Papers by Jin Jin
Efficiently Aligned Cross-Lingual Transfer Learning for Conversational Tasks using Prompt-Tuning (2024.findings-eacl)
Copied to clipboard
| Challenge: | Cross-lingual transfer of language models trained on high-resource languages such as English has been limited due to the high cost of obtaining non-English conversational data. |
| Approach: | They introduce a parallel and large-scale multilingual conversation dataset that is used for cross-lingual alignment pretraining by translating the English-only Schema-Guided Dialogue dataset into 105 other languages. |
| Outcome: | The proposed model performs well on slot-filling and intent classification tasks, and is able to perform well in other languages. |
Restoring and Mining the Records of the Joseon Dynasty via Neural Language Modeling and Machine Translation (2021.naacl-main)
Copied to clipboard
| Challenge: | voluminous historical records are difficult to fully utilize since they are written in ancient languages and some parts are damaged over time. |
| Approach: | They propose a multi-task learning approach to restore and translate historical documents using a self-attention mechanism. |
| Outcome: | The proposed approach improves the accuracy of the translation task over baselines without multi-task learning. |
Enhancing Effectiveness and Robustness in a Low-Resource Regime via Decision-Boundary-aware Data Augmentation (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods to augment textual data are limited due to the discrete characteristics of the textual dataset. |
| Approach: | They propose a decision-boundary-aware data augmentation strategy to enhance robustness using pretrained language models by shifting latent features closer to the decision boundary and reconstruction to generate an ambiguous version with a soft label. |
| Outcome: | The proposed method performs better than existing methods and is extensible with curriculum data augmentation. |
Evaluating Answer Leakage Robustness of LLM Tutors against Adversarial Student Attacks (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are increasingly used in education, yet their default usefulness conflicts with pedagogical principles. |
| Approach: | They propose an adversarial student agent that they fine-tune to jailbreak LLM-based tutors and propose a benchmark to evaluate tutor robustness. |
| Outcome: | The proposed model fine-tunes to jailbreak LLM-based tutors, and shows that they perform well under adversarial student attacks. |
TRAVEL: Tag-Aware Conversational FAQ Retrieval via Reinforcement Learning (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods aim to fully utilize the dynamic conversation context to enhance the semantic association between the user query and FAQ questions, but they are limited by noise and e.g., users may click questions they don't like, leading to inaccurate semantics modeling. |
| Approach: | They propose to introduce tags of FAQ questions to reduce noise in the conversation context and integrate them into a reinforcement learning framework to minimize the negative impact of irrelevant information. |
| Outcome: | The proposed method can eliminate irrelevant information and minimize negative impact of irrelevant information in the dynamic conversation context. |
PruneCD: Contrasting Pruned Self Model to Improve Decoding Factuality (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to decode early exit logits in large language models are lacking in factuality and accuracy. |
| Approach: | They propose a contrastive decoding method that constructs the amateur model via layer pruning rather than early exit. |
| Outcome: | The proposed method improves factuality with minimal inference overhead and is robust and practical. |
Connect-the-Dots: Bridging Semantics between Words and Definitions via Aligning Word Sense Inventories (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing supervised models struggle to make correct predictions on rare word senses due to limited training data. |
| Approach: | They propose a gloss alignment algorithm that can align definition sentences with the same meaning from different sense inventories to collect rich lexical knowledge. |
| Outcome: | The proposed method outperforms previous methods on both frequent and rare word senses. |
Modeling Hierarchical Syntax Structure with Triplet Position for Source Code Summarization (2022.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to describe the syntax structure of code are lacking in retaining the semantic structure of source code. |
| Approach: | They propose to use a triplet position to model hierarchical syntax structure of code by introducing a graph neural network and Transformer to preserve the structural and sequential information of code. |
| Outcome: | The proposed model preserves the structural and sequential information of code and a pointer-generator network that pays attention to both the structure and sequential tokens of code for a better summary generation. |
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%. |
Prior Knowledge and Memory Enriched Transformer for Sign Language Translation (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for sign language translation do not explore all of them . visual and textual understanding and additional prior knowledge learning are challenging . |
| Approach: | They propose a method which integrates auxiliary information into vanilla transformer for SLT . they use visual-textual context information and additional auxiliary knowledge of a word . |
| Outcome: | The proposed method improves the understanding of sign language videos with visual and textual understanding and additional prior knowledge learning. |
Causally Testing Gender Bias in LLMs: A Case Study on Occupational Bias (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing studies have shown that large language models can cause harmful, human-like biases against various demographics. |
| Approach: | They propose a causal formulation for bias measurement in generative language models based on a list of desiderata for designing robust bias benchmarks and a bias-measuring procedure to investigate occupational gender bias. |
| Outcome: | The proposed framework is generalizable and can be extended to include other datasets. |
ASPO: Adaptive Sentence-Level Preference Optimization for Fine-Grained Multimodal Reasoning (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent advances have extended DPO to multimodal scenarios, achieving strong performance. |
| Approach: | They propose to use a sentence-level preference optimization technique to optimize individual sentences for more precise preference optimization without additional models or parameters. |
| Outcome: | Experiments show that Adaptive Sentence-level Preference Optimization significantly improves the alignment of multimodal models. |
Less is More: Mitigating Multimodal Hallucination from an EOS Decision Perspective (2024.acl-long)
Copied to clipboard
| Challenge: | Extensive research has shed light on the origins of multimodal hallucinations, including the inability of vision encoders to represent finegrained visual details and model reliance on inherent parametric knowledge such as language priors and statistical biases. |
| Approach: | They propose to use EOS to terminate generation of large multimodal models by comparing the generated text with the image to mitigate multimodal hallucinations. |
| Outcome: | The proposed method significantly improves the hallucination performance of Large Multimodal Models without additional data or knowledge. |
CODERL+: Improving Code Generation via Reinforcement with Execution Semantics Alignment (2026.acl-long)
Copied to clipboard
Xue Jiang, Yihong Dong, Mengyang Liu, Deng Hongyi, Tian Wang, Yongding Tao, Zhi Jin, Wenpin Jiao, Ge Li
| Challenge: | Large Language Models excel at code generation by learning from vast code corpora, but a fundamental semantic gap remains between training on textual patterns and the goal of functional correctness . reinforcement learning with verifiable rewards (RLVR) approaches are inefficient for establishing a well-aligned connection between the textual representation of code and its execution semantics. |
| Approach: | They propose a novel approach that integrates execution semantics alignment into the RLVR training pipeline for code generation. |
| Outcome: | The proposed model outperforms baseline training and RLVR and shows strong applicability across RL and LLMs. |
Agent-RewardBench: Towards a Unified Benchmark for Reward Modeling across Perception, Planning, and Safety in Real-World Multimodal Agents (2025.acl-long)
Copied to clipboard
| Challenge: | Multimodal Large Language Models (MLLMs) are developing but lack external feedback . there is no clear on how to select reward models for agents . |
| Approach: | They propose a benchmark to evaluate agent reward modeling ability in MLLMs . they use multiple dimensions and real-world agent scenarios evaluation . |
| Outcome: | The proposed benchmark evaluates agent performance in multimodal large language models . it covers perception, planning, and safety with 7 scenarios and is highly difficult and high-quality . |
Complex Evolutional Pattern Learning for Temporal Knowledge Graph Reasoning (2022.acl-short)
Copied to clipboard
Zixuan Li, Saiping Guan, Xiaolong Jin, Weihua Peng, Yajuan Lyu, Yong Zhu, Long Bai, Wei Li, Jiafeng Guo, Xueqi Cheng
| Challenge: | Existing models for TKG reasoning focus on modeling fact sequences of a fixed length, which cannot discover complex evolutional patterns that vary in length. |
| Approach: | They propose to use a length-aware Convolutional Neural Network to handle evolutional patterns of different lengths via an easy-to-difficult curriculum learning strategy. |
| Outcome: | The proposed model improves performance under both offline and online learning strategies. |
Competition of Mechanisms: Tracing How Language Models Handle Facts and Counterfactuals (2024.acl-long)
Copied to clipboard
| Challenge: | Existing interpretability research focused on analyzing a single mechanism . et al., 2023) focused on finding how models copy or recall factual knowledge . |
| Approach: | They propose a competition of mechanisms that focuses on the interplay of multiple mechanisms instead of individual mechanisms . they uncover how and where the competition of mechanism happens within LLMs using logit inspection and attention modification methods. |
| Outcome: | The proposed model is based on two interpretability methods, logit inspection and attention modification. |
Sequicity: Simplifying Task-oriented Dialogue Systems with Single Sequence-to-Sequence Architectures (P18-1)
Copied to clipboard
| Challenge: | Existing solutions to task-oriented dialogue systems follow pipeline designs which introduces complexity and fragility. |
| Approach: | They propose a novel sequence-to-sequence (seq2sequ) model which tracks dialogue believes and a two stage copynet instantiation which emonstrates good scalability. |
| Outcome: | The proposed framework outperforms state-of-the-art pipeline-based methods on large datasets and retains satisfactory entity match rate on out-of vocabulary (OOV) cases where pipeline-designed competitors totally fail. |
Language to Network: Conditional Parameter Adaptation with Natural Language Descriptions (2020.acl-main)
Copied to clipboard
| Challenge: | Experimental results show that N3 can out-perform previous natural-language based zero-shot learning methods across 4 different zero- shot image classification benchmarks. |
| Approach: | They propose a new paradigm for synthesizing task-specific neural networks from language descriptions and a generic pre-trained model from natural language. |
| Outcome: | The proposed model outperforms natural-language based zero-shot learning methods across 4 zero- shot image classification benchmarks. |
CHIFRAUD: A Long-term Web Text Dataset for Chinese Fraud Detection (2025.coling-main)
Copied to clipboard
| Challenge: | Detecting fraudulent online text is essential as they exploit human greed and deceive individuals. |
| Approach: | They propose to build a long-term dataset of Chinese fraudulent texts collected over 12 months. |
| Outcome: | The proposed dataset includes 59,106 entries extracted from billions of web pages and includes large language model-based detectors and pre-trained language model approaches. |
Light-weight Fine-tuning Method for Defending Adversarial Noise in Pre-trained Medical Vision-Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing fine-tuning algorithms for vision-language models are restricted by patient privacy concerns and can contain imperceptible noise. |
| Approach: | They propose a framework to mitigate adversarial noise and mitigate upstream noise during fine-tuning. |
| Outcome: | The proposed framework improves model robustness and transferability while decreasing noise levels negatively impact downstream performance. |
SiLP: Enhancing Non-Dominant Language Capabilities with a Selective Bidirectional Language Projection Framework (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods to improve performance of large language models rely on additional training objectives or language-specific parameters. |
| Approach: | They propose a bidirectional language projection framework that enables efficient multilingual alignment and language shift using the intrinsic parameters. |
| Outcome: | The proposed framework improves performance of non-dominant languages and improves internal representations. |
ScaleLLM: A Resource-Frugal LLM Serving Framework by Optimizing End-to-End Efficiency (2024.emnlp-industry)
Copied to clipboard
Yuhang Yao, Han Jin, Alay Shah, Shanshan Han, Zijian Hu, Dimitris Stripelis, Yide Ran, Zhaozhuo Xu, Salman Avestimehr, Chaoyang He
| Challenge: | Large language models (LLMs) are widely used in commercial applications . low latency is crucial due to system latency, query concurrency, and computational resources constraints. |
| Approach: | They propose a system that can be resource-efficiently served by addressing bottlenecks beyond LLM inference . they propose 4.3 speed up over vLLM and 1.5 higher throughput . |
| Outcome: | The proposed system outperforms state-of-the-arts with 1.5 higher throughput . it achieves 4.3 speed up with 64 concurrent requests on Mixtral 8x7B . |
Learning What to Share: Leaky Multi-Task Network for Text Classification (C18-1)
Copied to clipboard
| Challenge: | Existing approaches to multi-task learning suffer from the interference between tasks because they lack selection mechanism for feature sharing. |
| Approach: | They propose a multi-task convolutional neural network with the Leaky Unit which has memory and forgetting mechanism to filter the feature flows between tasks. |
| Outcome: | The proposed model can filter feature flows between tasks and improve performance on five datasets. |
Friend-training: Learning from Models of Different but Related Tasks (2023.eacl-main)
Copied to clipboard
| Challenge: | Current self-training methods focus on improving model performance on a single task. |
| Approach: | They propose a cross-task self-training framework where models trained to do different tasks are used in iterative training, pseudo-labeling, and retraining processes to help each other for better selection of pseudo-labeled labels. |
| Outcome: | The proposed framework achieves the best performance compared to baselines on two dialogue understanding tasks. |
OpenSR: Open-Modality Speech Recognition via Maintaining Multi-Modality Alignment (2023.acl-long)
Copied to clipboard
| Challenge: | Speech Recognition often gets stuck in the lack of new domain utterances when training a model of new-domain speech. |
| Approach: | They propose a training system Open-modality Speech Recognition that enables zero-shot modality transfer . they use multi-modal alignment in phoneme space to maintain multi-modality alignment . |
| Outcome: | The proposed system achieves zero-shot modality transfer compared to existing methods . it achieves state-of-the-art performance on audio-visual speech recognition and lip-reading with 2.7% and 25.0%, respectively. |
FuxiTranyu: A Multilingual Large Language Model Trained with Balanced Data (2024.emnlp-industry)
Copied to clipboard
Haoran Sun, Renren Jin, Shaoyang Xu, Leiyu Pan, null Supryadi, Menglong Cui, Jiangcun Du, Yikun Lei, Lei Yang, Ling Shi, Juesi Xiao, Shaolin Zhu, Deyi Xiong
| Challenge: | Large language models exhibit significant performance discrepancies between high- and low-resource languages. |
| Approach: | They present an open-source multilingual LLM with 8 billion parameters and a multilingual instruction dataset. |
| Outcome: | The proposed model achieves consistent multilingual representations across languages. |
Multi-Channel Spatio-Temporal Transformer for Sign Language Production (2024.lrec-main)
Copied to clipboard
| Challenge: | Sign language production models ignore structural correlations between channels and use multi-channel spatial attention to capture correlations across channels. |
| Approach: | They propose a novel approach to transform sign language into a unified feature representation using multi-channel spatial attention and temporal attention to learn sequential dependencies for each channel over time. |
| Outcome: | The proposed model outperforms state-of-the-art models on two sign language datasets from diverse cultures. |
Federated Document-Level Biomedical Relation Extraction with Localized Context Contrast (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing studies on relation extraction focus on document-level training without sharing raw medical texts. |
| Approach: | They propose a federated framework for relation extraction that enables collaborative training without sharing raw medical texts. |
| Outcome: | The proposed framework extends document-level relation extraction to a federated environment. |
HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference (2025.findings-acl)
Copied to clipboard
Ping Gong, Jiawei Yi, Shengnan Wang, Juncheng Zhang, Zewen Jin, Ouxiang Zhou, Ruibo Liu, Guanbin Xu, Youhui Bai, Bowen Ye, Kun Yuan, Tong Yang, Gong Zhang, Renhai Chen, Feng Wu, Cheng Li
| Challenge: | Existing top-k attention methods struggle to strike a balance between efficiency and accuracy. |
| Approach: | They propose a top-k attention approach that integrates low-overhead techniques into the Top-k Attention process to achieve 7.2 speedup compared to vanilla full attention. |
| Outcome: | The proposed approach achieves 7.2 speedup compared to current top-k attention methods while maintaining model accuracy. |
Two Pathways to Truthfulness: On the Intrinsic Encoding of LLM Hallucinations (2026.acl-long)
Copied to clipboard
Wen Luo, Guangyue Peng, Wei Li, Shaohang Wei, Feifan Song, Liang Wang, Nan Yang, Xingxing Zhang, Jing Jin, Furu Wei, Houfeng Wang
| Challenge: | Previous work shows that large language models generate hallucinations, yet the origins and mechanisms of these signals remain unclear. |
| Approach: | They propose to validate and disentangle two different pathways for truthfulness cues . they also propose to use the same mechanism to derive self-contained evidence from the generated answer . |
| Outcome: | The proposed applications improve hallucination detection performance by integrating two different inputs. |
Generative-to-Discriminative Test-Time Adaptation via Manifold-Aware Diffusion and Bayesian Distillation (2026.findings-acl)
Copied to clipboard
Boyun Zhang, Zequn Xie, Fangming Feng, Zihan Zhang, Yongbo He, Chuxin Wang, Sihang Cai, Tao Jin, Qifei Zhang
| Challenge: | Existing discriminative approaches suffer from "confident but wrong" failure mode, blindly adapting to OOD noise leading to error accumulation. |
| Approach: | They propose a TTA framework that harmonizes the robustness of generative diffusion models with the efficiency of discriminative regression networks via Bayesian Diffusion Distillation (BDD). |
| Outcome: | The proposed framework reduces MAE from 0.6872 to 0.5673 and boosts binary accuracy by 5.81 percentage points (reaching 57.33%) it also reduces the MAE of the MOSI to SIMS shift and achieves an 11.18-point gain over the baseline. |
Do Large Language Models excel in Complex Logical Reasoning with Formal Language? (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies on LLMs have focused on formal language, but evaluations of their performance are limited. |
| Approach: | They propose to use a formal language to evaluate LLMs across logical reasoning problems using formal languages. |
| Outcome: | The proposed model outperforms Instruct models in three dimensions, taxonomy of tasks, and format of trajectories, and achieves the best generalization performance across other languages. |
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. |
IntentCoding: Amplifying User Intent in Code Generation (2026.findings-acl)
Copied to clipboard
| Challenge: | IntentCoding captures the influence of user intent by masking out the intent, and integrates seamlessly with existing decoding procedures. |
| Approach: | They propose a decoding strategy that captures the influence of user intent by masking out the intent and applies a multi-strength ensemble mechanism to amplify the effect of user intention during generation. |
| Outcome: | The proposed model significantly improves both constraint satisfaction and functional correctness compared to greedy decoding approaches. |
Vocabulary Adaptation for Domain Adaptation in Neural Machine Translation (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Neural network methods exhibit strong performance only in a few resource-rich domains. |
| Approach: | They propose a method that fine-tunes embedding layers of a pre-trained NMT model to the target domain. |
| Outcome: | The proposed method improves fine-tuning performance in En-Ja and De-En translation by 3.86 and 3.28 BLEU points. |
CoBA: Counterbias Text Augmentation for Mitigating Various Spurious Correlations via Semantic Triples (2025.emnlp-main)
Copied to clipboard
| Challenge: | Spurious correlations are patterns that appear in datasets but do not represent genuine relationships. |
| Approach: | They propose a more general form of counterfactual data augmentation that tackles multiple biases . they propose 'CoBA' that decomposes text into subject-predicate-object triples and modifies them to disrupt spurious correlations. |
| Outcome: | The proposed framework reduces biases and strengthens out-of-distribution resilience. |
Grasping the Essentials: Tailoring Large Language Models for Zero-Shot Relation Extraction (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing Relation extraction models require extensive annotated training data, which is costly and labor-intensive to collect. |
| Approach: | They propose a new zero-shot RE task where only relation definitions are provided instead of seen-unseen relation instances. |
| Outcome: | The proposed task significantly improves cost-effective zero-shot performance by large margins. |
EmoMM: Benchmarking and Steering MLLM for Multimodal Emotion Recognition under Conflict and Missingness (2026.findings-acl)
Copied to clipboard
| Challenge: | Multimodal Large Language Models (MLLMs) have shown promise in MER, but their internal decision-making mechanisms under modality conflict and missingness remain underexplored. |
| Approach: | They propose a multimodal large language model that can detect and control modality conflicts and missing subsets by a lightweight mechanism that detects and controls modality conflict. |
| Outcome: | The proposed framework improves performance across settings, showing it can handle conflict and missing behaviors. |
Search from History and Reason for Future: Two-stage Reasoning on Temporal Knowledge Graphs (2021.acl-long)
Copied to clipboard
| Challenge: | Temporal Knowledge Graphs (TKGs) are used in many different areas of research. |
| Approach: | They propose to use a beam search policy to induce multiple clues from historical facts . they propose to adopt a graph convolution network based sequence method to deduce answers from clues . |
| Outcome: | The proposed model can predict future facts in two stages, Clue Searching and Temporal Reasoning. |
Semantic-conditioned Dual Adaptation for Cross-domain Query-based Visual Segmentation (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to visual segmentation from language queries require expensive labeling and degradation when deployed to an unseen domain. |
| Approach: | They propose a task to adapt a visual segmentation model from a labeled domain to an unseen domain. |
| Outcome: | The proposed framework achieves precise feature- and relation-invariant across domains via universal semantic structure. |
DRAE: Dynamic Retrieval-Augmented Expert Networks for Lifelong Learning and Task Adaptation in Robotics (2025.acl-long)
Copied to clipboard
| Challenge: | Experimental results show that Dynamic Retrieval-Augmented Expert Networks outperforms baseline approaches in long-term task retention and knowledge reuse. |
| Approach: | They propose a dynamic routing architecture that leverages MoE and Retrieval-Augmented Generation to augment the learning process. |
| Outcome: | The proposed architecture outperforms baseline approaches in long-term task retention and knowledge reuse. |
Beyond Under-Alignment: Atomic Preference Enhanced Factuality Tuning for Large Language Models (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing work evaluates the factuality of large language models on in-domain (ID) datasets and the factuality on out-of-domain datasets. |
| Approach: | They propose a framework that enhances model’s awareness of factuality at the granularity of individual facts and propose 'Atomic Preference Enhanced Factuality Tuning' this framework enhances the model’ s awareness and accuracy of factual information at the level of individual factual facts. |
| Outcome: | The proposed framework improves model performance by an average of on ID and OOD datasets, which is highly effective. |
Disentangling Logic: The Role of Context in Large Language Model Reasoning Capabilities (2025.findings-acl)
Copied to clipboard
Wenyue Hua, Kaijie Zhu, Lingyao Li, Lizhou Fan, Mingyu Jin, Shuhang Lin, Haochen Xue, Zelong Li, Jindong Wang, Yongfeng Zhang
| Challenge: | Using large language models, large language model models can be used to evaluate reasoning abilities in context-rich scenarios. |
| Approach: | They construct datasets for both propositional logic and abductive logic reasoning with four difficulty levels across 12 distinct domains based on Wikipedia categorization and those with purely abstract variables. |
| Outcome: | The proposed model can be used to benchmark LLMs in real-world scenarios, but not in context-rich scenarios. |
Disentangling Memory and Reasoning Ability in Large Language Models (2025.acl-long)
Copied to clipboard
Mingyu Jin, Weidi Luo, Sitao Cheng, Xinyi Wang, Wenyue Hua, Ruixiang Tang, William Yang Wang, Yongfeng Zhang
| Challenge: | Existing LLMs operate as an opaque process without explicit separation between knowledge retrieval and reasoning steps, making the decision-making process unclear and disorganized. |
| Approach: | They propose a language model inference paradigm that decomposes the complex inference process into two distinct and clear actions: (1) memory recall: which retrieves relevant knowledge, and (2) reasoning: which performs reasoning steps based on the recalled knowledge. |
| Outcome: | The proposed paradigm decomposes the inference process into two distinct and clear actions, memory and reason, guiding the model to distinguish between steps that require knowledge retrieval and those that involve reasoning. |
SQLForge: Synthesizing Reliable and Diverse Data to Enhance Text-to-SQL Reasoning in LLMs (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing closed-source LLMs have a performance gap in text-to-SQL reasoning tasks. |
| Approach: | They propose a SQL-based approach to synthesize reliable data to enhance text-to-SQL reasoning in LLMs. |
| Outcome: | The proposed model achieves state-of-the-art accuracy on the widely recognized Spider and BIRD benchmarks, significantly narrowing the performance gap with closed-source methods. |
Label-aware Hard Negative Sampling Strategies with Momentum Contrastive Learning for Implicit Hate Speech Detection (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing models for implicit hate speech detection do not have significant advantage over cross-entropy loss-based learning. |
| Approach: | They propose a label-aware hard negative sampling strategy that encourages the model to learn detailed features from hard negative samples instead of random batch. |
| Outcome: | The proposed models outperform existing models for implicit hate speech detection both in- and cross-datasets. |
Forest for the Trees: Overarching Prompting Evokes High-Level Reasoning in Large Language Models (2025.naacl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have greatly propelled the progress of natural language process (NLP). |
| Approach: | They propose a deductive paradigm that decomposes the reasoning process and a prompting method that elicits high-level thinking of large language models (LLMs). |
| Outcome: | The proposed method improves ChatGPT and CoT by 19.0% and 3.1% on MMLU’s College Physics, 8.8% and 2.3% on GSM8k, and 10.3% and 2.5% on StrategyQA, respectively. |
Decentralized Arena: Towards Democratic and Scalable Automatic Evaluation of Language Models (2026.acl-long)
Copied to clipboard
Yanbin Yin, Kun Zhou, Zhen Wang, Xiangdong Zhang, Yifei Shao, Shibo Hao, Yi Gu, Jieyuan Liu, Somanshu Singla, Tianyang Liu, Eric P. Xing, Zhengzhong Liu, Haojian Jin, Zhiting Hu
| Challenge: | closed-ended question-based benchmarks struggle with saturation as newer models emerge . crowd-sourced leaderboards rely on costly and slow human judges . |
| Approach: | They propose a framework that leverages collective intelligence from all large language models to evaluate each other. |
| Outcome: | a new framework enables a democratic, pairwise evaluation of all large language models . it achieves 97% correlation with human judgements, while significantly reducing the cost. |
Domain Generalization via Switch Knowledge Distillation for Robust Review Representation (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing models for review representations of unseen or anonymous users are limited by their in-domain nature. |
| Approach: | They propose to use in-domain user and product information to generalize reviews . they use switch knowledge distillation to learn review representations for unseen users . |
| Outcome: | The proposed model performs well for existing or anonymous unseen users. |
Tracking Life’s Ups and Downs: Mining Life Events from Social Media Posts for Mental Health Analysis (2025.acl-long)
Copied to clipboard
| Challenge: | Existing studies have indicated that major life events can greatly impact individuals’ mental health, but shedding its light on social media data is challenging due to the complexity and ambiguity nature of life events. |
| Approach: | They propose to extract life events mentioned in posts on social media to uncover a social media event dataset which includes 12 major life event categories that are likely to occur in everyday life. |
| Outcome: | The proposed dataset includes 12 life event categories that are likely to occur in everyday life and is human-annotated under iterative procedure and boasts a high level of quality. |
POLYCHARTQA: Benchmarking Large Vision-Language Models with Multilingual Chart Question Answering (2026.acl-long)
Copied to clipboard
| Challenge: | Existing chart understanding benchmarks are overwhelmingly English-centric, limiting their accessibility and relevance to global audiences. |
| Approach: | They propose a multilingual chart question answering benchmark that enables efficient multilingual generation via data translation and code reuse. |
| Outcome: | The proposed benchmark systematically evaluates multilingual chart understanding on state-of-the-art LVLMs and shows a significant performance gap between English and other languages. |
TrInk: Ink Generation with Transformer Network (2025.emnlp-main)
Copied to clipboard
Zezhong Jin, Shubhang Desai, Xu Chen, Biyi Fang, Zhuoyi Huang, Zhe Li, Chong-Xin Gan, Xiao Tu, Man-Wai Mak, Yan Lu, Shujie Liu
| Challenge: | Existing methods for handwriting generation capture global dependencies and can generate high-quality handwritten samples. |
| Approach: | They propose a Transformer-based model for ink generation, TrInk, which captures global dependencies. |
| Outcome: | The proposed model reduces character error rate and word error rate by 35.56% on the IAM-OnDB dataset compared to previous models. |
WavRAG: Audio-Integrated Retrieval Augmented Generation for Spoken Dialogue Models (2025.acl-long)
Copied to clipboard
| Challenge: | Existing RAG frameworks rely on Automatic Speech Recognition to process speech input, which discards crucial audio information and increases computational overhead. |
| Approach: | They propose a retrieval augmented generation framework with native, end-to-end audio support that integrates audio and text into a unified knowledge representation. |
| Outcome: | The proposed framework can perform 10x faster than current pipelines while delivering 10x acceleration. |
