks for multi-disciplinary writing are limited . continual learning (CL) is a promising solution to handle domain-specific linguistic variation and prevent catastrophic forgetting. |
| Approach: | They propose a Chinese Literature Continual Learning benchmark to evaluate adaptive CGEC across disciplines. |
| Outcome: | The proposed benchmark includes 10,000 human-annotated sentences spanning 10 disciplines, each exhibiting distinct linguistic styles and error patterns. |
Measuring Human Contribution in AI-Assisted Content Generation (2026.acl-long)
Copied to clipboard
Yueqi Xie, Tao Qi, Jingwei Yi, Xiyuan Yang, Ryan Whalen, Junming Huang, Qian Ding, Yu Xie, Xing Xie, Fangzhao Wu
| Challenge: | generative AI has created a new way to generate content with humans . varying degrees of human contribution in content generation poses significant challenges for the delineation of originality . |
| Approach: | They propose a framework to measure human contribution in AI-assisted content generation by calculating mutual information between human input and AI-aided output relative to self-information of AI-assist output. |
| Outcome: | The proposed measure discriminates between varying degrees of human contribution across multiple creative domains and is validated in real-world applications. |
Self-Demos: Eliciting Out-of-Demonstration Generalizability in Large Language Models (2024.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods that rely on limited demos and out-of-demonstration (OOD) queries fail when faced with out- of-demotion queries. |
| Approach: | They propose a query-aware prompting method that elicits the inherent generalizability of large language models by query-based demo generation. |
| Outcome: | The proposed method outperforms state-of-the-art methods in the OOD setting and two public math benchmarks. |
Making Harmful Behaviors Unlearnable for Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) are often customized by fine-tuning for the requirements of different domains. |
| Approach: | They propose a controllable training framework to make undesired behaviors unlearnable during the fine-tuning process. |
| Outcome: | The proposed framework makes undesired behaviors unlearnable during the fine-tuning process while preserving the ability to learn other information. |
MEFT: Memory-Efficient Fine-Tuning through Sparse Adapter (2024.acl-long)
Copied to clipboard
| Challenge: | Parameter-Efficient Fine-tuning (PEFT) methods are limited on knowledge-intensive tasks due to the limited number of trainable parameters. |
| Approach: | They propose a mechanism that fine-tunes Large Language Models with larger adapters . they store and update the parameters of larger adapter adapters on the CPU . |
| Outcome: | The proposed method achieves comparable results to those obtained with larger memory capacities over the limited bandwidth of PCI Express (PCIe). |
LongAlign: A Recipe for Long Context Alignment of Large Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies to build long context language models focus on context extension and continual training on long text. |
| Approach: | They propose a recipe for instruction fine-tuning on input sequences of similar length . they adopt packing and sorted batching strategies to speed up supervised fine-uning . |
| Outcome: | The proposed model outperforms existing recipes for LLMs in long context tasks by 30% while maintaining proficiency in handling short, generic tasks. |
WantWords: An Open-source Online Reverse Dictionary System (2020.emnlp-demos)
Copied to clipboard
| Challenge: | Existing reverse dictionary systems only support English reverse dictionary queries . a reverse dictionary can help people who can't remember a word from memory . |
| Approach: | They propose an online reverse dictionary system that outperforms other reverse dictionary systems . it supports Chinese and English-Chinese as well as Chinese-English cross-lingual reverse dictionary queries . |
| Outcome: | The proposed reverse dictionary outperforms other reverse dictionary systems on performance . it supports Chinese and English-Chinese as well as Chinese-English queries . |
M-CNER: A Corpus for Chinese Named Entity Recognition in Multi-Domains (L18-1)
Copied to clipboard
| Challenge: | NER is one of the most important natural language processing tasks. |
| Approach: | They propose to annotate sentences from human-computer interaction, social media, and e-commerce using two rounds of annotation. |
| Outcome: | The proposed system performs the best on all the data sets. |
Can Large Language Models Adequately Perform Symbolic Reasoning Over Time Series? (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) and Multimodal LLMs (MLLMs) show strong performance in complex reasoning tasks, but their ability to extract symbolic laws from time series data remains underexplored. |
| Approach: | They propose a benchmark to assess symbolic reasoning over real-world time series across three tasks: multivariate symbolic regression, Boolean network inference, and causal discovery. |
| Outcome: | The proposed framework integrates LLMs with genetic programming to form a closed-loop symbolic reasoning system. |
Is Cognition Consistent with Perception? Assessing and Mitigating Multimodal Knowledge Conflicts in Document Understanding (2025.emnlp-main)
Copied to clipboard
| Challenge: | Multimodal large language models (MLLMs) have shown impressive capabilities in document understanding due to different types of annotation noise in training. |
| Approach: | They propose a method to reduce C&P knowledge conflicts across all tested MLLMs . they propose to use annotation noise to train models to understand document content . |
| Outcome: | The proposed method reduces C&P knowledge conflicts across all tested MLLMs and enhances their performance in both cognitive and perceptual tasks. |
SENT: Sentence-level Distant Relation Extraction via Negative Training (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods for relation extraction use bag labels, which introduce noise, to train the model. |
| Approach: | They propose to use negative training to train a model using complementary labels to separate the noisy data from the training data. |
| Outcome: | The proposed method improves on previous methods on sentence-level evaluation and de-noise effect. |
UniDrop: A Simple yet Effective Technique to Improve Transformer without Extra Cost (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing approaches to improve the performance of natural language processing models are over-parameterized and overfitted. |
| Approach: | They propose an approach to integrate dropout techniques into the training of Transformer models. |
| Outcome: | The proposed approach can achieve 1.5 BLEU improvement on IWSLT14 translation tasks and better accuracy for the classification even using strong pre-trained RoBERTa as backbone. |
A Survey of Inductive Reasoning for Large Language Models (2026.acl-long)
Copied to clipboard
Kedi Chen, Dezhao Ruan, Yuhao Dan, Yaoting Wang, Siyu Yan, Xuecheng Wu, Yinqi Zhang, Qin Chen, Jie Zhou, Liang He, Biqing Qi, Linyang Li, Qipeng Guo, Xiaoming Shi, Wei Zhang
| Challenge: | Inductive reasoning is an important task for large language models (LLMs). |
| Approach: | They propose a survey of inductive reasoning for large language models . they categorize methods into three main areas: post-training enhancement, test-time exploration, and data augmentation. |
| Outcome: | The proposed method improves inductive reasoning in large language models. |
AutoVecCoder: Teaching LLMs to Generate Explicitly Vectorized Code (2026.findings-acl)
Copied to clipboard
ShangZhan Li, Xinyu Yin, Xuanyu Jin, Ye He, Yuxin Zhou, Yuxuan Li, Xu Han, Wanxiang Che, Qi Shi, Ting Liu, Maosong Sun
| Challenge: | Current development practices face a dichotomy between automation and performance. |
| Approach: | They propose a framework to empower LLMs with the capability of automated explicit vectorization. |
| Outcome: | The proposed framework achieves state-of-the-art performance on the SSE and AVX subsets of SimdBench. |
Exploring Hybrid Question Answering via Program-based Prompting (2024.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to question answering over heterogeneous data are limited due to large scale of information and organic coupling of heterogenous data. |
| Approach: | They propose a program-based prompting framework for hybrid question answering tasks . it integrates various functions to perform hybrid information-seeking over data . |
| Outcome: | The proposed framework surpasses baseline systems and achieves the best performance under the fewshot settings. |
ReAL: How Can LLMs Simulate the Real Teacher? Retrieval-enhanced Agent for Adaptive Learning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Prior methods model learner-item interactions based only on ID sequences, leading to insufficient use of both learner and item information. |
| Approach: | They propose a Retrieval-enhanced Agent for Adaptive Learning powered by large language models to simulate teacher decision-making with extensive prior knowledge and teaching experience. |
| Outcome: | The proposed model outperforms existing models on three real-world datasets in both internal and external perspectives. |
PASUM: A Pre-training Architecture for Social Media User Modeling Based on Text Graph (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing studies have incorporated different digital traces to better learn the representations of social media users, limited by overloaded text information and hard-to-collect social network information. |
| Approach: | They propose a Pre-training Architecture for Social Media User Modeling based on Text Graph and combine microblogs to represent social media users based upon the text graph model. |
| Outcome: | The proposed framework can represent users based on text even without social network information on microblogs. |
Advancing Sequential Numerical Prediction in Autoregressive Models (2025.acl-short)
Copied to clipboard
| Challenge: | Autoregressive models are the de facto choice for sequence generation tasks, but standard approaches treat digits as independent tokens and apply cross-entropy loss, overlooking the coherent structure of numerical sequences. |
| Approach: | They propose a novel approach to entropy loss by extending the Earth Mover’s Distance to preserve ordinal relationships between numerical values and sequence-level to penalize the overall discrepancy between predicted and actual sequences. |
| Outcome: | Extensive experiments show that NTIL improves numerical prediction and integrates effectively with LLMs/MLLMs. |
FaithBench: A Diverse Hallucination Benchmark for Summarization by Modern LLMs (2025.naacl-short)
Copied to clipboard
Forrest Sheng Bao, Miaoran Li, Renyi Qu, Ge Luo, Erana Wan, Yujia Tang, Weisi Fan, Manveer Singh Tamber, Suleman Kazi, Vivek Sourabh, Mike Qi, Ruixuan Tu, Chenyu Xu, Matthew Gonzales, Ofer Mendelevitch, Amin Ahmad
| Challenge: | Existing evaluations of hallucinations in large language models suffer from a lack of diversity and recency in the LLM and LLM families considered. |
| Approach: | They propose a summarization hallucination benchmark that challenges models to disagree on hallucines . they use models to generate answers or summaries from textual input . |
| Outcome: | The proposed model combines the best of 10 modern LLMs with ground truth annotations. |
Retrieval over Classification: Integrating Relation Semantics for Multimodal Relation Extraction (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to multimodal relation extraction ignore structural constraints and lack semantic expressiveness for fine-grained relation understanding. |
| Approach: | They propose a framework that reformulates multimodal relation extraction as a retrieval task driven by relation semantics. |
| Outcome: | The proposed framework achieves state-of-the-art performance on the benchmark datasets MNRE and MORE and exhibits stronger robustness and interpretability. |
ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems (2020.acl-demos)
Copied to clipboard
Qi Zhu, Zheng Zhang, Yan Fang, Xiang Li, Ryuichi Takanobu, Jinchao Li, Baolin Peng, Jianfeng Gao, Xiaoyan Zhu, Minlie Huang
| Challenge: | ConvLab-2 inherits Convlab's framework but integrates more powerful dialogue models and supports more datasets. |
| Approach: | They present ConvLab-2, an open-source toolkit that enables researchers to build task-oriented dialogue systems with state-of-the-art models and perform an end-to-end evaluation. |
| Outcome: | The new tool inherits ConvLab's framework and extends it by integrating many recently proposed state-of-the-art dialogue models. |
HealthCards: Exploring Text-to-Image Generation as Visual Aids for Healthcare Knowledge Democratizing and Education (2025.emnlp-main)
Copied to clipboard
| Challenge: | Text-to-image (T2I) generation has the potential to advance knowledge democratization and education. |
| Approach: | They explore ways to harness T2I models for generating health knowledge flashcards . they curated a high-quality healthcare knowledge flash card dataset . |
| Outcome: | The proposed models can generate health knowledge flashcards with appealing images . the results show that the open-source models can be fine tuned to generate health content . |
Hierarchical Chinese Legal event extraction via Pedal Attention Mechanism (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods for event extraction cannot express connections between arguments, which are crucial in legal events. |
| Approach: | They propose a dynamic event structure for Chinese legal events to distinguish between similar events by hierarchical event features for event detection and a pedal attention mechanism to extract the semantic relation between two words through their dependent adjacent words. |
| Outcome: | The proposed model surpasses state-of-the-art models on a Chinese legal event dataset. |
Improving Pre-trained Language Models with Knowledge Enhancement and Filtering Framework (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing knowledge enhancement techniques for pre-trained language models (PLMs) introduce noisy entity representations. |
| Approach: | They propose a knowledge enhancement filter that integrates external knowledge bases to enhance PLMs' ability to capture entity knowledge. |
| Outcome: | The proposed method achieves the highest F1-score and accuracy while reducing the computational cost by 1.7-2.5x. |
Continual Prompt Tuning for Dialog State Tracking (2022.acl-long)
Copied to clipboard
| Challenge: | Existing methods to train a model on a sequence of tasks are not efficient enough to mitigate catastrophic forgetting. |
| Approach: | They propose a parameter-efficient framework that prevents forgetting and enables knowledge transfer between tasks by learning and freezing a pre-trained model. |
| Outcome: | The proposed framework avoids forgetting and enables knowledge transfer between tasks. |
SpellGCN: Incorporating Phonological and Visual Similarities into Language Models for Chinese Spelling Check (2020.acl-main)
Copied to clipboard
| Challenge: | Existing methods to detect and correct spelling errors in Chinese take external input or just heuristic rules. |
| Approach: | They propose to incorporate phonological and visual similarity knowledge into Chinese language models by using a specialized graph convolutional network. |
| Outcome: | The proposed method outperforms existing models on three human-annotated datasets. |
Unpaired Sentiment-to-Sentiment Translation: A Cycled Reinforcement Learning Approach (P18-1)
Copied to clipboard
| Challenge: | Existing studies for sentiment-to-sentiment "translation" only change the underlying sentiment and fail to keep the semantic content. |