Media Attitude Detection via Framing Analysis with Events and their Relations (2024.emnlp-main)
Copied to clipboard
| Challenge: | a recent study examined the effects of media framing on public perception and understanding of news articles. |
| Approach: | They propose to extract framing devices employed by media to assess their role in framating the narrative. |
| Outcome: | The proposed method surpasses baseline models and offers a more detailed and explainable analysis of media framing effects. |
Dual Adversarial Neural Transfer for Low-Resource Named Entity Recognition (P19-1)
Copied to clipboard
| Challenge: | Named entity recognition (NER) is an important step in most natural language processing (NLP) applications. |
| Approach: | They propose a dual-adversarial neural transfer method for addressing low-resource Named Entity Recognition (NER) they propose 'Generalized Resource-Adversarial Discriminator' and 'accidental training' |
| Outcome: | The proposed method improves on low-resource Named Entity Recognition (NER) with two variants, i.e., DATNet-F and DATNET-P, and adversarial training is adopted to boost model generalization. |
The Impact of Reasoning Step Length on Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Long reasoning steps in LLMs improve reasoning abilities, but the correlation between their effectiveness and the length of reasoning steps remains largely unknown. |
| Approach: | They conducted experiments that expand and compress the rationale reasoning steps within CoT demonstrations while keeping all other factors constant. |
| Outcome: | The results show that lengthening the reasoning steps in prompts significantly enhances LLMs’ reasoning abilities across multiple datasets. |
Unsupervised Sentence Representation Learning with Syntactically Aligned Negative Samples (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing approaches to sentence representation learning often encounter semantic inconsistencies and feature suppression. |
| Approach: | They propose a method for generating syntactically aligned negative (SAN) samples using a semantic importance-aware Masked Language Model (MLM) approach. |
| Outcome: | The proposed method produces negative samples with substantial textual overlap with the original sentences while conveying different meanings. |
Multi-source Meta Transfer for Low Resource Multiple-Choice Question Answering (2020.acl-main)
Copied to clipboard
| Challenge: | Existing MCQA datasets are small in size, which increases difficulty of model learning and generalization. |
| Approach: | They propose a multi-source meta transfer framework for low-resource multiple-choice question answering . they extend meta learning by incorporating multiple training sources to learn a generalized feature representation across domains . |
| Outcome: | The proposed framework is independent of backbone language models and can bridge the distribution gap between training sources and target. |
Chart-MRAG: Benchmarking Multimodal Retrieval Augmented Generation on Chart-based Documents (2026.acl-long)
Copied to clipboard
null Ymyang, Jiang Zhong, Li Jin, Xiao Sun, Jingwang Huang, null Gaojinpeng, Qing Liu, Yang Bai, Jingyuan Zhang, Rui Jiang, Qin Lei, Kaiwen Wei
| Challenge: | Existing benchmarks focus on simple image-text interactions, overlooking complex visual formats like charts. |
| Approach: | They propose a semi-automatic framework for generating evaluation samples through multi-modal keypoint extraction, knowledge graph construction, and qa pair synthesis. |
| Outcome: | The proposed framework generates 4,738 question-answering pairs across 8 domains from real-world documents. |
Look Light, Think Heavy: What Multimodal Chain-of-Thought Reasoning Can and Cannot Do (2026.acl-long)
Copied to clipboard
| Challenge: | Existing open-source models often yield only marginal overall improvements, possibly due to an overemphasis on mathematical reasoning at the expense of broader capabilities. |
| Approach: | They evaluate 12 multimodal tasks using 14 non-reasoning models and 8 reasoning models. |
| Outcome: | The proposed method is effective in multimodal reasoning tasks, the authors show . they show that it lacks the ability to maintain deep visual introspection throughout the reasoning process. |
Temporal Knowledge Graph Reasoning Based on N-tuple Modeling (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing Temporal Knowledge Graphs (TKGs) only contain their core entities and form them as quadruples. |
| Approach: | They propose to describe a temporal fact more accurately as an n-tuple . they propose to use a neural network to learn evolutional representations of entities . |
| Outcome: | The proposed model oversimplifies and causes information loss on two datasets. |
Benchmarking Retrieval-Augmented Generation for Medicine (2024.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have state-of-the-art performance on a wide range of medical question answering tasks, but they still face challenges with hallucinations and outdated knowledge. |
| Approach: | They propose a benchmark to evaluate medical RAG systems using large-scale experiments with over 1.8 trillion prompt tokens. |
| Outcome: | The proposed benchmark improves accuracy of six different LLMs by up to 18% over chain-of-thought prompting. |
TensorOpera Router: A Multi-Model Router for Efficient LLM Inference (2024.emnlp-industry)
Copied to clipboard
Dimitris Stripelis, Zhaozhuo Xu, Zijian Hu, Alay Shah, Han Jin, Yuhang Yao, Jipeng Zhang, Tong Zhang, Salman Avestimehr, Chaoyang He
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable performance across a diverse set of domain-specific tasks. |
| Approach: | They propose a non-monolithic LLM querying system that seamlessly integrates various LLM experts into a single query interface and dynamically routes incoming queries to the most high-performant expert based on query’s requirements. |
| Outcome: | The proposed model improves query efficiency by 40% and costs by 30% while maintaining or enhancing model performance by 10%. |
Instruction-following Evaluation through Verbalizer Manipulation (2024.findings-naacl)
Copied to clipboard
| Challenge: | Existing benchmarks focus on common instructions that align well with what the model learned during training, but proficiency in responding to these instructions does not necessarily imply strong ability in instruction following. |
| Approach: | They propose a new instruction-following evaluation protocol called verbalizer manipulation that instructs the model to verbalize the task label with words aligning with model priors to different extents. |
| Outcome: | The proposed protocol can be integrated with any classification benchmark to examine the model’s reliance on priors and its ability to override them to accurately follow the instructions. |
End-to-End Modeling via Information Tree for One-Shot Natural Language Spatial Video Grounding (2022.acl-long)
Copied to clipboard
Mengze Li, Tianbao Wang, Haoyu Zhang, Shengyu Zhang, Zhou Zhao, Jiaxu Miao, Wenqiao Zhang, Wenming Tan, Jin Wang, Peng Wang, Shiliang Pu, Fei Wu
| Challenge: | Existing methods for grounding video frames with dense annotations require enormous amount of human effort. |
| Approach: | They propose to ground natural language in video frames with only one frame labeled . they propose an end-to-end model that eliminates interference of irrelevant frames . |
| Outcome: | The proposed model can ground natural language in all video frames with only one frame labeled . the proposed model eliminates interference of irrelevant frames based on branch search and cropping techniques . |
MultiCMET: A Novel Chinese Benchmark for Understanding Multimodal Metaphor (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing research on multimodal metaphors does not address categorizing the source and target domains in metaphors beyond the English language. |
| Approach: | They propose a Cascading Domain Knowledge Integration benchmark to detect metaphors by introducing domain-specific lexical features. |
| Outcome: | The proposed dataset includes 13,820 text-image pairs of advertisements with manual annotations of the occurrence of metaphors, domain categories, and sentiments metaphors convey. |
Omni-Chart-600K: A Comprehensive Dataset of Chart Types for Chart Understanding (2025.findings-naacl)
Copied to clipboard
Shulei Wang, Shuai Yang, Wang Lin, Zirun Guo, Sihang Cai, Hai Huang, Ye Wang, Jingyuan Chen, Tao Jin
| Challenge: | Existing chart-related training methods lack capabilities in information extraction, mathematical reasoning, and understanding of multiple chart types. |
| Approach: | They propose a two-stage training strategy and method for jointly training a vision encoder tailored for multi-type charts to address the deficiencies in chart types and limited scope of chart tasks in existing datasets. |
| Outcome: | The proposed dataset includes 21 diverse chart types and tasks, including data retrieval and mathematical reasoning. |
Neural Models for Reasoning over Multiple Mentions Using Coreference (N18-2)
Copied to clipboard
| Challenge: | Existing Recurrent Neural Network (RNN) layers are biased towards short-term dependencies and hence not suited to such tasks. |
| Approach: | They propose a recurrent layer which is instead biased towards coreferent dependencies and uses coreference annotations extracted from an external system to connect entity mentions belonging to the same cluster. |
| Outcome: | The proposed layer improves performance on Wikihop, LAMBADA and the bAbi AI datasets with large gains when training data is scarce. |
Feature-Adaptive and Data-Scalable In-Context Learning (2024.acl-long)
Copied to clipboard
| Challenge: | In-context learning (ICL) is a popular way to stimulate LLM capabilities for downstream tasks due to context length constraints. |
| Approach: | They propose a feature-adaptive and data-scalable in-context learning framework which leverages task-adaptives to promote inference on the downstream task. |
| Outcome: | The proposed framework outperforms state-of-the-art methods on 10 datasets under different data settings and LLM scale. |
CodeArena: Evaluating and Aligning CodeLLMs on Human Preference (2025.emnlp-main)
Copied to clipboard
Jian Yang, Jiaxi Yang, Wei Zhang, Jin Ke, Yibo Miao, Lei Zhang, Liqun Yang, Zeyu Cui, Yichang Zhang, Zhoujun Li, Binyuan Hui, Junyang Lin
| Challenge: | Code large language models (codeLLMs) focus on synthesizing the correct code snippet, ignoring the alignment with human preferences. |
| Approach: | They propose a benchmark code-based on 40 categories and 44 programming languages to emulate real-world coding tasks. |
| Outcome: | The proposed benchmarks show that open-source code LLMs perform better than open-sourced ones. |
LUME: LLM Unlearning with Multitask Evaluations (2025.findings-emnlp)
Copied to clipboard
Anil Ramakrishna, Yixin Wan, Xiaomeng Jin, Kai-Wei Chang, Zhiqi Bu, Bhanukiran Vinzamuri, Volkan Cevher, Mingyi Hong, Rahul Gupta
| Challenge: | Unlearning aims to remove copyrighted, sensitive, or private content from large language models without a full retraining. |
| Approach: | They propose a multi-task unlearning benchmark LUME that unlearns short novels, biographies and public biographie . |
| Outcome: | The proposed benchmark unlearns short novels, biographies and public biographie . it also releases fine-tuned models with 1B and 7B parameter sizes as targets . |
Neural Retrieval for Question Answering with Cross-Attention Supervised Data Augmentation (2021.acl-short)
Copied to clipboard
| Challenge: | Early fusion models with cross-attention have shown better-than-human performance on some question answer benchmarks, while it is a poor fit for retrieval since it prevents pre-computation of the answer representations. |
| Approach: | They propose a supervised data mining method to train an efficient late fusion retrieval model by using cross-attention models with cross-references. |
| Outcome: | The proposed model outperforms retrieval models trained with gold annotations on Precision at N (P@N) and Mean Reciprocal Rank (MRR). |
Revealing Personality Traits: A New Benchmark Dataset for Explainable Personality Recognition on Dialogues (2024.emnlp-main)
Copied to clipboard
| Challenge: | Current research treats personality recognition as a classification task, failing to reveal the supporting evidence for the recognized personality. |
| Approach: | They propose a task that aims to reveal the reasoning process as supporting evidence of the personality trait. |
| Outcome: | The proposed task reveals the reasoning process as supporting evidence of the personality trait. |
Self-Consistency Boosts Calibration for Math Reasoning (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing solutions for math reasoning tasks use semantic parsing or AST decoding, but performance can degrade dramatically even with slight changes to the questions. |
| Approach: | They propose three calibration methods based on self-consistency for math reasoning tasks. |
| Outcome: | The proposed methods bridge model confidence and accuracy better than existing methods based on p(True) or logit. |
Topology-of-Question-Decomposition: Enhancing Large Language Models with Information Retrieval for Knowledge-Intensive Tasks (2025.coling-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) are constrained to chaining immediate reasoning steps and relying solely on parametric knowledge. |
| Approach: | They propose a framework that activates retrieval only when necessary to improve answer accuracy. |
| Outcome: | Experiments show that the proposed framework improves performance in knowledge-intensive tasks. |
When Seeing Overrides Knowing: Disentangling Knowledge Conflicts in Vision-Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Vision-language models combine visual and textual information to perform complex tasks. conflicts between internal knowledge and external visual input can lead to hallucinations and unreliable predictions. |
| Approach: | They propose to use a dataset to identify attention heads that deliberately contradict internal commonsense knowledge to resolve cross-modal conflicts. |
| Outcome: | The proposed model can be manipulated to find out which visual inputs are conflicting . the model can then be orientated towards internal parametric knowledge or visual information . |
Tug-of-War between Knowledge: Exploring and Resolving Knowledge Conflicts in Retrieval-Augmented Language Models (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing knowledge conflicts in RALMs can ensnare them in a tug-of-war between knowledge and evidence, limiting their practical applicability. |
| Approach: | They propose a method called Conflict-Disentangle Contrastive Decoding (CD2) to better calibrate the model’s confidence. |
| Outcome: | The proposed method can resolve knowledge conflicts in large language models with the help of conflict-disentangle contrast decoding (CD2) . |
DRBO: Mitigating Short Board Effect via Dynamic Reward Balancing in Multi-reward LLM Optimization (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a new framework to optimize large language models (LLMs) for evaluation metrics is needed to balance weaker metrics. |
| Approach: | They propose a Dynamic Reward Balancing Optimization framework to mitigate the "short-board effect" they apply it to single-task and multi-type task scenarios . |
| Outcome: | The proposed framework improves performance and balances performance across multiple metrics. |
Social Bias Benchmark for Generation: A Comparison of Generation and QA-Based Evaluations (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for assessing social bias in large language models (LLMs) do not capture nuanced and context-dependent nature of natural language generation. |
| Approach: | They propose a Bias Benchmark for Generation (BBG) that evaluates social bias in long-form generation by having LLMs generate continuations of story prompts. |
| Outcome: | The proposed benchmark is based on the English BBQ and Korean BBQ datasets and compares it with multiplechoice BBQ evaluation. |
Perception Compressor: A Training-Free Prompt Compression Framework in Long Context Scenarios (2025.findings-naacl)
Copied to clipboard
| Challenge: | Long prompts contain redundant information and are sensitive to the position of key information in long context scenarios. |
| Approach: | They propose a training-free prompt compression framework that retains key information at token level while removing distracting tokens. |
| Outcome: | The proposed framework outperforms existing methods on long context benchmarks. |
CODE-MVP: Learning to Represent Source Code from Multiple Views with Contrastive Pre-Training (2022.findings-naacl)
Copied to clipboard
| Challenge: | Recent studies have focused on code representation learning, which aims to represent the semantics of source code into distributed vectors. |
| Approach: | They propose to integrate different views with the natural-language description of source code into a unified framework with Multi-View contrastive Pre-training. |
| Outcome: | The proposed model outperforms state-of-the-art models on three downstream tasks over five datasets. |
HacRED: A Large-Scale Relation Extraction Dataset Toward Hard Cases in Practical Applications (2021.findings-acl)
Copied to clipboard
Qiao Cheng, Juntao Liu, Xiaoye Qu, Jin Zhao, Jiaqing Liang, Zhefeng Wang, Baoxing Huai, Nicholas Jing Yuan, Yanghua Xiao
| Challenge: | Relation extraction (RE) is an essential topic in natural language processing and has attracted extensive attention. |
| Approach: | They propose a case-oriented construction framework to build a hard case relation extraction dataset with 65,225 relational facts annotated from 9,231 documents. |
| Outcome: | The proposed model achieves a high 96% F1 score on data quality and is far lower than humans. |
MCapsNet: Capsule Network for Text with Multi-Task Learning (D18-1)
Copied to clipboard
| Challenge: | Multi-task learning has been frustrated by the interference among tasks. |
| Approach: | They propose a capsule-based multi-task learning architecture which is unified, simple and effective. |
| Outcome: | The proposed model can cluster features for each task in the network, which helps reduce the interference among tasks. |
Rule-Aware Reinforcement Learning for Knowledge Graph Reasoning (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to reason missing facts on Knowledge Graphs face with serious incompleteness due to their black-box nature. |
| Approach: | They propose a multi-hop reasoning method that injects high quality symbolic rules into the model's reasoning process and employs partially random beam search. |
| Outcome: | The proposed method outperforms existing multi-hop reasoning methods in terms of Hit@1 and MRR. |
BERT-EMD: Many-to-Many Layer Mapping for BERT Compression with Earth Mover’s Distance (2020.emnlp-main)
Copied to clipboard
| Challenge: | Pre-trained language models have been proposed and applied to many NLP tasks, yielding state-of-the-art performance, but high storage and computational costs obstruct them to be effectively deployed on resource-constrained devices and real-time applications. |
| Approach: | They propose a BERT distillation method which allows each intermediate student layer to learn from any intermediate teacher layers. |
| Outcome: | The proposed method can learn from different teacher layers adaptively for different NLP tasks. |
DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories (2024.findings-acl)
Copied to clipboard
Jia Li, Ge Li, Yunfei Zhao, Yongmin Li, Huanyu Liu, Hao Zhu, Lecheng Wang, Kaibo Liu, Zheng Fang, Lanshen Wang, Jiazheng Ding, Xuanming Zhang, Yuqi Zhu, Yihong Dong, Zhi Jin, Binhua Li, Fei Huang, Yongbin Li, Bin Gu, Mengfei Yang
| Challenge: | Existing benchmarks are poorly aligned with real-world code repositories and are insufficient to evaluate the coding abilities of Large Language Models (LLMs). |
| Approach: | They propose a repository-level benchmark named DevEval to evaluate LLMs' coding abilities in real-world code repositories. |
| Outcome: | The proposed benchmarks show that the LLMs perform better in real-world code repositories than existing benchmarks. |
Arena-lite: Efficient and Reliable Large Language Model Evaluation via Tournament-Based Direct Comparisons (2025.emnlp-main)
Copied to clipboard
| Challenge: | Current benchmarks typically compare system outputs against baselines, but this method yields lower reliability than direct comparison. |
| Approach: | They propose to integrate tournament structure on top of head-to-head comparison. |
| Outcome: | The proposed model achieves higher reliability with fewer comparisons even with smaller datasets or weaker judges. |
CLUTRR: A Diagnostic Benchmark for Inductive Reasoning from Text (D19-1)
Copied to clipboard
| Challenge: | Existing datasets for reading comprehension tasks have been used to test the generalization of natural language understanding systems. |
| Approach: | They propose a diagnostic benchmark suite to clarify key issues related to the robustness and systematicity of NLU systems. |
| Outcome: | The proposed benchmark suite clarifies key issues related to the robustness and systematicity of NLU systems. |
ECG-QALM: Entity-Controlled Synthetic Text Generation using Contextual Q&A for NER (2023.findings-acl)
Copied to clipboard
| Challenge: | Named Entity Recognition (NER) requires high-quality labeled datasets. |
| Approach: | They propose a method that uses pre-trained language models to generate entity-controlled text to augment small labeled datasets for downstream NER tasks. |
| Outcome: | The proposed method produces full text samples with desired entities appearing in a controllable way while retaining sentence coherence closest to the real world data. |
Agent-to-Agent Theory of Mind: Testing Interlocutor Awareness among Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Prior work has focused on situational awareness, which refers to a model's ability to recognize its operating phase and constraints, but it has neglected the complementary capacity to identify and adapt to the identity and characteristics of a dialogue partner. |
| Approach: | They formalize interlocutor awareness and evaluate its emergence in contemporary LLMs. |
| Outcome: | The proposed model reliably identify same-family peers and certain prominent model families, such as GPT and Claude. |
Moûsai: Efficient Text-to-Music Diffusion Models (2024.acl-long)
Copied to clipboard
| Challenge: | Recent years have seen the rapid development of large generative models for text; however, little research has explored the connection between text and another “language” of communication – music. |
| Approach: | They develop a text-to-music generation model that can generate multiple minutes of high-quality stereo music at 48kHz from textual descriptions. |
| Outcome: | The proposed model can generate multiple minutes of high-quality stereo music at 48kHz from textual descriptions. |
Generating Structured Pseudo Labels for Noise-resistant Zero-shot Video Sentence Localization (2023.acl-long)
Copied to clipboard
| Challenge: | Existing zero-shot pipelines generate event proposals and then generate a pseudo query for each event proposal. |
| Approach: | They propose a Structure-based Pseudo Label generation (SPL) that generates free-form interpretable pseudo queries before constructing query-dependent event proposals. |
| Outcome: | The proposed method learns with only video data without any annotation . it generates free-form interpretable pseudo queries before constructing query-dependent event proposals . |
A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discovery (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing surveys on scientific LLMs focus on one or two fields or a single modality. |
| Approach: | They survey 260 scientific LLMs and examine their architectures and pre-training techniques . they also discuss commonalities and differences between LLM architectures . |
| Outcome: | The proposed model architectures and evaluation techniques are used to improve scientific discovery. |
CogKTR: A Knowledge-Enhanced Text Representation Toolkit for Natural Language Understanding (2022.emnlp-demos)
Copied to clipboard
Zhuoran Jin, Tianyi Men, Hongbang Yuan, Yuyang Zhou, Pengfei Cao, Yubo Chen, Zhipeng Xue, Kang Liu, Jun Zhao
| Challenge: | Existing knowledge-enhanced methods are limited to knowledge-intensive tasks. |
| Approach: | They propose a knowledge-enhanced text representation toolkit for natural language understanding . it combines knowledge acquisition, knowledge representation, knowledge injection and knowledge application . |
| Outcome: | The proposed toolkit supports knowledge acquisition, knowledge representation, knowledge injection, and knowledge application. |
Data Whisperer: Efficient Data Selection for Task-Specific LLM Fine-Tuning via Few-Shot In-Context Learning (2025.acl-long)
Copied to clipboard
Shaobo Wang, Xiangqi Jin, Ziming Wang, Jize Wang, Jiajun Zhang, Kaixin Li, Zichen Wen, Zhong Li, Conghui He, Xuming Hu, Linfeng Zhang
| Challenge: | Using fine-tuning on task-specific data is essential for large language models to be effective in specialized tasks. |
| Approach: | They propose a method that leverages few-shot in-context learning with the model to be fine-tuned. |
| Outcome: | The proposed method outperforms existing methods with a 3.1-point improvement and a 7.4 speedup on the Llama-3-8B-Instruct model using just 10% of the dataset. |
Exploring Multimodal Relation Extraction of Hierarchical Tabular Data with Multi-task Learning (2025.acl-long)
Copied to clipboard
| Challenge: | Existing studies overlook the need of mining relations among multiple columns rather than just the semantic relation between two specific columns in real-world practice. |
| Approach: | They propose a Chain-of-Thought distillation framework with self-correction mechanism to enhance MLLMs’ reasoning capabilities without increasing parameter scale. |
| Outcome: | The proposed method significantly outperforms baselines on wide datasets. |
Inconsistent dialogue responses and how to recover from them (2024.findings-eacl)
Copied to clipboard
| Challenge: | Existing methods to assess and bolster utterance consistency of chat systems have been shown difficult to detect. |
| Approach: | They propose to use annotators to write dialogue responses and recovery utterances to assess and bolster utteration consistency of chat systems. |
| Outcome: | The proposed dataset significantly improves the detection and resolution of inconsistencies in chat conversations. |
Generalization-Enhanced Code Vulnerability Detection via Multi-Task Instruction Fine-Tuning (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing CodePre-trained models struggle to generalize due to superficial mapping from source code to labels instead of understanding the root causes of code vulnerabilities. |
| Approach: | They propose a framework that integrates multi-task learning with Large Language Models to effectively mine deep-seated vulnerability features. |
| Outcome: | The proposed framework surpasses seven state-of-the-art models in effectiveness, generalization, and robustness. |
TITA: A Two-stage Interaction and Topic-Aware Text Matching Model (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing models for keyword-document matching do not define topic-aware relevance clearly. |
| Approach: | They propose a two-stage interaction and topic-aware text matching model to solve this problem . they propose to combine latent topic of document with deep neural representation to model complex interactions between keyword and document. |
| Outcome: | The proposed model outperforms other well-designed baselines and shows excellent performance in the recommendation system. |
A Troublemaker with Contagious Jailbreak Makes Chaos in Honest Towns (2025.acl-long)
Copied to clipboard
| Challenge: | Existing research focuses on single-agent attacks and shared memory attacks, but real-world scenarios often involve independent memory. |
| Approach: | They propose a large-scale, multi-agent, multitopology attack evaluation framework that exploits the memory of an agent to make it more vulnerable to jailbreak attacks. |
| Outcome: | The proposed framework improves on the troublemaker makes chaos in Honest Town task with 23.51%, 18.95%, and 52.93% improvements in line, star topologies, and 100-agent settings. |
TAVT: Towards Transferable Audio-Visual Text Generation (2023.acl-long)
Copied to clipboard
| Challenge: | Existing transfer learning techniques focus on uni-modal analysis and lack consideration of multi-modal content and cross-modal relation. |
| Approach: | They propose a transferable audio-visual text generation framework that incorporates two components: Audio-Visual Meta-Mapper and Dual Counterfactual Contrastive Learning. |
| Outcome: | The proposed framework outperforms the state-of-the-art methods across multiple domains and modal settings. |
Retracing the Past: LLMs Emit Training Data When They Get Lost (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for extracting training data from large language models exhibit limited success . existing methods offer limited insight into the fundamental drivers of memorization leakage . |
| Approach: | They propose a framework for extracting memorized data by maximizing model uncertainty . they propose mismatched fine-tuning to weaken alignment and induce confusion . |
| Outcome: | The proposed attacks outperform baselines on unaligned and aligned LLMs . the proposed attacks exploit the model uncertainty of the input snippets induced by the model entropy spike . |
Respond in my Language: Mitigating Language Inconsistency in Response Generation based on Large Language Models (2024.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) show strong instruction understanding ability across multiple languages, but are easily biased towards English in instruction tuning. |
| Approach: | They propose to use a model with Pseudo-Inconsistent Penalization to prevent the model from generating English responses when given non-English language prompts during training and prior Enhanced decoding to improve the language consistency of the model. |
| Outcome: | The proposed methods significantly improve the language consistency of the model without multilingual data. |
Can Language Models Serve as Temporal Knowledge Bases? (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies have only considered language models as knowledge bases in a static setting . memorizing conflicting information is still challenging for LMs and hinders memorization of other unrelated one-to-one relationships. |
| Approach: | They propose two requirements for treating language models as temporal knowledge bases . they propose a dataset which is aimed at probing temporally-scoped knowledge . |
| Outcome: | The proposed model can store conflicting information and use stored knowledge for temporal knowledge queries. |
A Survey on Efficient Large Language Model Training: From Data-centric Perspectives (2025.acl-long)
Copied to clipboard
Junyu Luo, Bohan Wu, Xiao Luo, Zhiping Xiao, Yiqiao Jin, Rong-Cheng Tu, Nan Yin, Yifan Wang, Jingyang Yuan, Wei Ju, Ming Zhang
| Challenge: | achieving data-efficient post-training of Large Language Models is a key research question. |
| Approach: | They propose a taxonomy of data-efficient LLM post-training methods from a data-centric perspective. |
| Outcome: | The proposed methods cover data selection, data quality enhancement, synthetic data generation, data distillation and compression, and self-evolving data ecosystems. |
COPEN: Probing Conceptual Knowledge in Pre-trained Language Models (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing knowledge probing studies focus on evaluating factual knowledge of pre-trained language models (PLMs) but ignore conceptual knowledge. |
| Approach: | They evaluate conceptual knowledge of pre-trained language models by annotating 24k data instances covering 393 concepts. |
| Outcome: | The proposed tasks evaluate pre-trained language models' conceptual knowledge of entities, learn conceptual properties, and conceptualize entities in contexts. |
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. |
How do Words Contribute to Sentence Semantics? Revisiting Sentence Embeddings with a Perturbation Method (2023.eacl-main)
Copied to clipboard
| Challenge: | Existing studies on sentence representation learning focus on human annotation, but they neglect the critical property that essential contents should contribute to sentence semantics more than non-essential contents when encoding a sentence. |
| Approach: | They propose a perturbation method for unsupervised semantic analysis that uses a sentence compression metric to adapt sentence compression datasets for automatic evaluation. |
| Outcome: | The proposed method can capture the main semantics of sentences better than several SOTA unsupervised sentence embedding models. |
PsyScore: A Psychometrically-Aware Framework for Trait-Adaptive Essay Scoring and ZPD-Scaffolded Feedback (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to Automated Essay Scoring (AES) treat scoring and feedback as separate components, resulting in fragmentation. |