| Approach: | They propose a cycled reinforcement learning method that combines neutralization module and emotionalization module. |
| Outcome: | The proposed method outperforms state-of-the-art systems on Yelp and Amazon review datasets. |
Modeling Intra and Inter-modality Incongruity for Multi-Modal Sarcasm Detection (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for sarcasm detection ignore the incongruity character in sarcasm, which is often manifested between modalities or within modalités. |
| Approach: | They propose to capture inter-modality incongruity in a text-based model by using a self-attention mechanism and a co-attention model to model the contradiction within the text. |
| Outcome: | The proposed model achieves state-of-the-art on a public multi-modal sarcasm detection dataset. |
SMR: State Memory Replay for Long Sequence Modeling (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing state space models (SSMs) address non-uniform sampling, but their recursive structures impede efficient SSM computation via convolution. |
| Approach: | They propose a plug-and-play mechanism to solve the Non-Stable State problem by adjusting input sequences with early memories. |
| Outcome: | The proposed method overcomes the non-uniform sample processing problem . it can achieve Sampling Step Adaptation (SSA) by adjusting input sequences with early memories. |
Unifying Cross-Lingual and Cross-Modal Modeling Towards Weakly Supervised Multilingual Vision-Language Pre-training (2023.acl-long)
Copied to clipboard
| Challenge: | Existing studies address the problem of translating English data into other languages, but they are limited in form and scale. |
| Approach: | They propose a framework to unify cross-lingual and cross-modal pre-training by using English data. |
| Outcome: | The proposed framework unifies cross-lingual and cross-modal pre-training on different data. |
Answering Cross-Dimensional Geometric Visual Questions by Multi-constraint Spatial Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for solving complex visual questions are limited in their ability to represent in a cross-dimensional space. |
| Approach: | They propose a method that can answer complex visual questions using cross-dimensional reasoning. |
| Outcome: | The proposed method can answer complex visual questions in 2D to 3D space with great application value. |
Do Syntax Trees Help Pre-trained Transformers Extract Information? (2021.eacl-main)
Copied to clipboard
| Challenge: | Recent work suggests that incorporating syntax information from dependency trees can improve task-specific transformer models. |
| Approach: | They propose to incorporate dependency tree information into pre-trained transformers for three tasks . they propose a late fusion approach and a joint fusion technique to infuses syntax structure into attention layers. |
| Outcome: | The proposed models obtain state-of-the-art results on SRL and relation extraction tasks. |
CodeRetriever: A Large Scale Contrastive Pre-Training Method for Code Search (2022.emnlp-main)
Copied to clipboard
Xiaonan Li, Yeyun Gong, Yelong Shen, Xipeng Qiu, Hang Zhang, Bolun Yao, Weizhen Qi, Daxin Jiang, Weizhu Chen, Nan Duan
| Challenge: | Existing code pre-training approaches often adopt (masked) language modeling as the training objective which targets on learning to predict (macked) tokens in a given code context. |
| Approach: | They propose a code-text contrastive learning model which learns function-level code semantic representations through large-scale code corpus. |
| Outcome: | The proposed model achieves new state-of-the-art with significant improvement over existing pre-trained models on eleven domain/language-specific code search tasks with six programming languages in different code granularity. |
Improving Time Sensitivity for Question Answering over Temporal Knowledge Graphs (2022.acl-long)
Copied to clipboard
| Challenge: | Temporal knowledge graphs record entity relations and when they occur in time . previous work fails to address time-related challenges such as time-order issues . paper proposes time-sensitive question answering framework to address these problems . |
| Approach: | They propose a time-sensitive question answering framework that uses temporal KGs to answer natural language questions. |
| Outcome: | The proposed framework outperforms the state-of-the-art on a new benchmark for question answering over temporal knowledge graphs. |
Towards Building More Robust NER datasets: An Empirical Study on NER Dataset Bias from a Dataset Difficulty View (2023.emnlp-main)
Copied to clipboard
| Challenge: | Named Entity Recognition (NER) models rely on superficial entity patterns for predictions, without considering evidence from the context. |
| Approach: | They propose to de-bias NER datasets by altering entity-context distribution . they also validate the feasibility of the proposed de-bianking techniques . |
| Outcome: | The proposed methods can be applied to different models and improve existing models. |
StepCoder: Improving Code Generation with Reinforcement Learning from Compiler Feedback (2024.acl-long)
Copied to clipboard
Shihan Dou, Yan Liu, Haoxiang Jia, Enyu Zhou, Limao Xiong, Junjie Shan, Caishuang Huang, Xiao Wang, Xiaoran Fan, Zhiheng Xi, Yuhao Zhou, Tao Ji, Rui Zheng, Qi Zhang, Tao Gui, Xuanjing Huang
| Challenge: | Existing work integrates reinforcement learning with compiler feedback to enhance code generation quality but the long code generated by LLMs makes RL exploration ineffective. |
| Approach: | They propose a framework that integrates reinforcement learning and compiler feedback to enhance code generation quality. |
| Outcome: | The proposed framework outperforms state-of-the-art approaches in corresponding benchmarks and integrates reinforcement learning with compiler feedback to improve code generation quality. |
Towards Economical Inference: Enabling DeepSeek’s Multi-Head Latent Attention in Any Transformer-based LLMs (2025.acl-long)
Copied to clipboard
Tao Ji, Bin Guo, Yuanbin Wu, Qipeng Guo, Shenlixing Shenlixing, Chenzhan Chenzhan, Xipeng Qiu, Qi Zhang, Tao Gui
| Challenge: | Multi-head Latent Attention (MLA) is an innovative architecture designed to ensure efficient and economical inference by significantly compressing the Key-Value (KV) cache into a latent vector. |
| Approach: | They propose a data-efficient fine-tuning method for transitioning from MHA to MLA using a latent vector cache. |
| Outcome: | The proposed architecture reduces the KV cache size of Llama2-7B by 92.19%, with only 1% drop in LongBench performance. |
Towards Better Entity Linking with Multi-View Enhanced Distillation (2023.acl-long)
Copied to clipboard
Yi Liu, Yuan Tian, Jianxun Lian, Xinlong Wang, Yanan Cao, Fang Fang, Wen Zhang, Haizhen Huang, Weiwei Deng, Qi Zhang
| Challenge: | Entity linking is a fundamental task in Natural Language Processing (NLP), connecting mentions within unstructured contexts to their corresponding entities in a Knowledge Base (KB). |
| Approach: | They propose a dual-encoder framework that can efficiently match mentions to two-encoding frameworks by a global-view. |
| Outcome: | The proposed framework achieves state-of-the-art on several entity linking benchmarks. |
Enhancing Generalization in Natural Language Inference by Syntax (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Pre-trained language models such as BERT have the state-of-the-art performance on natural language inference (NLI). |
| Approach: | They propose to use dependency trees to enhance generalization of BERT in a natural language inference task by leveraging on a graph convolutional network to represent a syntax-based matching graph with heterogeneous matching patterns. |
| Outcome: | The proposed method makes BERT more robust on syntactic changes. |
Modelling Uncertainty in Collaborative Document Quality Assessment (D19-55)
Copied to clipboard
| Challenge: | Existing work on document quality assessment relies on predicting the quality of a document relative to a putative gold standard, without paying attention to the subjectivity of this task. |
| Approach: | They propose to use Gaussian processes and random forests to measure the uncertainty in document quality predictions. |
| Outcome: | The proposed methods can predict the quality of Wikipedia articles while providing an estimate of uncertainty when there is inconsistency in the quality labels from the contributors. |
Simplify the Usage of Lexicon in Chinese NER (2020.acl-main)
Copied to clipboard
| Challenge: | Named entity recognition (NER) is concerned with the identification of named entities in unstructured text. |
| Approach: | They propose a method for incorporating word lexicon into character representations . experimental results show method can be easily incorporated with pre-trained models . |
| Outcome: | The proposed method achieves 6.15 times faster inference speed and better performance on four benchmark Chinese NER datasets. |
Graph of Attacks with Pruning: Optimizing Stealthy Jailbreak Prompt Generation for Enhanced LLM Content Moderation (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Existing jailbreaking methods create adversarial prompts to bypass LLM safeguards. |
| Approach: | They propose a framework for generating stealthy jailbreak prompts that enables knowledge sharing across attack paths. |
| Outcome: | The proposed framework outperforms state-of-the-art methods for attacking both open and closed LLMs with attack success rates of >96%. |
MAVEN-FACT: A Large-scale Event Factuality Detection Dataset (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Event factuality detection is under-explored due to the lack of high-quality large-scale data . efd is a subfield of event understanding, which aims to determine the factuity of textual events. |
| Approach: | They propose a large-scale EFD dataset with factuality annotations of 112,276 events . they find that adopting event arguments and relations helps in event factuity detection . |
| Outcome: | The proposed dataset includes factuality annotations of 112,276 events . it is the largest EFD dataset and is challenging for fine-tuned models and large language models . |
A Relation-Oriented Clustering Method for Open Relation Extraction (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for open relation extraction (OpenRE) are designed for predefined relations, which cannot deal with new emerging relations in the real world. |
| Approach: | They propose a relation-oriented clustering model that leverages readily available labeled data to learn a relationship-oriented representation. |
| Outcome: | The proposed model reduces error rate by 29.2% and 15.7% on two datasets compared with current SOTA methods. |
UPPAM: A Unified Pre-training Architecture for Political Actor Modeling based on Language (2023.acl-long)
Copied to clipboard
| Challenge: | Existing studies have incorporated contextual information to better learn the representation of political actors for specific tasks. |
| Approach: | They propose to use statements to represent political actors and learn mapping from languages to representations using social networks and behaviors as self-constructed supervision. |
| Outcome: | The proposed model can be generalized to political actors and solve downstream tasks. |
Harnessing Negative Signals: Reinforcement Distillation from Teacher Data for LLM Reasoning (2026.acl-long)
Copied to clipboard
| Challenge: | Recent advances in model distillation show that data from advanced reasoning models can effectively train smaller student models. |
| Approach: | They propose a method to use both positive and negative distilled reasoning traces to maximize LLM reasoning performance in offline settings. |
| Outcome: | The proposed model outperforms existing methods in the distillation context. |
CRaSh: Clustering, Removing, and Sharing Enhance Fine-tuning without Full Large Language Model (2023.emnlp-main)
Copied to clipboard
| Challenge: | Instruction tuning is an effective way of aligning large language models with private instruction data. |
| Approach: | They propose a training-free strategy to derive improved emulators from LLMs by using Offsite-Tuning (OFT) they propose CRaSh, which transfers transformer blocks between centralized LLM and downstream emulators . |
| Outcome: | The proposed technique boosts performance of large language models with billions of parameters. |
SCOPE: Boosting LLM Efficiency with Scoped Position Encoding (2026.acl-long)
Copied to clipboard
| Challenge: | Positional encodings are fundamental to Transformers, but explicit methods like RoPE can degrade under length extrapolation and incur extra arithmetic and memory-access overhead. |
| Approach: | They propose a framework that reimagines structured sparsity as an intrinsic position encoding mechanism. |
| Outcome: | The proposed framework reduces the number of attention FLOPs by 8x compared to RoPE on LLaMA-3-8B architectures while reducing training and inference latency. |
MIND: A Large-scale Dataset for News Recommendation (2020.acl-main)
Copied to clipboard
Fangzhao Wu, Ying Qiao, Jiun-Hung Chen, Chuhan Wu, Tao Qi, Jianxun Lian, Danyang Liu, Xing Xie, Jianfeng Gao, Winnie Wu, Ming Zhou
| Challenge: | Personalized news recommendation is an important technique for personalized news service. |
| Approach: | They propose to build a large-scale news recommendation dataset from Microsoft News . they demonstrate that news recommendation relies on the quality of news content understanding . |
| Outcome: | The proposed dataset contains 1 million users and more than 160k English news articles, each of which has rich textual content such as title, abstract and body. |
PRIMO: Progressive Induction for Multi-hop Open Rule Generation (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing approaches focus on single-hop open rule generation, ignoring scenarios involving multiple hops, leading to logical inconsistencies between premise and hypothesis atoms, as well as semantic duplication of generated rule atom. |
| Approach: | They propose a multi-stage open rule generation method called PRIMO that introduces ontology information during the rule generation stage to reduce ambiguity and improve rule accuracy. |
| Outcome: | The proposed method reduces the repetition rate of rule atoms while preserving the latent knowledge within the model. |
Try to Substitute: An Unsupervised Chinese Word Sense Disambiguation Method Based on HowNet (2020.coling-main)
Copied to clipboard
| Challenge: | Existing unsupervised methods for word sense disambiguation cannot work for HowNet-based WSD because of its uniqueness. |
| Approach: | They propose a method which exploits the masked language model task of pre-trained language models to conduct word sense disambiguation using a lexical knowledge base as the sense inventory. |
| Outcome: | The proposed method achieves significantly better performance than baseline methods. |
Dancing in Chains: Reconciling Instruction Following and Faithfulness in Language Models (2024.emnlp-main)
Copied to clipboard
Zhengxuan Wu, Yuhao Zhang, Peng Qi, Yumo Xu, Rujun Han, Yian Zhang, Jifan Chen, Bonan Min, Zhiheng Huang
| Challenge: | Modern language models fail to follow human instructions while being faithful . a trade-off exists between instruction following and faithfulness when training LMs . |
| Approach: | They propose a method that relies on Reject-sampling by Self-instruct with Continued Fine-tuning to train LMs to follow human instructions while being faithful. |
| Outcome: | The proposed method outperforms vanilla MTL with high-quality data, but with significantly smaller data. |
Can LLMs Evaluate Complex Attribution in QA? Automatic Benchmarking using Knowledge Graphs (2025.acl-long)
Copied to clipboard
Nan Hu, Jiaoyan Chen, Yike Wu, Guilin Qi, Hongru Wang, Sheng Bi, Yongrui Chen, Tongtong Wu, Jeff Z. Pan
| Challenge: | Attributed Question Answering (AQA) has attracted wide attention, but there are several limitations in evaluating the attributions. |
| Approach: | They propose a large-scale benchmark containing comprehensive attribution categories . they compare 25 automatic evaluators with human evaluers and tested LLM evalators . |
| Outcome: | The proposed method can compare attributions with subtle differences and provide feedback to improve them. |
Mitigating Position Bias in Transformers via Layer-Specific Positional Embedding Scaling (2026.findings-acl)
Copied to clipboard
Zhenghua Wang, Yiran Ding, Changze Lv, Yixin Wu, Tianlong Li, Zhibo Xu, Muling Wu, Tianyuan Shi, Shizheng Li, Qi Qian, Xuanjing Huang, Xiaoqing Zheng
| Challenge: | Existing methods to address the "lost-in-the-middle" problem suffer from high latency or suboptimal hand-crafted scaling strategies. |
| Approach: | They propose a layer-specific positional embedding scaling method that assigns distinct scaling factors to each layer. |
| Outcome: | Experiments show that the proposed method mitigates positional attention bias and delivers consistent improvements across multiple long-context benchmarks. |
Graph Convolution over Pruned Dependency Trees Improves Relation Extraction (D18-1)
Copied to clipboard
| Challenge: | Existing dependency-based models neglect crucial information (e.g., negation) by pruning the dependency trees too aggressively. |
| Approach: | They propose an extension of graph convolutional networks that is tailored for relation extraction by pruning dependency trees too aggressively. |
| Outcome: | The proposed model outperforms existing sequence and dependency-based models on the large-scale TACRED dataset and has complementary strengths to sequence models. |
Rethinking Pragmatics in Large Language Models: Towards Open-Ended Evaluation and Preference Tuning (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to assess social-pragmatic inference in large language models are inadequacy, and preferential tuning is the best approach. |
| Approach: | They propose to use free-form models' responses as a measure to assess social-pragmatic reasoning and advocate for preference optimization over supervised finetuning (SFT). |
| Outcome: | The proposed model outperforms supervised finetuning (SFT) and offers a near-free launch in pragmatic abilities without compromising general capabilities. |
RealBehavior: A Framework for Faithfully Characterizing Foundation Models’ Human-like Behavior Mechanisms (2023.findings-emnlp)
Copied to clipboard
Enyu Zhou, Rui Zheng, Zhiheng Xi, Songyang Gao, Xiaoran Fan, Zichu Fei, Jingting Ye, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing studies on human-like behaviors in foundation models do not verify their faithfulness . a simple application of psychological tools cannot faithfully characterize all human-type behaviors . |
| Approach: | They propose a framework to characterize humanoid behaviors in foundation models . they argue that a simple application of psychological tools cannot faithfully characterize all human-like behaviors . |
| Outcome: | The proposed framework assesses the faithfulness of results based on reproducibility, internal consistency, and generalizability. |
Are Structural Concepts Universal in Transformer Language Models? Towards Interpretable Cross-Lingual Generalization (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models (LLMs) have implicitly transfer knowledge across languages, but not all languages have such generalization capabilities. |
| Approach: | They propose a meta-learning-based method to learn to align conceptual spaces of different languages to enhance cross-lingual generalization. |
| Outcome: | The proposed method achieves competitive results with state-of-the-art methods and narrows the performance gap between languages. |
UrbanGeoEval: A City-Scale Benchmark for Evaluating Large Language Models in Geospatial Reasoning (2026.acl-long)
Copied to clipboard
| Challenge: | Extensive experiments on 18 widely used LLMs uncover critical insights: (1) models exhibit severe geographic biases and resolution gaps; (2) failures in complex multi-hop tasks stem from brittle foundational spatial skills rather than high-level logic deficits. |
| Approach: | They propose a dual-module framework that disentangles factual recall and spatial logic from the model's real capabilities in urban environments. |
| Outcome: | Extensive tests on 18 widely used LLMs reveal that models exhibit severe geographic biases and resolution gaps, and failures in complex multi-hop tasks often stem from brittle foundational spatial skills rather than high-level logic deficits. |
Understanding Gender Bias in Knowledge Base Embeddings (2022.acl-long)
Copied to clipboard
| Challenge: | Knowledge base (KB) embeddings have been shown to contain gender biases . authors develop two new bias measures to quantify them and trace their origins in KB . |
| Approach: | They propose two ways to quantify gender biases in knowledge base (KB) embeddings . they use the influence function to inspect the contribution of each triple in KB to the overall group bias . |
| Outcome: | The proposed measures are compared with real-world census data to examine gender biases. |
MicroEdit: Neuron-level Knowledge Disentanglement and Localization in Lifelong Model Editing (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for enhancing large language models are designed for single or limited edits, lacking the capacity to support long-term, multi-round knowledge updates. |
| Approach: | They propose a neuron-level editing method that performs minimal interventions within large language models (LLMs) by leveraging a sparse autoencoder, MicroEdit disentangles knowledge representations and activates only a minimal set of necessary neurons for precise parameter updates. |
| Outcome: | Extensive experiments show that MicroEdit outperforms prior methods and robustly handles lifelong knowledge editing across QA and Hallucination settings on LLaM and Mistral. |
from Benign import Toxic: Jailbreaking the Language Model via Adversarial Metaphors (2025.acl-long)
Copied to clipboard
| Challenge: | Recent studies have exposed the risk of Large Language Models (LLMs) generating harmful content by jailbreak attacks. |
| Approach: | They propose a framework that exploits AdVersArial meTAphoR to induce LLMs to calibrate harmful metaphors for jailbreaking. |
| Outcome: | The proposed framework can successfully jailbreak Large Language Models (LLMs) by leveraging the AdVersArial meTAphoR (AVATAR) framework achieves state-of-the-art attack success rate across multiple advanced LLMs. |
Tokenization Consistency Matters for Generative Models on Extractive NLP Tasks (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Pretrained sequence-to-sequence (seq2sequ) models have been widely used to solve extractive tasks, where parts of the input are extracted to form the desired output. |
| Approach: | They propose a simple fix to tokenization inconsistency that damages extractive nature of generative models by causing performance drop and hallucination. |
| Outcome: | The proposed model performs better in both in-domain and out-of-domain datasets with a notable average of +1.7 F1 gain when a BART model is trained on SQuAD and evaluated on 8 QA datasets. |
Divide and Conquer: Text Semantic Matching with Disentangled Keywords and Intents (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing text semantic matching models do not provide granularity for text comparison. |
| Approach: | They propose a simple yet effective training strategy for text semantic matching by disentangling keywords from intents. |
| Outcome: | The proposed approach achieves stable performance improvements against a wide range of models on three benchmarks. |
MidPO: Dual Preference Optimization for Safety and Helpfulness in Large Language Models via a Mixture of Experts Framework (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Recent studies address safety-constrained online and offline preferences optimizations, but offline methods perform poorly in adaptively balancing safety and helpfulness. |
| Approach: | They propose a mixture of experts framework for safety-helpfulness dual Preference Optimization . they combine a single-preference enhanced direct preference optimization approach with a dynamic routing mechanism . |
| Outcome: | The proposed framework outperforms state-of-the-art methods in safety and helpfulness. |
Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels (2025.emnlp-main)
Copied to clipboard
Junjie Ye, Yuming Yang, Yang Nan, Shuo Li, Qi Zhang, Tao Gui, Xuanjing Huang, Peng Wang, Zhongchao Shi, Jianping Fan
| Challenge: | Large language models (LLMs) acquire substantial world knowledge during pretraining, which is further shaped by post-training techniques such as supervised fine-tuning (SFT). |
| Approach: | They evaluate closed-book question answering (CBQA) performance across five LLMs from the LLaMA-2 and LLama-3 families and examine the impact of supervised fine-tuning on model knowledge. |
| Outcome: | The proposed model performance is 14% worse than models fine-tuned on 1,920 samples and 12% worse on 240 samples. |
Calibrating LLM-Based Evaluator (2024.lrec-main)
Copied to clipboard
Yuxuan Liu, Tianchi Yang, Shaohan Huang, Zihan Zhang, Haizhen Huang, Furu Wei, Weiwei Deng, Feng Sun, Qi Zhang
| Challenge: | Existing models for large language models lack the ability to calibrate their outputs towards human preference. |
| Approach: | They propose a multi-stage, gradient-free approach to calibrate an LLM-based evaluator toward human preference. |
| Outcome: | The proposed approach improves correlation with expert evaluation on multiple text quality evaluation datasets. |
AXIS: Efficient Human-Agent-Computer Interaction with API-First LLM-Based Agents (2025.acl-long)
Copied to clipboard
Junting Lu, Zhiyang Zhang, Fangkai Yang, Jue Zhang, Lu Wang, Chao Du, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang, Qi Zhang
| Challenge: | Multimodal large language models (MLLMs) have enabled LLM-based agents to directly interact with application user interfaces (UIs), enhancing agents’ performance in complex tasks. |
| Approach: | They propose a novel agent framework that prioritizes actions through application programming interfaces over UI actions and facilitates the creation and expansion of APIs through automated exploration of applications. |
| Outcome: | The proposed framework reduces task completion time by 65%-70% and cognitive workload by 38%-53% while maintaining accuracy of 97%-98% compared to humans. |
VRPO: Rethinking Value Modeling for Robust RL under Noisy Supervision in LLM Post-Training (2026.acl-long)
Copied to clipboard
Dingwei Zhu, Shihan Dou, Zhiheng Xi, Senjie Jin, Guoqiang Zhang, Jiazheng Zhang, Junjie Ye, Mingxu Chai, Enyu Zhou, Ming Zhang, Yuhui Wang, Caishuang Huang, Chenhao Huang, Yunke Zhang, Yuran Wang, Tao Gui, Qi Zhang, Xipeng Qiu, Xuanjing Huang
| Challenge: | Reinforcement Learning (RL) in real-world environments often suffers from ambiguous or incomplete supervision. |
| Approach: | They propose a framework that enhances value modeling for robust RL in LLM post-training by integrating auxiliary losses guided by entropy and perplexity from a frozen language model and variational information bottleneck. |
| Outcome: | The proposed framework outperforms baselines on multi-turn dialogue, math reasoning, and science QA with rule-based and model-based rewards. |
HybGRAG: Hybrid Retrieval-Augmented Generation on Textual and Relational Knowledge Bases (2025.acl-long)
Copied to clipboard
Meng-Chieh Lee, Qi Zhu, Costas Mavromatis, Zhen Han, Soji Adeshina, Vassilis N. Ioannidis, Huzefa Rangwala, Christos Faloutsos
| Challenge: | Existing methods for retrieving information from a semi-structured knowledge base are struggling with hybrid questions. |
| Approach: | They propose a retrieval method that leverages both textual and relational information from a semi-structured knowledge base to answer user questions. |
| Outcome: | The proposed method surpasses all baselines on the STaRK benchmark and achieves significant performance gains. |
DocHieNet: A Large and Diverse Dataset for Document Hierarchy Parsing (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for document hierarchy parsing are limited due to the small scale and inconsistency of datasets. |
| Approach: | They propose a document hierarchy parsing dataset to compensate for the data scarcity problem and propose 'dHP' framework to grasp fine-grained text content and coarse-grounded pattern at layout element level. |
| Outcome: | The proposed framework grasps both fine-grained text content and coarse-grounded pattern at layout element level, enhancing the capacity of pre-trained text-layout models in handling multi-page and multi-level challenges. |
High-Quality Medical Dialogue Synthesis for Improving EMR Generation (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Existing methods for generating EMRs from doctor-patient dialogues produce rigid and repetitive dialogues. |
| Approach: | They propose a framework that integrates Intent Graph Planning, Dual-Agent Simulation and Rule-Reward Quality Control to generate realistic doctor-patient dialogues. |
| Outcome: | The proposed framework significantly enhances realism, diversity and downstream EMR quality, reducing physician editing efforts. |
Vision-and-Language Navigation: A Survey of Tasks, Methods, and Future Directions (2022.acl-long)
Copied to clipboard
| Challenge: | Vision-and-Language Navigation (VLN) is a research topic that is gaining attention in the field of artificial intelligence. |
| Approach: | They propose to build an embodied agent that can communicate with humans in natural language and navigate in real 3D environments. |
| Outcome: | This paper reviews current studies in the emerging field of vision-and-language navigation . it highlights limitations and opportunities for future work . |
UPRISE: Universal Prompt Retrieval for Improving Zero-Shot Evaluation (2023.emnlp-main)
Copied to clipboard
Daixuan Cheng, Shaohan Huang, Junyu Bi, Yuefeng Zhan, Jianfeng Liu, Yujing Wang, Hao Sun, Furu Wei, Weiwei Deng, Qi Zhang
| Challenge: | Large Language Models (LLMs) have impressive capabilities but need for task-specific prompt engineering can hinder their generalization. |
| Approach: | They propose a lightweight and versatile retriever that automatically retrieves prompts for a given zero-shot task input. |
| Outcome: | The proposed model is universally applicable across tasks and models . it mitigates hallucination problem in chatGPT, and it improves even the strongest LLMs. |
UAlign: Leveraging Uncertainty Estimations for Factuality Alignment on Large Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) often struggle to accurately express factual knowledge, especially in cases where the knowledge boundaries are ambiguous. |
| Approach: | They propose a framework that leverages Uncertainty estimations to represent knowledge boundaries and incorporates these representations into prompts for LLMs to Align with factual knowledge. |
| Outcome: | The proposed framework significantly improves the LLMs’ capacities to confidently answer known questions and refuse unknown questions on both in-domain and out-of-domain tasks. |
Hallucination Detection in Long-Form Text Generated by LLMs: A Benchmark and a Hyper-Relational Knowledge Graph Approach (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for hallucination detection are coarse-grained and lack long-range consistency checks. |
| Approach: | They propose a benchmark for long-form hallucination detection that incorporates diverse entity types and intricate factual dependencies spanning extended contexts. |
| Outcome: | The proposed framework outperforms baselines and robustly integrates fact-centric hyper-relational knowledge graphs. |