| Approach: | They propose a psychometrically-aware framework that integrates diagnostic assessment with instructional scaffolding through a shared latent ability representation. |
| Outcome: | The proposed framework integrates diagnostic assessment with instructional scaffolding through a shared latent ability representation. |
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. |
Zero-shot Generalization in Dialog State Tracking through Generative Question Answering (2021.eacl-main)
Copied to clipboard
| Challenge: | Existing methods for Dialog State Tracking do not generalize well to new domains and unseen slots. |
| Approach: | They propose an ontology-free framework that queries for unseen constraints and slots in multi-domain task-oriented dialogs using a conditional language model pre-trained on substantive English sentences. |
| Outcome: | The proposed framework improves goal accuracy in zero-shot domain adaptation settings by up to 9% over the previous state-of-the-art on the MultiWOZ 2.1 dataset. |
Cutting Off the Head Ends the Conflict: A Mechanism for Interpreting and Mitigating Knowledge Conflicts in Language Models (2024.findings-acl)
Copied to clipboard
Zhuoran Jin, Pengfei Cao, Hongbang Yuan, Yubo Chen, Jiexin Xu, Huaijun Li, Xiaojian Jiang, Kang Liu, Jun Zhao
| Challenge: | Existing methods to expand internal memory boundaries of language models by providing external context can often conflict, leading to knowledge conflicts. |
| Approach: | They propose a method that prunes conflicting attention heads without updating model parameters. |
| Outcome: | The proposed method can flexibly control eight LMs to use internal memory or external context without updating model parameters. |
InfoMetIC: An Informative Metric for Reference-free Image Caption Evaluation (2023.acl-long)
Copied to clipboard
| Challenge: | Existing image captioning metrics provide a single score to measure caption qualities, which are less explainable and informative. |
| Approach: | They propose an Informative Metric for Reference-free Image Caption evaluation to support this feedback . they propose to provide a text precision score, a vision recall score and an overall quality score . |
| Outcome: | The proposed method improves on existing metrics on multiple benchmarks and compares coarse-grained scores with human judgements. |
Leveraging LLM Reasoning Enhances Personalized Recommender Systems (2024.findings-acl)
Copied to clipboard
Alicia Tsai, Adam Kraft, Long Jin, Chenwei Cai, Anahita Hosseini, Taibai Xu, Zemin Zhang, Lichan Hong, Ed H. Chi, Xinyang Yi
| Challenge: | Recent advances have showcased the potential of Large Language Models (LLMs) in executing reasoning tasks, particularly facilitated by Chain-of-Thought (CoT) prompting. |
| Approach: | They propose to use Large Language Models to perform tasks with subjectivity and personalized preferences as inputs to RecSys. |
| Outcome: | The proposed framework aligns with real human judgment on the coherence and faithfulness of LLM reasoning responses. |
DialGuide: Aligning Dialogue Model Behavior with Developer Guidelines (2023.findings-emnlp)
Copied to clipboard
Prakhar Gupta, Yang Liu, Di Jin, Behnam Hedayatnia, Spandana Gella, Sijia Liu, Patrick Lange, Julia Hirschberg, Dilek Hakkani-Tur
| Challenge: | Dialogue models are able to generate fluent and interesting responses, but they can be difficult to control and may produce non-engaging, unsafe results. |
| Approach: | They propose a framework for controlling dialogue model behavior using natural language rules, or guidelines, which provide information about the context they are applicable to and what should be included in the response. |
| Outcome: | The proposed framework is effective in three open-domain dialogue response generation tasks and is consistent with the developer's expectations and intent. |
Semantic and Syntactic Enhanced Aspect Sentiment Triplet Extraction (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to extract triplets from sentences neglect the mutual information between aspects and have the problem of error propagation. |
| Approach: | They propose a Semantic and Syntactic Enhanced aspect Sentiment triplet Extraction model to exploit the syntactical and semantic relationships between the triplet elements and jointly extract them. |
| Outcome: | The proposed model outperforms existing methods on four benchmark datasets and significantly outperformed existing approaches. |
GER-LLM: Efficient and Effective Geospatial Entity Resolution with Large Language Model (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for integrating spatial data from diverse sources are limited by their reliance on large amounts of training data and their inability to incorporate commonsense knowledge. |
| Approach: | They propose a framework that integrates large language models into the GER pipeline. |
| Outcome: | The proposed framework improves on real-world geospatial datasets and shows that it is more efficient than state-of-the-art methods. |
MPRF: Interpretable Stance Detection through Multi-Path Reasoning Framework (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing stance detection methods treat the task as a classification problem, where models output a stance label without providing interpretable reasoning paths. |
| Approach: | They propose a framework that generates, evaluates, and integrates multiple reasoning paths to improve accuracy, robustness, and transparency in stance detection. |
| Outcome: | The proposed framework outperforms existing models on the SEM16, VAST, and PStance datasets and is highly interpretable and reliable. |
Bridging the Pose-Semantic Gap: A Cascade Framework for Text-Based Person Anomaly Search (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for person anomaly search fail to address the complexities of real-world security, authors say . Existing approaches fail to detect subtle semantic distinctions, authors argue . |
| Approach: | They propose a framework that decouples retrieval into two stages . structure-aware coarse retrieval and detective squad interaction are proposed . |
| Outcome: | The proposed framework achieves state-of-the-art performance by balancing efficiency and semantic reasoning. |
STYLE: Improving Domain Transferability of Asking Clarification Questions in Large Language Model Powered Conversational Agents (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for addressing ambiguities in conversational search systems are one-size-fits-all and struggle to achieve effective domain transferability. |
| Approach: | They propose a method to provide search engines with strategies regarding when to ask clarification questions in a post-hoc manner. |
| Outcome: | The proposed method improves search performance 10% on four unseen domains. |
Title2Event: Benchmarking Open Event Extraction with a Large-scale Chinese Title Dataset (2022.emnlp-main)
Copied to clipboard
Haolin Deng, Yanan Zhang, Yangfan Zhang, Wangyang Ying, Changlong Yu, Jun Gao, Wei Wang, Xiaoling Bai, Nan Yang, Jin Ma, Xiang Chen, Tianhua Zhou
| Challenge: | Existing EE datasets define fixed event types and design specific schemas for each of them, failing to cover diverse events emerging from the online text. |
| Approach: | They propose to use a sentence-level dataset to benchmark Open Event Extraction without restricting event types. |
| Outcome: | The proposed dataset contains more than 42,000 news titles in 34 topics collected from Chinese web pages. |
Shedding New Light on the Language of the Dark Web (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing studies on text classification of the Dark Web have been ineffective due to its inherent characteristics. |
| Approach: | They propose a publicly available Dark Web dataset tailored towards text-based analysis. |
| Outcome: | The proposed method compares with an existing public Dark Web dataset and evaluates its suitability for various use cases. |
Beyond Static Testbeds: An Interaction-Centric Agent Simulation Platform for Dynamic Recommender Systems (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing platforms lack a mechanism for user actions to dynamically reshape the environment. |
| Approach: | They propose a novel agent-based simulation platform for recommender systems with a robust interaction mechanism. |
| Outcome: | The proposed platform improves the credibility of the simulation and replicates the Matthew Effect and Brand Loyalty. |
R³A: Reinforced Reasoning for Relevance Assessment for RAG in User-Generated Content Platforms (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing approaches to query–document relevance assessment are limited . ambiguous user intent and asymmetric relevance are challenges for RAG platforms . |
| Approach: | They propose a decomposed reasoning model for relevance assessment that decomposes query intent into intent inference and evidence grounding. |
| Outcome: | The proposed model outperforms strong baselines on offline benchmarks and achieves significant gains in large-scale online A/B testing. |
Flaming-hot Initiation with Regular Execution Sampling for Large Language Models (2025.findings-naacl)
Copied to clipboard
Weizhe Chen, Zhicheng Zhang, Guanlin Liu, Renjie Zheng, Wenlei Shi, Chen Dun, Zheng Wu, Xing Jin, Lin Yan
| Challenge: | Large language models (LLMs) have demonstrated remarkable capabilities across various domains since the release of ChatGPT . a key challenge in developing these general capabilities is efficiently sourcing diverse, high-quality data. |
| Approach: | They introduce Flaming-hot Initiation with Regular Execution (FIRE) sampling to efficiently find good responses by promoting diversity. |
| Outcome: | The proposed method enhances inference-time generation quality and benefits training in the alignment stage. |
UniLG: A Unified Structure-aware Framework for Lyrics Generation (2023.acl-long)
Copied to clipboard
| Challenge: | Existing works ignore musical attributes hidden behind lyrics and structure of lyrics . existing works ignore structure of generated lyrics and do not consider structure of songs . |
| Approach: | They propose a framework for conditional lyrics generation that considers structure and relationship between lyrics and music. |
| Outcome: | The proposed framework improves the structure modeling and unifies different conditions for different types of lyrics generation. |
A Neural Transition-based Model for Nested Mention Recognition (D18-1)
Copied to clipboard
| Challenge: | Existing methods to recognize nested mentions are based on Stack-LSTM . nesting mentions can be used for downstream tasks like question answering and relation extraction. |
| Approach: | They propose a scalable transition-based method to model the nested structure of mentions. |
| Outcome: | The proposed method gets the state-of-the-art performance in ACE datasets showing its effectiveness in detecting nested mentions. |
Building a Broad Infrastructure for Uniform Meaning Representations (2024.lrec-main)
Copied to clipboard
Julia Bonn, Matthew J. Buchholz, Jayeol Chun, Andrew Cowell, William Croft, Lukas Denk, Sijia Ge, Jan Hajič, Kenneth Lai, James H. Martin, Skatje Myers, Alexis Palmer, Martha Palmer, Claire Benet Post, James Pustejovsky, Kristine Stenzel, Haibo Sun, Zdeňka Urešová, Rosa Vallejos, Jens E. L. Van Gysel, Meagan Vigus, Nianwen Xue, Jin Zhao
| Challenge: | This paper reports the first release of the UMR data set for six languages . it includes annotations for six different languages that vary greatly in terms of their linguistic properties and resource availability. |
| Approach: | They report the first release of the UMR data set for six languages . they describe on-going efforts to enlarge the data set and extend it to other languages - including Navajo, Navájo, and Sanapaná . |
| Outcome: | The first release of the UMR data set includes annotations for six languages . the language dataset is available for free and can be extended to other languages if needed . |
Weakly-Supervised Spoken Video Grounding via Semantic Interaction Learning (2023.acl-long)
Copied to clipboard
| Challenge: | Recent work on spoken video grounding challenges extracting semantic information from speech . previous studies focused on textual queries, but recent work focuses on spoken queries . |
| Approach: | They propose a framework for weakly-supervised spoken video grounding to represent cross-modal semantics without expensive temporal annotations. |
| Outcome: | The proposed framework is more efficient than existing methods. |
MMGCN: Multimodal Fusion via Deep Graph Convolution Network for Emotion Recognition in Conversation (2021.acl-long)
Copied to clipboard
| Challenge: | Emotion recognition in conversation is a crucial component in affective dialogue systems, which helps the system understand users’ emotions and generate empathetic responses. |
| Approach: | They propose a multimodal fused graph convolutional network model which leverages multimodal dependencies and speaker information to model inter-speaker and intra-speech dependency. |
| Outcome: | The proposed model outperforms other SOTA methods on two public benchmark datasets, IEMOCAP and MELD. |
Focus on Your Question! Interpreting and Mitigating Toxic CoT Problems in Commonsense Reasoning (2024.acl-long)
Copied to clipboard
| Challenge: | Large language models exhibit high-level commonsense reasoning abilities, especially with enhancement methods like Chain-of-Thought (CoT). |
| Approach: | They propose a chain-of-thought-like method to elicit models' potential abilities to generate rationales and answers that are based on attribution tracing and causal tracers to probe the internal working mechanism of the LLM. |
| Outcome: | The proposed method eliminates Toxic CoT problems and improves the model’s overall commonsense reasoning performance by 5.5%. |
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. |
Distributed LLM Serving on Consumer-Grade GPUs by Reconciling Computation and Communication (2025.findings-emnlp)
Copied to clipboard
Lewei Jin, Kui Zhang, Yongqi Chen, null Zhuoyifan, Renjie Li, Yi Gao, Bowei Yang, Zhengong Cai, Wei Dong
| Challenge: | Large language models are reshaping internet services, and serving them is costly. |
| Approach: | They propose an efficient distributed LLM serving system that splits prefill and decode requests into smaller chunks . |
| Outcome: | The proposed system reduces TTFT, TPOT, and latency compared to the state-of-the-art system. |
A Regex Minimization Benchmark: A PSPACE-Complete Challenge for Language Models (2026.eacl-long)
Copied to clipboard
| Challenge: | Language models (LMs) have demonstrated impressive reasoning capabilities across domains . but their ability to handle PSPACE-complete problems remains underexplored . a new benchmark for regex minimization is proposed to evaluate LMs' reasoning capabilities . |
| Approach: | They propose a benchmark for regex minimization to evaluate LMs' reasoning power . they use a million regexes paired with their minimal equivalents to evaluate their performance . |
| Outcome: | The proposed model can solve NP-complete problems, but their ability to handle PSPACE-complete ones remains underexplored. |
Depth Aware Hierarchical Replay Continual Learning for Knowledge Based Question Answering (2024.lrec-main)
Copied to clipboard
| Challenge: | Continual learning models adapt well to the latest data but lose ability to remember past data due to changes in the data source. |
| Approach: | They propose a hierarchical replay framework that allows models to keep a small memory of previous learned data that uses replay. |
| Outcome: | The proposed model outperforms previous continual learning methods in mitigating catastrophic forgetting. |
BatchMixup: Improving Training by Interpolating Hidden States of the Entire Mini-batch (2021.findings-acl)
Copied to clipboard
| Challenge: | a data augmentation technique is used to augment data, but it has two drawbacks. |
| Approach: | They propose a new mixup paradigm that generates new points scattered throughout the whole mini-batch. |
| Outcome: | The proposed model improves the performance of NLP tasks while using different ratios of training data. |
Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluation (2024.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to addressing factual inaccuracies require high-quality human factuality annotations to mitigate these hallucinations. |
| Approach: | They propose to leverage the self-evaluation capability of an LLM to provide training signals that steer the model towards factuality. |
| Outcome: | The proposed approach significantly improves factual accuracy over LLMs across three key knowledge-intensive tasks on TruthfulQA and BioGEN. |
Tailoring Diagnostic Modeling to Individual Learners: Personalized Distractor Generation via MCTS-Guided Reasoning Reconstruction (2026.acl-long)
Copied to clipboard
| Challenge: | Current distractor generation methods produce shared distractors for all students, ignoring individual variations in reasoning, which limits their diagnostic effectiveness. |
| Approach: | They propose a method which tailors distractors to each student’s specific cognitive flaws, inferred from their past question-answering (QA) history. |
| Outcome: | The proposed framework outperforms existing methods in generating plausible distractors and adapts to group-level settings. |
Hierarchical Neural Networks for Sequential Sentence Classification in Medical Scientific Abstracts (D18-1)
Copied to clipboard
| Challenge: | Existing sentences classification models often classify sentences in isolation without considering the context in which sentences appear. |
| Approach: | They propose a hierarchical sequential labeling network to make use of contextual information within surrounding sentences to help classify the current sentence. |
| Outcome: | The proposed model outperforms the state-of-the-art methods by 2%-3% on two benchmarking datasets for sequential sentence classification in medical scientific abstracts. |
LLM-Driven Knowledge Injection Advances Zero-Shot and Cross-Target Stance Detection (2024.naacl-short)
Copied to clipboard
| Challenge: | Existing methods for stance detection focus on background information and not on the accompanying input texts. |
| Approach: | They propose to prompt Large Language Models to explicitly extract the relationship between paired text and unseen target as contextual knowledge and inject it into a generation model BART to exploit the rich contexts and semantics. |
| Outcome: | The proposed model is able to detect stance labels in zero-shot and cross-target scenarios. |
HELENE: Hessian Layer-wise Clipping and Gradient Annealing for Accelerating Fine-tuning LLM with Zeroth-order Optimization (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) face memory challenges due to the high cost of backpropagation. |
| Approach: | They propose a zeroth-order (ZO) optimization that matches memory usage to inference . they propose scalable and memory-efficient zeroth order (ZE) optimizer that integrates annealed A-GNB gradients with diagonal Hessian estimation and layer-wise clipping as a second-order pre-conditioner. |
| Outcome: | The proposed algorithm outperforms state-of-the-art methods with an average speedup of 20 over MeZO on RoBERTa-large and OPT-1.3B. |
MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing (2026.acl-industry)
Copied to clipboard
Junbo Niu, Zheng Liu, Zhuangcheng Gu, Bin Wang, Linke Ouyang, Zhiyuan Zhao, Tao Chu, Tianyao He, Fan Wu, Qintong Zhang, Zhenjiang Jin, Guang Liang, Rui Zhang, Wenzheng Zhang, Yuan Qu, Zhifei Ren, Yuefeng Sun, Zirui Tang, Boyu Niu, Yuanhong Zheng, Dongsheng Ma, Ziyang Miao, Hejun Dong, Siyi Qian, Junyuan Zhang, Fangdong Wang, Jingzhou Chen, Xiaomeng Zhao, Liqun Wei, Wei Li, Shasha Wang, RuiLiang Xu, Yuanyuan Cao, Lu Chen, Qianqian Wu, Huaiyu Gu, Lindong Lu, Dechen Lin, null Shenguanlin, Xuanhe Zhou, Linfeng Zhang, Yuhang Zang, Xiaoyi Dong, Jiaqi Wang, Bo Zhang, Lei Bai, Pei Chu, Weijia Li, Jiang Wu, Lijun Wu, Zhenxiang Li, Guangyu Wang, Zhongying Tu, Chao Xu, Kai Chen, Bowen Zhou, Dahua Lin, Wentao Zhang, Conghui He
| Challenge: | Document images are characterized by higher resolutions, denser content, and more complex structural layouts. |
| Approach: | They propose a 1.2B-parameter document parsing vision-language model that decouples layout analysis from local content recognition. |
| Outcome: | The proposed model surpasses general-purpose and domain-specific models on multiple benchmarks while maintaining significantly lower computational overhead. |
Sharing Encoder Representations across Languages, Domains and Tasks in Large-Scale Spoken Language Understanding (2023.acl-industry)
Copied to clipboard
Jonathan Hueser, Judith Gaspers, Thomas Gueudre, Chandana Prakash, Jin Cao, Daniil Sorokin, Quynh Do, Nicolas Anastassacos, Tobias Falke, Turan Gojayev
| Challenge: | Larger encoders can improve accuracy for spoken language understanding (SLU) but are difficult to use given the inference latency constraints of online systems. |
| Approach: | They propose to use a larger 170M parameter BERT encoder that shares representations across languages, domains and tasks for SLU. |
| Outcome: | The proposed encoders achieve state-of-the-art performance on numerous NLP tasks. |
Decomposition for Enhancing Attention: Improving LLM-based Text-to-SQL through Workflow Paradigm (2024.findings-acl)
Copied to clipboard
Yuanzhen Xie, Xinzhou Jin, Tao Xie, Matrixmxlin Matrixmxlin, Liang Chen, Chenyun Yu, Cheng Lei, Chengxiang Zhuo, Bo Hu, Zang Li
| Challenge: | In-context learning of large-language models has achieved remarkable success in the field of natural language processing . however, the single-step chain-of-thought prompting approach faces challenges such as attention diffusion and inadequate performance in complex tasks like text-to-SQL. |
| Approach: | They propose a workflow paradigm method to enhance the attention and problem-solving scope of large-language models through decomposition. |
| Outcome: | The proposed method outperforms existing methods on three datasets and improves the upper limit of LLM-based approaches. |
TongGu: Mastering Classical Chinese Understanding with Knowledge-Grounded Large Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable capability in Natural Language Processing (NLP), but struggle with Classical Chinese Understanding (CCU) Existing models, including general-purpose and preliminary LLMs, lack the ability to address CCU in data-demanding and knowledge-intensive tasks. |
| Approach: | They propose to use a classical Chinese corpora-based instruction-tuning dataset to unlock the full CCU potential of LLMs. |
| Outcome: | The proposed model unlocks the full CCU potential of LLMs by preserving its foundational knowledge while maintaining redundancy-aware tuning (RAT) and CCU-RAG. |
SoftMCL: Soft Momentum Contrastive Learning for Fine-grained Sentiment-aware Pre-training (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods for pre-training language models capture general language understanding but fail to distinguish affective impact of a particular context to a specific word. |
| Approach: | They propose a soft momentum contrastive learning method for fine-grained sentiment-aware pre-training that uses valence ratings as soft-label supervision instead of hard labels. |
| Outcome: | The proposed method improves on four sentiment-related tasks and the results are published online. |
AssistedDS: Benchmarking How External Domain Knowledge Assists LLMs in Automated Data Science (2025.findings-emnlp)
Copied to clipboard
An Luo, Xun Xian, Jin Du, Fangqiao Tian, Ganghua Wang, Ming Zhong, Shengchun Zhao, Xuan Bi, Zirui Liu, Jiawei Zhou, Jayanth Srinivasa, Ashish Kundu, Charles Fleming, Mingyi Hong, Jie Ding
| Challenge: | Large language models (LLMs) have advanced the automation of data science workflows, yet it remains unclear whether they can critically leverage external domain knowledge as human data scientists do in practice. |
| Approach: | They propose a benchmark to evaluate how large language models handle external domain knowledge in tabular prediction tasks. |
| Outcome: | The proposed model evaluates whether it can critically leverage external domain knowledge as human data scientists do in practice. |
ERRV: Eliciting Efficient Reasoning through Reasoning Vectors for Policy Optimization in Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing efforts to improve reasoning efficiency of large language models focus on modifying the reinforcement learning reward, such as adding length penalties. |
| Approach: | They propose a training framework that elicits efficient reasoning through reasoning vectors and a framework that allows the model to generate high-quality responses during reinforcement learning. |
| Outcome: | The proposed framework reduces reasoning length by 30% while maintaining stability, while retaining high accuracy. |
FinSight: Towards Real-World Financial Deep Research (2026.acl-long)
Copied to clipboard
| Challenge: | FinSight is the first multi-agent framework for automating end-to-end professional, multimodal financial reports. |
| Approach: | They propose a code agent with variable memory architecture that unifies data, tools, and agents into a programmable variable space. |
| Outcome: | The proposed framework outperforms leading deep research systems in factual accuracy, analytical depth, and presentation quality. |
MccSTN: Multi-Scale Contrast and Fine-Grained Feature Fusion Networks for Subject-driven Style Transfer (2024.lrec-main)
Copied to clipboard
| Challenge: | Stylistic style transfer is an important part of the image processing field . due to the low semantic similarity between the original image and the style image, many fine-grained style features are discarded. |
| Approach: | They propose a new style representation and transfer framework that can be adapted to existing image style transfers. |
| Outcome: | The proposed framework can be adapted to existing image style transfers. |
Neural Attention-Aware Hierarchical Topic Model (2021.emnlp-main)
Copied to clipboard
| Challenge: | Neural topic models (NTMs) use deep neural networks to learn topic information. |
| Approach: | They propose a variational autoencoder model that reconstructs sentence and document word counts using bag-of-words embeddings and pre-trained semantic embedders. |
| Outcome: | The proposed model lowers reconstruction errors at sentence and document levels and finds more coherent topics from real-world datasets. |
CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents (2025.findings-acl)
Copied to clipboard
Tianqi Xu, Linyao Chen, Dai-Jie Wu, Yanjun Chen, Zecheng Zhang, Xiang Yao, Zhiqiang Xie, Yongchao Chen, Shilong Liu, Bochen Qian, Anjie Yang, Zhaoxuan Jin, Jianbo Deng, Philip Torr, Bernard Ghanem, Guohao Li
| Challenge: | Existing benchmarks for MLM agents in interactive environments are limited by their focus on a single environment, lack of detailed and generalized evaluation methods, and the complexity of constructing tasks and evaluators. |
| Approach: | They propose a cross-environment agent benchmark framework that integrates graph-based evaluation and task generation methods. |
| Outcome: | The proposed framework supports multiple devices and can be easily extended to any environment with a Python interface. |
Interaction-Aware Topic Model for Microblog Conversations through Network Embedding and User Attention (C18-1)
Copied to clipboard
| Challenge: | Existing topic models ignore that one discusses diverse topics when dynamically interacting with different people. |
| Approach: | They propose an Interaction-Aware Topic Model (IATM) for microblog conversations by integrating network embedding and user attention. |
| Outcome: | The proposed model is based on three real-world microblog datasets. |
Two-Stage Regularization-Based Structured Pruning for LLMs (2026.acl-long)
Copied to clipboard
Mingkuan Feng, Jinyang Wu, Siyuan Liu, Shuai Zhang, Hongjian Fang, Ruihan Jin, Feihu Che, Pengpeng Shao, Zhengqi Wen, Jianhua Tao
| Challenge: | Structural pruning is a promising solution for large language models . prior structured pruning methods remove unimportant parameters based on certain metrics . |
| Approach: | They propose a structural pruning method that iteratively learns the weights of transformer layers by adding their l1-norm to the loss function. |
| Outcome: | The proposed pruning method outperforms strong layer-wise pruning methods without requiring retraining. |
Balancing Fidelity and Plasticity: Aligning Mixed-Precision Fine-Tuning with Linguistic Hierarchies (2026.findings-acl)
Copied to clipboard
Changhai Zhou, Shiyang Zhang, Yuhua Zhou, Jun Gao, Qian Qiao, Shichao Weng, Weizhong Zhang, Cheng Jin
| Challenge: | Existing quantization-aware fine-tuning methods decouple weight precision and adapter capacity, overlooking that a layer’s ability to adapt is constrained by the information preserved in its frozen weights. |
| Approach: | They propose a framework that jointly optimizes per-layer quantization bit-width and LoRA rank. |
| Outcome: | Experiments on LLaMA and Qwen models show that the proposed framework matches or approaches 16-bit baselines while using substantially less memory. |
A Multi-persona Framework for Argument Quality Assessment (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for argument quality assessment do not consider multi-perspective evaluation due to subjective nature of arguments. |
| Approach: | They propose a multi-persona framework for argument quality assessment that simulates diverse evaluator perspectives through large language models. |
| Outcome: | The proposed framework outperforms baselines while providing comprehensive multi-perspective rationales on IBM-Rank-30k and IBM-ArgQ-5.3kArgs datasets. |
Pause or Fabricate? Training Language Models for Grounded Reasoning (2026.findings-acl)
Copied to clipboard
Yiwen Qiu, Linjuan Wu, Yizhou Liu, Yuchen Yan, Jin Ma, Xu Tan, Yao Hu, Daoxin Zhang, Wenqi Zhang, Weiming Lu, Jun Xiao, Yongliang Shen
| Challenge: | Large language models implicitly fabricate information when inputs are incomplete, causing confidence but unreliable conclusions. |
| Approach: | They propose a framework for grounded reasoning under incomplete information that decomposes reasoning into two stages . they propose stage-specific rewards to penalize hallucinations, enabling models to detect gaps, stop proactively, and resume reasoning after clarification. |
| Outcome: | The proposed framework improves premise detection and task success by 30% . it also reduces average response length by over 20% . |
A Knowledge Plug-and-Play Test Bed for Open-domain Dialogue Generation (2024.lrec-main)
Copied to clipboard
| Challenge: | Knowledge-based open-domain dialogue generation aims to build chit-chat systems that talk to humans using mined support knowledge. |
| Approach: | They propose a benchmark for evaluating multi-source dialogue knowledge selection and response generation using Wikipedia's wizard of Wikipedia. |
| Outcome: | The proposed benchmark is called multi-source Wizard of Wikipedia (Ms.WoW) it contains clean support knowledge, grounded at the utterance level and partitioned into multiple knowledge sources. |
MEEL: Multi-Modal Event Evolution Learning (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing models fail to grasp the principles governing event evolution in various scenarios. |
| Approach: | They propose a multi-modal event evolution learning approach to grasp event evolution . they propose an instruction encapsulation process that transforms evolving graphs into instruction-tuning data . |
| Outcome: | The proposed model grasps the event evolution mechanism yielding advanced MMER ability. |
ChemReason-Bench: Benchmarking Large Language Models for Procedural Reasoning in Experimental Chemistry (2026.acl-long)
Copied to clipboard
| Challenge: | Experimental protocols in organic synthesis specify not only the intended transformation, but also an executable sequence of operations and conditions. |
| Approach: | They propose a human-validated benchmark for verifiable experimental procedure reasoning . they instantiate 7306 benchmark tasks across six complementary formats . |
| Outcome: | The proposed benchmarks show that the evaluations are less diagnostic of procedure-level decision making. |
Identifying Factual Inconsistencies in Summaries: Grounding LLM Inference via Task Taxonomy (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies have focused on specialized BERT-variants and recent LLMs to reason inconsistencies. |
| Approach: | They propose to incorporate task-specific taxonomy into inferences to facilitate both zero-shot and supervised paradigms. |
| Outcome: | The proposed model outperforms specialized non-LLM and recent LLM models in a number of domains. |
Multi-Granularity Interaction Network for Extractive and Abstractive Multi-Document Summarization (2020.acl-main)
Copied to clipboard
| Challenge: | Existing methods for document summarization use extractive and abstractive representations, but they don't take into account hierarchical structure of document clusters. |
| Approach: | They propose a multi-granularity interaction network for extractive and abstractive multi-document summarization which jointly learn semantic representations for words, sentences, and documents. |
| Outcome: | The proposed model outperforms baseline methods and achieves the best results on the Multi-News dataset. |