ScdNER: Span-Based Consistency-Aware Document-Level Named Entity Recognition (2023.emnlp-main)
Copied to clipboard
| Challenge: | Named entity recognition (NER) is an important task for many natural language processing applications. |
| Approach: | They propose to fuse global features of tokens via word-based key-value memory to produce documentlevel encoding for token label prediction. |
| Outcome: | The proposed model can produce consistent and consistent predictions on word level with reduced impact of non-entity sequences and adaptive global feature fusion. |
RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQL (2022.emnlp-main)
Copied to clipboard
Jiexing Qi, Jingyao Tang, Ziwei He, Xiangpeng Wan, Yu Cheng, Chenghu Zhou, Xinbing Wang, Quanshi Zhang, Zhouhan Lin
| Challenge: | Experimental results show RASAT can leverage a variety of relational structures while inheriting the pretrained parameters from the T5 model. |
| Approach: | They propose a Transformer seq2seq architecture augmented with relation-aware self-attention that leverages relational structures while inheriting pretrained parameters from the T5 model. |
| Outcome: | The proposed model can leverage relational structures while inheriting pretrained parameters from the T5 model effectively. |
Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments (2026.findings-acl)
Copied to clipboard
Junjie Ye, Changhao Jiang, Zhengyin Du, Yufei Xu, Xuesong Yao, Zhiheng Xi, Xiaoran Fan, Qi Zhang, Tao Gui, Xuanjing Huang, Jiecao Chen
| Challenge: | Currently, there are no efficient reinforcement learning (RL) frameworks specifically designed for tool use. |
| Approach: | They propose an automated environment construction pipeline that incorporates scenario decomposition, document generation, function integration, complexity scaling, and localized deployment to enable high-quality training environments without external tools. |
| Outcome: | The proposed framework significantly improves the models’ tool-use performance without degrading their general capabilities. |
POS-Constrained Parallel Decoding for Non-autoregressive Generation (2021.acl-long)
Copied to clipboard
| Challenge: | Existing non-autoregressive generation systems face multimodality problem due to conditionally independent decoding. |
| Approach: | They propose to incorporate linguistic structure into NAG inference instead of teacher AG . they propose a method that provides a specific POS sequence to constrain the NAG model . |
| Outcome: | The proposed method improves NAG models on four text generation tasks to a greater extent compared to knowledge distillation. |
LeTS: Learning to Think-and-Search via Process-and-Outcome Reward Hybridization (2025.emnlp-main)
Copied to clipboard
Qi Zhang, Shouqing Yang, Lirong Gao, Hao Chen, Xiaomeng Hu, Jinglei Chen, Jiexiang Wang, Sheng Guo, Bo Zheng, Haobo Wang, Junbo Zhao
| Challenge: | Recent research focuses on integrating reasoning capabilities into the realm of retrieval-augmented generation (RAG) via outcome-supervised reinforcement learning (RL). |
| Approach: | They propose a process-level reward module to mitigate the unawareness of intermediate reasoning steps in outcome-level supervision without additional annotation. |
| Outcome: | The proposed framework can boost LLMs’ reasoning ability by integrating external knowledge sources through retrieval-augmented generation (RAG) The proposed model can mitigate the unawareness of intermediate reasoning steps in outcome-level supervision without additional annotation. |
Planning, Creation, Usage: Benchmarking LLMs for Comprehensive Tool Utilization in Real-World Complex Scenarios (2024.findings-acl)
Copied to clipboard
Shijue Huang, Wanjun Zhong, Jianqiao Lu, Qi Zhu, Jiahui Gao, Weiwen Liu, Yutai Hou, Xingshan Zeng, Yasheng Wang, Lifeng Shang, Xin Jiang, Ruifeng Xu, Qun Liu
| Challenge: | Existing benchmarks focus on simple synthesized queries that do not reflect real-world complexity, thereby offering limited perspectives in evaluating tool utilization. |
| Approach: | They propose a benchmark to evaluate LLMs’ ability in tool utilization within real-world scenarios. |
| Outcome: | The proposed benchmark improves LLMs’ ability in tool utilization within real-world scenarios and eliminates the restriction of pre-defined toolset. |
Reducing Sensitivity on Speaker Names for Text Generation from Dialogues (2023.findings-acl)
Copied to clipboard
| Challenge: | Pre-trained language models are sensitive to nuances, resulting in unfairness in real-world applications. |
| Approach: | They propose to quantitatively measure a model's sensitivity on speaker names and comprehensively evaluate a number of known methods for reducing speaker name sensitivity. |
| Outcome: | The proposed approach reduces speaker name sensitivity and improves quality of generation. |
GATEAU: Selecting Influential Samples for Long Context Alignment (2025.emnlp-main)
Copied to clipboard
Shuzheng Si, Haozhe Zhao, Gang Chen, Yunshui Li, Kangyang Luo, Chuancheng Lv, Kaikai An, Fanchao Qi, Baobao Chang, Maosong Sun
| Challenge: | Existing studies have attempted to scale up the available data volume by synthesizing long instruction-following samples, but a lack of a well-defined strategy for ensuring data quality may introduce low-quality samples and restrict the model’s performance. |
| Approach: | They propose a framework to identify influential samples enriched with long-range dependency relations that can be used to align large language models to handle instructions with extremely long contexts. |
| Outcome: | The proposed framework identifies samples with long-range dependency relations and shows that the model trained on these samples exhibits better instruction-following and long-context understanding capabilities. |
Stepwise Reasoning Disruption Attack of LLMs (2025.acl-long)
Copied to clipboard
Jingyu Peng, Maolin Wang, Xiangyu Zhao, Kai Zhang, Wanyu Wang, Pengyue Jia, Qidong Liu, Ruocheng Guo, Qi Liu
| Challenge: | Existing attacks on LLM reasoning are constrained by specific settings or lack of imperceptibility, limiting their feasibility and generalizability. |
| Approach: | They propose a stepwise rEasoning error disruption attack that subtly injects errors into prior reasoning steps to mislead the model into producing incorrect subsequent reasoning and final answers. |
| Outcome: | The proposed attack is compatible with zero-shot and few-shot settings, maintains the natural reasoning flow, and ensures covert execution without modification of the instruction. |
Annotating and Detecting Fine-grained Factual Errors for Dialogue Summarization (2023.acl-long)
Copied to clipboard
| Challenge: | Existing work on factual inconsistency in abstractive summarization addresses this problem. |
| Approach: | They propose a dataset with fine-grained factual error annotations named DIASUMFACT and an unsupervised model named ENDERANKER. |
| Outcome: | The proposed model performs on par with the state-of-the-art models while requiring fewer resources. |
AEA: Adaptive Expert Allocation Improves Sentence Embeddings from Mixture-of-Experts LLM (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods to improve embeddings from Mixture-of-Experts models allocate a fixed number of experts uniformly across all layers and tokens, ignoring inter-layer and inter-token heterogeneity. |
| Approach: | They propose an Adaptive Expert Allocation framework that performs layer-wise and token-wise expert allocation to enhance embedding quality. |
| Outcome: | The proposed method improves embedding quality across multiple MoE models. |
Posterior-regularized REINFORCE for Instance Selection in Distant Supervision (N19-1)
Copied to clipboard
| Challenge: | Existing methods to train unbiased methods such as REINFORCE take time to train. |
| Approach: | They propose to use posterior regularization to integrate domain-specific rules in instance selection using REINFORCE to improve the performance of the relation classifier trained on cleaned distant supervision datasets. |
| Outcome: | The proposed method improves the performance of the relation classifier trained on cleaned distant supervision dataset as well as the efficiency of the REINFORCE training. |
EA2E: Improving Consistency with Event Awareness for Document-Level Argument Extraction (2022.findings-naacl)
Copied to clipboard
| Challenge: | Recent work on document-level event argument extraction models each individual event in isolation and therefore causes inconsistency among extracted arguments across events. |
| Approach: | They propose an event-aware argument extraction model with augmented context to improve consistency . they hypothesize that participants tend to play consistent roles across multiple events in a document . |
| Outcome: | The proposed model improves consistency and accuracy of arguments extracted from documents. |
PerSphere: A Comprehensive Framework for Multi-Faceted Perspective Retrieval and Summarization (2025.acl-long)
Copied to clipboard
| Challenge: | Experimental results show that the main challenge lies in long context and perspective extraction. |
| Approach: | They propose a benchmark to facilitate multi-faceted perspective retrieval and summarization . they propose measurable metrics to evaluate the comprehensiveness of the retrieval pipeline . |
| Outcome: | The proposed system breaks free from information silos by combining two opposing claims . it can be used to extract multiple perspectives and improve performance on the platform . |
Mutual Reinforcement of LLM Dialogue Synthesis and Summarization Capabilities for Few-Shot Dialogue Summarization (2025.findings-naacl)
Copied to clipboard
Yen-Ju Lu, Ting-Yao Hu, Hema Swetha Koppula, Hadi Pouransari, Jen-Hao Rick Chang, Yin Xia, Xiang Kong, Qi Zhu, Xiaoming Simon Wang, Oncel Tuzel, Raviteja Vemulapalli
| Challenge: | Empirical results demonstrate that our method improves dialogue summarization, achieving a 1.5% increase in ROUGE scores and a 0.3% improvement in BERT scores in few-shot settings. |
| Approach: | They propose Mutual Reinforcing Data Synthesis (MRDS) within large language models to enhance few-shot dialogue summarization task. |
| Outcome: | Empirical results show that the proposed method improves dialogue summarization, achieving a 1.5% increase in ROUGE scores and a 0.3% improvement in BERT scores in few-shot settings. |
Mitigating Hallucinations in VLMs: Enhancing Visual Attention via Head-Wise Perturbation (2026.findings-acl)
Copied to clipboard
| Challenge: | Vision–Language Models (VLMs) have demonstrated strong capabilities in tasks that require joint understanding of text and images. |
| Approach: | They propose a strategy that incorporates head-wise attention perturbation via continuous multiplicative noise coupled with a visual-guided loss focused on vision-sensitive text tokens to promote a more balanced attention distribution. |
| Outcome: | The proposed approach outperforms baseline models on three benchmarks and consistently outperformed the baseline model. |
Alleviating Performance Degradation Caused by Out-of-Distribution Issues in Embedding-Based Retrieval (2025.findings-emnlp)
Copied to clipboard
Haotong Bao, Jianjin Zhang, Qi Chen, Weihao Han, Zhengxin Zeng, Ruiheng Chang, Mingzheng Li, Hao Sun, Weiwei Deng, Feng Sun, Qi Zhang
| Challenge: | Recent studies reveal query out-of-distribution issues degrading ANN performance . a distribution regularizer is introduced into the encoder training objective to encourage alignment between query and base embeddings. |
| Approach: | They introduce a distribution regularizer into the encoder training objective to encourage alignment between query and base embeddings. |
| Outcome: | The proposed method consistently improves retrieval performance across multiple datasets. |
Improving Unsupervised Relation Extraction by Augmenting Diverse Sentence Pairs (2023.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies on relation representation learning focus on contrastive learning strategies, but these studies overlook important aspects. |
| Approach: | They propose to use within-sentence pairs augmentation and cross-sentent pairs extraction to increase diversity of positive pairs and strengthen the discriminative power of contrastive learning. |
| Outcome: | The proposed task increases diversity of positive pairs and strengthens discriminative power . it overcomes limitations of traditional Relation Extraction tasks, which require manual annotations . |
SimulBench: Evaluating Language Models with Creative Simulation Tasks (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing benchmarks for large language models do not fully evaluate their potential for broad implementation. |
| Approach: | They propose to use a fixed LLM as a user agent to engage with an LLM to collect dialogues first under different tasks. |
| Outcome: | The proposed framework outperforms LLaMA-3-70b-Chat on 18.55% more cases. |
QTSumm: Query-Focused Summarization over Tabular Data (2023.emnlp-main)
Copied to clipboard
Yilun Zhao, Zhenting Qi, Linyong Nan, Boyu Mi, Yixin Liu, Weijin Zou, Simeng Han, Ruizhe Chen, Xiangru Tang, Yumo Xu, Dragomir Radev, Arman Cohan
| Challenge: | Existing text generation systems that can provide accurate table summaries can facilitate more efficient access to relevant data insights. |
| Approach: | They propose a query-focused task where text generation models have to perform human-like reasoning and analysis over the given table to generate a tailored table summary. |
| Outcome: | The proposed method improves existing baselines on table-to-text generation and large language models by concatenating generated facts to the model input. |
Neural Relation Extraction for Knowledge Base Enrichment (P19-1)
Copied to clipboard
| Challenge: | Existing studies focus on the extraction itself and rely on Named Entity Disambiguation (NED) to map triples into knowledge base (KB) enrichment. |
| Approach: | They propose an end-to-end relation extraction model for knowledge base enrichment based on a neural encoder-decoder model . they propose to extract entities and their relationships from sentences in the form of triples and map the elements of the extracted triples to an existing KB in an end to end manner. |
| Outcome: | The proposed model outperforms state-of-the-art baselines by 15.51% and 8.38% on two real-world datasets. |
Rethinking Expert Trajectory Utilization in LLM Post-training for Mathematical Reasoning (2026.acl-long)
Copied to clipboard
Bowen Ding, Yuhan Chen, Jiayang Lyu, Jiyao Yuan, Qi Zhu, Shuangshuang Tian, Dantong Zhu, Futing Wang, Heyuan Deng, Fei Mi, Lifeng Shang, Tao Lin
| Challenge: | evolving generic Large Language Models into specialized Large Reasoning Models requires effective post-training. |
| Approach: | They propose a plasticity-ceiling framework to harness expert trajectories . they establish the Sequential SFT-then-RL pipeline as the superior standard . |
| Outcome: | The proposed framework overcomes stability and premature convergence deficits in synchronized approaches. |
Learn to Relax with Large Language Models: Solving Constraint Optimization Problems via Bidirectional Coevolution (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Model (LLM)-based optimization has shown promise for autonomous problem solving, but most approaches cast LLMs as passive constraint checkers rather than proactive strategy designers. |
| Approach: | They propose an end-to-end Automated Constraint Optimization method that tightly couples operations-research principles of constraint relaxation with LLM reasoning. |
| Outcome: | Extensive experiments on three challenging COP benchmarks validate AutoCO’s consistent effectiveness and superior performance, especially in hard regimes where current methods degrade. |
StyleDubber: Towards Multi-Scale Style Learning for Movie Dubbing (2024.findings-acl)
Copied to clipboard
Gaoxiang Cong, Yuankai Qi, Liang Li, Amin Beheshti, Zhedong Zhang, Anton Hengel, Ming-Hsuan Yang, Chenggang Yan, Qingming Huang
| Challenge: | Existing methods for movie dubbing break phonemes in scripts, resulting in incomplete phoneme pronunciation and poor identity stability. |
| Approach: | They propose a method that switches dubbing learning from frame level to phoneme level . it uses a multimodal style adaptor to learn pronunciation style from audio . |
| Outcome: | The proposed method improves on two benchmarks, V2C and Grid, and is available on github. |
GuideLLM: Exploring LLM-Guided Conversation with Applications in Autobiography Interviewing (2025.naacl-long)
Copied to clipboard
Jinhao Duan, Xinyu Zhao, Zhuoxuan Zhang, Eunhye Grace Ko, Lily Boddy, Chenan Wang, Tianhao Li, Alexander Rasgon, Junyuan Hong, Min Kyung Lee, Chenxi Yuan, Qi Long, Ying Ding, Tianlong Chen, Kaidi Xu
| Challenge: | Large Language Models (LLMs) have demonstrated their effectiveness in human-guided dialogues, but tasks in the real world are more complex and require greater autonomy from LLMs. |
| Approach: | They propose to characterize LLM-guided conversation into three fundamental components: Goal Navigation, Context Management, Empathetic Engagement and implement an interviewing environment for the evaluation of LLMs. |
| Outcome: | The proposed LLM outperforms baseline LLMs in interviewing quality and autobiography generation quality. |
Masked Conditional Random Fields for Sequence Labeling (2021.naacl-main)
Copied to clipboard
| Challenge: | Conditional Random Fields (CRF) based neural models are among the most performant for sequence labeling problems, but they can sometimes generate illegal sequences of tags. |
| Approach: | They propose a conditional random field-based model that imposes restrictions on candidate paths during both training and decoding phases. |
| Outcome: | The proposed method improves on existing CRF models with near zero additional cost. |
Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems (2025.acl-long)
Copied to clipboard
| Challenge: | Existing reward models focus on human preferences, neglecting verifiable correctness signals. |
| Approach: | They propose a reward system that combines human preference rewards with verifiable correctness signals to provide reliable rewards. |
| Outcome: | The proposed reward agent significantly outperforms vanilla reward models on benchmarks and inference-time best-of-n searches on real-world tasks. |
Loose lips sink ships: Mitigating Length Bias in Reinforcement Learning from Human Feedback (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Experimental results prove that language models can learn from human feedback better, irrespective of sequence length . emergence of length bias often induces the model to favor longer outputs . |
| Approach: | They propose to separate reward modeling from the influence of sequence length by using the Product-of-Experts technique. |
| Outcome: | The proposed approach shows that language models perform better regardless of sequence length . the main expert is focused on understanding human intents, while the biased expert targets the identification and capture of length bias. |
Nirvana: A Specialized Generalist Model With Task-Aware Memory Mechanism (2026.acl-long)
Copied to clipboard
Yuhua Jiang, Shuang Cheng, Yihao Liu, Ermo Hua, Che Jiang, Weigao Sun, Yu Cheng, Feifei Gao, Biqing Qi, Bowen Zhou
| Challenge: | Existing models lack task-guided specialized memory mechanisms . specialized generalist models excel at general language tasks but struggle in specialized domains. |
| Approach: | They propose a specialized generalist model with specialized memory and updater that can optimize for specialized domains. |
| Outcome: | The proposed model matches or surpasses baselines on general benchmarks and achieves lowest perplexity across specialized domains. |
ImgTrojan: Jailbreaking Vision-Language Models with ONE Image (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing studies on the safety of large language models (LLMs) with human values have focused on the integration of multi-modal user input into these models. |
| Approach: | They propose a method to bypass safety constraints of large language models by using poisoned images instead of original textual captions. |
| Outcome: | The proposed attack bypasses safety constraints of large language models (VLMs) by replacing the original textual captions with malicious jailbreak prompts. |
Representation Learning for Information Extraction from Form-like Documents (2020.acl-main)
Copied to clipboard
| Challenge: | Form-like documents like invoices, purchase orders, tax forms and insurance quotes are common in day-to-day business workflows, but current techniques for processing them largely still employ manual effort or brittle and error-prone heuristics for extraction. |
| Approach: | They propose an extraction system that uses knowledge of the types of the target fields to generate extraction candidates and a neural network architecture that learns a dense representation of each candidate based on neighboring words in the document. |
| Outcome: | The proposed system generates extraction candidates based on neighboring words in the document and is interpretable, as shown using loss cases. |
From Scores to Preferences: Redefining Evaluation Paradigm for Speech Quality Reward Modeling (2026.findings-acl)
Copied to clipboard
Yifei Cao, Changhao Jiang, Jiabao Zhuang, Jiajun Sun, Ming Zhang, Zhiheng Xi, Hui Li, Shihan Dou, Yuran Wang, Yunke Zhang, Tao Ji, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Experimental results show that the MOS-aware GRM significantly improves fine-grained speech quality discrimination. |
| Approach: | They propose a MOS-aware reward model that incorporates MOS gap into reward function during reinforcement learning. |
| Outcome: | The proposed model significantly improves fine-grained speech quality discrimination. |
Template-free Prompt Tuning for Few-shot NER (2022.naacl-main)
Copied to clipboard
| Challenge: | Prompt-based methods have been successfully applied in few-shot learning tasks . however, when applied to token-level labeling tasks, it would be time-consuming to enumerate the template queries over all potential entity spans. |
| Approach: | They propose a method to reformulate NER tasks as LM problems without templates. |
| Outcome: | The proposed method is 30.12 times faster than the template-based method under few-shot settings. |
TMATH A Dataset for Evaluating Large Language Models in Generating Educational Hints for Math Word Problems (2025.coling-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are increasingly being applied in education, showing significant potential in personalized instruction, student feedback, and intelligent tutoring systems (ITSs). |
| Approach: | They propose a dataset specifically designed to evaluate LLMs’ ability to generate high-quality hints for Math Word Problems. |
| Outcome: | The proposed dataset shows that LLMs can generate more accurate and contextually appropriate educational hints for math word problems without offering direct answers. |
RethinkCWS: Is Chinese Word Segmentation a Solved Task? (2020.emnlp-main)
Copied to clipboard
| Challenge: | Recent years have seen remarkable success in the use of deep neural networks on Chinese word segmentation (CWS) however, the performance of CWS systems has gradually reached a plateau with the rapid development of deep networks. |
| Approach: | They propose a fine-grained evaluation for existing Chinese word segmentation systems that allows us to diagnose the strengths and weaknesses of existing models. |
| Outcome: | The proposed model can diagnose strengths and weaknesses of existing models and alleviate negative transfer problem when doing multi-criteria learning. |
Role Prompting Guided Domain Adaptation with General Capability Preserve for Large Language Models (2024.findings-naacl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) suffer catastrophic forgetting when tailored to specific domains . authors present a novel approach to manage multi-domain LLM adaptation . |
| Approach: | They propose a strategy to manage multi-domain LLM adaptation using self-distillation and role integration. |
| Outcome: | The proposed model alleviates catastrophic forgetting and inter-domain confusion while maintaining robust general capabilities. |
DocFusion: A Unified Framework for Document Parsing Tasks (2025.findings-acl)
Copied to clipboard
Mingxu Chai, Ziyu Shen, Chong Zhang, Yue Zhang, Xiao Wang, Shihan Dou, Jihua Kang, Jiazheng Zhang, Qi Zhang
| Challenge: | Existing methods for document parsing often employ multiple models, limiting performance . Existing models often employ discrete tokens, whereas recognition relies on continuous coordinates . |
| Approach: | They propose a Gaussian-Kernel Cross-Entropy Loss (GK-CEL) that unifies detection and recognition by enabling generative frameworks to handle both tasks simultaneously. |
| Outcome: | The proposed model performs competitively across four core document parsing tasks. |
AID: Adaptive Integration of Detectors for Safe AI with Language Models (2025.naacl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) are increasingly used to generate human-like text, but safety concerns have emerged with the deployment of LLMs. |
| Approach: | They propose an approach that orchestrates the strengths of multiple pretrained detectors to ensure comprehensive effectiveness in diverse scenarios. |
| Outcome: | The proposed approach can improve the area under the curve (AUC) by 0.07 to 0.21, with a median of 0.12, compared to the best individual detectors developed for specific safety aspects. |
FastBERT: a Self-distilling BERT with Adaptive Inference Time (2020.acl-main)
Copied to clipboard
| Challenge: | Pre-trained language models like BERT have proven to be highly performant, but are often computationally expensive in many practical scenarios. |
| Approach: | They propose a speed-tunable FastBERT with adaptive inference time that can be flexibly adjusted under varying demands. |
| Outcome: | The proposed model achieves promising results in English and Chinese datasets. |
AlphaQT-Bench: Diagnosing the Gap between Financial Code Generation and Quantitative Reasoning in LLMs (2026.findings-acl)
Copied to clipboard
Sichun Luo, Yi Huang, Shichang Meng, Fengyuan Liu, Mukai Li, Qinghua Yao, Zefa Hu, Junlan Feng, Qi Liu
| Challenge: | Existing benchmarks rely on outcome-driven metrics such as profitability and look-ahead bias. |
| Approach: | They propose a diagnostic benchmark for instruction-grounded financial code generation under strict semantic and temporal constraints. |
| Outcome: | The proposed benchmarks show that the models fail under causal, structural, or functional constraints. |
When Models Reason in Your Language: Controlling Thinking Language Comes at the Cost of Accuracy (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Recent Large Reasoning Models (LRMs) with thinking traces have shown strong performance on English reasoning tasks. |
| Approach: | They evaluate two leading LRMs with thinking traces on established benchmark XReasoning and propose directions for future research. |
| Outcome: | The proposed models often revert to English or produce fragmented reasoning in other languages, revealing a substantial gap in the capability of thinking in non-English languages. |
Reasoning with Graphs: Structuring Implicit Knowledge to Enhance LLMs Reasoning (2025.findings-acl)
Copied to clipboard
Haoyu Han, Yaochen Xie, Hui Liu, Xianfeng Tang, Sreyashi Nag, William Headden, Yang Li, Chen Luo, Shuiwang Ji, Qi He, Jiliang Tang
| Challenge: | Large language models (LLMs) have demonstrated remarkable success across a wide range of tasks, however, they still face challenges in reasoning tasks that require understanding and inferring relationships between distinct pieces of information within text sequences. |
| Approach: | They propose to construct explicit graphs from context and leverage them to enhance LLM reasoning performance on reasoning tasks. |
| Outcome: | Extensive experiments show that the proposed method improves both logical reasoning and multi-hop question answering tasks. |
Breaking through Deterministic Barriers: Randomized Pruning Mask Generation and Selection (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing pruning methods focus on a single pruning criterion and lack variety. |
| Approach: | They propose a model pruning strategy that generates several pruning masks randomly and then chooses the optimal mask from the pool of mask candidates. |
| Outcome: | The proposed pruning strategy achieves state-of-the-art performance across eight datasets from GLUE, particularly excelling at high levels of sparsity. |
MDIT-Bench: Evaluating the Dual-Implicit Toxicity in Large Multimodal Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Large Multimodal Models (LMMs) have raised concerns about model toxicity. |
| Approach: | They propose a model to measure the toxicity gap between models and their hard level to determine whether they can handle dual-implicit toxicity. |
| Outcome: | The proposed model can handle dual-implicit toxicity effectively on 13 prominent LMMs, but its performance drops significantly in hard level. |
Few-shot Intent Classification and Slot Filling with Retrieved Examples (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing methods for few-shot learning are based on labeled examples, but they are non-trivial . few-sshot learning is challenging due to the imbalance in the amount of data between the source and target domains. |
| Approach: | They propose retrieval-based methods for intent classification and slot filling tasks . they use a batch-softmax objective to learn similar contextualized representations for spans . |
| Outcome: | The proposed method outperforms previous systems on the CLINC and SNIPS benchmarks. |
STAPO: Selective Trajectory-Aware Policy Optimization for LLM Agent Training (2026.acl-long)
Copied to clipboard
Qiuyi Qi, Tian Liang, Mutian Bao, Jinjian Zhang, Dongnan Liu, Wei Zhou, Linjian Mo, Ming Kong, Jie Liu, Feng Zhang, Qiang Zhu
| Challenge: | Prior work has explored step-level supervision using Shannon-entropy-based uncertainty signals, which conflate inherent state complexity with agent confidence. |
| Approach: | They propose a hierarchical group-based RL framework that leverages normalized entropy to locate outlier steps associated with trajectory neglect and optimizes them via a mechanism of trajectory-aware reward and trajectory-independent penalty. |
| Outcome: | Experiments on ALFWorld, WebShop, and Search-Augmented QA show that STAPO achieves state-of-the-art performance while substantially alleviating trajectory neglect. |
No Free Lunch: Retrieval-Augmented Generation Undermines Fairness in LLMs, Even for Vigilant Users (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Retrieval-augmented generation is widely adopted for its effectiveness and cost-efficiency in mitigating hallucinations. |
| Approach: | They propose a practical three-level threat model from the perspective of user fairness awareness. |
| Outcome: | The proposed model shows that RAG can undermine fairness alignment without fine-tuning or retraining. |
SRAP-Agent: Simulating and Optimizing Scarce Resource Allocation Policy with LLM-based Agent (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing research on the allocation of public scarce resources has limitations due to data scarcity and data scariness. |
| Approach: | They propose a framework that integrates Large Language Models into economic simulations . they conduct extensive policy simulation experiments to verify the framework's effectiveness . |