Towards Fine-Grained and Multi-Granular Contrastive Language-Speech Pre-training (2026.acl-long)
Copied to clipboard
Yifan Yang, Bing Han, Hui Wang, Wei Wang, Ziyang Ma, Long Zhou, Zengrui Jin, Guanrou Yang, Tianrui Wang, Xu Tan, Xie Chen
| Challenge: | Existing models for fine-grained speaking styles are limited in terms of accuracy, coverage, and naturalness. |
| Approach: | They propose a model that pre-trains with coarse captions and annotates with a pipeline that grounds captions in audio. |
| Outcome: | The proposed model outperforms existing models with fine-grained style annotations . it integrates global and fine-granular supervision, enabling unified representations based on the proposed model . |
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. |
Your Reasoning Benchmark May Not Test Reasoning: Revealing Perception Bottleneck in Abstract Reasoning Benchmarks (2026.acl-long)
Copied to clipboard
| Challenge: | Abstraction and Reasoning Corpus and ARC-AGI are widely used to assess progress in artificial intelligence. |
| Approach: | They propose a two-stage pipeline that separates perception and reasoning . they propose to test this pipeline against standard end-to-end one-stage evaluation . |
| Outcome: | The proposed pipeline separates perception and reasoning, and isolates reasoning from bottlenecks. |
Reasoning with Trees: Faithful Question Answering over Knowledge Graph (2025.coling-main)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have shown remarkable progress in reasoning capabilities, yet they still face challenges in complex, multi-step reasoning tasks. |
| Approach: | They propose a framework that synergistically integrates LLMs with knowledge graphs (KGs) to enhance reasoning performance and interpretability. |
| Outcome: | The proposed framework outperforms existing state-of-the-art methods on two benchmark KGQA datasets and improves on the MCTS process. |
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. |
Adaptive Rank Selections for Low-Rank Approximation of Language Models (2024.naacl-long)
Copied to clipboard
| Challenge: | Singular Value Decomposition (SVD) or its weighted variants has progressed in compressing language models. |
| Approach: | They propose a binary masking mechanism for optimizing the number of ranks in a differentiable framework. |
| Outcome: | The proposed algorithm achieves much better accuracy than previous SVD and its weighted variants. |
FinMaster: A Holistic Benchmark for Full-Pipeline Financial Management with Large Language Models (2026.findings-acl)
Copied to clipboard
Junzhe Jiang, Chang Yang, Aixin Cui, Sihan Jin, Yujing Zhang, Yilin Xiao, Ruiyu Wang, Bo Li, Xiao Huang, Danny Dongning Sun, Xinrun Wang
| Challenge: | Existing benchmarks lack domain-specific data, realistic workflow-level task design, and standardized workflow- level evaluation. |
| Approach: | a new benchmark evaluates large language models on financial management workflows . the global financial services market is projected to grow to $37 trillion by 2027 . |
| Outcome: | a new benchmark for large language models on financial management workflows reveals critical capability gaps . accuracy drops from 90% on basic tasks to 40% on complex scenarios requiring multi-step reasoning . the global financial services market reached $25.8 trillion in 2022 and is projected to grow to $37 trillion by 2027 . |
SciAssess: Benchmarking LLM Proficiency in Scientific Literature Analysis (2025.findings-naacl)
Copied to clipboard
Hengxing Cai, Xiaochen Cai, Junhan Chang, Sihang Li, Lin Yao, Wang Changxin, Zhifeng Gao, Hongshuai Wang, Li Yongge, Mujie Lin, Shuwen Yang, Jiankun Wang, Mingjun Xu, Jin Huang, Xi Fang, Jiaxi Zhuang, Yuqi Yin, Yaqi Li, Changhong Chen, Zheng Cheng, Zifeng Zhao, Linfeng Zhang, Guolin Ke
| Challenge: | Existing benchmarks fail to adequately evaluate the proficiency of Large Language Models (LLMs) Existing standards do not cover the skills needed to evaluate LLMs in scientific literature analysis. |
| Approach: | They propose a benchmark to evaluate the proficiency of large language models in scientific literature analysis. |
| Outcome: | SciAssess evaluates 11 LLMs on multiple tasks across scientific fields. |
mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding (2024.findings-emnlp)
Copied to clipboard
Anwen Hu, Haiyang Xu, Jiabo Ye, Ming Yan, Liang Zhang, Bo Zhang, Ji Zhang, Qin Jin, Fei Huang, Jingren Zhou
| Challenge: | Existing Multimodal Large Language Models lack general structure understanding abilities for text-rich document images. |
| Approach: | They propose to use unified structure learning to boost the performance of MLLMs by encoding structure information into text-rich images. |
| Outcome: | The proposed model achieves state-of-the-art on 10 visual document understanding benchmarks. |
CausalCite: A Causal Formulation of Paper Citations (2024.findings-acl)
Copied to clipboard
Ishan Agrawal, Zhijing Jin, Ehsan Mokhtarian, Siyuan Guo, Yuen Chen, Mrinmaya Sachan, Bernhard Schölkopf
| Challenge: | citation counts are often criticized for failing to accurately reflect the true impact of a paper. |
| Approach: | They propose a method to measure the impact of a paper on follow-up papers by comparing similar papers by cosine similarity. |
| Outcome: | The proposed method is based on a new causal inference method, TextMatch. |
Self-Edit: Fault-Aware Code Editor for Code Generation (2023.acl-long)
Copied to clipboard
| Challenge: | Existing Large language models (LLMs) have low pass rates and accuracy on competitive programming tasks. |
| Approach: | They propose a generate-and-edit approach that uses execution results of generated code from LLMs to improve code quality on competitive programming tasks. |
| Outcome: | The proposed method improves pass@1 by 89% on APPS-dev, 31% on apps-test, and 48% on HumanEval over nine popular code generation LLMs with parameter sizes ranging from 110M to 175B. |
Democratic or Authoritarian? Probing a New Dimension of Political Biases in Large Language Models (2026.eacl-long)
Copied to clipboard
| Challenge: | Prior work on LLM biases focused on socio-demographic and left–right political dimensions, but little attention has been paid to how they align with broader geopolitical value systems. |
| Approach: | They propose a method to assess how LLMs align with broader geopolitical value systems, particularly the democracy–authoritarianism spectrum. |
| Outcome: | The proposed method combines the F-scale, FavScore and role-model probing to assess which figures are cited as general role models by LLMs. |
OpenEval: Benchmarking Chinese LLMs across Capability, Alignment and Safety (2024.acl-demos)
Copied to clipboard
Chuang Liu, Linhao Yu, Jiaxuan Li, Renren Jin, Yufei Huang, Ling Shi, Junhui Zhang, Xinmeng Ji, Tingting Cui, Liutao Liutao, Jinwang Song, Hongying Zan, Sun Li, Deyi Xiong
| Challenge: | a rapid development of Chinese large language models poses big challenges for efficient LLM evaluation. |
| Approach: | They propose an evaluation testbed that benchmarks Chinese LLMs across capability, alignment and safety. |
| Outcome: | The evaluation platform OpenEval benchmarks Chinese LLMs across capability, alignment and safety. |
mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding (2025.acl-long)
Copied to clipboard
| Challenge: | Multimodal Large Language Models (MLLMs) have improved document understanding performance but generate thousands of visual tokens for a single document image, leading to excessive GPU memory and slower inference times. |
| Approach: | They propose a high-resolution document compression module to generate 324 tokens for a single document image. |
| Outcome: | The proposed module reduces first token latency by more than 50% and improves document comprehension performance. |
Parameter-efficient Tuning for Large Language Model without Calculating Its Gradients (2023.emnlp-main)
Copied to clipboard
| Challenge: | Recent parameter-efficient tuning methods can only save 30% of training memory . gradient computation and backpropagation are still necessary for these methods . |
| Approach: | They propose a parameter-efficient tuning method that can be used to fine-tune large language models without calculating gradients. |
| Outcome: | The proposed method saves 30% of training memory and improves performance on large language models. |
Hooks in the Headline: Learning to Generate Headlines with Controlled Styles (2020.acl-main)
Copied to clipboard
| Challenge: | Current summarization systems only produce plain, factual headlines, far from the practical needs for exposure and memorableness of the articles. |
| Approach: | They propose a task to generate relevant headlines with three style options . they propose combining summarization and reconstruction tasks into a multitasking framework . |
| Outcome: | The proposed method outperforms the state-of-the-art summarization model by 9.68% . it can generate relevant, fluent headlines with humor, romance and clickbait . |
WorkForceAgent-R1: Incentivizing Reasoning Capability in LLM-based Web Agents via Reinforcement Learning (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing web agents relying on supervised fine-tuning struggle with generalization and robustness due to insufficient reasoning capabilities when handling the inherently dynamic nature of web interactions. |
| Approach: | They propose a large language model-empowered web agent that trains using a rule-based reinforcement learning framework to enhance single-step reasoning and planning for business-oriented web navigation tasks. |
| Outcome: | The proposed agent outperforms baseline LLM-based agents on the WorkArena benchmark by 10.26–16.59%. |
Abstractive Multi-Document Summarization via Joint Learning with Single-Document Summarization (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for document summarization are extractive and abstractive. |
| Approach: | They propose to jointly learn an abstractive single-document decoder and a decoding controller to aggregate the decoded outputs for multiple input documents. |
| Outcome: | The proposed model outperforms several baselines on two multi-document summarization datasets and proves that it is useful for both tasks. |
QSpell 250K: A Large-Scale, Practical Dataset for Chinese Search Query Spell Correction (2025.naacl-industry)
Copied to clipboard
| Challenge: | Chinese Search Query Spell Correction is a task designed to identify and correct typographical errors within queries. |
| Approach: | They propose a large-scale benchmark specifically developed for Chinese Query Spell Correction. |
| Outcome: | The proposed benchmark covers a broad range of topics, including formal entities, everyday colloquialisms and idiomatic expressions. |
Factuality Assessment as Modal Dependency Parsing (2021.acl-long)
Copied to clipboard
| Challenge: | a critical step towards factuality assessment is to determine the factuality of events in text. |
| Approach: | They propose a modal dependency parsing task that assesses the factuality of events in text . they crowdsource a large-scale data set annotated with modal dependence structures . |
| Outcome: | The proposed model outperforms the pipeline model in factuality assessment . the proposed model is based on a crowdsourced dataset . |
Exploring Attention Attractors in Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Existing studies have suggested that attention attractors function as "summary tokens" while others speculate that tokens with weaker semantics attract high attention, they act as attention sinks that offload excessive attention. |
| Approach: | They examine attention attractors, tokens that draw significantly high attention, in large language models. |
| Outcome: | The proposed models are able to capture long-range dependencies within a given context. |
AudioVSR: Enhancing Video Speech Recognition with Audio Data (2024.emnlp-main)
Copied to clipboard
Xiaoda Yang, Xize Cheng, Jiaqi Duan, Hongshun Qiu, Minjie Hong, Minghui Fang, Shengpeng Ji, Jialong Zuo, Zhiqing Hong, Zhimeng Zhang, Tao Jin
| Challenge: | Recent work has shown poor performance with non-Indo-European languages . previous work primarily utilizes video information to build VSR models . |
| Approach: | They propose a generative model for data inflation that integrates synthetic data with authentic visual data to enhance the VSR model. |
| Outcome: | The proposed model improves on the audio-visual alignment problem in audio-video tasks. |
Taylor Unswift: Secured Weight Release for Large Language Models via Taylor Expansion (2024.emnlp-main)
Copied to clipboard
Guanchu Wang, Yu-Neng Chuang, Ruixiang Tang, Shaochen Zhong, Jiayi Yuan, Hongye Jin, Zirui Liu, Vipin Chaudhary, Shuai Xu, James Caverlee, Xia Hu
| Challenge: | Existing mechanisms compromise ownership rights or raise data privacy concerns . existing mechanisms compromise security of released large language models . |
| Approach: | They propose a TaylorMLP to preserve the ownership of large language models by transforming the weights of LLMs into Taylor-series parameters instead of releasing original weights . |
| Outcome: | The proposed model preserves ownership of large language models and prevents their abuse by adjusting the generation speed and causing low-speed token generation. |
Leveraging Prefix Transfer for Multi-Intent Text Revision (2023.acl-short)
Copied to clipboard
Ruining Chong, Cunliang Kong, Liu Wu, Zhenghao Liu, Ziye Jin, Liner Yang, Yange Fan, Hanghang Fan, Erhong Yang
| Challenge: | Text revision is a necessary process to improve text quality. |
| Approach: | They propose a multi-intent text revision system that can revise texts without explicit intent annotation. |
| Outcome: | The proposed system outperforms baselines on the IteraTeR dataset and significantly improves the SARI score with more than 3% improvement. |
CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges (2024.acl-long)
Copied to clipboard
| Challenge: | Large Language Models excel in simple tasks such as generating standalone code units, but real-world software development often involves complex code repositories with complex dependencies and extensive documentation. |
| Approach: | They propose a novel LLM-based agent framework that employs external tools for effective repo-level code generation. |
| Outcome: | The proposed framework outperforms commercial products like Github Copilot in the humanEval benchmark and shows that it is adaptable and efficient across multiple code generation tasks. |
InsLogicBench: An Argumentation Logic Grounded Benchmark for Complex Insurance Claims Adjudication (2026.acl-long)
Copied to clipboard
Jin Liu, Yunpeng Liu, Keyi Wang, Jie Shi, Xiao Xu, Wenkang Huang, Xingzhong Xu, Xin Liang, Yanghua Xiao
| Challenge: | Existing benchmarks for insurance claims adjudication are limited to information retrieval or simple multiple-choice setups. |
| Approach: | They propose a benchmark that provides complete reasoning traces linking factual inputs, relevant policy clauses, and final verdicts. |
| Outcome: | The proposed benchmark shows that models often produce correct decisions but fail to provide precise justifications, highlighting a critical discrepancy between decision accuracy and logical reasoning capabilities. |
RouteRAG: Efficient Retrieval-Augmented Generation from Text and Graph via Reinforcement Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing graph-based or hybrid systems lack the ability to integrate supplementary evidence as reasoning unfolds. |
| Approach: | They propose a framework that integrates non-parametric knowledge into Large Language Models . they use a RL-based framework to optimize the entire generation process via RL . |
| Outcome: | The proposed framework outperforms existing RAG frameworks in five question answering benchmarks. |
PACE: Improving Prompt with Actor-Critic Editing for Large Language Model (2024.findings-acl)
Copied to clipboard
| Challenge: | Prompt with Actor-Critic Editing (PACE) for LLMs improves performance of different human-written prompts, resulting in significant performance discrepancies. |
| Approach: | They propose to use LLMs as actors and critics to enable automatic prompt editing by taking feedback from both actors performing prompt and criticizing response into account. |
| Outcome: | The proposed model improves the performance of human-written prompts by 98% and compares to high-quality human-writing prompts. |
BIDER: Bridging Knowledge Inconsistency for Efficient Retrieval-Augmented LLMs via Key Supporting Evidence (2024.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated efficacy in knowledge-intensive tasks such as open-domain QA, but inconsistencies between retrieval knowledge and the necessary knowledge for LLMs, leading to a decline in LLM’s answer quality. |
| Approach: | They propose a retrieval-augmented large language model that refines retrieval documents into Key Supporting Evidence (KSE) through knowledge synthesis, supervised fine-tuning, and preference alignment. |
| Outcome: | The proposed model outperforms existing methods in five datasets and boosts answer quality by 7% while reducing input content length by 80%. |
LLM-REDIAL: A Large-Scale Dataset for Conversational Recommender Systems Created from User Behaviors with LLMs (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing CRS datasets suffer from data inextensibility and semantic inconsistency . |
| Approach: | They introduce the LLM-REDIAL dataset to facilitate the research in CRS by leveraging large language models to generate high-quality dialogues. |
| Outcome: | The proposed dataset is the largest multi-domain CRS dataset which consists of 47.6k multi-turn dialogues with 482.6k utterances across 4 domains. |
Automatic Generation of Model and Data Cards: A Step Towards Responsible AI (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing models and datasets are incomplete and lack consistent documentation. |
| Approach: | They propose an automated generation approach using Large Language Models (LLMs) their paper establishes a comprehensive dataset and develops 'CardGen' pipeline . |
| Outcome: | The proposed approach exhibits enhanced completeness, objectivity, and faithfulness in generated model and data cards, a significant step in responsible AI documentation practices ensuring better accountability and traceability. |
MULFE: A Multi-Level Benchmark for Free Text Model Editing (2024.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have impressive capabilities in comprehending human language and vast parametric knowledge obtained from large corpora. |
| Approach: | They propose a multi-level benchmark for free text model editing to bridge the gap . they categorize probe queries into three levels of generalization . |
| Outcome: | The proposed method improves the generalization performance of large langugae models. |
Analyzing Norm Violations in Live-Stream Chat (2023.emnlp-main)
Copied to clipboard
Jihyung Moon, Dong-Ho Lee, Hyundong Cho, Woojeong Jin, Chan Park, Minwoo Kim, Jonathan May, Jay Pujara, Sungjoon Park
| Challenge: | Existing methods for detecting toxic language and norm violations are limited to live-streaming platforms . existing methods are less effective when applied to live streaming platforms based on a limited time frame . |
| Approach: | They propose to use contextual information to automatically moderate toxic content on live streaming platforms. |
| Outcome: | The proposed model improves on live-streaming platforms by 35%. |
FinRAGBench-V: A Benchmark for Multimodal RAG with Visual Citation in the Financial Domain (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing RAG research focuses on textual data, overlooking rich visual content in financial documents. |
| Approach: | They propose a visual RAG benchmark tailored for finance that integrates multimodal data and provides visual citation to ensure traceability. |
| Outcome: | The proposed visual RAG benchmark integrates multimodal data and provides visual citation to ensure traceability. |
A Topic Augmented Text Generation Model: Joint Learning of Semantics and Structural Features (D19-1)
Copied to clipboard
| Challenge: | Existing methods for text generation are limited in supervised setting and designed for specific applications. |
| Approach: | They propose a text generation model that learns semantics and structural features simultaneously . their model leverages a topic-based model to enhance the recognition of text semantics . |
| Outcome: | The proposed model outperforms state-of-the-art models in terms of text perplexity and topic coherence. |
Zero-Shot Cross-Domain Dialogue State Tracking via Dual Low-Rank Adaptation (2024.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to zero-shot dialogue state tracking (DST) involve embedding prompts into language models, but these methods have inherent limitations. |
| Approach: | They propose a plug-and-play architecture designed for zero-shot dialogue state tracking (DST) dual low-rank adaptation targets dialogue context processing and prompt optimization without incurring additional inference latency. |
| Outcome: | The proposed architecture outperforms baseline methods on multi-domain datasets and the MultiWOZ dataset. |
PaperMentor: A Human-Centered Multi-Agent Writing Tutor for AI Research Papers in Overleaf (2026.acl-demo)
Copied to clipboard
Jiarui Liu, Terry Jingchen Zhang, Ryan Faulkner, Xuanqiang Angelo Huang, Vilém Zouhar, Dominik Glandorf, Isabel Dahlgren, Rishit Dagli, Yuen Chen, Felix Leeb, Van Q. Truong, Punya Syon Pandey, Yves Bicker, Suvajit Majumder, Wenyuan Jiang, Zeju Qiu, Sankalan Pal Chowdhury, Mrinmaya Sachan, Bernhard Schölkopf, Mona T. Diab, Zhijing Jin
| Challenge: | Emerging AI-powered writing assistants focus on grammar fixes or simulating peer review with final scores, yet they fall short of providing concrete, actionable suggestions that help students improve their papers during drafting. |
| Approach: | They propose a human-centered writing assistant system that delivers actionable suggestions as Overleaf-native inline comments while leaving the actual writing entirely to human authors. |
| Outcome: | The proposed system outperforms a baseline with the skill library and provides actionable suggestions while leaving the actual writing to human authors. |
On Transferability of Bias Mitigation Effects in Language Model Fine-Tuning (2021.naacl-main)
Copied to clipboard
| Challenge: | PTLMs can exhibit biases against protected groups in a host of modeling tasks . but, fine-tuned LMs may propagate bias to downstream classifiers . |
| Approach: | They propose to use upstream bias mitigation techniques to reduce bias on downstream tasks by fine-tuning an upstream model and applying it to a downstream model. |
| Outcome: | The proposed model reduces bias on hate speech detection, toxicity detection and coreference resolution tasks over bias factors. |
LLMs are Biased Evaluators But Not Biased for Fact-Centric Retrieval Augmented Generation (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent studies have shown that large language models (LLMs) exhibit significant biases in evaluation tasks, especially in preferentially rating and favoring self-generated content. |
| Approach: | They propose to simulate two critical phases of retrieval-augmented generation (RAG) frameworks where keyword extraction and factual accuracy take precedence over stylistic elements. |
| Outcome: | The proposed model emulates two critical phases of the retrieval-augmented generation framework. |
PCEE-BERT: Accelerating BERT Inference via Patient and Confident Early Exiting (2022.findings-naacl)
Copied to clipboard
| Challenge: | Pre-trained language models (PLMs) are the state-of-the-art (SOTA) models for natural language processing (NLP). |
| Approach: | They propose a patient and confident early exiting BERT (PCEE-BERT) that can work with different PLMs and popular model compression methods. |
| Outcome: | The proposed method outperforms existing models on the GLUE benchmarks and achieves different speed-up ratios. |
MM-SOC: Benchmarking Multimodal Large Language Models in Social Media Platforms (2024.findings-acl)
Copied to clipboard
| Challenge: | Social media platforms are hubs for multimodal information exchange, encompassing text, images, and videos, making it challenging for machines to comprehend the information or emotions associated with interactions in online spaces. |
| Approach: | They propose a benchmark to evaluate MLLMs' understanding of multimodal social media content and a large-scale YouTube tagging dataset to evaluate their performance. |
| Outcome: | The proposed model performs better in a zero-shot setting, suggesting potential improvements. |
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. |
Finite State Automata Inside Transformers with Chain-of-Thought: A Mechanistic Study on State Tracking (2025.acl-long)
Copied to clipboard
| Challenge: | Existing studies show that Chain-of-thought (CoT) can enhance the performance of large language models (LLMs) however, there is limited understanding of the algorithms that Transformer+CoT can learn. |
| Approach: | They propose two metrics to evaluate Transformer+CoT's state tracking capabilities and identify the circuit responsible for tracking the world state. |
| Outcome: | The proposed model achieves 100% accuracy for each state, highlighting an implicit finite state automaton (FSA) embedded within the model. |
CONTRANS: Weak-to-Strong Alignment Engineering via Concept Transplantation (2025.coling-main)
Copied to clipboard
| Challenge: | Large language models behave consistently with human goals, values and intentions, but are computationally expensive. |
| Approach: | They propose a framework that enables weak-to-strong alignment transfer via concept transplantation. |
| Outcome: | The proposed framework surpasses instruction-tuned models in terms of truthfulness. |
CogKGE: A Knowledge Graph Embedding Toolkit and Benchmark for Representing Multi-source and Heterogeneous Knowledge (2022.acl-demo)
Copied to clipboard
Zhuoran Jin, Tianyi Men, Hongbang Yuan, Zhitao He, Dianbo Sui, Chenhao Wang, Zhipeng Xue, Yubo Chen, Jun Zhao
| Challenge: | Existing methods focus on entity-centric knowledge, but CogKGE supports heterogeneous knowledge. |
| Approach: | They propose a knowledge graph embedding toolkit to represent multi-source and heterogeneous knowledge. |
| Outcome: | The proposed toolkit provides a unified programming framework for KGE tasks and a series of knowledge representations for downstream tasks. |
NeuInfer: Knowledge Inference on N-ary Facts (2020.acl-main)
Copied to clipboard
| Challenge: | Existing studies on knowledge inference on binary facts have focused on finding out connotative valid facts. |
| Approach: | They propose a neural network model, NeuInfer, for knowledge inference on n-ary facts. |
| Outcome: | The proposed model can cope with the task to infer an unknown element in a whole fact, while ignoring the binary facts. |
Exploring Quality and Diversity in Synthetic Data Generation for Argument Mining (2025.emnlp-main)
Copied to clipboard
| Challenge: | Argument Mining (AM) is hindered by the scarcity of structure-annotated datasets, which are expensive to create manually. |
| Approach: | They propose to use quality-oriented synthesis and diversity-oriented approach to generate argumentative texts with diverse topics and argument structures. |
| Outcome: | The proposed approach significantly improves existing models in full-data and low-resource settings. |
Beyond Logits: Aligning Feature Dynamics for Effective Knowledge Distillation (2025.acl-long)
Copied to clipboard
Guoqiang Gong, Jiaxing Wang, Jin Xu, Deping Xiang, Zicheng Zhang, Leqi Shen, Yifeng Zhang, JunhuaShu JunhuaShu, ZhaolongXing ZhaolongXing, Zhen Chen, Pengzhang Liu, Ke Zhang
| Challenge: | Knowledge distillation (KD) compresses large language models into lightweight versions called student models. |
| Approach: | They propose to align the entire feature dynamics between teacher and student models by using two additional loss terms to achieve this. |
| Outcome: | The proposed method matches the entire feature dynamics between teacher and student models rather than just the final states. |
Self-Harmonized Chain of Thought (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing methods for chain-of-thought prompting have limitations . arithmetic, commonsense, and symbolic reasoning tasks are challenging . |
| Approach: | They propose a method that unifies diverse solution paths into a consistent reasoning pattern. |
| Outcome: | The proposed method outperforms existing methods by 2.8% on reasoning tasks. |
Taming LLMs with Gradient Grouping (2025.acl-long)
Copied to clipboard
| Challenge: | a new study presents scaling with gradient grouping (SGG) the adaptive learning rate scaling approach is based on per-parameter statistics, which incurs memory overhead. |
| Approach: | They propose an optimizer wrapper that improves adaptive learning rate estimation by dynamic grouping and group-specific scaling. |
| Outcome: | The proposed algorithm improves learning rate estimation on diverse models with different model sizes and batch sizes. |
Accelerating Inference for Pretrained Language Models by Unified Multi-Perspective Early Exiting (2022.coling-1)
Copied to clipboard
| Challenge: | Existing competitive methods to accelerate inference of pretrained language models are limited by their complexity and computational consumption. |
| Approach: | They propose a unified horizontal and vertical multi-perspective early exiting framework to accelerate inference of transformer-based models. |
| Outcome: | Experiments show that MPEE can achieve higher acceleration inference with competent performance than existing competitive methods. |
DocumentNet: Bridging the Data Gap in Document Pre-training (2023.emnlp-industry)
Copied to clipboard
| Challenge: | Document understanding tasks are a tedious task that requires extensive training and privacy constraints. |
| Approach: | They propose a method to collect weakly labeled data from the web to benefit VDER training . the collected dataset does not depend on specific document types or entity sets . |
| Outcome: | The proposed method does not depend on specific document types or entity sets, making it universally applicable to all VDER tasks. |
M3CoT: A Novel Benchmark for Multi-Domain Multi-step Multi-modal Chain-of-Thought (2024.acl-long)
Copied to clipboard
| Challenge: | MCoT requires models to leverage knowledge from both textual and visual modalities for step-by-step reasoning. |
| Approach: | They propose a benchmark to address the challenges of MCoT, and evaluate it using vision large language models. |
| Outcome: | The proposed benchmark addresses the above challenges and shows that current models still struggle to reason in M3CoT. |
StuBot: Learning by Teaching a Conversational Agent Through Machine Reading Comprehension (2022.findings-emnlp)
Copied to clipboard
| Challenge: | StuBot provides adaptive feedback for learning by teaching . |
| Approach: | They propose a text-based conversational agent that provides adaptive feedback for learning by teaching. |
| Outcome: | The proposed agent improves learning performance, immersion, and overall experience by providing adaptive feedback to the users who input the explanation text. |
Evaluating Readability and Faithfulness of Concept-based Explanations (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for evaluating concepts from different perspectives lack a unified formalization. |
| Approach: | They propose a formal definition of concepts generalizing to diverse concept-based explanations’ settings and apply it to other types of explanations or tasks. |
| Outcome: | Extensive experimental analysis was carried out to determine the evaluation measures for explanation evaluation measures. |
Low-Rank HOCA: Efficient High-Order Cross-Modal Attention for Video Captioning (D19-1)
Copied to clipboard
| Challenge: | Existing studies on video captioning focus on the association relationships between multiple modalities. |
| Approach: | They propose a video captioning model with high-order cross-modal attention (HOCA) they propose low-rank HOCA which adopts tensor decomposition to reduce the space requirement . |
| Outcome: | The proposed model captures cross-modal interaction of different modalities and reduces space requirement. |
Text Augmented Open Knowledge Graph Completion via Pre-Trained Language Models (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to augment knowledge graph completion require factual triples or manual prompts to extract knowledge from a pre-trained language model. |
| Approach: | They propose a tool that generates quality query prompts and retrieves support information from large text corpora to probe knowledge from a pre-trained language model. |
| Outcome: | The proposed method outperforms embedding-based, graph-based and PLM-based methods on two benchmark datasets. |
MIND: From Passive Mimicry to Active Reasoning through Capability-Aware Multi-Perspective CoT Distillation (2026.acl-long)
Copied to clipboard
Jin Cui, Jiaqi Guo, Jiepeng Zhou, Ruixuan Yang, Jiayi Lu, Jiajun Xu, Jiangcheng Song, Boran Zhao, Pengju Ren
| Challenge: | Existing approaches restrict students to following a single golden rationale and treat different reasoning paths independently, causing suboptimal performance. |