| Outcome: | The proposed framework bridges the gap between theoretical models and real-world dynamics by integrating large language models into economic simulations. |
KokoroChat: A Japanese Psychological Counseling Dialogue Dataset Collected via Role-Playing by Trained Counselors (2025.acl-long)
Copied to clipboard
| Challenge: | Recent studies have explored using large language models to augment counseling dialogue datasets, but data from real-world counseling environments may suffer from limited diversity and authenticity. |
| Approach: | They propose to use a Japanese psychological counseling dialogue dataset to simulate counselor-client interactions by using open-source LLMs. |
| Outcome: | The proposed model improves the quality of generated counseling responses and the automatic evaluation of counseling dialogues. |
What Makes a Good Order of Examples in In-Context Learning (2024.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) demonstrate impressive few-shot learning capabilities via in-context learning (ICL). |
| Approach: | They propose to use unlabeled data to evaluate order performance . they propose to filter out subsets of orders with label fairness and select the most influential order for each test instance. |
| Outcome: | The proposed method is superior over strong baselines and validates generalizability across settings. |
Uncertainty-Aware Label Refinement for Sequence Labeling (2020.emnlp-main)
Copied to clipboard
| Challenge: | Conditional random fields (CRF) for label decoding have been a problem for many tasks. |
| Approach: | They propose a two-stage label decoding framework that model long-term label dependencies while being much more computationally efficient. |
| Outcome: | The proposed method outperforms the CRF-based methods and greatly accelerates the inference process. |
ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool Use (2025.acl-long)
Copied to clipboard
Junjie Ye, Zhengyin Du, Xuesong Yao, Weijian Lin, Yufei Xu, Zehui Chen, Zaiyuan Wang, Sining Zhu, Zhiheng Xi, Siyu Yuan, Tao Gui, Qi Zhang, Xuanjing Huang, Jiecao Chen
| Challenge: | Effective evaluation of multi-hop tool use is critical for analyzing the understanding, reasoning, and function-calling capabilities of large language models. |
| Approach: | They propose a dataset that provides rigorous evaluation of multi-hop tool use. |
| Outcome: | The proposed model achieves 49.04% accuracy across five model families. |
A Lexicon-Based Supervised Attention Model for Neural Sentiment Analysis (C18-1)
Copied to clipboard
| Challenge: | Existing attention models do not take full advantage of sentiment lexicons, which provide rich sentiment information and play a critical role in sentiment analysis. |
| Approach: | They propose a lexicon-based supervised attention model which allows a neural network to focus on the sentiment content, thus generating sentiment-informative representations. |
| Outcome: | The proposed model outperforms existing models on three large-scale sentiment classification datasets. |
Mitigating Object Hallucinations in MLLMs via Multi-Frequency Perturbations (2025.findings-emnlp)
Copied to clipboard
Shuo Li, Jiajun Sun, Guodong Zheng, Xiaoran Fan, Yujiong Shen, Yi Lu, Zhiheng Xi, Yuming Yang, Wenming Tan, Tao Ji, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Multimodal large language models have demonstrated remarkable performance in visual-language tasks, but their authenticity is often compromised by object hallucinations. |
| Approach: | They propose a multi-frequency perturbation method that leverages both low-frequency and high-frequency features of images to perturb visual feature representations and explicitly suppress redundant frequency-domain features during inference. |
| Outcome: | The proposed method significantly mitigates object hallucinations across various model architectures. |
Distill Visual Chart Reasoning Ability from LLMs to MLLMs (2025.findings-emnlp)
Copied to clipboard
Wei He, Zhiheng Xi, Wanxu Zhao, Xiaoran Fan, Yiwen Ding, Zifei Shan, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | a new method for generating chart annotations is proposed to improve visual reasoning in multimodal large language models. |
| Approach: | They propose a code-as-intermediary translation method for distilling visual reasoning abilities from LLMs to MLLMs. |
| Outcome: | The proposed method is cost-effective, efficient and scalable. |
AdvancedIF: Rubric-Based Benchmarking and Reinforcement Learning for Advancing LLM Instruction Following (2026.acl-long)
Copied to clipboard
Yun He, Wenzhe Li, Hejia Zhang, Songlin Li, Karishma Mandyam, Sopan Khosla, Yuanhao Xiong, Nanshu Wang, Xiaoliang Peng, Beibin Li, Shengjie Bi, Shishir G Patil, Qi Qi, Shengyu Feng, Julian Katz-Samuels, Richard Yuanzhe Pang, Sujan Kumar Gonugondla, Hunter Lang, Yue Yu, Yundi Qian, Maryam Fazel-Zarandi, Licheng Yu, Amine Benhalloum, Hany Hassan Awadalla, Manaal Faruqui
| Challenge: | Recent advances in large language models (LLMs) have shown impressive performance on a range of tasks, yet advanced instruction following (IF) remains a significant challenge. |
| Approach: | They propose a benchmark that features over 1,600 prompts and expert-curated rubrics that assess LLMs’ ability to follow complex, multi-turn, and system-level instructions. |
| Outcome: | The proposed framework improves instruction-following abilities of large language models, achieving a 6.7% gain on AdvancedIF and strong results on public benchmarks. |
Sina Mandarin Alphabetical Words:A Web-driven Code-mixing Lexical Resource (2020.aacl-main)
Copied to clipboard
| Challenge: | Mandarin Alphabetical Words (MAWs) are a key component of Modern Chinese . they are characterized by unique code-mixing idiosyncrasies influenced by language exchanges . |
| Approach: | They propose to construct a large collection of Mandarin Alphabetic Words from Sina Weibo . they propose to use a web-based technique to identify and validate MAWs . |
| Outcome: | The proposed method identifies 16,207 Mandarin Alphabetic Words (MAWs) using a web-based technique . the results show that the proposed method is useful for linguistic research and inquiries . |
Graph-Assisted Large Language Models: A Perspective on Mitigating Intrinsic Limitations (2026.findings-acl)
Copied to clipboard
Haitong Luo, Fali Wang, Weiyao Zhang, Xianren Zhang, Zhiwei Zhang, Tianxiang Zhao, Minhua Lin, Jiahao Zhang, Hui Liu, Xianfeng Tang, Qi He, Suhang Wang, Xuying Meng, Yujun Zhang
| Challenge: | Large language models exhibit intrinsic limitations such as knowledge cutoff, single-threaded reasoning that hinders finer-grained branch and aggregation, and rigid collaboration mechanisms that struggle to coordinate specialized capabilities. |
| Approach: | They propose a taxonomy spanning *Graph-Assisted Knowledge Augmentation*, *Graph Assisted Reasoning and Planning*, and *Graphed LLM Collaboration*. |
| Outcome: | The proposed models show that graphs can augment and correct LLMs and support dynamic coordination among experts and agents in collaborative settings. |
Think Twice, Generate Once: Safeguarding by Progressive Self-Reflection (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models generate coherent and contextually relevant text, but their deployment raises significant concerns about the potential for harmful or inappropriate content. |
| Approach: | They propose a novel inference-time technique that empowers LLMs to self-monitor and correct their outputs dynamically. |
| Outcome: | The proposed method reduces the attack success rate from 77.47% to 5.86%, to Llama-3.1-8B base from 89.70% to 5.56%, and to Qwen2.5-7B-Instruct from 44.44% to 3.84%, without additional training. |
Efficiently Selecting Response Generation Strategies for Synthetic Data Construction by Self-Aligned Perplexity (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Using a small sample of data, we find that perplexity is suboptimal in characterizing “familiarity” . |
| Approach: | They propose a method that assesses a small subset of generated data to estimate suitability for a specific target LLM. |
| Outcome: | The proposed method assesses a small subset of generated data to estimate suitability for a specific target LLM. |
Golden Touchstone: A Comprehensive Bilingual Benchmark for Evaluating Financial Large Language Models (2025.findings-emnlp)
Copied to clipboard
Xiaojun Wu, Junxi Liu, Huan-Yi Su, Zhouchi Lin, Yiyan Qi, Chengjin Xu, Jiajun Su, Jiajie Zhong, Fuwei Wang, Saizhuo Wang, Fengrui Hua, Jia Li, Jian Guo
| Challenge: | Existing financial benchmarks suffer from limited language and task coverage, low-quality datasets, and inadequate adaptability for LLM evaluation. |
| Approach: | They propose a bilingual benchmark for financial LLMs that assesses models’ language understanding and generation capabilities. |
| Outcome: | The proposed bilingual benchmark assesses models’ language understanding and generation capabilities. |
RIMRULE: Improving Tool-Using Language Agents via MDL-Guided Rule Learning (2026.acl-long)
Copied to clipboard
Xiang Gao, Yuguang Yao, Qi Zhang, Kaiwen Dong, Avinash Baidya, Ruocheng Guo, Hilaf Hasson, Kamalika Das
| Challenge: | Large language models (LLMs) struggle to use tools reliably in domain-specific settings. |
| Approach: | They propose a neuro-symbolic approach to adapt large language models to task-specific tools . they propose reusable rules that are distilled from failure traces and injected into the prompt . |
| Outcome: | Experiments show that the proposed approach outperforms prompting-based adaptation methods and complements finetuning. |
Better Robustness by More Coverage: Adversarial and Mixup Data Augmentation for Robust Finetuning (2021.findings-acl)
Copied to clipboard
| Challenge: | Pretrained language models perform poorly under adversarial attacks due to the large search space. |
| Approach: | They propose a method to cover a much larger proportion of the attack search space by adding textual adversarial examples during training. |
| Outcome: | The proposed method covers a much larger proportion of the attack search space. |
LLM×MapReduce: Simplified Long-Sequence Processing using Large Language Models (2025.acl-long)
Copied to clipboard
Zihan Zhou, Chong Li, Xinyi Chen, Shuo Wang, Yu Chao, Zhili Li, Haoyu Wang, Qi Shi, Zhixing Tan, Xu Han, Xiaodong Shi, Zhiyuan Liu, Maosong Sun
| Challenge: | Existing studies have focused on extending the context length of large language models (LLMs) due to their quadratic computational complexity and a lack of high-quality long training examples, most LLMs are trained with a limited window size. |
| Approach: | They propose a training-free framework that enables large language models to effectively process long texts using a divide-and-conquer strategy for comprehensive document understanding. |
| Outcome: | The proposed framework outperforms open-source and commercial long-context LLMs and is compatible with several models. |
Unnatural Error Correction: GPT-4 Can Almost Perfectly Handle Unnatural Scrambled Text (2023.emnlp-main)
Copied to clipboard
| Challenge: | Large language models exhibit remarkable proficiency in many tasks, but much about their inner workings remains unclear. |
| Approach: | They propose a test suite to measure the resilience of Large Language Models (LLMs) when subjected to extensive character-level permutations. |
| Outcome: | The proposed test suite measures the resilience of large language models to scrambled inputs. |
Parameter-free Automatically Prompting: A Latent Pseudo Label Mapping Model for Prompt-based Learning (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing manual label mapping methods that require extra parameters and human knowledge are limited in data. |
| Approach: | They propose a Latent Pseudo Label Mapping method that optimizes the label mapping without human knowledge and extra parameters. |
| Outcome: | The proposed method outperforms the standard SOTA method in few-shot learning tasks and significantly outperformed the standard ALM method which requires extra task-specific prior knowledge. |
HoH: A Dynamic Benchmark for Evaluating the Impact of Outdated Information on Retrieval-Augmented Generation (2025.acl-long)
Copied to clipboard
| Challenge: | Current approaches to addressing knowledge outdating in LLMs struggle with retrieval and generation aspects when handling outdated information. |
| Approach: | They propose a benchmark to evaluate the impact of outdated information on RAG . they use token-level diff algorithms and LLM pipelines to create a large-scale QA dataset . |
| Outcome: | The proposed benchmark analyzes the impact of outdated information on RAG performance. |
Evaluating and Mitigating Object Hallucination in Large Vision-Language Models: Can They Still See Removed Objects? (2025.naacl-long)
Copied to clipboard
| Challenge: | LVLMs often mistakenly determine objects as present in images where they do not exist . authors propose a new benchmark to evaluate object hallucinations by removing objects from images and asking the model whether it can still see the removed objects. |
| Approach: | They propose a benchmark to evaluate object hallucinations by removing objects from images . they propose oDPO, a direct preference optimization objective based on visual objects . |
| Outcome: | The proposed benchmark reduces the likelihood of object hallucinations by removing objects from images and asking the model whether it can still see the removed objects. |
SoulChat: Improving LLMs’ Empathy, Listening, and Comfort Abilities through Fine-tuning with Multi-turn Empathy Conversations (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models (LLMs) are used in psychological counseling to provide universal advice. |
| Approach: | They constructed a multi-turn empathetic conversation dataset with 2 million samples . they found that the model's empathy ability is enhanced when finetuning . |
| Outcome: | Experiments show that large language models can be finetuned to provide empathy . but, when applied to mental health or emotional support conversation, there are three main issues . |
QA-Driven Zero-shot Slot Filling with Weak Supervision Pretraining (2021.acl-short)
Copied to clipboard
| Challenge: | Existing methods to predict slots and their values do not encode enough semantic information, limiting the models’ zero-shot capability. |
| Approach: | They propose a QA-driven slot filling model which extracts slot-filler spans from utterances with a span-based QA model. |
| Outcome: | The proposed model outperforms baselines by over 5% on the SNIPS benchmark. |
An Effective Incorporating Heterogeneous Knowledge Curriculum Learning for Sequence Labeling (2025.acl-short)
Copied to clipboard
| Challenge: | Existing approaches to enhance sequence labeling models require data heterogeneity and additional modules. |
| Approach: | They propose a dual-stage curriculum learning framework specifically designed for sequence labeling tasks. |
| Outcome: | The proposed model improves training and accelerates training, mitigating the slow training issue of complex models. |
When Agents Look the Same: Quantifying Distillation-Induced Similarity in Tool-Use Behaviors (2026.acl-long)
Copied to clipboard
| Challenge: | Existing metrics fail to distinguish mandatory behaviors required for task success from non-mandatory patterns that reflect a model’s autonomous preferences. |
| Approach: | They propose to use response pattern similarity and action graph similarity to isolate non-mandatory behaviors from mandatory behaviors. |
| Outcome: | Evaluating 18 models from 8 providers on -Bench and 2-Bench against Claude Sonnet 4.5, the authors find that within-family model pairs score 5.9 pp higher in response pattern similarity and action graph similarity . |
Advancing E-commerce Merchants Telemarketing with Synthetic Data-Driven LLMs (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are proving broadly applicable across diverse industries, including e-commerce. |
| Approach: | They propose a hybrid data synthesis framework that unifies the input schema with profile and strategy designed by top sales and extracts them via a Multi-task paradigm. |
| Outcome: | The proposed model reaches the performance level of the top 25% of human sales in terms of the final marketing results. |
PrivLM-Bench: A Multi-level Privacy Evaluation Benchmark for Language Models (2024.acl-long)
Copied to clipboard
Haoran Li, Dadi Guo, Donghao Li, Wei Fan, Qi Hu, Xin Liu, Chunkit Chan, Duanyi Yao, Yuan Yao, Yangqiu Song
| Challenge: | generative large language models (LLMs) exhibit surprising capability and integrate previous tasks into a unified text generation formulation. |
| Approach: | They propose a privacy evaluation benchmark to quantify the privacy leakage of language models. |
| Outcome: | The proposed benchmark compares PPLMs with different privacy implementations to find out how privacy leakage is handled. |
Cross-Linguistic Syntactic Difference in Multilingual BERT: How Good is It and How Does It Affect Transfer? (2022.emnlp-main)
Copied to clipboard
| Challenge: | Multilingual BERT (mBERT) has demonstrated considerable cross-lingual syntactic ability, but it is not well understood what leads to this variation and whether it fairly reflects difference between languages. |
| Approach: | They propose to use multilingual BERT to enable zero-shot cross-lingual transfer of syntactic knowledge between different languages by generating grammatical relations in 24 different languages. |
| Outcome: | The results show that the distance between the distributions of different languages is highly consistent with the syntactic difference in terms of linguistic formalisms. |
CiteEval: Principle-Driven Citation Evaluation for Source Attribution (2025.acl-long)
Copied to clipboard
Yumo Xu, Peng Qi, Jifan Chen, Kunlun Liu, Rujun Han, Lan Liu, Bonan Min, Vittorio Castelli, Arshit Gupta, Zhiguo Wang
| Challenge: | Current evaluation frameworks rely on NLI to assess binary or ternary support from cited sources, which is suboptimal for citation evaluation. |
| Approach: | They propose a citation evaluation framework based on fine-grained citation ratings within a broad context and construct a multi-domain benchmark with high-quality human annotations. |
| Outcome: | The proposed framework provides a high-quality human annotation benchmark and a suite of model-based metrics that exhibit strong correlation with human judgments. |
Learn to Combine Linguistic and Symbolic Information for Table-based Fact Verification (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods for fact verification lack attention to combine linguistic and symbolic information. |
| Approach: | They propose a graph-based reasoning approach that learns to combine linguistic and symbolic information effectively. |
| Outcome: | The proposed method can combine linguistic and symbolic information effectively. |
Knowledge-Enhanced Named Entity Disambiguation for Short Text (2020.aacl-main)
Copied to clipboard
| Challenge: | Existing methods for named entity disambiguation are weak for short text . performance of existing methods drops dramatically for short texts . |
| Approach: | They propose a knowledge-enhanced method for named entity disambiguation . they use factual knowledge graph and conceptual knowledge graph to provide additional knowledge . |
| Outcome: | The proposed method achieves significant improvement on a large manually annotated short-text dataset and the state-of-the-art on three standard datasets. |
GoViG: Goal-Conditioned Visual Navigation Instruction Generation via Multimodal Reasoning (2026.findings-acl)
Copied to clipboard
Fengyi Wu, Yifei Dong, Yilong Dai, Guangyu Chen, Qifeng Wu, Huiting Huang, Hang Wang, Qi Dai, Alexander G Hauptmann, Zhi-Qi Cheng
| Challenge: | Current methods for instruction generation depend on privileged inputs such as semantic maps, landmark annotations, and panoramic views. |
| Approach: | They propose a task that generates coherent navigation instructions from egocentric visual observations. |
| Outcome: | The proposed task generates coherent navigation instructions from egocentric visual data . the proposed task improves performance over state-of-the-art methods in BLEU-4 and CIDEr scores . |
A Unified Dialogue User Simulator for Few-shot Data Augmentation (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to augment large-scale task-oriented dialogues rely on annotated data. |
| Approach: | They propose to build a unified dialogue user simulation model by pre-training on publicly available datasets. |
| Outcome: | The proposed model can be tuned on a target domain with few-shot data. |
Context Compression for Auto-regressive Transformers with Sentinel Tokens (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing Transformer-based LLMs have limited performance due to complexity of attention module . key-value cache is the major memory footprint and inference latency problem . |
| Approach: | They propose a plug-and-play approach that incrementally compresses token activation into compact ones . they also profile the benefit of context compression on improving the system throughout . |
| Outcome: | The proposed approach reduces memory footprint and inference latency by compressing tokens into compact ones. |
Length Control in Abstractive Summarization by Pretraining Information Selection (2022.acl-long)
Copied to clipboard
| Challenge: | Existing length-controllable summarization models generate summaries as long as training data . current methods only control lengths at decoding stage, but adapt to desired lengths . |
| Approach: | They propose a length-aware attention mechanism to adapt the encoding of the source based on the desired length. |
| Outcome: | The proposed method produces high-quality summaries with desired lengths and even those short lengths never seen in the training data. |
EvoWiki: Evaluating LLMs on Evolving Knowledge (2025.acl-long)
Copied to clipboard
Wei Tang, Yixin Cao, Yang Deng, Jiahao Ying, Bo Wang, Yizhe Yang, Yuyue Zhao, Qi Zhang, Xuanjing Huang, Yu-Gang Jiang, Yong Liao
| Challenge: | Existing knowledge evolution benchmarks are static and fail to capture the evolving nature of LLMs and knowledge. |
| Approach: | They propose an evolving dataset that categorizes information into stable, evolved, and uncharted states. |
| Outcome: | The proposed dataset is auto-updatable and enables evaluation of continuously changing knowledge and newly released LLMs. |
SafeScientist: Enhancing AI Scientist Safety for Risk-Aware Scientific Discovery (2025.emnlp-main)
Copied to clipboard
Kunlun Zhu, Jiaxun Zhang, Ziheng Qi, Nuoxing Shang, Zijia Liu, Peixuan Han, Yue Su, Haofei Yu, Jiaxuan You
| Challenge: | Recent advances in large language model (LLM) agents have significantly accelerated scientific discovery automation, yet raised critical ethical and safety concerns. |
| Approach: | They propose a framework to enhance safety and ethical responsibility in AI-driven scientific exploration. |
| Outcome: | The proposed framework significantly improves safety performance by 35% compared to traditional frameworks. |
A Progressive Framework for Role-Aware Rumor Resolution (2022.coling-1)
Copied to clipboard
| Challenge: | Existing methods for rumor resolution ignore intrinsic propagation mechanisms of rumors and present poor adaptive ability when unprecedented news emerges. |
| Approach: | They propose to identify triggering posts and exploit their characteristics to facilitate rumor verification. |
| Outcome: | The proposed model and scheme exploits rumor diffusion patterns and linguistic features to facilitate verification. |
Escaping the Echo Trap: On Credit Assignment Failure in Multi-turn LLM Self-Reflection (2026.acl-long)
Copied to clipboard
Linxuan Du, Guangquan Xue, Xiaobo Liang, Qipeng Huang, Yuyang Ding, Xinyu Shi, Zhang Yijun, Ji Qi, Wenpeng Zhu, Juntao Li, Min Zhang
| Challenge: | Existing methods for multi-turn self-reflection are limited by the Echo Trap problem . the model is limited by its inherent capabilities and repeats earlier reflections to preserve reward signals . |
| Approach: | They propose a tree-structured extension of GRPO for multi-turn self-reflection which enables more accurate advantage estimation. |
| Outcome: | The proposed method mitigates behavior collapse and improves performance across benchmarks. |
Can Language Models Understand Physical Concepts? (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing language models do not understand basic physical concepts in the human world. |
| Approach: | They propose a method to transfer embodied knowledge from visual models to LMs . they use visual concepts and embodies concepts learned from interaction with the world . |
| Outcome: | The proposed method achieves comparable performance with scaling up parameters of LMs 134. |
ConvLab: Multi-Domain End-to-End Dialog System Platform (P19-3)
Copied to clipboard
Sungjin Lee, Qi Zhu, Ryuichi Takanobu, Zheng Zhang, Yaoqin Zhang, Xiang Li, Jinchao Li, Baolin Peng, Xiujun Li, Minlie Huang, Jianfeng Gao
| Challenge: | ConvLab is an open-source multi-domain end-to-end dialog system platform . it allows researchers to quickly set up experiments with reusable components and compare a large set of different approaches in common environments. |
| Approach: | They propose to use an open-source multi-domain end-to-end dialog system platform to train and evaluate dialog bots in common environments. |
| Outcome: | The proposed system enables researchers to quickly set up experiments with reusable components and compare a large set of different approaches in common environments. |
Learning When to Concentrate or Divert Attention: Self-Adaptive Attention Temperature for Neural Machine Translation (D18-1)
Copied to clipboard
| Challenge: | Neural Machine Translation models treat decoding at each time step equally with the same matrix . conventional methods treat decoder outputs at all time steps with the identical weight matrix causing inaccuracy . |
| Approach: | They propose a model with a mechanism to control the softness of attention by means of an attention temperature. |
| Outcome: | The proposed model outperforms baseline models on Chinese-English and English-Vietnamese translations. |
TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing (2021.acl-demo)
Copied to clipboard
Xiao Wang, Qin Liu, Tao Gui, Qi Zhang, Yicheng Zou, Xin Zhou, Jiacheng Ye, Yongxin Zhang, Rui Zheng, Zexiong Pang, Qinzhuo Wu, Zhengyan Li, Chong Zhang, Ruotian Ma, Zichu Fei, Ruijian Cai, Jun Zhao, Xingwu Hu, Zhiheng Yan, Yiding Tan, Yuan Hu, Qiyuan Bian, Zhihua Liu, Shan Qin, Bolin Zhu, Xiaoyu Xing, Jinlan Fu, Yue Zhang, Minlong Peng, Xiaoqing Zheng, Yaqian Zhou, Zhongyu Wei, Xipeng Qiu, Xuanjing Huang
| Challenge: | Existing approaches to textual robustness evaluation focus on slightly modifying the input data, which maintains the original meaning and results in a different prediction. |
| Approach: | They propose a multilingual robustness evaluation toolkit for NLP that integrates universal text transformations, task-specific transformations and adversarial attack. |
| Outcome: | The toolkit includes universal text transformation, task-specific transformation, adversarial attack, subpopulation, and their combinations to provide comprehensive robustness analyses. |
LONG2RAG: Evaluating Long-Context & Long-Form Retrieval-Augmented Generation with Key Point Recall (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Retrieval-augmented generation (RAG) is a promising approach to address limitations of fixed knowledge in large language models. |
| Approach: | They propose a benchmark and a metric to assess LLMs' ability to generate long-form responses that exploit retrieved information. |
| Outcome: | The proposed benchmarks lack a comprehensive evaluation method to assess LLMs' ability to generate long-form responses that effectively exploits retrieved information. |
Stanza: A Python Natural Language Processing Toolkit for Many Human Languages (2020.acl-demos)
Copied to clipboard
| Challenge: | Existing tools that support only a few major languages are under-optimized for accuracy due to a focus on efficiency or use of less powerful models. |
| Approach: | They introduce a Python natural language processing toolkit that supports 66 languages . they train Stanza on 112 datasets and show it generalizes well on all languages compared to other tools . |
| Outcome: | The proposed toolkit performs well on 112 datasets and is compatible with the popular Java CoreNLP software. |
Prompt-based Zero-shot Text Classification with Conceptual Knowledge (2023.acl-srw)
Copied to clipboard
| Challenge: | Existing approaches to pre-training language models rely on verbalizers to translate the predicted vocabulary to task-specific labels. |
| Approach: | They propose a framework that incorporates conceptual knowledge for text classification in the extreme zero-shot setting. |
| Outcome: | The proposed framework outperforms prompt-based approaches on four widely-used datasets for sentiment analysis and topic detection on the same experimental settings. |
Named Entity Recognition in Multi-level Contexts (2020.aacl-main)
Copied to clipboard
| Challenge: | Existing methods for named entity recognition are unsatisfactory for recognizing entities in limited or ambiguous sentence-level contexts. |
| Approach: | They propose a framework to incorporate multi-level contexts for named entity recognition using TagLM as a baseline model and an auxiliary task to mine word-level contextual information. |
| Outcome: | The proposed framework is based on a set of sentence-level contexts and a document-level task to mine word-level contextual information. |
DSRM: Boost Textual Adversarial Training with Distribution Shift Risk Minimization (2023.acl-long)
Copied to clipboard
| Challenge: | Existing adversarial training methods require multi-step gradient ascents or word substitutions to obtain adversarials, which impairs the effectiveness of adversariarial training. |
| Approach: | They propose a procedure for instead adversarial training with only clean data that estimates the adversarials loss by perturbing the input data’s probability distribution rather than their embeddings. |
| Outcome: | The proposed procedure reduces time consumption by up to 70% compared to current best-performing adversarial training methods. |
Tasty Burgers, Soggy Fries: Probing Aspect Robustness in Aspect-Based Sentiment Analysis (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing ABSA test sets cannot be used to distinguish the sentiment of the target aspect from the non-target aspect. |
| Approach: | They propose a simple but effective approach to enrich ABSA test sets by disentangle the confounding sentiments of non-target aspects from the target aspect’s sentiment. |
| Outcome: | The proposed model can distinguish the sentiment of the non-target aspects from the target aspect’s sentiment by using the Aspect Robustness Test Set (ARTS). |
Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting (2025.findings-acl)
Copied to clipboard
Hao Feng, Shu Wei, Xiang Fei, Wei Shi, Yingdong Han, Lei Liao, Jinghui Lu, Binghong Wu, Qi Liu, Chunhui Lin, Jingqun Tang, Hao Liu, Can Huang
| Challenge: | Current document image parsing solutions rely on specialized models or generate content autoregressively. |
| Approach: | They propose a multimodal document image parsing model that integrates specialized models with autogeneous content generation. |
| Outcome: | The proposed model achieves state-of-the-art performance across diverse page-level and element-level settings while ensuring superior efficiency. |