| Approach: | They propose a capability-adaptive framework that transitions distillation from passive mimicry to active cognitive construction and employ a feedback-driven inertia calibration mechanism to align supervision with the student’s current adaptability. |
| Outcome: | Experiments show that the proposed framework achieves state-of-the-art performance on both in-distribution and out-of distribution benchmarks. |
HSCR: Hierarchical Self-Contrastive Rewarding for Aligning Medical Vision Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for medical vision-language models overlook modality misalignment . HSCR generates high-quality preference data with higher sampling probability . |
| Approach: | They propose a hierarchical self-contrastive reward approach that addresses two challenges in alignment . they leverage the inherent capability of Med-VLMs to generate dispreferred responses . |
| Outcome: | The proposed approach improves accuracy and trustworthiness of medical vision-label models with 2,000 training entries. |
Learn Continually, Generalize Rapidly: Lifelong Knowledge Accumulation for Few-shot Learning (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models that pursue rapid generalization to new tasks are mostly trained in a single shot on fixed datasets, unable to dynamically expand their knowledge. |
| Approach: | They propose a new learning setup that assumes a model learns from a sequence of diverse NLP tasks arriving sequentially, accumulating knowledge for improved generalization to new tasks. |
| Outcome: | The proposed learning setup improves generalization ability while retaining performance on the tasks learned earlier. |
Cross-lingual Text-to-SQL Semantic Parsing with Representation Mixup (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Experimental results show that Rex can benefit from cross-lingual training and improve the effectiveness of semantic parsers. |
| Approach: | They propose a Representation Mixup Framework for effectively exploiting translations in the cross-lingual Text-to-SQL task. |
| Outcome: | The proposed framework can benefit from cross-lingual training and improve the effectiveness of semantic parsers, achieving state-of-the-art performance. |
Joint Semantic and Strategy Matching for Persuasive Dialogue (2023.findings-emnlp)
Copied to clipboard
Chuhao Jin, Yutao Zhu, Lingzhen Kong, Shijie Li, Xiao Zhang, Ruihua Song, Xu Chen, Huan Chen, Yuchong Sun, Yu Chen, Jun Xu
| Challenge: | Persuasive dialogue models rely on utterance semantic matching and a key aspect has been ignored . compared with utterrance semantics, conversation strategies are high-level concepts, which can be informative and provide complementary information to achieve effective persuation. |
| Approach: | They propose to model conversation semantics and strategies to match them using a BERT-like module and an auto-regressive predictor. |
| Outcome: | The proposed model improves state-of-the-art by 5% on a small and 37% on 'large' datasets. |
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. |
Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Tools (2025.acl-long)
Copied to clipboard
| Challenge: | Existing reasoning methods excel in structured domains like math and code, but they are not all effective in knowledge-intensive tasks. |
| Approach: | They introduce a framework that enhances large language model reasoning by integrating external tool-using agents. |
| Outcome: | The proposed framework achieves state-of-the-art among public models and delivers comparable performance to OpenAI Deep Research. |
Fisher Information-based Efficient Curriculum Federated Learning with Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing frameworks for learning Large Language Models (LLMs) require adaptive data processing and low-rank adjustment to improve accuracy and fine-tuning speed. |
| Approach: | They propose a fisher information-based adaptive federated curriculum learning framework with two novel methods to improve FL fine-tuning process. |
| Outcome: | The proposed framework improves performance and fine-tuning speed compared with baseline approaches. |
End-to-End Conversational Search for Online Shopping with Utterance Transfer (2021.emnlp-main)
Copied to clipboard
Liqiang Xiao, Jun Ma, Xin Luna Dong, Pascual Martínez-Gómez, Nasser Zalmout, Chenwei Zhang, Tong Zhao, Hao He, Yaohui Jin
| Challenge: | a new study proposes a conversational search system that integrates product attributes and dialog with search . but it faces two real world challenges: imperfect product schema/knowledge and lack of training dialog data . |
| Approach: | They propose an end-to-end conversational search system that integrates search with text . they propose an utterance transfer approach that generates dialogue utterations from other domains . |
| Outcome: | The proposed system outperforms the best tested baseline in a conversational search dataset for online shopping. |
Why Does Reinforcement Learning Generalize? A Feature-Level Mechanistic Study of Post-Training in Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Reinforcement learning (RL)-based post-training often improves the reasoning performance of large language models beyond the training domain, while supervised fine-tuning (SFT) frequently leads to general capabilities forgetting. |
| Approach: | They propose a feature-level mechanistic analysis methodology to probe RL generalization using a controlled experimental setup. |
| Outcome: | The proposed method identifies a compact, task-agnostic set of features that directly mediate generalization across diverse tasks. |
HiSMatch: Historical Structure Matching based Temporal Knowledge Graph Reasoning (2022.findings-emnlp)
Copied to clipboard
Zixuan Li, Zhongni Hou, Saiping Guan, Xiaolong Jin, Weihua Peng, Long Bai, Yajuan Lyu, Wei Li, Jiafeng Guo, Xueqi Cheng
| Challenge: | Temporal Knowledge Graphs (TKGs) store facts as triples in the form of subject, relation, object, timestamps. |
| Approach: | They propose a Temporal Knowledge Graph (TKG) model that extends each triple with a timestamp to describe dynamic facts. |
| Outcome: | The proposed model improves on six benchmark datasets with up to 5.6% performance improvement compared to the state-of-the-art models. |
Knowledgeable or Educated Guess? Revisiting Language Models as Knowledge Bases (2021.acl-long)
Copied to clipboard
| Challenge: | Recent studies show that pre-trained masked language models can be factual knowledge bases. |
| Approach: | They conduct a rigorous study to explore the underlying predicting mechanisms of MLMs . they find that previous decent performance mainly owes to the biased prompts which overfit dataset artifacts a . |
| Outcome: | The proposed model improves on illustrative cases and external contexts . the results question the previous findings that MLMs can be reliable factual knowledge bases . |
How Can Cross-lingual Knowledge Contribute Better to Fine-Grained Entity Typing? (2022.findings-acl)
Copied to clipboard
| Challenge: | Extensive experiments on multi-lingual datasets show that our method significantly outperforms multiple baselines and can robustly handle negative transfer. |
| Approach: | They propose to transfer semantic knowledge from rich-resourced languages to low-resource languages by using multilingual transfer learning. |
| Outcome: | The proposed model outperforms baselines and can handle negative transfer. |
Adaptive Axes: A Pipeline for In-domain Social Stereotype Analysis (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to quantify social stereotypes have struggled to capture the variability in stereotypes across conceptual domains for the same social group. |
| Approach: | They propose to use text embedding models and adaptive semantic axes to recover stereotypes from contextual representations by using large language models. |
| Outcome: | The proposed pipeline surpasses token-based methods in capturing in-domain framing and tracks stereotypes along domain-specific semantic axes for in- domain texts. |
T-MAD: Target-driven Multimodal Alignment for Stance Detection (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for Multimodal Stance Detection struggle with generalizing to unseen targets and handling modality inconsistencies. |
| Approach: | They propose a multimodal stability detection model which captures target-specific relationships and balances modality contributions by iterative reasoning. |
| Outcome: | Experiments on the MMSD and MultiClimate datasets show that the proposed model outperforms state-of-the-art models with optimal results achieved using RoBERTa, ViT, and an iterative depth of 5. |
A Comprehensive Evaluation of Quantization Strategies for Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Quantization studies have focused on instruction-tuned LLMs, leaving their performance on other benchmarks unclear. |
| Approach: | They propose a framework to evaluate quantized large language models using four dimensions . they propose to reduce the bits needed for model weights or activations with minimal performance loss . |
| Outcome: | The proposed framework can retain comparable performance to non-quantized LLMs on most benchmarks. |
MM-BizRAG: Rethinking Multimodal Retrieval-Augmented Generation for General Purpose Enterprise Q&A (2026.acl-industry)
Copied to clipboard
Hanoz Bhathena, Parin Rajesh Jhaveri, Rohan Mittal, Prateek Singh, Aymen Kallala, Rachneet Kaur, Yiqiao Jin, Zhen Zeng, Adwait Ratnaparkhi, Denis Kochedykov
| Challenge: | Recent advances in multimodal retrieval-augmented generation (MM-RAG) have shifted toward minimal parsing, relying on page-level images for producing retriever embeddings and answer generation. |
| Approach: | They propose a document structure-aware split that extracts and represents document structure via a structure-based split that dynamically routes documents through orientation-specific ingestion pipelines. |
| Outcome: | The proposed model outperforms state-of-the-art vision-centric baselines by up to 32% points and achieves strong gains on report-style layouts. |
SYNTHIA: Novel Concept Design with Affordance Composition (2025.acl-long)
Copied to clipboard
Hyeonjeong Ha, Xiaomeng Jin, Jeonghwan Kim, Jiateng Liu, Zhenhailong Wang, Khanh Duy Nguyen, Ansel Blume, Nanyun Peng, Kai-Wei Chang, Heng Ji
| Challenge: | Existing studies on concept design using text-to-image models have enabled rapid ideation of novel visual concepts. |
| Approach: | They propose a framework for generating novel, functionally coherent designs based on desired affordances by decomposing concepts into parts and affordance . they also develop a curriculum learning scheme that fine-tunes T2I models to progressively learn affordance composition while maintaining visual novelty. |
| Outcome: | The proposed framework outperforms state-of-the-art models for novelty and functional coherence in human evaluation. |
Multimodal Prompt Learning with Missing Modalities for Sentiment Analysis and Emotion Recognition (2024.acl-long)
Copied to clipboard
| Challenge: | Existing methods for multimodal sentiment analysis often fail due to equipment failure, data corruption, privacy issues and the like. |
| Approach: | They propose a multimodal Transformer framework using prompt learning to address the issue of missing modalities. |
| Outcome: | The proposed framework outperforms existing methods significantly across evaluation metrics. |
Improving Neutral Point-of-View Generation with Data- and Parameter-Efficient RL (2025.emnlp-main)
Copied to clipboard
Jessica Hoffmann, Christiane Ahlheim, Zac Yu, Aria Walfrand, Jarvis Jin, Marie Tano, Ahmad Beirami, Erin MacMurray van Liemt, Nithum Thain, Hakim Sidahmed, Lucas Dixon
| Challenge: | Parameter-efficient reinforcement learning (PE-RL) is a highly effective training regime to improve large language models’ ability to answer queries on sensitive topics with a Neutral Point of View (NPOV). |
| Approach: | They propose to use parameter-efficient reinforcement learning to train large language models to answer queries with a Neutral Point of View (NPOV) This is compared to the strongest baseline, LoRA finetuning, SFT and RLHF. |
| Outcome: | The proposed training regime improves on NPOV quality and scores higher on features identified by linguists as key to separating good answers from the best answers. |
Generative Music Models’ Alignment with Professional and Amateur Users’ Expectations (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent years have witnessed rapid advances in text-to-music generation using large language models. |
| Approach: | They propose a task to align AI-generated music with human expressions . they use a dataset of over 1.5 million songs to analyze their content . |
| Outcome: | The proposed framework outperforms baseline models and facilitates end-to-end generation of songs audio. |
“Well, Keep Thinking”: Enhancing LLM Reasoning with Adaptive Injection Decoding (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) exhibit strong reasoning abilities, often attributed to few-shot or zero-shot Chain-of-Thought (CoT) prompting. |
| Approach: | They propose a decoding strategy that nudges LLMs to continue reasoning, thereby preventing immature reasoning processes. |
| Outcome: | The proposed method significantly improves LLM reasoning capabilities on diverse reasoning benchmarks. |
A Parallelized Framework for Simulating Large-Scale LLM Agents with Realistic Environments and Interactions (2025.acl-industry)
Copied to clipboard
| Challenge: | Existing work on large language models lacks a realistic environment and parallelized framework to support complex interactions between agents and environments. |
| Approach: | They propose a framework that integrates realistic societal environments and parallelized interactions to support simulations of large-scale agents. |
| Outcome: | The proposed framework can support simulations of 30,000 agents faster than the wall-clock time with 24 NVIDIA A800 GPUs and the performance increases linearly with the increase of LLM computational resources. |
Guide the Many-to-One Assignment: Open Information Extraction via IoU-aware Optimal Transport (2023.acl-long)
Copied to clipboard
Kaiwen Wei, Yiran Yang, Li Jin, Xian Sun, Zequn Zhang, Jingyuan Zhang, Xiao Li, Linhao Zhang, Jintao Liu, Guo Zhi
| Challenge: | Open Information Extraction (OIE) aims to extract structured information from text without the limitations of close ontology. |
| Approach: | They propose a method to assign ground truth labels to parallelly generated tuple proposals . they leverage intersection-over-union (IoU) as assignment quality measurement . |
| Outcome: | The proposed method outperforms the state-of-the-art models on three benchmarks. |
Combining Deep Learning and Topic Modeling for Review Understanding in Context-Aware Recommendation (N18-1)
Copied to clipboard
| Challenge: | Existing models for user reviews are limited by data sparsity and lack of data. |
| Approach: | They propose to integrate LSTM and Topic Modeling to extract review information for recommender systems by utilizing user reviews. |
| Outcome: | The proposed model outperforms existing models on Amazon review dataset and shows better ability on making topic clustering than traditional topic model based method. |
NOVA: An Iterative Planning Framework for Enhancing Scientific Innovation with Large Language Models (2025.findings-acl)
Copied to clipboard
Xiang Hu, Hongyu Fu, Jinge Wang, Yifeng Wang, Zhikun Li, Renjun Xu, Yu Lu, Yaochu Jin, Lili Pan, Zhenzhong Lan
| Challenge: | Existing approaches to generate research ideas rely on retrieval or prompt engineering to generate ideas. |
| Approach: | They propose a method that uses iterative planning and search to boost creative potential of LLMs by integrating external knowledge with broader and deeper insights. |
| Outcome: | The proposed method outperforms the current state-of-the-art in generating 2.5 times more top-rated ideas based on 170 seed papers in a Swiss Tournament evaluation. |
Improving Continual Relation Extraction through Prototypical Contrastive Learning (2022.coling-1)
Copied to clipboard
| Challenge: | Continual relation extraction (CRE) aims to extract relations towards the continuous and iterative arrival of new data, of which the major challenge is the catastrophic forgetting of old tasks. |
| Approach: | They propose a Continual Relation Extraction framework with Contrastive Learning which is built with a classification network and a prototypical contrastive network to achieve incremental-class learning of CRE. |
| Outcome: | The proposed framework outperforms the state-of-the-art methods on two public datasets and proves its effectiveness on improving performance. |
Polynomial Expansion Rank Adaptation: Enhancing Low-Rank Fine-Tuning with High-Order Interactions (2026.findings-acl)
Copied to clipboard
| Challenge: | Low-rank adaptation (LoRA) is a widely used strategy for efficient fine-tuning of large language models, but its strictly linear structure limits expressive capacity. |
| Approach: | They propose a method that introduces structured polynomial expansion directly into the low-rank factor space. |
| Outcome: | The proposed method outperforms state-of-the-art methods across diverse benchmarks. |
ADEPT-SQL: A High-performance Text-to-SQL Application for Real-World Enterprise-Level Databases (2025.acl-demo)
Copied to clipboard
Yongnan Chen, Zhuo Chang, Shijia Gu, Yuanhang Zong, Zhang Mei, Shiyu Wang, Hezixiang Hezixiang, Hongzhi Chen, Jin Wei, Bin Cui
| Challenge: | et al., 2017) address domain-specific knowledge barriers, schemas complexity, and computational costs of large LLMs. |
| Approach: | They propose a domain-adapted Text2SQL system that addresses critical deployment challenges in professional fields. |
| Outcome: | The proposed system achieves 97% execution accuracy on real-world databases . it is faster than existing systems and has a higher performance than existing ones. |
Musical Score Understanding Benchmark: Evaluating Large Language Models’ Comprehension of Complete Musical Scores (2026.acl-long)
Copied to clipboard
Congren Dai, Yue Yang, Krinos Li, Huichi Zhou, Shijie Liang, Zhang Bo, Enyang Liu, Ge Jin, Hongran An, Haosen Zhang, Peiyuan Jing, KinHei Lee, Zhenxuan Zhang, Xiaobing Li, Maosong Sun
| Challenge: | Existing benchmarks for musical score understanding are narrow in scope, focusing on isolated fragments, short excerpts, or multiple-choice formulations, rather than supporting holistic reasoning over entire scores. |
| Approach: | They propose a benchmark for score-level musical understanding across textual and visual modalities. |
| Outcome: | The musical score understanding benchmark contains 1,800 question-answer pairs from works by Bach, Beethoven, Chopin, Debussy, and others. |
Video-LLaVA: Learning United Visual Representation by Alignment Before Projection (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to visual-language understanding lack unified tokenization for images and videos . lack of unified visual representations makes it difficult to learn multi-modal interactions from poor projection layers. |
| Approach: | They propose to unify visual representation into the language feature space to advance the foundational LLM towards a unified LVLM. |
| Outcome: | The proposed model outperforms Video-ChatGPT on image benchmarks and on 9 image benchmark benchmarks. |
Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection (2024.naacl-long)
Copied to clipboard
Jun Yan, Vikas Yadav, Shiyang Li, Lichang Chen, Zheng Tang, Hai Wang, Vijay Srinivasan, Xiang Ren, Hongxia Jin
| Challenge: | Instruction-tuned Large Language Models (LLMs) can modulate responses based on human instructions, but they can be maliciously steered to impact society in subtle but persistent ways. |
| Approach: | They propose a backdoor attack setting that allows an attacker to inject a virtual prompt into an LLM to steer it without any explicit injection at its input. |
| Outcome: | The proposed method is able to poison the model's instruction tuning data and show that it is highly effective in steering the model. |
Text-Guided Multi-Scale Frequency Representation Adaptation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for fine-tuning visual signals are limited by their size and complexity. |
| Approach: | They propose a multi-scale frequency-based fine-tuning method that integrates textual information and performs multi-level fine- tuning of visual signals in the frequency domain. |
| Outcome: | Extensive experiments on multimodal models, including CLIP and LLaVA, demonstrate that the proposed method significantly improves performance and efficiency with minimal cost and fast convergence within one epoch. |
EVIT: Event-Oriented Instruction Tuning for Event Reasoning (2024.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have made significant advances in event reasoning . however, smaller instruction-tuned models do not consistently demonstrate exceptional proficiency . |
| Approach: | They propose an event-oriented instruction tuning technique to train a large language model . they propose a structure named event quadruple which contains the structure and semantics of events . |
| Outcome: | The proposed model achieves competitive performances on event reasoning tasks. |
Toward Global AI Inclusivity: A Large-Scale Multilingual Terminology Dataset (GIST) (2025.findings-acl)
Copied to clipboard
Jiarui Liu, Iman Ouzzani, Wenkai Li, Lechen Zhang, Tianyue Ou, Houda Bouamor, Zhijing Jin, Mona T. Diab
| Challenge: | Despite advances in machine translation, domain-specific terminology translation remains challenging. |
| Approach: | They propose a large-scale multilingual AI terminology dataset that combines LLMs for extraction with human expertise for translation. |
| Outcome: | The proposed framework combines human translation expertise with LLMs to improve translation accuracy and improve BLEU and COMET scores. |
Depth-bounding is effective: Improvements and evaluation of unsupervised PCFG induction (D18-1)
Copied to clipboard
| Challenge: | Recent attempts to improve grammar induction systems by bounding complexity of the model have not been compared against unbounded induction models. |
| Approach: | They propose to use a Bayesian induction inducer to limit the search space of the model and then sample trees with or without bounding. |
| Outcome: | The proposed model produces trees more accurately than or competitively with state-of-the-art constituency grammar induction models. |
ChangJuan: A Comprehensive Benchmark for Book-Length Chinese Story Evaluation (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models (LLMs) have significantly enhanced the capacity of Automatic Story Evaluation. |
| Approach: | They propose a method to distill raw reviews into generally agreed viewpoints across key evaluation aspects such as plot and character. |
| Outcome: | The proposed model outperforms open-source baselines and raises Qwen3’s Kendall’s tau correlation with human judgments from 24.8 to 34.1. |
DuetSim: Building User Simulator with Dual Large Language Models for Task-Oriented Dialogues (2024.lrec-main)
Copied to clipboard
| Challenge: | User Simulators are used to train task-oriented dialogue systems . traditional training paradigms rely on human-engineered agendas resulting in generated responses that lack diversity and spontaneity. |
| Approach: | They propose a framework that leverages large language models to generate diverse responses . they use two LLMs to generate and verify responses, which are preferred by users . |
| Outcome: | The proposed framework produces responses that exhibit diversity and are preferred by human users. |
SlideAgent: Hierarchical Agentic Framework for Multi-Page Visual Document Understanding (2026.acl-long)
Copied to clipboard
| Challenge: | Multimodal large language models (MLLMs) are a promising tool for document understanding, but they are not able to handle complex multi-page visual documents. |
| Approach: | They propose a flexible agentic framework for understanding multi-modal, multi-page, and multi-layout documents . SlideAgent employs specialized agents and decomposes reasoning into three specialized levels . |
| Outcome: | a new agentic framework improves accuracy over open-source and proprietary models . it decomposes reasoning into three levels to capture themes and visual cues . the framework is based on a multimodal large language model and a MLLM . |
Whispers that Shake Foundations: Analyzing and Mitigating False Premise Hallucinations in Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models generate hallucinated text when confronted with false premise questions . authors propose a method to mitigate false premises hallucinosity . |
| Approach: | They propose a method to constrain false premise attention heads during the model inference process. |
| Outcome: | The proposed method improves performance by constraining false premise attention heads . it yields a notable increase of nearly 20% of model performance . |
Video Dialog via Progressive Inference and Cross-Transformer (D19-1)
Copied to clipboard
| Challenge: | Existing visual dialog methods use RNN to encode the dialog history as a vector representation . a new method for video dialog is proposed, which progressively updates query information based on dialog history and video content until the agent think the information is sufficient and unambiguous. |
| Approach: | They propose a method which progressively updates query information based on dialog history and video content until the agent thinks it is sufficient and unambiguous. |
| Outcome: | The proposed method can be used to infer video dialog answers on large-scale datasets. |
RSA-Bench: Benchmarking Audio Large Models in Real-World Acoustic Scenarios (2026.findings-acl)
Copied to clipboard
Yibo Zhang, Kaiwen Luo, Liang Lin, Shilinlu Yan, Jin Wang, Yaoqi Guo, Yitian Chen, Yalan Qin, Zhenhong Zhou, Kun Wang, Li Sun
| Challenge: | Existing evaluations rely on synthetic Gaussian noise or simplistic single-source interference, failing to capture the intricate, multi-layered acoustic dynamics that characterize authentic physical environments. |
| Approach: | They propose a robustness benchmark to stress-test Audio Large Models (ALLMs) using high-fidelity auditory scene simulations. |
| Outcome: | The proposed model performs well on a wide range of tasks, including automatic speech recognition, speech translation, and audio-based reasoning. |
Entropy Guided Extrapolative Decoding to Improve Factuality in Large Language Models (2025.coling-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) exhibit impressive natural language capabilities but suffer from hallucination – generating content that does not align with realworld facts. |
| Approach: | They propose to extrapolate critical token probabilities beyond the last layer to improve decoding by manipulating the predicted distributions at inference time. |
| Outcome: | The proposed methods surpass state-of-the-art on multiple datasets by large margins. |
LINKED: Eliciting, Filtering and Integrating Knowledge in Large Language Model for Commonsense Reasoning (2024.findings-emnlp)
Copied to clipboard
Jiachun Li, Pengfei Cao, Chenhao Wang, Zhuoran Jin, Yubo Chen, Kang Liu, Xiaojian Jiang, Jiexin Xu, Jun Zhao
| Challenge: | Large language models (LLMs) often exhibit poor performance on knowledge-intensive tasks, such as commonsense reasoning. |
| Approach: | They propose a method to elicit, filter and integrate knowledge in large language models (LINKED) they propose 'reward model' to filter out noisy knowledge and 'take marginal consistent reasoning module' |
| Outcome: | The proposed method outperforms SOTA baselines on two commonsense reasoning tasks. |
FINEST: Improving LLM Responses to Sensitive Topics Through Fine-Grained Evaluation (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing evaluation frameworks lack systematic methods to identify weaknesses in LLMs . Existing methods to evaluate LLM responses to sensitive topics are lacking . |
| Approach: | They propose a FINE-grained response evaluation taxonomy for sensitive topics that breaks down helpfulness and harmlessness into errors across three main categories: Content, Logic, and Appropriateness. |
| Outcome: | The proposed model outperforms refinement without guidance on Korean-sensitive questions . FINEST significantly improves the model responses across all three categories . |
How Good Is NLP? A Sober Look at NLP Tasks through the Lens of Social Impact (2021.findings-acl)
Copied to clipboard
| Challenge: | Recent years have seen many breakthroughs in natural language processing (NLP), transitioning it from a mostly theoretical field to one with many real-world applications. |
| Approach: | They propose a moral philosophy definition of social good and a framework to evaluate the direct and indirect real-world impact of NLP tasks. |
| Outcome: | The proposed framework evaluates the direct and indirect real-world impact of NLP tasks and adopts the methodology of global priorities research to identify priority causes for NLP research. |
On-policy Reinforcement Fine-tuning with Offline reward for Multi-step Embodied Planning (2026.acl-long)
Copied to clipboard
| Challenge: | Embodied planning requires agents to make coherent multi-step decisions based on dynamic visual observations and verbal goals. |
| Approach: | They propose an On-policy Reinforcement fine-tuning framework with offline rewards for Embodied Task Planning that preserves generalization benefits of RFT while addressing costly interaction and sparse rewards. |
| Outcome: | The proposed framework outperforms closed-source and online-RL methods on EmbodiedBench, a recent benchmark for interactive embodied tasks. |
Reasoning over Precedents Alongside Statutes: Case-Augmented Deliberative Alignment for LLM Safety (2026.acl-long)
Copied to clipboard
Can Jin, Rui Wu, Tong Che, Qixin Zhang, Hongwu Peng, Jiahui Zhao, Zhenting Wang, Wenqi Wei, Ligong Han, Zhao Zhang, Yuan Cao, Ruixiang Tang, Dimitris N. Metaxas
| Challenge: | OpenAI introduces deliberative alignment (DA) to enhance safety of its o-series models, but effectiveness of this approach in open-source LLMs is understudied. |
| Approach: | They propose a case-augmented deliberative alignment method for large language models . they propose to use reinforcement learning on self-generated safety reasoning chains . |
| Outcome: | The proposed method avoids narrowly enumerated rules and allows broader adaptability. |
Unlearning as multi-task optimization: A normalized gradient difference approach with an adaptive learning rate (2025.naacl-long)
Copied to clipboard
Xiaomeng Jin, Zhiqi Bu, Bhanukiran Vinzamuri, Anil Ramakrishna, Kai-Wei Chang, Volkan Cevher, Mingyi Hong
| Challenge: | Existing methods to remove unwanted knowledge from large language models are formulated as minimizing memorization through the loss of the model. |
| Approach: | They propose a normalized gradient difference algorithm that optimizes a forgetting objective and an automatic learning rate scheduler that allows for better control over the trade-off between the objectives. |
| Outcome: | The proposed method improves on TOFU and MUSE datasets while exhibiting stable training. |
LongLeader: A Comprehensive Leaderboard for Large Language Models in Long-context Scenarios (2025.naacl-long)
Copied to clipboard
Pei Chen, Hongye Jin, Cheng-Che Lee, Rulin Shao, Jingfeng Yang, Mingyu Zhao, Zhaoyu Zhang, Qin Lu, Kaiwen Men, Ning Xie, Huasheng Li, Bing Yin, Han Li, Lingyun Wang
| Challenge: | LongLeader aims to assess different LLMs' long-context comprehension abilities . long-constext comprehension is a key bottleneck for many use cases . |
| Approach: | They propose a leaderboard to assess different LLMs' long-context comprehension abilities . they offer open-source access to the benchmarks and maintain a dedicated website . |
| Outcome: | The proposed model assesses different LLMs on selected benchmarks and provides open-source access to the benchmarks. |
DDPrompt: Differential Diversity Prompting in Large Language Models (2024.acl-short)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have shown that their reasoning ability can be enhanced through approaches like Chain-of-Thought (CoT) prompting. |
| Approach: | They propose a method that generates differentially diverse reasoning paths for different types of questions by voting on the optimal prompts. |
| Outcome: | The proposed method improves LLMs' reasoning ability on complex reasoning tasks by learning from demonstrations while keeping their parameters frozen. |
LiveFact: A Dynamic, Time-Aware Benchmark for LLM-Driven Fake News Detection (2026.acl-long)
Copied to clipboard
| Challenge: | Current evaluation frameworks are static and vulnerable to benchmark data contamination . current models are ineffective at assessing reasoning under temporal uncertainty . |
| Approach: | They propose a live-based benchmark that simulates the real-world "fog of war" they propose evaluating models on their ability to reason with evolving, incomplete information . |
| Outcome: | The proposed model outperforms proprietary state-of-the-art models in classification and evidence mode . it also provides a component to monitor BDC explicitly . |
GS-Quant: Granular Semantic and Generative Structural Quantization for Knowledge Graph Completion (2026.acl-long)