Towards Robust Pruning: An Adaptive Knowledge-Retention Pruning Strategy for Language Models (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing pruning strategies struggle to enhance robustness against adversarial attacks when continually increasing model sparsity and require a retraining process. |
| Approach: | They propose a pruning strategy that replicates embedding space and feature space of dense language models and aims to conserve more pre-trained knowledge during the pruning process. |
| Outcome: | The proposed pruning strategy replicates embedding space and feature space of dense language models, aiming to conserve more pre-trained knowledge during the pruning process. |
Modeling Semantic Compositionality with Sememe Knowledge (P19-1)
Copied to clipboard
| Challenge: | Semantic compositionality (SC) is defined as the phenomenon that the meaning of a complex linguistic unit can be composed of the meanings of its constituents. |
| Approach: | They propose to incorporate sememes into SC models and employ them in learning multiword expressions. |
| Outcome: | The proposed models achieve significant performance boost compared to baseline methods without sememe knowledge. |
Fisher-Driven Adaptive Locating for Knowledge Editing in Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for locating and editing static knowledge are costly and risk catastrophic forgetting or error. |
| Approach: | They propose a Fisher-driven adaptation-aware locating strategy that dynamically identifies which model components should be edited for a given knowledge update. |
| Outcome: | Experiments on standard benchmarks show that FiDAL improves editing effectiveness and knowledge preservation across multiple editing methods. |
NewsBERT: Distilling Pre-trained Language Model for Intelligent News Application (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing language models are pre-trained and distilled on general corpus like Wikipedia, which has gaps with the news domain and may be suboptimal for news intelligence. |
| Approach: | They propose a method to distill existing language models on Wikipedia to enable efficient news intelligence. |
| Outcome: | The proposed model can be used to build and test a news intelligence application on Wikipedia and Wikipedia. |
LoRACoE: Improving Large Language Model via Composition-based LoRA Expert (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies show that the Mixture of Experts architecture improves performance of large language models. |
| Approach: | They propose a method to build static experts using LoRA parameters . they propose to use rank-level parameters to build experts based on rank-based parameters based in LoRA module. |
| Outcome: | The proposed method improves task performance across a broader range of tasks. |
QCRD: Quality-guided Contrastive Rationale Distillation for Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent research has focused on smaller, task-specific models enhanced by distilling knowledge from LLMs, but the diversity and quality of negative knowledge remains understudied. |
| Approach: | They propose a quality-guided contrastive rationale distillation framework that aims to enhance reasoning capabilities through contrastive knowledge learning. |
| Outcome: | The proposed method consistently outperforms existing distillation techniques yielding higher-quality rationales. |
One2Set: Generating Diverse Keyphrases as a Set (2021.acl-long)
Copied to clipboard
| Challenge: | Recent keyphrase generation models are wrongly imposing a predefined order on keyphrases . a new training paradigm is proposed to concatenate keyphrase sequences in parallel . |
| Approach: | They propose a training paradigm that concatenates keyphrases in a predefined order . they propose combining a fixed set of learned control codes with a bipartite matching mechanism . |
| Outcome: | The proposed model outperforms the state-of-the-art methods on multiple benchmarks. |
PrivaCI-Bench: Evaluating Privacy with Contextual Integrity and Legal Compliance (2025.acl-long)
Copied to clipboard
Haoran Li, Wenbin Hu, Huihao Jing, Yulin Chen, Qi Hu, Sirui Han, Tianshu Chu, Peizhao Hu, Yangqiu Song
| Challenge: | Recent advances in generative large language models (LLMs) have enabled wider applicability, accessibility, and flexibility. |
| Approach: | They propose a contextual privacy evaluation benchmark that covers the entire relevant social context through private information flows. |
| Outcome: | The proposed benchmarks cover legal compliance, real court cases, privacy policies, and synthetic data. |
Once is Enough: A Light-Weight Cross-Attention for Fast Sentence Pair Modeling (2023.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies suggest that transformer-based models perform cross-attention over input pairs, leading to computational cost. |
| Approach: | They propose a lightweight cross-attention mechanism that performs query encoding only once while modeling the query-candidate interaction in parallel. |
| Outcome: | The proposed model speeds up sentence pairing by over 113x while achieving comparable performance as the more expensive models. |
Beyond Scaling: Measuring and Predicting the Upper Bound of Knowledge Retention in Language Model Pre-Training (2026.acl-long)
Copied to clipboard
Changhao Jiang, Ming Zhang, Yifei Cao, Junjie Ye, Xiaoran Fan, Shihan Dou, Zhiheng Xi, Jiajun Sun, Yi Dong, Yujiong Shen, Jingqi Tong, Baoyu Fan, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing methods to predict performance of large language models are lacking . authors propose a size-dependent mutual information predictor for closed-book question answering accuracy . |
| Approach: | They propose a size-dependent mutual information predictor that integrates knowledge frequency, knowledge specificity, and model size to forecast closed-book question answering accuracy. |
| Outcome: | The proposed method outperforms baseline models and achieves R2 > 0.7 in predicting QA accuracy without additional training. |
DialogVED: A Pre-trained Latent Variable Encoder-Decoder Model for Dialog Response Generation (2022.acl-long)
Copied to clipboard
Wei Chen, Yeyun Gong, Song Wang, Bolun Yao, Weizhen Qi, Zhongyu Wei, Xiaowu Hu, Bartuer Zhou, Yi Mao, Weizhu Chen, Biao Cheng, Nan Duan
| Challenge: | Existing pre-trained dialog models shed light on various downstream tasks in natural language processing (NLP). |
| Approach: | They propose a dialog pre-training framework that introduces latent variables into the enhanced encoder-decoder pre-train framework to increase relevance and diversity of responses. |
| Outcome: | The proposed model achieves state-of-the-art on personaChat, DailyDialog, and DSTC7-AVSD datasets. |
TextObfuscator: Making Pre-trained Language Model a Privacy Protector via Obfuscating Word Representations (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing inference services are plagued by privacy concerns, such as sharing sensitive data with service providers. |
| Approach: | They propose a framework for protecting inference privacy by applying random perturbations to clustered representations. |
| Outcome: | The proposed framework protects inference privacy by applying random perturbations to clustered representations. |
When and Why Are Pre-Trained Word Embeddings Useful for Neural Machine Translation? (N18-2)
Copied to clipboard
| Challenge: | Pre-trained word embeddings have proven to be invaluable for improving performance in natural language analysis tasks where large-scale parallel corpora cannot be obtained. |
| Approach: | They perform five sets of experiments to analyze when pre-trained word embeddings can be useful in NMT tasks. |
| Outcome: | The embeddings provide gains of up to 20 BLEU points in the most favorable setting. |
Navigating the OverKill in Large Language Models (2024.acl-long)
Copied to clipboard
Chenyu Shi, Xiao Wang, Qiming Ge, Songyang Gao, Xianjun Yang, Tao Gui, Qi Zhang, Xuanjing Huang, Xun Zhao, Dahua Lin
| Challenge: | Recent studies have highlighted a tendency among large language models to refuse to answer benign queries. |
| Approach: | They propose a model-agnostic approach to reduce excessive attention to harmful words like ‘kill’ and a method to decode the next-token predictions by contrastive decoding. |
| Outcome: | The proposed approach reduces the refusal rate by 20% while having little impact on safety. |
The SIFo Benchmark: Investigating the Sequential Instruction Following Ability of Large Language Models (2024.findings-emnlp)
Copied to clipboard
Xinyi Chen, Baohao Liao, Jirui Qi, Panagiotis Eustratiadis, Christof Monz, Arianna Bisazza, Maarten Rijke
| Challenge: | Current evaluation resources for instruction following focus on single task instructions, but the instruction sequences in these benchmarks often lack coherence. |
| Approach: | They propose to evaluate models’ abilities to follow multiple instructions through sequential instruction following tasks using four tasks to assess different aspects of sequential instruction followed. |
| Outcome: | The proposed benchmark outperforms open-source and closed-source models on four tasks assessing different aspects of sequential instruction following. |
Example Quality Matters: Multi-Aspects Example Augmentation for Private Library Programming (2026.acl-long)
Copied to clipboard
Yuhao Li, Haifeng Sun, Xuesong Zhang, Shu Yao, Haoyu Zheng, Yvchuan Wang, Huazheng Wang, Zirui Zhuang, Qi Qi, Jianxin Liao, Jingyu Wang
| Challenge: | Existing approaches to code generation fail to consider the quality of retrieved examples. |
| Approach: | They propose a retrieval-augmented generation method that combines existing API examples to improve complexity and readability. |
| Outcome: | The proposed method achieves up to 22% accuracy improvement over baseline methods. |
KV-Latent: Dimensional-level KV Cache Reduction with Frequency-aware Rotary Positional Embedding (2025.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) based on Transformer Decoders have become the preferred choice for conversational generative AI. |
| Approach: | They propose a paradigm called KV-Latent to reduce the KV cache footprint and improve inference speed by down-sampling the Key-Value vector dimensions into a latent space. |
| Outcome: | The proposed paradigm reduces the KV Cache footprint and improves inference speed with a small amount of extra training, less than 1% of pre-training takes. |
Capsule Network with Interactive Attention for Aspect-Level Sentiment Classification (D19-1)
Copied to clipboard
| Challenge: | Existing methods for aspect-level sentiment classification are limited for dealing with overlapped features. |
| Approach: | They propose to use capsule network to construct vector-based feature representation and cluster features by an EM routing algorithm to model semantic relationship between aspect terms and context. |
| Outcome: | The proposed model achieves state-of-the-art on three datasets. |
Re-Examine Distantly Supervised NER: A New Benchmark and a Simple Approach (2025.coling-main)
Copied to clipboard
| Challenge: | Existing DS-NER approaches rely on large validation sets and test set for tuning inappropriately. |
| Approach: | They propose a method where training data is annotated using domain dictionaries and test data is analyzed by domain experts. |
| Outcome: | The proposed method reduces the need for labor-intensive manual annotations but rely on large human labeled validation set. |
Few-shot Joint Multimodal Aspect-Sentiment Analysis Based on Generative Multimodal Prompt (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing studies require massive labeled data to train models for multimodal data analysis. |
| Approach: | They propose a novel multimodal prompt model that captures specific aspect terms in a few-shot scenario. |
| Outcome: | The proposed model outperforms baselines on two MABSA-related tasks on a few-shot dataset. |
Answering Complex Open-domain Questions Through Iterative Query Generation (D19-1)
Copied to clipboard
| Challenge: | Currently, one-step retrieve-and-read question answering systems cannot answer such questions because they rarely contain retrievable clues about the missing entity. |
| Approach: | They propose a multi-step approach to retrieve relevant content with the question, then reading the paragraphs returned by the information retrieval component to arrive at the final answer. |
| Outcome: | The proposed model outperforms the best previously published model despite not using pretrained language models such as BERT. |
Rhombus: Incentivizing Coordination in Parallel Thinking through Reinforcement Learning (2026.findings-acl)
Copied to clipboard
Ziyuan Nan, Qi Yi, Di Huang, Yutong Wu, Guanhua Huang, Xue Gong, Kejiao Li, Yuhao Jiang, Chenchen Zhang, Zenan Xu, Xing Hu, Bo Zhou
| Challenge: | Parallel thinking is a promising avenue for scaling test-time compute in Large Language Models . however, coordinating the exploration and aggregation stages remains challenging . |
| Approach: | They propose a parallel thinking framework that explicitly incentivizes coordination between components via end-to-end reinforcement learning. |
| Outcome: | The proposed framework improves accuracy by 6.0% over long chain-of-thought baselines while reducing wall-clock latency by 39.4% under matched token budgets. |
Controllable Memory Usage: Balancing Anchoring and Innovation in Long-Term Human–Agent Interaction (2026.acl-long)
Copied to clipboard
Zisu Huang, Muzhao Tian, Xiaohua Wang, Jingwen Xu, Zhengkang Guo, Qi Qian, Kaitao Song, Jiakang Yuan, Changze Lv, Xiaoqing Zheng
| Challenge: | Existing systems that use memory as an "all-or-nothing" approach to memory usage are often static and rely on experience-following tendencies. |
| Approach: | They propose a framework that allows users to dynamically regulate memory reliance by adding context into the model's prompt. |
| Outcome: | The proposed model outperforms prompting and memory masking strategies in multiple scenarios. |
Reference-free Summarization Evaluation via Semantic Correlation and Compression Ratio (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing evaluation metrics for summarization use human annotations as reference. |
| Approach: | They propose a new automatic reference-free evaluation metric that compares semantic distribution between source document and summary by pretrained language models and considers summary compression ratio. |
| Outcome: | The proposed metric is more consistent with human evaluation in terms of coherence, consistency, relevance and fluency. |
Structured Object Language Modeling (SO-LM): Native Structured Objects Generation Conforming to Complex Schemas with Self-Supervised Denoising (2024.emnlp-industry)
Copied to clipboard
| Challenge: | Structured objects generation is a challenging problem for existing Large Language Models. |
| Approach: | They propose a self-supervised method to train an LLM to perform the task natively without prompt-engineering. |
| Outcome: | The proposed method matches or outperforms prompt-engineered state-of-the-art models while being more cost-efficient. |
ModularMoE: Fast LLM Customization with Parameter-Sharing Mixture-of-Experts for Low-Resource Settings (2026.findings-acl)
Copied to clipboard
Jiaxing Liu, Qi Qi, Haifeng Sun, Dunjun Li, Zirui Zhuang, Bo He, Xiang Yang, Cong Liu, Jianxin Liao, Jingyu Wang
| Challenge: | Large Language Models impose significant computational and storage burdens on personal devices . existing customization approaches incur excessive computational costs or lead to suboptimal performance . |
| Approach: | They propose a training framework that converts pre-trained LLMs into parameter-sharing MoE models for lightweight deployment. |
| Outcome: | The proposed training framework outperforms state-of-the-art training frameworks at the same sparsity level while delivering up to 2.71 inference speedup. |