Copied to clipboard
| Challenge: | Existing quantization-based approaches to knowledge Graph Completion (KGC) are incomplete. |
| Approach: | They propose a framework that generates semantically coherent discrete codes for KG entities . they introduce a Granular Semantic Enhancement module that injects hierarchical knowledge into the codebook . |
| Outcome: | The proposed framework outperforms existing text-based and embedding-based baselines in the KGC domain. |
Privacy Risks of Intermediate Representations: Attribute Inference in Distributed LLM Inference (2026.findings-acl)
Copied to clipboard
| Challenge: | Distributed LLMs avoid raw inputs by transmitting intermediate hidden states, a practice widely assumed to preserve privacy. |
| Approach: | They propose a distributed inference framework that transmits intermediate hidden states to avoid sending raw inputs by exposing sensitive user attributes. |
| Outcome: | The proposed approach achieves Top-1 accuracy of 0.997 on CMS, 0.980 on Skytrax, and 0.986 on ECHR. |
LogicPro: Improving Complex Logical Reasoning via Program-Guided Learning (2025.acl-long)
Copied to clipboard
Jin Jiang, Yuchen Yan, Yang Liu, Jianing Wang, Shuai Peng, Xunliang Cai, Yixin Cao, Mengdi Zhang, Liangcai Gao
| Challenge: | LogicPro is a data synthesis method that uses LeetCode-style algorithm problems and their corresponding Program solutions to generate complex logic data. |
| Approach: | They propose a new method which leverages LeetCode-style algorithm Problems and their corresponding Program solutions to synthesize complex logic data in text format. |
| Outcome: | The proposed method outperforms existing models for BBH27, LogicBench, DROP, AR-LSAT, and GSM8K, and a wide range of reasoning datasets. |
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. |
Investigating Dynamic Routing in Tree-Structured LSTM for Sentiment Analysis (D19-1)
Copied to clipboard
| Challenge: | Existing deep neural network models such as LSTM and tree-LSTM have a bias problem where the words in the tail of a sentence are more heavily emphasized than those in the header. |
| Approach: | They propose a capsule tree-LSTM model that uses dynamic routing to build sentence representations by assigning different weights to nodes according to their contributions to prediction. |
| Outcome: | The proposed model improves on the Stanford Sentiment Treebank and EmoBank datasets. |
VisPCO: Visual Token Pruning Configuration Optimization via Budget-Aware Pareto-Frontier Learning for Vision-Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for visual token pruning rely on predefined configurations without determining whether they achieve optimal performance. |
| Approach: | They propose a framework that formulates visual token pruning as a Pareto configuration optimization problem to automatically identify optimal configurations. |
| Outcome: | The proposed framework approximates the empirical Pareto frontier obtained through grid search and generalizes well across pruning methods and VLM architectures. |
Ignore Me But Don’t Replace Me: Utilizing Non-Linguistic Elements for Pretraining on the Cybersecurity Domain (2024.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods to train domain expertise for cybersecurity text domains are expensive to train and run. |
| Approach: | They propose to use pretraining methods to account for non-linguistic elements in cybersecurity texts and evaluate their effectiveness through downstream tasks and probing tasks. |
| Outcome: | The proposed strategy outperforms the commonly taken approach of replacing NLEs and outperformed other cybersecurity PLMs on most tasks. |
Syllable-based Neural Thai Word Segmentation (2020.coling-main)
Copied to clipboard
| Challenge: | Word segmentation is a challenging pre-processing step for Thai Natural Language Processing due to the lack of explicit word boundaries. |
| Approach: | They propose a neural Thai word segmenter that uses syllable embeddings to capture linguistic constraints and dilated CNN filters to capture the environment of each character. |
| Outcome: | The proposed system outperforms the previous state-of-the-art system on both in-domain and out-domain datasets. |
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. |
SumCSE: Summary as a transformation for Contrastive Learning (2024.findings-naacl)
Copied to clipboard
| Challenge: | Sentence embedding models are typically trained using contrastive learning (CL) using human annotations directly or by repurposing other annotated datasets. |
| Approach: | They propose to use generative language models to generate CL data using annotated data. |
| Outcome: | The proposed method outperforms the previous best unsupervised method by 1.8 points and SimCSE, a strong supervised baseline by 0.3 points on the semantic text similarity (STS) benchmark. |
ARAIDA: Analogical Reasoning-Augmented Interactive Data Annotation (2024.acl-long)
Copied to clipboard
| Challenge: | Empirical studies demonstrate that Araida reduces human correction labor by 11.02% compared to vanilla interactive data annotation methods. |
| Approach: | They propose an analogical reasoning-based approach that enhances automatic annotation accuracy in the interactive data annotation setting and reduces the need for human corrections. |
| Outcome: | Empirical studies show that Araida reduces human correction labor by 11.02% compared to vanilla interactive data annotation methods. |
VideoCuRL: Video Curriculum Reinforcement Learning with Orthogonal Difficulty Decomposition (2026.acl-long)
Copied to clipboard
| Challenge: | Reinforcement Learning (RL) is crucial for Video-LLMs with complex spatiotemporal reasoning. |
| Approach: | They propose a framework that decomposes difficulty into two axes in video understanding . they employ efficient, training-free proxies to map data onto a 2D curriculum grid . |
| Outcome: | The proposed framework surpasses strong RL baselines on reasoning and perception tasks. |
Skin-in-the-Game: Decision Making via Multi-Stakeholder Alignment in LLMs (2024.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have shown remarkable capabilities in tasks such as summarization, arithmetic reasoning, and question answering. |
| Approach: | They propose a framework that explores decisions’ consequences from multiple stakeholder perspectives and a SKIG framework to enhance moral reasoning in large language models. |
| Outcome: | The proposed framework exhibits marked improvements compared to baselines across different language models and benchmarks. |
Are Language Models Consequentialist or Deontological Moral Reasoners? (2025.emnlp-main)
Copied to clipboard
Keenan Samway, Max Kleiman-Weiner, David Guzman Piedrahita, Rada Mihalcea, Bernhard Schölkopf, Zhijing Jin
| Challenge: | Recent studies have focused on the moral judgments in large language models rather than their underlying moral reasoning process. |
| Approach: | They propose a taxonomy of moral rationales to classify reasoning traces according to consequentialism and deontology . they use trolley problems to analyze moral reasoning tracing in large language models . |
| Outcome: | The proposed taxonomy of moral rationales sheds light on consequentialism and deontology . it systematically classifies reasoning traces according to two main ethical theories . |
Modeling Content Importance for Summarization with Pre-trained Language Models (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies on content importance do not consider semantics and context when evaluating importance. |
| Approach: | They apply information theory to pre-trained language models to define the concept of importance from the perspective of information amount. |
| Outcome: | Experiments on CNN/Daily Mail and New York Times show that the proposed model can model the importance of content better than previous methods based on F1 and ROUGE scores. |
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. |
Logical Fallacy Detection (2022.findings-emnlp)
Copied to clipboard
Zhijing Jin, Abhinav Lalwani, Tejas Vaidhya, Xiaoyu Shen, Yiwen Ding, Zhiheng Lyu, Mrinmaya Sachan, Rada Mihalcea, Bernhard Schoelkopf
| Challenge: | Existing language models perform poorly on logical fallacy detection . fallacious arguments can lead to disagreements, conflicts, endless debates, and a lack of consensus . |
| Approach: | They propose a task of logical fallacy detection and propose LogicClimate to detect fallacies in text. |
| Outcome: | The proposed task outperforms the best language model on Logic and LogicClimate . human reasoning is marred by logical fallacies, and some exacerbate misinformation . |
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. |
Grounded PCFG Induction with Images (2020.aacl-main)
Copied to clipboard
| Challenge: | Recent work in unsupervised parsing has tried to incorporate visual information into learning, but results suggest that these models need linguistic bias to compete against models that only rely on text. |
| Approach: | They propose to use visual information from images for labeled parsing and compare them to existing models which only use text. |
| Outcome: | The proposed models achieve state-of-the-art results on multilingual induction datasets even without help from linguistic knowledge or pretrained image encoders. |
Leveraging Visual Knowledge in Language Tasks: An Empirical Study on Intermediate Pre-training for Cross-Modal Knowledge Transfer (2022.acl-long)
Copied to clipboard
| Challenge: | Pre-trained language models lack visual knowledge of common objects due to reporting bias. |
| Approach: | They investigate whether integrating visual knowledge into a language model can fill the gap . they use captions and images to transfer visual knowledge to 5 downstream tasks . |
| Outcome: | The proposed model can improve performance on 5 tasks that may need visual knowledge to solve the problem. |
Towards Robust Universal Information Extraction: Dataset, Evaluation, and Solution (2025.acl-long)
Copied to clipboard
| Challenge: | Existing robust benchmark datasets generate only a limited range of perturbations for a single Information Extraction (UIE) task, which fails to evaluate the robustness of UIE models effectively. |
| Approach: | They propose a new benchmark dataset that utilizes Large Language Models to generate more diverse and realistic perturbations across different IE tasks. |
| Outcome: | The proposed model performs better with only 15% of the data and is more robust with other models. |
Empirical Study on Data Attributes Insufficiency of Evaluation Benchmarks for LLMs (2025.coling-main)
Copied to clipboard
| Challenge: | Existing benchmarks for evaluating large language models neglect key qualitative data attributes that can significantly impact the final rankings of LLMs. |
| Approach: | They propose a framework with three modules designed to assess diversity, redundancy, and difficulty. |
| Outcome: | The proposed framework systematically incorporates diversity, redundancy, and difficulty attributes and shows that they influence the ranking of LLMs. |
KnowCoder: Coding Structured Knowledge into LLMs for Universal Information Extraction (2024.acl-long)
Copied to clipboard
Zixuan Li, Yutao Zeng, Yuxin Zuo, Weicheng Ren, Wenxuan Liu, Miao Su, Yucan Guo, Yantao Liu, Lixiang Lixiang, Zhilei Hu, Long Bai, Wei Li, Yidan Liu, Pan Yang, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng
| Challenge: | None. None.. None! |
| Approach: | None. None.. None! |
| Outcome: | None. None. No. : |
ALERT: Adapt Language Models to Reasoning Tasks (2023.acl-long)
Copied to clipboard
Ping Yu, Tianlu Wang, Olga Golovneva, Badr AlKhamissi, Siddharth Verma, Zhijing Jin, Gargi Ghosh, Mona Diab, Asli Celikyilmaz
| Challenge: | Large language models have shown increasing in-context learning capabilities with scaling up the model and data sizes. |
| Approach: | They propose a benchmark and suite of analyses to evaluate reasoning skills of large language models. |
| Outcome: | The proposed model compares pre-trained and fine-tuned models on tasks that require reasoning skills to solve. |
Cross-Modal Discrete Representation Learning (2022.acl-long)
Copied to clipboard
| Challenge: | a new framework for learning representations from multimodal data is proposed . the proposed framework uses discretized embedding vectors to capture finer levels of granularity . |
| Approach: | They propose a self-supervised representation learning framework that captures finer levels of granularity across different modalities. |
| Outcome: | The proposed representation can capture finer levels of granularity across different modalities . it can be used on cross-modal retrieval tasks without direct supervision . |
Covariance Matrix-Driven Image Channel Allocation for Multimodal Fake News Detection (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods focus on designing efficient multimodal fusion frameworks to bridge the semantic gap between images and texts. |
| Approach: | They propose a covariance matrix-driven image channel allocation method that expands the number of original channel maps and assigns importance scores to the expanded channel maps. |
| Outcome: | The proposed method achieves state-of-the-art on three public multimodal fake news detection benchmark datasets. |
Predicting Clinical Trial Results by Implicit Evidence Integration (2020.emnlp-main)
Copied to clipboard
| Challenge: | Clinical trials are expensive and time-consuming, and inappropriately designed studies can be devastating in a pandemic. |
| Approach: | They propose a model that takes a PICO-formatted clinical trial proposal and predicts the outcome from it. |
| Outcome: | The proposed model outperforms baseline models on a benchmark dataset with 10.7% relative gain over BioBERT. |
SiMFy: A Simple Yet Effective Approach for Temporal Knowledge Graph Reasoning (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models for temporal knowledge graph reasoning suffer from low training efficiency and insufficient generalization ability. |
| Approach: | They propose a temporal knowledge graph reasoning approach that uses multilayer perceptron to model the structural dependencies of events and adopts a fixed-frequency strategy to incorporate historical frequency during inference. |
| Outcome: | The proposed model achieves state-of-the-art performance with faster convergence speed and better generalization ability. |
ReFT: Reasoning with Reinforced Fine-Tuning (2024.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to improve the generalization of large language models are using Supervised Fine-Tuning (SFT) this approach does not show sufficient generalization ability because it only relies on the given CoT data. |
| Approach: | They propose to use Chain-of-Thought annotations to train Large Language Models using supervised fine-tuning to improve generalization. |
| Outcome: | The proposed approach outperforms SFT on GSM8K, MathQA, and SVAMP datasets and shows a superior generalization ability. |
Trajectory2Task: Training Robust Tool-Calling Agents with Synthesized Yet Verifiable Data for Complex User Intents (2026.acl-long)
Copied to clipboard
Ziyi Wang, Yuxuan Lu, Yimeng Zhang, Pei Chen, Ziwei Dong, Jing Huang, Jiri Gesi, Xianfeng Tang, Chen Luo, Qun Liu, Yisi Sang, Hanqing Lu, Manling Li, Jin Lai, Dakuo Wang
| Challenge: | Tool-calling agents are increasingly deployed in real-world customer-facing workflows . but most studies on tool-callers focus on idealized settings with general, fixed, and well-specified tasks. |
| Approach: | They propose a tool-calling agent-based data pipeline that converts trajectories into user-facing tasks with controlled intent adaptations. |
| Outcome: | The proposed pipeline can be used to study tool use under three scenarios. |
What the #?*!: Disentangling Hate Across Target Identities (2025.naacl-long)
Copied to clipboard
| Challenge: | Hate speech classifiers do not perform equally well in detecting hateful expressions towards different target identities. |
| Approach: | They propose to use two recently proposed functionality test datasets to analyze the impact of different factors on HS prediction. |
| Outcome: | The proposed classifiers do not perform equally well across different datasets and different target identities. |
XQ-MEval: A Dataset with Cross-lingual Parallel Quality for Benchmarking Translation Metrics (2026.findings-acl)
Copied to clipboard
| Challenge: | averaging metric scores across languages is suspicious since translations of equal quality receive different scores across language. |
| Approach: | They propose a semi-automatically built dataset to benchmark translation metrics using MQM-defined errors and a normalization strategy to mitigate cross-lingual scoring bias. |
| Outcome: | The proposed model shows that translation metrics suffer from cross-lingual scoring bias . the proposed model is based on a semi-automatically built dataset covering nine translation directions . |
Incorporating Emoji Descriptions Improves Tweet Classification (N19-1)
Copied to clipboard
| Challenge: | Tweets are short messages that often include specialized language such as hashtags and emojis. |
| Approach: | They propose a simple strategy to replace emojis with their natural language description and use pretrained word embeddings to process tweets. |
| Outcome: | The proposed method is more effective than pretrained emoji embeddings for tweet classification. |
Threshold Filtering Packing for Supervised Fine-Tuning: Training Related Samples within Packs (2025.naacl-long)
Copied to clipboard
| Challenge: | Randomly concatenating data points can lead to cross-contamination due to the significant difference in their subject matter. |
| Approach: | They propose a method that randomly concatenates data of varying lengths until reaching the designed maximum length to optimize context length and reduce padding. |
| Outcome: | The proposed method significantly improves performance on GSM8K and HumanEval, and also improves fairness and accuracy by 15%. |
Causal Direction of Data Collection Matters: Implications of Causal and Anticausal Learning for NLP (2021.emnlp-main)
Copied to clipboard
Zhijing Jin, Julius von Kügelgen, Jingwei Ni, Tejas Vaidhya, Ayush Kaushal, Mrinmaya Sachan, Bernhard Schoelkopf
| Challenge: | a meta-analysis of published studies shows that the causal direction of data collection can explain some trends in NLP . semi-supervised learning and domain adaptation performance differ on a number of tasks . |
| Approach: | They argue that the causal direction of the data collection process has nontrivial implications . authors categorize common NLP tasks according to their causal direction . they also empirically assay the validity of the ICM principle for text data . |
| Outcome: | The proposed model can explain differences in semi-supervised learning and domain adaptation performance across settings. |
Neuronal Insights into LLM Attacks: Targeted Neuron Tuning for Precise and Robust Vulnerability Patching (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing gradient-based attribution methods are inapplicable to adversarial attacks . et al.: Targeted neuron tuning improves model robustness against jailbreak attacks despite the model's vulnerability to jailbreak. |
| Approach: | They propose a gradient-based method to identify key neurons sensitive to adversarial behaviors in open-ended generation tasks. |
| Outcome: | The proposed method detects key neurons sensitive to adversarial behaviors in open-ended tasks. |
EMNLP: Educator-role Moral and Normative Large Language Models Profiling (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing frameworks for evaluating the ethical and moral alignment of large language models (LLMs) in educational AI are lacking. |
| Approach: | They propose a framework for a teacher-role moral and normative LLMs profiling . they extend existing scales and construct 88 teacher-specific moral dilemmas . |
| Outcome: | The proposed framework evaluates compliance and vulnerability of teacher-role LLMs under soft prompt injection. |
Seeing the Same Story Differently: Framing‐Divergent Event Coreference for Computational Framing Analysis (2025.emnlp-main)
Copied to clipboard
| Challenge: | a new task aims to capture subtle differences in how news articles frame events . a central challenge is capturing how same real-world event can evolve into sharply divergent narratives . |
| Approach: | They propose a task that identifies pairs of event mentions referring to the same underlying occurrence but differing in framing across documents. |
| Outcome: | The proposed method enables scalable, interpretable analysis of how media frame the same events differently. |
Explicit over Implict: Explicit Diversity Conditions for Effective Question Answer Generation (2024.lrec-main)
Copied to clipboard
| Challenge: | Recent pretrained and large language model-based QAG methods suffer from redundant generation of QA pairs, affecting downstream QA systems. |
| Approach: | They propose to use explicit diversity conditions to generate diverse question-answer synthetic data by focusing on spatial aspects, question types, and entities. |
| Outcome: | The proposed diversity conditions significantly increase diversity in QA generation over existing diversity techniques. |
FastCorrect 2: Fast Error Correction on Multiple Candidates for Automatic Speech Recognition (2021.findings-emnlp)
Copied to clipboard
Yichong Leng, Xu Tan, Rui Wang, Linchen Zhu, Jin Xu, Wenjie Liu, Linquan Liu, Xiang-Yang Li, Tao Qin, Edward Lin, Tie-Yan Liu
| Challenge: | Error correction is widely used in automatic speech recognition (ASR) to post-process the generated sentence. |
| Approach: | They propose a fast correction model that takes multiple ASR candidates as input for better correction accuracy. |
| Outcome: | The proposed model can reduce the word error rate (WER) with multiple candidates by 3.2% and 2.6%. |
Towards a Unified Paradigm of Concept Editing in Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Concept editing aims to control specific concepts in large language models (LLMs) however, there is a lack of rigorous theoretical analysis and a unified perspective to systematically understand and compare these methods. |
| Approach: | They propose a paradigm where conceptual injection is aligned at the neuron level. |
| Outcome: | The proposed paradigm offers a clear framework and valuable insights for advancing interpretability and controlled generation in large language models. |
CRAFTQA: A Code-Driven Adaptive Framework for Complex Structured Data Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing unified structured data question answering methods rely on a set of predefined functions, which restricts their ability to perform complex reasoning beyond these predefined operations. |
| Approach: | They propose a novel adaptive code-driven framework that generates code-based reasoning operations based on a question. |
| Outcome: | The proposed framework improves on multiple structured datasets on real-world scenarios. |
Masked Measurement Prediction: Learning to Jointly Predict Quantities and Units from Textual Context (2022.findings-naacl)
Copied to clipboard
| Challenge: | Current benchmarks do not evaluate numeracy of pretraining language models on measurements. |
| Approach: | They propose a new task where a model learns to reconstruct a number with its associated unit given masked text. |
| Outcome: | The proposed model significantly underperforms pre-trained model with baselines and ablations. |
BinaryBERT: Pushing the Limit of BERT Quantization (2021.acl-long)
Copied to clipboard
| Challenge: | Recent pre-trained language models have achieved remarkable performance improvement in various tasks, but the improvement generally comes at the cost of increasing model size and computation. |
| Approach: | They propose a binary quantization technique which initializes binaryBERT by splitting from a ternary network. |
| Outcome: | The proposed model achieves state-of-the-art performance on the GLUE and SQUAD benchmarks while being 24x smaller. |
GraphKV: Breaking the Static Selection Paradigm with Graph-Based KV Cache Eviction (2025.emnlp-main)
Copied to clipboard
| Challenge: | Efficient Key-Value (KV) cache management is essential for processing long text sequences in large language models (LLMs). |
| Approach: | They propose a graph-based framework that redefines token selection for KV cache compression. |
| Outcome: | The proposed framework can be used in existing KV cache eviction methods such as SnapKV and PyramidKV in a plug-and-play manner. |
DARS: Dynamic Action Re-Sampling to Enhance Coding Agent Performance by Adaptive Tree Traversal (2025.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to developing LLM-powered coding agents struggle with sub-optimal decision-making. |
| Approach: | They propose a novel inference time compute scaling approach that recovers from sub-optimal decisions by branching out a trajectory at certain key decision points by taking an alternative action given the history of the trajectory and execution feedback of the previous attempt. |
| Outcome: | The proposed approach achieves a pass@1 rate of 47% on the SWE-Bench Lite benchmark, outperforming state-of-the-art (SOTA) open-source frameworks. |
XY-Tokenizer: Mitigating the Semantic-Acoustic Conflict in Low-Bitrate Speech Codecs (2026.acl-long)
Copied to clipboard
Yitian Gong, Luozhijie Jin, Kuangwei Chen, Dong Zhang, Ruifan Deng, Xiaogui Yang, Xin Zhang, Zhaoye Fei, Qinyuan Cheng, Shimin Li, Xipeng Qiu
| Challenge: | Existing speech codecs struggle to balance these objectives at low bitrates . XY-Tokenizer achieves stronger semantic alignment than representative semantic-distillation codec . |
| Approach: | They propose a low-bitrate speech codec that aligns discrete speech representations with text while preserving fine-grained acoustic details for reconstruction. |
| Outcome: | The proposed codec outperforms existing low-bitrate speech codecs in speech understanding and generation tasks. |
Taming Object Hallucinations with Verified Atomic Confidence Estimation (2026.eacl-long)
Copied to clipboard
| Challenge: | Multimodal Large Language Models suffer from hallucinations, especially errors in object existence, attributes, or relations. |
| Approach: | They propose a framework that decomposes responses into atomic queries and estimates confidence using self-consistency or self-confidence aggregation. |
| Outcome: | Experiments on five benchmarks show that TACO outperforms direct prompting and Visual Contrastive Decoding and improves confidence calibration. |
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. |
QEFT: Quantization for Efficient Fine-Tuning of LLMs (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to optimize inference and fine-tuning for large language models have failed to improve all aspects of the process. |
| Approach: | They propose a new technique that accelerates both inference and fine-tuning while using fewer resources. |
| Outcome: | The proposed technique accelerates both inference and fine-tuning while using fewer resources. |
Exploring Logically Dependent Multi-task Learning with Causal Inference (2020.emnlp-main)
Copied to clipboard
| Challenge: | Hierarchical multi-task learning models can utilize task dependencies by stacking encoders and outperform democratic ones. |
| Approach: | They propose a model that utilizes the labels of all lower-level tasks and a Gumbel sampling model to deal with cascading errors. |
| Outcome: | The proposed model outperforms democratic models on six out of seven subtasks and achieves state-of-the-art on the two English and one Chinese datasets. |
Temporal Knowledge Graph Forecasting Without Knowledge Using In-Context Learning (2023.emnlp-main)
Copied to clipboard
| Challenge: | Temporal knowledge graphs (TKGs) are used to represent real-world facts in a structured way. |
| Approach: | They propose to use in-context learning with large language models for TKG forecasting . they compare naive LLMs to state-of-the-art (SOTA) supervised models . |
| Outcome: | The proposed approach performs well against pre-trained large language models . the proposed approach is based on simple heuristics and state-of-the-art models compared with pre-trainers . |
Informative Language Representation Learning for Massively Multilingual Neural Machine Translation (2022.coling-1)
Copied to clipboard
| Challenge: | Existing studies show that prepending language tokens fail to guide translation into right directions, especially on zero-shot translation. |
| Approach: | They propose to use language embedding embodiment and language-aware multi-head attention to learn informative language representations to channel translation into right directions. |
| Outcome: | The proposed methods improve translation direction guidance and significantly alleviate off-target translation issues on two datasets. |
HiRoPE: Length Extrapolation for Code Models Using Hierarchical Position (2024.acl-long)
Copied to clipboard
| Challenge: | Existing LLMs are constrained by their pre-trained context lengths, leading to performance issues . elucidating this limitation, we propose a training-free solution to the context length limitation in LLM applications . |
| Approach: | They propose a method that integrates hierarchical rotary position embedding into LLMs without extra training costs. |
| Outcome: | The proposed method improves performance on language modeling and long code completion tasks. |
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. |
A New Pipeline for Knowledge Graph Reasoning Enhanced by Large Language Models Without Fine-Tuning (2024.emnlp-main)
Copied to clipboard
| Challenge: | Conventional knowledge Graph Reasoning models learn the embeddings of KG components over the structure of a KG. |
| Approach: | They propose a pipeline to integrate knowledge from LLMs into KGs without fine-tuning . they propose knowledge alignment, KG reasoning and entity reranking to enhance conventional models . |
| Outcome: | The proposed pipeline can enhance the performance of conventional KGR models in incomplete and general situations. |
Inducer-tuning: Connecting Prefix-tuning and Adapter-tuning (2022.emnlp-main)
Copied to clipboard
| Challenge: | Prefix-tuning is an essential paradigm of parameter-efficient transfer learning . fine-tuned models require separate copies of model parameters for each task . |
| Approach: | They propose to understand and further develop prefix-tuning through the kernel lens . they propose a new variant of prefix tuning that shares the exact mechanism as prefix tun . |
| Outcome: | The proposed method improves prefix-tuning performance by training only a small portion of parameters. |
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. |
Attributed and Predictive Entity Embedding for Fine-Grained Entity Typing in Knowledge Bases (C18-1)
Copied to clipboard
| Challenge: | Existing methods for identifying semantic type of entities are incomplete even in large knowledge bases. |
| Approach: | They propose an attributed and predictive entity embedding method which can fully utilize various kinds of information comprehensively. |
| Outcome: | Experiments on two real DBpedia datasets show that the proposed method outperforms 8 state-of-the-art methods with 4.0% improvement in Mi-F1 and 5.2% improvement in Ma-F1. |
KnowDR-REC: Auditing Knowledge-Conditioned Visual Grounding in Referring Expression Comprehension (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing evaluation metrics suggest that Multimodal large language models have acquired fine-grained visual grounding capabilities. |
| Approach: | They propose a benchmark to assess Referring Expression Comprehension (REC) that uses intra-image visual cues to localize target objects and a controllable evaluation mechanism to test sensitivity to fine-grained factual changes. |
| Outcome: | The proposed benchmarks show that multimodal large language models have a high level of performance on the RefCOCO family of benchmarks. |
Beyond Benchmarks: Building a Richer Cross-Document Event Coreference Dataset with Decontextualization (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing datasets for Cross-Document Event Coreference (CDEC) are small and lacking diversity. |
| Approach: | They propose a new approach leveraging large language models to decontextualize event mentions by simplifying the document-level annotation task to sentence pairs with enriched context. |
| Outcome: | The proposed approach improves the quality of the dataset and generalizability of the model. |
BattleAgent: Multi-modal Dynamic Emulation on Historical Battles to Complement Historical Analysis (2024.emnlp-demo)
Copied to clipboard
Shuhang Lin, Wenyue Hua, Lingyao Li, Che-Jui Chang, Lizhou Fan, Jianchao Ji, Hang Hua, Mingyu Jin, Jiebo Luo, Yongfeng Zhang
| Challenge: | Recent advances in large language models have demonstrated impressive reasoning capabilities, indicating their potential to serve as the foundation for agents. |
| Approach: | They propose a detailed emulation system that combines large vision-language model and multi-agent system to emulate dynamic interactions between multiple agents over a period of time. |
| Outcome: | The proposed system combines large vision-language model and multi-agent system to emulate dynamic interactions between agents and their environments over a period of time. |
Knowledge-Enhanced Self-Supervised Prototypical Network for Few-Shot Event Detection (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for few-shot event detection are inaccurate and lack a prototype representation module. |
| Approach: | They propose a Knowledge-Enhanced self-supervised prototypical network for few-shot event detection . it adopts hybrid rules which align event types to FrameNet and introduces knowledge to obtain more instances . |
| Outcome: | The proposed network improves few-shot event detection performance on three benchmark datasets. |
Praetor: A Fine-Grained Generative LLM Evaluator with Instance-Level Customizable Evaluation Criteria (2025.acl-long)
Copied to clipboard
Yongqi Leng, Renren Jin, Yue Chen, Zhuowen Han, Ling Shi, Jianxiang Peng, Lei Yang, Juesi Xiao, Deyi Xiong
| Challenge: | Existing evaluation methods are inadequate to evaluate large language models (LLMs). |
| Approach: | They propose a fine-grained generative LLM evaluator with instance-level customazable evaluation criteria that can be used to evaluate large language models. |
| Outcome: | The proposed model outperforms existing LLM evaluators and instruction-tuned LLMs on multiple benchmarks and sets new SOTA results. |
CARD: Cross-modal Agent Framework for Generative and Editable Residential Design (2025.emnlp-main)
Copied to clipboard
| Challenge: | Architectural design automation has made significant progress, but the complexity of open-world environments makes residential design a challenging task. |
| Approach: | They propose a framework that leverages a system of specialized cross-modal agents to adapt to open-world residential design. |
| Outcome: | The proposed framework enables users to generate and edit residential design without requiring specialized expertise. |
A Good Prompt Is Worth Millions of Parameters: Low-resource Prompt-based Learning for Vision-Language Models (2022.acl-long)
Copied to clipboard
| Challenge: | Recent few-shot learning models such as GPT3 are expensive and slow to deploy for real-world applications. |
| Approach: | They propose a prompt-based low-resource learning method for VL tasks with a few examples . they pre-train a sequence-to-sequence transformer model with prefix and masked language modeling . |
| Outcome: | The proposed method outperforms Frozen on vision-language tasks with prompt-based learning by 18.2% point. |
SCCS: Semantics-Consistent Cross-domain Summarization via Optimal Transport Alignment (2023.findings-acl)
Copied to clipboard
Jielin Qiu, Jiacheng Zhu, Mengdi Xu, Franck Dernoncourt, Trung Bui, Zhaowen Wang, Bo Li, Ding Zhao, Hailin Jin
| Challenge: | Existing methods for multimodal summarization ignore the structure and semantics of the whole video and article. |
| Approach: | They propose a semantic-consistent cross-domain summarization model that extracts features from video and article and uses fusion methods to select representative one. |
| Outcome: | The proposed model produces high-quality multimodal summaries on three MSMO datasets. |
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. |
Search-o1: Agentic Search-Enhanced Large Reasoning Models (2025.emnlp-main)
Copied to clipboard
Xiaoxi Li, Guanting Dong, Jiajie Jin, Yuyao Zhang, Yujia Zhou, Yutao Zhu, Peitian Zhang, Zhicheng Dou
| Challenge: | Large reasoning models (LRMs) have demonstrated impressive long stepwise reasoning capabilities through large-scale reinforcement learning. |
| Approach: | They propose a framework that enhances large reasoning models with an agentic retrieval-augmented generation mechanism and a Reason-in-Documents module for refining retrieved documents. |
| Outcome: | The proposed framework enhances LRMs with an agentic retrieval-augmented generation mechanism and Reason-in-Documents module for refining retrieved documents. |
Improving Document Representations by Generating Pseudo Query Embeddings for Dense Retrieval (2021.acl-long)
Copied to clipboard
| Challenge: | Existing retrieval models based on dense representations show better performance than sparse representations. |
| Approach: | They propose a method to mimic the queries to each of the documents by an iterative clustering process and represent the documents using multiple pseudo queries. |
| Outcome: | The proposed model achieves state-of-the-art results on a large dataset while remaining high efficiency. |
VideoCLIP-XL: Advancing Long Description Understanding for Video CLIP Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies have shown that CLIP models with short summary texts cannot process extensive textual descriptions due to its text encoder's reliance on positional embeddings with length 77. |
| Approach: | They propose a Contrastive Language-Image Pre-training (CLIP) model which aims to unleash the long-description understanding capability of video CLIP models. |
| Outcome: | The proposed model can learn the distribution of feature space while expanding the long description capability. |
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. |
From Curated Data to Scalable Models: Continual Pre-training of Dense and MoE Large Language Models for Tibetan (2026.acl-long)
Copied to clipboard
Lei Yang, Leiyu Pan, Bojian Xiong, Renren Jin, Shaowei Zhang, Yue Chen, Ling Shi, Jiang Zhou, Junru Wu, Zhen Wang, Jianxiang Peng, Juesi Xiao, Tianyu Dong, Zhuowen Han, Zhuo Chen, Yuqi Ren, Deyi Xiong
| Challenge: | Large language models have achieved remarkable success across a wide range of tasks, yet their performance remains heavily biased toward high-resource languages. |
| Approach: | They propose a pipeline for advancing Tibetan language modeling through multilingual continual pre-training with Tibetan, Chinese, and English. |
| Outcome: | The proposed model outperforms open-source and Tibetan-focused models on diverse tasks. |
Synchronized Video Storytelling: Generating Video Narrations with Structured Storyline (2024.acl-long)
Copied to clipboard
| Challenge: | Existing studies on dense video captioning and video story generation have made some progress, but in practical applications, we typically require synchronized narrations for ongoing visual scenes. |
| Approach: | They propose a task of Synchronized Video Storytelling to generate synchronized narrations for videos using a benchmark dataset with rich annotations. |
| Outcome: | The proposed framework can generate narrations with the guidance of the generated or predefined storyline and human evaluations validate the effectiveness. |
Select High-quality Synthetic QA Pairs to Augment Training Data in MRC under the Reward Guidance of Generative Language Models (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing approaches focus on downstream metrics to select QA pairs, which lack generalization across different datasets. |
| Approach: | They propose a general selection method that uses a large pre-trained language model as a reward model in a Reinforcement Learning framework for the training of the selection agent. |
| Outcome: | The proposed method improves performance on generative and extractive datasets. |
PREDICT: Multi-Agent-based Debate Simulation for Generalized Hate Speech Detection (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to generalize hate speech detection models have been limited by the labeling criteria between datasets. |
| Approach: | They propose a framework that uses the concept of multi-agent for hate speech detection that uses a set of labeling criteria to create multiple agents based on the induced labeling of given datasets. |
| Outcome: | The proposed framework achieves superior cross-evaluation performance compared to methods that focus on specific labeling criteria or majority voting methods. |
Language Resource Efficient Learning for Captioning (2021.findings-emnlp)
Copied to clipboard
| Challenge: | XE loss and SC loss are both considered to be performance degradations for captioning tasks. |
| Approach: | They propose to generalize the single pairwise comparison in SC loss and use multiple generalized pairwise compares to reduce noise in baseline. |
| Outcome: | The proposed method outperforms state-of-the-art models on a video caption dataset using only half of the language resources. |
SyntheT2C: Generating Synthetic Data for Fine-Tuning Large Language Models on the Text2Cypher Task (2025.coling-main)
Copied to clipboard
| Challenge: | Existing efforts to bolster LLMs’ proficiency in Cypher generation are hindered by the lack of annotated datasets of Query-Cypher pairs. |
| Approach: | They propose a method for constructing a synthetic Query-Cypher pair dataset using LLM prompting and template-filling. |
| Outcome: | The proposed method enhances the performance of LLMs on Text2Cypher task via SFT. |
Efficient Cross-modal Prompt Learning with Semantic Enhancement for Domain-robust Fake News Detection (2025.coling-main)
Copied to clipboard
| Challenge: | Existing MFND methods conduct cross-modal information interaction at later stage, resulting in weak generalization ability. |
| Approach: | They propose an automatic multi-modal fake news detection method that exploits cross-modal information interaction at later stage. |
| Outcome: | The proposed method outperforms state-of-the-art methods on three MFND benchmarks. |
MoDULA: Mixture of Domain-Specific and Universal LoRA for Multi-Task Learning (2024.emnlp-main)
Copied to clipboard
Yufei Ma, Zihan Liang, Huangyu Dai, Ben Chen, Dehong Gao, Zhuoran Ran, Wang Zihan, Linbo Jin, Wen Jiang, Guannan Zhang, Xiaoyan Cai, Libin Yang
| Challenge: | Recent advances in open-source Large Language Models (LLMs) have achieved notable successes in natural language processing. |
| Approach: | They propose a Parameter Efficient Fine-Tuning paradigm for improved fine-tuning and parameter efficiency in multi-task learning. |
| Outcome: | The proposed model outperforms existing methods on multi-task learning while reducing training costs by over 80% without losing general capability. |
When Does Aggregating Multiple Skills with Multi-Task Learning Work? A Case Study in Financial NLP (2023.acl-long)
Copied to clipboard
| Challenge: | Multi-task learning (MTL) is a machine learning paradigm where multiple learning tasks are optimized simultaneously, exploiting commonalities and differences across them. |
| Approach: | They propose a parameter-efficient MTL architecture to improve task aggregation and to include loosely related skills from multiple datasets. |
| Outcome: | The proposed architecture outperforms single-task learning (STL) and is expected to outperformed it. |
Event Detection with Multi-Order Graph Convolution and Aggregated Attention (D19-1)
Copied to clipboard
| Challenge: | Existing methods for event detection use first-order syntactic relations to identify trigger words. |
| Approach: | They propose a dependency tree-based method to model and aggregate multi-order syntactic representations in sentences. |
| Outcome: | The proposed method outperforms existing methods on a benchmark dataset . it uses a dependency tree based graph convolution network with aggregative attention . |
Attention Fusion: a light yet efficient late fusion mechanism for task adaptation in NLU (2022.findings-naacl)
Copied to clipboard
| Challenge: | a recent study has shown that fine-tuning pre-trained models is parameter-inefficient and expensive. |
| Approach: | They propose a task-attuned token module which integrates pre-trained network representations into a pre-trainer. |
| Outcome: | The proposed model trains only 0.0009% of the parameters and is efficient during computation and scalable during deployment. |
Complaint Identification in Social Media with Transformer Networks (2020.coling-main)
Copied to clipboard
| Challenge: | Existing work on identifying complaints in social media has focused on feature-based and task-specific neural network models. |
| Approach: | They evaluate a battery of neural models underpinned by transformer networks and combine them with linguistic information to predict complaints. |
| Outcome: | The proposed models outperform state-of-the-art methods on a publicly available dataset achieving a macro F1 up to 87. |
HowToNarrate: A General-Domain Benchmark for Synchronized Video Narration with External Knowledge (2026.acl-long)
Copied to clipboard
| Challenge: | Existing MLLMs overemphasize knowledge retrieval while neglecting prior context, causing redundancy and incoherence. |
| Approach: | They propose a framework that combines context compression, knowledge retrieval, and narration generation to improve models' performance. |
| Outcome: | The proposed method significantly improves MLLM performance over existing models. |
KnowCoder-X: Boosting Multilingual Information Extraction via Code (2025.findings-acl)
Copied to clipboard
Yuxin Zuo, Wenxuan Jiang, Wenxuan Liu, Zixuan Li, Long Bai, Hanbin Wang, Yutao Zeng, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng
| Challenge: | Empirical evidence indicates that Large Language Models exhibit spontaneous cross-lingual alignment in Information Extraction (IE) however, a significant imbalance across languages persists, highlighting an underlying deficiency. |
| Approach: | They propose a code LLM with advanced cross-lingual and multilingual capabilities for universal IE that standardizes the representation of multilingual schemas using Python classes and conducts IE alignment instruction tuning on translated instance prediction task. |
| Outcome: | The proposed model surpasses ChatGPT and SoTA by 30.17% without training in 29 unseen languages and significantly improves cross-lingual IE transferability. |
Generating Dialogue Responses from a Semantic Latent Space (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing models for dialogue generation are unable to integrate information from multiple semantically similar valid responses of a given prompt. |
| Approach: | They propose to learn the pair relationship between the prompts and responses as a regression task instead of the end-to-end classification on vocabulary. |
| Outcome: | The proposed model learns the pair relationship between the prompts and responses on a latent space instead of the end-to-end classification on vocabulary. |
Find-the-Common: A Benchmark for Explaining Visual Patterns from Images (2024.lrec-main)
Copied to clipboard
| Challenge: | Recent advances in Instruction-fine-tuned Vision and Language Models (IVLMs) have prompted some studies to analyze the reasoning capabilities of IVLMs. |
| Approach: | They introduce a vision and language task for Inductive Visual Reasoning that uses common attributes across visual scenes to find common answers. |
| Outcome: | The proposed model can archive with 48% accuracy on the FTC, compared with state-of-the-art models. |
Improving Large Language Model Safety with Contrastive Representation Learning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing defenses against large language models (LLMs) are limited by their ability to generate responses to diverse inputs. |
| Approach: | They propose a model defense framework that finetunes a large-scale model using a triplet-based loss combined with adversarial hard negative mining to encourage separation between benign and harmful representations. |
| Outcome: | The proposed model defense outperforms previous representation engineering-based defenses while improving robustness against input-level and embedding-space attacks. |
GenWiki: A Dataset of 1.3 Million Content-Sharing Text and Graphs for Unsupervised Graph-to-Text Generation (2020.coling-main)
Copied to clipboard
| Challenge: | a large-scale, general-domain dataset is needed for knowledge graph-to-text generation . data collection is expensive and data-intensive, making it difficult to get good annotation . |
| Approach: | They propose to use a large-scale, general-domain dataset to generate unsupervised text from knowledge graphs. |
| Outcome: | The proposed dataset has 1.3M text and graph examples, and is a benchmark for future research . good annotation is expensive and difficult to get, and it's difficult to check quality . |
OpenFact: Factuality Enhanced Open Knowledge Extraction (2023.tacl-1)
Copied to clipboard
Linfeng Song, Ante Wang, Xiaoman Pan, Hongming Zhang, Dian Yu, Lifeng Jin, Haitao Mi, Jinsong Su, Yue Zhang, Dong Yu
| Challenge: | Existing OIE systems organize knowledge into subject-relation-object (SRO) triplets, and they use templates to extract such knowledge triplet. |
| Approach: | They propose a framework to handle expressiveness and groundedness in OpenFact . they propose to use templates, extra constraints, and adopt human efforts to ensure that most triplets contain enough details. |
| Outcome: | The proposed framework improves expressiveness and groundedness of OpenFact . it is more accurate and denser than OPIEC-Linked, which is grounded to Wikidata . |
Test of Time: Rethinking Temporal Signal of Benchmark Contamination (2026.acl-long)
Copied to clipboard
Terry Jingchen Zhang, Gopal Dev, Ning Wang, Max Obreiter, Punya Syon Pandey, Keenan Samway, Wenyuan Jiang, Yinya Huang, Bernhard Schölkopf, Mrinmaya Sachan, Zhijing Jin
| Challenge: | Existing work on benchmarks containing publicly available information has been interpreted as a temporal signal for benchmark contamination. |
| Approach: | They show that LLM-transformed questions can produce remarkably different temporal patterns compared to fill-in-the-blank questions directly retrieved from the very same documents. |
| Outcome: | The proposed model can produce different temporal patterns compared to fill-in-the-blank questions retrieved from the same documents. |
Enhancing Data Quality through Simple De-duplication: Navigating Responsible Computational Social Science Research (2024.emnlp-main)
Copied to clipboard
| Challenge: | Social media data exhibits distinctive characteristics such as rapid and continual topic evolution. |
| Approach: | They propose new protocols and best practices for improving dataset development from social media data and its usage. |
| Outcome: | The proposed protocols and best practices improve the performance of social media datasets and their usage. |
Align Attention Heads Before Merging Them: An Effective Way for Converting MHA to GQA (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated exceptional performance across diverse natural language processing tasks. |
| Approach: | They propose a method for converting multi-head attention into grouped-query attention with any compression ratio of KV heads. |
| Outcome: | The proposed method can compress up to 87.5% KV heads of LLaMA2-7B model and 75% Kv heads of Sheared-LLa MA-1.3B with acceptable performance degradation. |
Selective Temporal Knowledge Graph Reasoning (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing models cannot abstain from uncertain predictions, which will bring risks in real-world applications. |
| Approach: | They propose to abstain from uncertain future facts by using a confidence estimator . they take both the certainty of the current prediction and the accuracy of historical predictions into account . |
| Outcome: | The proposed abstention mechanism helps existing models make selective predictions instead of indiscriminate ones. |
Slangvolution: A Causal Analysis of Semantic Change and Frequency Dynamics in Slang (2022.acl-long)
Copied to clipboard
| Challenge: | a recent study suggests that language evolution is a diachronic process, but no causal analysis is performed to verify these claims. |
| Approach: | They analyze the semantic change and frequency shift of slang words and compare them to those of standard, nonslang terms. |
| Outcome: | The proposed model shows that slang has smaller semantic change but larger frequency shifts over time. |
From Pixels to Personas: Investigating and Modeling Self-Anthropomorphism in Human-Robot Dialogues (2024.findings-emnlp)
Copied to clipboard
| Challenge: | a recent study shows that robots display human-like characteristics in dialogues . this anthropomorphism raises concerns about the accuracy of AI and its capabilities . |
| Approach: | They propose to use a dataset to analyze self-anthropomorphic and non-self-anthropophilic responses in robots . they propose to combine these two types of responses to create a new category of bot responses . |
| Outcome: | The proposed approach preserves the original dialogues from existing corpora and enhances them with paired responses: self-anthropomorphic and non-self-anthropophilic for each original bot response. |
EvoHyper: Evolving Hypergraph Topologies for Unified Collaboration in Multi-Agent Communication (2026.findings-acl)
Copied to clipboard
Heng Zhang, Yihao Zhong, Lubin Gan, Zhihe Chen, Jiajun Wu, Yuling Shi, Xiaodong Gu, Hao Zhang, Haochen You, Jin Huang
| Challenge: | Existing methods for multi-agent collaboration use a fixed communication graph and manage collaboration structure and shared memory in separate modules. |
| Approach: | They propose a framework that uses an evolving hypergraph topology for multi-agent collaboration. |
| Outcome: | The proposed framework achieves 3.2% to 7.8% accuracy gains over state-of-the-art methods and efficient, reducing token consumption by up to 23.5%. |
P²Net: Parallel Pointer-based Network for Key Information Extraction with Complex Layouts (2025.findings-acl)
Copied to clipboard
Kaiwen Wei, Jie Yao, Jiang Zhong, Yangyang Kang, Jingyuan Zhang, Changlong Sun, Xin Zhang, Fengmao Lv, Li Jin
| Challenge: | Existing methods for key information extraction are based on a limited set of entity categories and fixed layouts. |
| Approach: | They propose a large-scale, human-annotated dataset for key information extraction . it is based on a human-annotated layout and 1,162 entity categories . they propose 'parallel pointer-based network' that leverages implicit relationships . |
| Outcome: | Experiments on widely-used datasets show that the proposed model outperforms state-of-the-art methods while maintaining fast inference speeds. |
Understanding the Language Model to Solve the Symbolic Multi-Step Reasoning Problem from the Perspective of Buffer Mechanism (2025.findings-emnlp)
Copied to clipboard
Zhiwei Wang, Yunji Wang, Zhongwang Zhang, Zhangchen Zhou, Hui Jin, Tianyang Hu, Jiacheng Sun, Zhenguo Li, Yaoyu Zhang, Zhi-Qin John Xu
| Challenge: | Large language models struggle with complex reasoning tasks, such as mathematical problem-solving. |
| Approach: | They constructed a symbolic multi-step reasoning task to investigate the information propagation mechanisms in Transformer models when solving the task through direct answering and Chain-of-Thought (CoT) reasoning. |
| Outcome: | The proposed algorithm improves on 7 multi-step reasoning datasets, while introducing only 132 trainable parameters. |
SafeConv: Explaining and Correcting Conversational Unsafe Behavior (2023.acl-long)
Copied to clipboard
| Challenge: | Existing datasets do not provide enough annotation to explain unsafe behavior . current chatbots generate toxic and offensive responses, which can be dangerous . |
| Approach: | They construct a dataset called SafeConv that provides comprehensive annotations for chatbots . they compare safe alternatives to rewrite unsafe responses . |
| Outcome: | The proposed model can explain unsafe behavior and detoxify chatbots, the authors show . the proposed model is able to detect unsafe utterances, extract unsafe spans, and convert unsafe responses to safe versions. |
The Reasoning-Memorization Interplay in Language Models Is Mediated by a Single Direction (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models excel on a variety of reasoning benchmarks, but struggle to generalize to unseen questions due to over-reliance on memorized training examples. |
| Approach: | They propose to identify a set of linear features in the model’s residual stream that govern the balance between genuine reasoning and memory recall. |
| Outcome: | The proposed model can be manipulated to activate the most relevant problem-solving capabilities during answer generation. |
Incorporating Chinese Characters of Words for Lexical Sememe Prediction (P18-1)
Copied to clipboard
| Challenge: | Existing methods of lexical sememe prediction rely on external context information of words to represent meaning. |
| Approach: | They propose a character-enhanced sememe prediction framework for Chinese language that takes advantage of internal character information and external context information. |
| Outcome: | The proposed framework outperforms state-of-the-art methods on a Chinese sememe knowledge base and maintains robust performance even for low-frequency words. |
KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches (2024.findings-emnlp)
Copied to clipboard
Jiayi Yuan, Hongyi Liu, Shaochen Zhong, Yu-Neng Chuang, Songchen Li, Guanchu Wang, Duy Le, Hongye Jin, Vipin Chaudhary, Zhaozhuo Xu, Zirui Liu, Xia Hu
| Challenge: | Long context capability is a crucial competency for large language models as it mitigates the human struggle to digest long-form texts. |
| Approach: | They propose to evaluate 10+ state-of-the-art approaches for long context-capable LLMs. |
| Outcome: | The proposed methods are compared against 10+ state-of-the-art approaches across seven categories of long context tasks. |
Sailor: Open Language Models for South-East Asia (2024.emnlp-demo)
Copied to clipboard
| Challenge: | Large language models (LLMs) rely on English data for training, but are often not comparable across other languages. |
| Approach: | They propose to develop a family of open language models for SEA languages . they use BPE dropout, aggressive data cleaning and deduplication to improve model robustness . |
| Outcome: | The proposed models perform well across four benchmarks, including commonsense reasoning, question answering, reading comprehension and examination. |
Time-MQA: Time Series Multi-Task Question Answering with Context Enhancement (2025.acl-long)
Copied to clipboard
Yaxuan Kong, Yiyuan Yang, Yoontae Hwang, Wenjie Du, Stefan Zohren, Zhangyang Wang, Ming Jin, Qingsong Wen
| Challenge: | Existing time series models focus on a narrow spectrum of tasks, such as forecasting or anomaly detection. |
| Approach: | They propose a framework that enables natural language queries across multiple time series tasks such as numerical analytical tasks and open-ended question answering with reasoning. |
| Outcome: | The proposed framework enables natural language queries across multiple time series tasks and allows for more advanced and intuitive interactions with temporal data. |
DC-MBR: Distributional Cooling for Minimum Bayesian Risk Decoding (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods for decoding target language are degenerate, hallucinating or empty. |
| Approach: | They propose a method that tunes down the Softmax temperature to reduce autoregressive over-smoothness by label smoothing the output distributions. |
| Outcome: | The proposed method improves MBR in various settings. |
Analyzing and Mitigating Inconsistency in Discrete Speech Tokens for Neural Codec Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models (LLMs) have demonstrated significant strides in generating high-quality speech . discretizing speech by neural audio codecs often results in sequences that differ from text sequences . |
| Approach: | They quantitatively analyze the Discrete Representation Inconsistency phenomenon within popular audio tokenizers such as EnCodec. |
| Outcome: | The proposed method mitigates the DRI phenomenon within popular audio tokenizers such as EnCodec. |
Is the Attention Matrix Really the Key to Self-Attention in Multivariate Long-Term Time Series Forecasting? (2026.acl-long)
Copied to clipboard
| Challenge: | In multivariate long-term time series forecasting, it is widely believed that the effectiveness of self-attention arises from its attention matrix. |
| Approach: | They propose a multi-branch MLP that isolates the ‘multi-brain mapping with element-wise operation’ structure from the Transformer and shows that it achieves competitive performance. |
| Outcome: | The proposed model outperforms three classic and three latest Transformer models and shows that it achieves competitive performance. |
GR1: Reinforcement-Enhanced LLM for Geoscience Reasoning (2026.findings-acl)
Copied to clipboard
Yule Xie, Jiaxin Ding, Cheng Deng, Shiqing Gao, Junran Zhang, Sibo Zhang, Zeyuan Wang, Ke Wu, Xin Ding, Luoyi Fu, Meng Jin, Xinbing Wang
| Challenge: | Recent advances in large language models have demonstrated RL's substantial capacity to enhance multi-step reasoning beyond what supervised instruction tuning achieves. |
| Approach: | They propose a framework that converts multimodal questions into descriptive text . they propose RL-enhanced geoscience reasoning that can be fine-tuned to a text-only level . |
| Outcome: | The proposed framework improves accuracy and accuracy on multimodal questions while preserving answerability and difficulty. |
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. |
LongMP-Bench: A Benchmark for Multimodal Persona Understanding in Long-Term Dialogues (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing datasets suffer from limited persona diversity and static, overly simplified settings, making them insufficient for capturing the complexity of real-world interactions. |
| Approach: | They propose a benchmark to evaluate models' ability to understand evolving user personas within long-term multimodal dialogues by using a dataset that contains long conversations from 150 users. |
| Outcome: | The proposed benchmark aims to assess models' ability to track persona evolution, integrate visual and textual inputs, and apply persona understanding in realistic dialogue scenarios. |
CLAMBER: A Benchmark of Identifying and Clarifying Ambiguous Information Needs in Large Language Models (2024.acl-long)
Copied to clipboard
Tong Zhang, Peixin Qin, Yang Deng, Chen Huang, Wenqiang Lei, Junhong Liu, Dingnan Jin, Hongru Liang, Tat-Seng Chua
| Challenge: | Large language models are used to meet user information needs, but their effectiveness in dealing with user queries that contain various types of ambiguity remains unknown. |
| Approach: | They propose a benchmark for evaluating large language models using a well-organized taxonomy. |
| Outcome: | The proposed model is based on a well-organized taxonomy and compares it with other models. |
Iterative Refinement of Project-Level Code Context for Precise Code Generation with Compiler Feedback (2024.findings-acl)
Copied to clipboard
Zhangqian Bi, Yao Wan, Zheng Wang, Hongyu Zhang, Batu Guan, Fangxin Lu, Zili Zhang, Yulei Sui, Hai Jin, Xuanhua Shi
| Challenge: | Large Language Models (LLMs) generate code for given contexts, such as incomplete code, class, data structure, or project-specific information. |
| Approach: | They propose a compiler feedback-based code generation approach that leverages static analysis to identify mismatches between the generated code and the project's context. |
| Outcome: | The proposed model outperforms retrieval-based code generation baselines and significantly outperfies the existing large language models. |
PivotFEC: Enhancing Few-shot Factual Error Correction with a Pivot Task Approach using Large Language Models (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for Factual Error Correction (FEC) use mask-then-correct paradigms . however, the lack of datasets containing false claims has impeded progress . |
| Approach: | They propose a method that enhances few-shot FEC with a pivot task approach using large language models. |
| Outcome: | The proposed method outperforms its few-shot counterpart by 7.9 points in SARI . it improves widely-adopted SARI metrics by 11.3 compared to the best-performing methods . |
Recurrent Event Network: Autoregressive Structure Inferenceover Temporal Knowledge Graphs (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for reasoning over temporal knowledge graphs focus on past timestamps and are not able to predict future interactions. |
| Approach: | They propose a novel autoregressive architecture for predicting future interactions using a recurrent event encoder and a neighborhood aggregator. |
| Outcome: | The proposed method achieves state-of-the-art on five public datasets. |
T2A-Feedback: Improving Basic Capabilities of Text-to-Audio Generation via Fine-grained AI Feedback (2025.acl-long)
Copied to clipboard
Zehan Wang, Ke Lei, Chen Zhu, Jiawei Huang, Sashuai Zhou, Luping Liu, Xize Cheng, Shengpeng Ji, Zhenhui Ye, Tao Jin, Zhou Zhao
| Challenge: | Text-to-audio (T2A) models still struggle to satisfy human preferences for prompt-following and acoustic quality when generating complex multi-event audio. |
| Approach: | They propose to use AI feedback learning to enhance basic capabilities of text-to-audio models . they use a large audio preference dataset to evaluate the model's capabilities . |
| Outcome: | The proposed model improves in simple and complex scenarios with AI feedback learning. |
RadialRouter: Structured Representation for Efficient and Robust Large Language Models Routing (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Current routing methods are limited in exploring the connection between query and LLM characteristics. |
| Approach: | They propose a framework for LLM routing that uses a transformer-based backbone and a radial structure to articulate the query-LLMs relationship. |
| Outcome: | The proposed framework outperforms existing routing methods by 9.2% and 5.8% on RouterBench. |
Error-Robust Retrieval for Chinese Spelling Check (2024.lrec-main)
Copied to clipboard
| Challenge: | Chinese Spelling Check (CSC) aims to detect and correct spelling errors in Chinese texts . current methods may not fully leverage existing datasets, resulting in insufficient annotated data . |
| Approach: | They propose a plug-and-play retrieval method with error-robust information for Chinese Spelling Check . they employ multimodal representations that fuse phonetic, morphologic, and contextual information . |
| Outcome: | The proposed method improves on the SIGHAN benchmarks on Chinese spelling check (CSC) the proposed method is based on training data and lacks adequate parallel corpora . |
Exploring Concept Depth: How Large Language Models Acquire Knowledge and Concept at Different Layers? (2025.coling-main)
Copied to clipboard
Mingyu Jin, Qinkai Yu, Jingyuan Huang, Qingcheng Zeng, Zhenting Wang, Wenyue Hua, Haiyan Zhao, Kai Mei, Yanda Meng, Kaize Ding, Fan Yang, Mengnan Du, Yongfeng Zhang
| Challenge: | Large language models have shown remarkable performances across a wide range of tasks, but mechanisms by which they encode tasks of varying complexity remain poorly understood. |
| Approach: | They propose to explore the possibility that LLMs process concepts in different layers . they propose to categorize concepts based on their level of abstraction . |
| Outcome: | The proposed model can process complex concepts in shallow layers, the authors show . the proposed model could be used to prob complex tasks in shallow ones . |
Improving LLM Generations via Fine-Grained Self-Endorsement (2024.findings-acl)
Copied to clipboard
| Challenge: | Recent large language models (LLMs) have demonstrated remarkable capabilities but can still fail frequently on knowledge-intensive tasks. |
| Approach: | They propose a self-endorsement framework that leverages fine-grained fact-level comparisons across multiple sampled responses. |
| Outcome: | The proposed framework can improve factuality of generations with simple prompts across scales of LLMs. |
LLM-ForcedAligner: A Non-Autoregressive and Accurate LLM-Based Forced Aligner for Multilingual and Long-Form Speech (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for forcing alignment are language-specific and prone to temporal shifts. |
| Approach: | They propose a slot-filling paradigm that uses time indices to predict slot positions. |
| Outcome: | The proposed method reduces accumulated temporal shifts by 69% compared with prior methods. |
Dynamic Model-Bank Test-Time Adaptation for Automatic Speech Recognition (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing ASR TTA methods struggle with instability under continual and long-term distribution shifts. |
| Approach: | They propose a continuous adaptive model-bank framework that adapts to domain shifts in ASR test-time scenarios. |
| Outcome: | Experiments on diverse, continuously shifting ASR benchmarks show that DMSUTA outperforms existing continual TTA baselines. |
Aspect-Category Enhanced Learning with a Neural Coherence Model for Implicit Sentiment Analysis (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Aspect-based sentiment analysis (ABSA) is a major research topic in NLP since social networking services have increased . but the recognition of implicit sentiments that do not contain obvious opinion words remains unexplored . elcom captures document-level coherence by using contrastive learning and sentence-level by a hypergraph . |
| Approach: | They propose aspect-category enhanced learning with a neural coherence model . it captures document-level coherency by contrastive learning and sentence-level by a hypergraph . |
| Outcome: | The proposed model captures document-level coherence by using contrastive learning and sentence-level by a hypergraph to mine opinions from explicit sentences to aid implicit sentiment classification. |
Data-centric NLP Backdoor Defense from the Lens of Memorization (2025.findings-naacl)
Copied to clipboard
| Challenge: | Backdoor attacks pose a severe threat to the trustworthiness of DNN-based language models. |
| Approach: | They propose a data-centric defense that extends memorization definitions to fine-grained sentences . they find that duplicated sentence elements are necessary for successful backdoor attacks . |
| Outcome: | The proposed defense outperforms state-of-the-art defenses against backdoor attacks. |
Learn over Past, Evolve for Future: Forecasting Temporal Trends for Fake News Detection (2023.acl-industry)
Copied to clipboard
| Challenge: | Existing work on fake news detection does not consider the temporal shift issue caused by the rapidly-evolving nature of news data. |
| Approach: | They propose a framework to forecast temporal patterns of news data and guide detector to fast adapt to future distributions. |
| Outcome: | The proposed framework forecasts temporal distribution patterns and guides detector to fast adapt to future distribution. |
SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression (2026.acl-long)
Copied to clipboard
| Challenge: | Retrieval-augmented generation (RAG) extends large language models with external knowledge, but it must balance limited effective context, redundant retrieved evidence, and the loss of fine-grained facts. |
| Approach: | They propose a hybrid RAG framework that uses natural-language snippets and semantic compression vectors to preserve passages in text form and compress remaining evidence into interpretable vectors for iterative evidence reranking. |
| Outcome: | The proposed framework improves answer relevance, answer correctness and semantic similarity across 9 datasets and 5 open-source LLMs. |
Assist Non-native Viewers: Multimodal Cross-Lingual Summarization for How2 Videos (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing multimodal summarization methods are limited to monolingual videos . a proposed task aims to generate cross-lingual summaries from multimodal inputs . |
| Approach: | They propose a task to generate cross-lingual summaries from multimodal inputs of videos . they propose fusion network that integrates multimodal and cross-linguistic information . |
| Outcome: | The proposed task outperforms existing methods on a reorganized How2 dataset on the reorganized How2 data set. |
A New Concept of Deep Reinforcement Learning based Augmented General Tagging System (C18-1)
Copied to clipboard
| Challenge: | Existing systems for general sequence tagging/labeling are based on neural network architectures. |
| Approach: | They propose a deep neural network based sequence labeling model and a augmented tagger to improve system performance by modeling the data with minority tags. |
| Outcome: | The proposed system outperforms the current state-of-the-art model on ATIS and CoNLL-2003 datasets by 1.9% and 1.4%. |
RIPRAG: Hack a Black-box Retrieval-Augmented Generation Question-Answering System with Reinforcement Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to generate RAG documents require knowledge of the target RAG system’s internal composition and implementation details, whereas black-box methods are unable to utilize interactive information. |
| Approach: | They propose a RIPRAG attack framework that treats the target RAG system as a black box and leverages a Reinforcement Learning from Black-box Feedback (RLBF) method to optimize the generation model for poisoned documents. |
| Outcome: | The proposed method achieves an attack success rate (ASR) improvement of up to 0.72 compared to baseline methods. |
Rethinking Multiple-Choice Questions for RLVR: Unlocking Potential via Distractor Design (2026.findings-acl)
Copied to clipboard
Xu Guo, Qiming Ge, Jian Tong, Kedi Chen, Jin Zhang, Xiaogui Yang, Xuan Gao, Haijun Lv, Zhihui Lu, Yicheng Zou, Qipeng Guo
| Challenge: | Existing approaches to RLVR use multiple-choice questions as verifiable rewards . however, not all tasks provide reliable verification . |
| Approach: | They propose a framework that actively constructs high-quality distractors to block elimination shortcuts and promote deep reasoning. |
| Outcome: | The proposed method significantly improves reasoning capabilities of Large Language Models. |
Model-Based Imaginative Planning for Embodied Agents (2026.acl-long)
Copied to clipboard
Junru Song, Hengzhe Jin, Yucong Huang, Tingsong Jiang, Weien Zhou, Feifei Wang, Yang Yang, Ying Wen, Wen Yao
| Challenge: | a lightweight world model converts raw pixels into object-centric symbolic states amenable to language-based reasoning . IMPLEMENT is a framework for grounding language agents in visual embodied environments . |
| Approach: | They propose a model-based reasoning framework that enables frozen large language models to perform imaginative planning. |
| Outcome: | The proposed framework can be used to ground language agents in visual embodied environments. |
MdEval: Massively Multilingual Code Debugging (2026.findings-acl)
Copied to clipboard
Shukai Liu, Linzheng Chai, Jian Yang, Jiajun Shi, He Zhu, Liran Wang, Jin Ke, Wei Zhang, Hualei Zhu, Shuyue Guo, Tao Sun, Jiaheng Liu, Yunlong Duan, Yu Hao, Liqun Yang, Guanglin Niu, Ge Zhang, Zhoujun Li
| Challenge: | Existing benchmarks primarily focus on Python and are limited in terms of language diversity. |
| Approach: | They propose a multilingual debugging benchmark that includes 3.9K test samples of 20 programming languages and introduces the debug instruction corpora MdEval-Instruct by injecting bugs into the correct multilingual queries and solutions. |
| Outcome: | The proposed benchmark includes 3.9K test samples of 20 programming languages and covers the automated program repair task, bug localization task, and bug identification task. |
Exploring Cross-Cultural Differences in English Hate Speech Annotations: From Dataset Construction to Analysis (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing datasets for hate speech detection neglect the cultural diversity within a single language. |
| Approach: | They propose a CR**oss-cultural **E**nglish **Hate* speech dataset that uses culturally hateful keywords to identify posts from four countries plus the United States. |
| Outcome: | The proposed dataset shows that only 56.2% of the posts in CREHate achieve consensus among all countries, with the highest pairwise label difference rate of 26%. |
TinyChart: Efficient Chart Understanding with Program-of-Thoughts Learning and Visual Token Merging (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies have shown that multimodal large language models can be useful for chart understanding, but their size limits their use in resource-constrained environments. |
| Approach: | They propose an efficient multimodal large language model with only 3B parameters for chart understanding. |
| Outcome: | The proposed model outperforms several chart-understanding MLLMs with up to 13B parameters on ChartQA, Chart-to-Text, Chart to Table, OpenCQA, and ChartX. |
Revisiting Entropy in Reinforcement Learning for Large Reasoning Models (2026.findings-acl)
Copied to clipboard
Renren Jin, Pengzhi Gao, Yuqi Ren, Zhuowen Han, Tongxuan Zhang, Wuwei Huang, Wei Liu, Jian Luan, Deyi Xiong
| Challenge: | Reinforcement learning with verifiable rewards (RLVR) has emerged as a paradigm for enhancing the reasoning capabilities of large language models. |
| Approach: | They propose a positive-advantage reweighting approach that regulates model entropy by adjusting the loss weights assigned to tokens with positive advantages during RLVR training. |
| Outcome: | The proposed approach regulates model entropy by adjusting loss weights assigned to tokens with positive advantages during RLVR training while maintaining competitive performance. |
To What Extent Do Natural Language Understanding Datasets Correlate to Logical Reasoning? A Method for Diagnosing Logical Reasoning. (2022.coling-1)
Copied to clipboard
| Challenge: | Reasoning and knowledge-related skills are considered as fundamental skills for natural language understanding (NLU) tasks. |
| Approach: | They propose a method to diagnose correlations between an NLU dataset and a specific skill. |
| Outcome: | The proposed method is able to diagnose correlations between dataset and logical reasoning skill on 8 MRC and 3 NLI datasets. |
From Prediction to Intervention: Personalized Meal-Level Glucose Regulation via an LLM Agent (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to individualized glucose regulation are generic and do not account for individual-specific glucose dynamics. |
| Approach: | They propose a physio-feedback agentic loop that integrates individualized absorption modeling with dietary intervention to regulate glucose response. |
| Outcome: | The proposed system improves prediction accuracy and reduces glucose excursions. |
Event Coreference Resolution with their Paraphrases and Argument-aware Embeddings (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods for event coreference resolution do not identify paraphrase relations between events. |
| Approach: | They propose a new event-specific paraphrase and argument-aware semantic Embedding model for event coreference resolution based on event-related paraphrases and argument embeddings . EPASE recognizes deep paraphrase relations in an event- specific context of sentences and can cover event paraphrase of more situations . |
| Outcome: | Experiments on within- and cross-document event coreference show it is superior compared to existing methods. |
More Than Words: Collocation Retokenization for Latent Dirichlet Allocation Models (2022.findings-acl)
Copied to clipboard
| Challenge: | Latent Dirichlet Allocation models ingest words to discover their latent topics . but it is unclear how to achieve the best results for languages without marked word boundaries . |
| Approach: | They propose to use retokenization to merge frequent token ngrams into collocations in input to a Latent Dirichlet Allocation model. |
| Outcome: | The proposed model improves topic coherence and coherency in Chinese and Thai . the proposed model is more coherent and clearer than unmerged models . |
How Robust Are Router-LLMs? Analysis of the Fragility of LLM Routing Capabilities (2026.eacl-long)
Copied to clipboard
| Challenge: | Large language model (LLM) routing has emerged as a promising solution to balancing computational costs and performance. |
| Approach: | They propose a framework that categorizes router performance across a broad spectrum of query types . large language models have revolutionized natural language processing . |
| Outcome: | The proposed framework categorizes router performance across a broad spectrum of query types . it integrates privacy and safety assessments to reveal hidden risks . |
The Odyssey of Commonsense Causality: From Foundational Benchmarks to Cutting-Edge Reasoning (2024.emnlp-main)
Copied to clipboard
| Challenge: | Despite its significance, a systematic exploration of commonsense causality is lacking. |
| Approach: | They focus on taxonomies, benchmarks, acquisition methods, qualitative reasoning, and quantitative measurements in commonsense causality. |
| Outcome: | The proposed method synthesizes insights from over 200 representative articles and provides a practical guide for beginners. |
Logographic Information Aids Learning Better Representations for Natural Language Inference (2022.findings-aacl)
Copied to clipboard
| Challenge: | Statistical language models often ignore information related to logographic features of written text . many languages, including Chinese and Vietnamese, use logographic writing systems . |
| Approach: | They propose to provide language models with logographic information to learn better semantic representations. |
| Outcome: | The proposed model improves semantic representations in six languages with logographic writing systems. |
HisDoc-OCR: Restoring Visual Grounding in MLLMs for Chinese Historical Document OCR (2026.findings-acl)
Copied to clipboard
| Challenge: | Despite multimodal large language models' strong performance on modern document OCR, their application to historical Chinese texts suffers from severe hallucinations, character fabrication, uncontrolled repetition, and semantic drift. |
| Approach: | They propose a multimodal large language model which restores visual grounding through three synergistic strategies: Layout Injection, First-Occurrence Boost, Self-Distilled Attention Focusing and HisDoc-OCR. |
| Outcome: | The proposed model outperforms general-purpose and OCR-specific models on Chinese historical documents. |
Event Schema Induction with Double Graph Autoencoders (2022.naacl-main)
Copied to clipboard
| Challenge: | Experimental results show that a new method for learning event schemas from historical events is effective. |
| Approach: | They propose a new event schema induction framework which captures global dependencies among nodes in event graphs. |
| Outcome: | Experimental results show that the proposed model can learn event schemas with global consistency. |
Chain-of-Thought Tuning: Masked Language Models can also Think Step By Step in Natural Language Understanding (2023.emnlp-main)
Copied to clipboard
| Challenge: | Chain-of-Thought (CoT) is a technique that guides large language models to decompose complex tasks into multi-step reasoning processes. |
| Approach: | They propose a two-step reasoning framework based on prompt tuning to implement step-by-step thinking for MLMs on NLU tasks. |
| Outcome: | The proposed framework outperforms baselines and achieves state-of-the-art performance on two NLU tasks. |
MultiConIR: Towards Multi-Condition Information Retrieval (2025.findings-emnlp)
Copied to clipboard
Xuan Lu, Sifan Liu, Bochao Yin, Yongqi Li, Xinghao Chen, Hui Su, Yaohui Jin, Wenjun Zeng, Xiaoyu Shen
| Challenge: | MultiConIR is a benchmark designed to evaluate retrieval and reranking models under nuanced multi-condition query scenarios. |
| Approach: | They propose a benchmark to evaluate retrieval and reranking models under nuanced multi-condition query scenarios. |
| Outcome: | The proposed benchmark evaluates retrieval and reranking models under nuanced multi-condition query scenarios across five domains. |
Harder Task Needs More Experts: Dynamic Routing in MoE Models (2024.acl-long)
Copied to clipboard
Quzhe Huang, Zhenwei An, Nan Zhuang, Mingxu Tao, Chen Zhang, Yang Jin, Kun Xu, Kun Xu, Liwei Chen, Songfang Huang, Yansong Feng
| Challenge: | Unlike existing MoE approaches that rely on fixed TopK Routing, our dynamic expert selection framework dynamically allocates experts based on the confidence level in expert selection for each input. |
| Approach: | They propose a dynamic expert selection framework that dynamically allocates experts based on the confidence level in expert selection for each input. |
| Outcome: | The proposed method achieves an average improvement of 0.7% with less than 90% activated parameters and outperforms dense models in QA and machine translation tasks. |
Wrong-of-Thought: An Integrated Reasoning Framework with Multi-Perspective Verification and Wrong Information (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Chain-of-Thought (CoT) is a key technique for enhancing the performance of Large Language Models. |
| Approach: | They propose a framework that optimizes outputs by utilizing wrong information and multi-perspective verification. |
| Outcome: | The proposed framework surpasses all baselines on 8 datasets and 5 LLMs. |
Solving Math Word Problems with Multi-Encoders and Multi-Decoders (2020.coling-main)
Copied to clipboard
| Challenge: | Existing models that transform text descriptions into equation expressions only consider input/output objects as sequences, ignoring important structural information contained in text descriptions and equation expression. |
| Approach: | They propose a model that uses sequence-based encoders and graph-based decoders to enhance the representation of text descriptions and generate different equation expressions. |
| Outcome: | The proposed model outperforms existing state-of-the-art methods on a dataset with a n-word problem. |
DimABSA: Building Multilingual and Multidomain Datasets for Dimensional Aspect-Based Sentiment Analysis (2026.acl-long)
Copied to clipboard
Lung-Hao Lee, Liang-Chih Yu, Natalia V Loukachevitch, Ilseyar Alimova, Alexander Panchenko, Tzu-Mi Lin, Zhe-Yu Xu, Jian-Yu Zhou, Guangmin Zheng, Jin Wang, Sharanya Awasthi, Jonas Becker, Jan Philip Wahle, Terry Ruas, Shamsuddeen Hassan Muhammad, Saif M. Mohammad
| Challenge: | Existing ABSA research relies on coarse-grained categorical labels, which limits its ability to capture nuanced affective states. |
| Approach: | They propose a dimensional approach that represents sentiment with continuous valence–arousal (VA) scores, enabling fine-grained analysis at both the aspect and sentiment levels. |
| Outcome: | The proposed approach represents sentiment with continuous valence–arousal (VA) scores, enabling fine-grained analysis at both the aspect and sentiment levels. |
Benchmarking Long-Context Language Models on Long Code Understanding (2025.acl-long)
Copied to clipboard
Jia Li, Xuyuan Guo, Lei Li, Kechi Zhang, Ge Li, Jia Li, Zhengwei Tao, Fang Liu, Chongyang Tao, Yuqi Zhu, Zhi Jin
| Challenge: | Currently, long-context language models are limited by the lack of a rigorous evaluation framework for long code understanding. |
| Approach: | They propose to use a long code understanding benchmark LongCodeU to evaluate LCLMs' long code comprehension ability for practical applications. |
| Outcome: | The proposed benchmarks show that current LCLMs are limited in their long code understanding ability, particularly when the long code length is greater than 32K, falling far short of their claimed 128K to 1M context windows. |
Few-shot Link Prediction on Hyper-relational Facts (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods to predict missing elements in hyper-relational facts require high-quality data. |
| Approach: | They propose a task to predict a missing entity in a hyper-relational fact with limited support instances. |
| Outcome: | The proposed model outperforms existing models on three datasets. |
GBT: Generative Boosting Training Approach for Paraphrase Identification (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Paraphrase Identification (PI) is a fundamental natural language understanding task with non-trivial challenges. |
| Approach: | They propose a Generative Boosting Training approach for Paraphrase Identification (PI) they use a seq2seq model to perform DA on misclassified instances periodically . |
| Outcome: | The proposed method outperforms state-of-the-art PI models on English and Chinese PI tasks with good efficiency and effectiveness. |
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. |
Contextualizing Hate Speech Classifiers with Post-hoc Explanation (2020.acl-main)
Copied to clipboard
| Challenge: | Modern text classifiers struggle to learn a model of hate speech that generalizes to real-world applications. |
| Approach: | They propose a method to regularize BERT classifiers to detect bias towards identity terms by providing explanations for group identifiers and allowing models to learn from the context of group identifiers. |
| Outcome: | The proposed method limiting false positives on out-of-domain data while maintaining and improving in-domain performance. |
How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training (2025.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have exceptional capabilities in knowledge-intensive tasks . however, they struggle with knowledge updates due to dynamic nature of world knowledge . |
| Approach: | They propose to identify computational subgraphs that facilitate knowledge storage and processing . they also identify a phase shift from formation to optimization in LLMs . |
| Outcome: | The proposed model can capture factual knowledge from pre-training corpus and encapsulate it as extensive parametric knowledge. |
StreamHover: Livestream Transcript Summarization and Annotation (2021.emnlp-main)
Copied to clipboard
Sangwoo Cho, Franck Dernoncourt, Tim Ganter, Trung Bui, Nedim Lipka, Walter Chang, Hailin Jin, Jonathan Brandt, Hassan Foroosh, Fei Liu
| Challenge: | StreamHover is a framework for annotating and summarizing livestream transcripts . the problem is that there is n't enough annotated datasets to summarize livestreams based on the informal nature of spoken language . |
| Approach: | They propose a framework for annotating and summarizing livestream transcripts using a text preview. |
| Outcome: | The proposed model generalizes better and improves over strong baselines. |
MedKInstruct: A Multimodal Knowledge Graph Based Framework for Multi-Hop and Hard-Negative Instruction Data Synthesis in MedVQA (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for medical visual question answering focus on image–caption pairs, limiting the model’s ability to learn relevant medical knowledge during training. |
| Approach: | They propose to synthesize instruction data from image–caption pairs and incorporate a multimodal medical knowledge graph to assist LVLMs in synthesizing knowledge-intensive instruction data. |
| Outcome: | The proposed model outperforms existing methods on the public datasets Slake and VQA-RAD by 4.16% and 4.50%. |
TrapDoc: Deceiving LLM Users by Injecting Imperceptible Phantom Tokens into Documents (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a growing number of LLMs have been used to provide reasoning, writing, text-editing capabilities. |
| Approach: | They propose a method to inject imperceptible phantom tokens into LLMs to deceive users . the technique generates outputs that appear plausible to users but are in fact incorrect . |
| Outcome: | a new method injects imperceptible tokens into documents to deceive users . the proposed framework is compared to baselines to show its effectiveness . |
Dual-Encoder Transformers with Cross-modal Alignment for Multimodal Aspect-based Sentiment Analysis (2022.aacl-main)
Copied to clipboard
| Challenge: | Multimodal aspect-based sentiment analysis (MABSA) aims to extract aspect terms from text and image pairs, and then analyze their corresponding sentiment. |
| Approach: | They propose a dual-encoder transformer with cross-modal alignment to extract aspect terms from text and image pairs and then analyze their corresponding sentiments. |
| Outcome: | The proposed approach outperforms existing methods on two benchmarks. |
Attention Weights as an Indicator: Analyzing and Improving Document Utilization in Retrieval-Augmented Generation (2026.acl-long)
Copied to clipboard
| Challenge: | In traditional RAG models, documents are grouped into categories based on their quality and order, and the quality of inputs is variable due to ineffective retrievers or misalignment between the retriever and generator. |
| Approach: | They propose to use attention weights to enhance document utilization from three perspectives: document ranking, placement, and filtering. |
| Outcome: | The proposed method outperforms baselines and improves document utilization effectiveness in a training-free manner. |
A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Language Models (2023.acl-long)
Copied to clipboard
| Challenge: | Recent work shows that language models can rely on shallow patterns in problem description when generating a solution. |
| Approach: | They propose a framework which pins down the causal effect of various factors on the output solution. |
| Outcome: | The proposed framework improves robustness and sensitivity to direct interventions on a test bed of math word problems. |
AgentGC: Evolutionary Learning-based Lossless Compression for Genomics Data with LLM-driven Multiple Agent (2026.findings-acl)
Copied to clipboard
Sun Hui, Ding Yanfeng, Huidong Ma, Chang Xu, Keyan Jin, Lizheng Zu, Cheng Zhong, Xiaoguang Liu, Gang Wang, Wentong Cai
| Challenge: | Lossless compression has made significant advancements in Genomics Data storage, sharing and management. |
| Approach: | They propose a novel agent-based GD Compressor with 3 layers with a multi-agent named Leader and Worker. |
| Outcome: | The proposed method improves on existing methods with low-level modeling and limited adaptability and user-unfriendly interface. |
View-R1: Asymmetric Policy Optimization for Difficulty-Aware Multimodal Reinforcement Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Multimodal Large Language Models (MLLMs) are powerful at integrating diverse data but struggle with complex reasoning. |
| Approach: | They propose a method which separates responses into positive and negative groups to stabilize training and preserve knowledge. |
| Outcome: | The proposed model View-R1 achieves a 10.55% improvement in reasoning and outperforms larger models while maintaining and improving performance on general tasks. |
Neural Graph Matching Networks for Chinese Short Text Matching (2020.acl-main)
Copied to clipboard
| Challenge: | Chinese word segmentation can be erroneous, ambiguous or inconsistent, causing performance problems. |
| Approach: | They propose a sentence matching framework that uses paired word lattices as input instead of a character sequence. |
| Outcome: | The proposed framework outperforms the state-of-the-art short text matching models on two Chinese datasets. |
Differentially Private Language Models for Secure Data Sharing (2022.emnlp-main)
Copied to clipboard
| Challenge: | a variety of deanonymization attacks allow the re-identification of individuals from tabular data. |
| Approach: | They propose to train a language model in a differentially private manner and sample data from it . they find that the model generates fluent textual datasets with privacy guarantees . |
| Outcome: | The proposed methods outperform direct classifiers with DP-SGD in the real-world. |
Instance-adaptive training with noise-robust losses against noisy labels (2021.emnlp-main)
Copied to clipboard
| Challenge: | Several noise-robust losses have been proposed and evaluated on tasks in computer vision, but they use a single dataset-wise hyperparamter to control the strength of noise resistance. |
| Approach: | They propose to change single dataset-wise hyperparameters of noise resistance to be instance-wise. |
| Outcome: | The proposed frameworks increase noise-robustness on noisy and corrupted NLP datasets. |
SynFix: Dependency-Aware Program Repair via RelationGraph Analysis (2025.findings-acl)
Copied to clipboard
Xunzhu Tang, Jiechao Gao, Jin Xu, Tiezhu Sun, Yewei Song, Saad Ezzini, Wendkûuni C. Ouédraogo, Jacques Klein, Tegawendé F. Bissyandé
| Challenge: | Existing methods for resolving repository-level debugging are limited by their interdependencies. |
| Approach: | They propose a RelationGraph-based approach that integrates large language models with structural search and synchronization techniques for coordinated program repair across codebases. |
| Outcome: | SynFix resolves 52.33% of issues in SWE-bench-lite, 55.8% in Swe-bech-verified and 29.86% in S WE-beach-full. |
Nested Event Extraction upon Pivot Element Recognition (2024.lrec-main)
Copied to clipboard
Weicheng Ren, Zixuan Li, Xiaolong Jin, Long Bai, Miao Su, Yantao Liu, Saiping Guan, Jiafeng Guo, Xueqi Cheng
| Challenge: | Nested Event Extraction (NEE) aims to extract complex event structures where an event contains other events as its arguments recursively. |
| Approach: | They propose a new model that extracts nested events mainly based on recognizing PEs. |
| Outcome: | The proposed model can extract nested events based on recognizing PEs . it incorporates information from both event types and argument roles to improve performance . |
De-Confounded Variational Encoder-Decoder for Logical Table-to-Text Generation (2021.acl-long)
Copied to clipboard
| Challenge: | Logical table-to-text generation is challenging where deep learning models capture surface-level spurious correlations rather than the causal relationships between the table x and the sentence y. |
| Approach: | They propose to use variational inference to estimate the confounders in the latent space and cooperate with the causal intervention based on Pearl’s do-calculus to alleviate the spurious correlations. |
| Outcome: | The proposed model outperforms baselines and achieves new state-of-the-art performance on two logical table-to-text datasets in terms of logical fidelity. |
Chain-of-Specificity: Enhancing Task-Specific Constraint Adherence in Large Language Models (2025.coling-main)
Copied to clipboard
| Challenge: | Existing approaches to enhancing large language models fail to emphasize specific constraints and unlock the underlying knowledge. |
| Approach: | They propose a method that emphasizes specific constraints and unlocks knowledge within LLMs by iteratively emphasising on specific constraints. |
| Outcome: | The proposed method outperforms existing methods in enhancing generated content, especially in terms of specificity. |
Detection, Diagnosis, and Explanation: A Benchmark for Chinese Medial Hallucination Evaluation (2024.lrec-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have made significant progress in recent years, but their practical use is hindered by their tendency to generate hallucinations. |
| Approach: | They propose to use ICD-10 and MeSH to evaluate LLMs' ability to detect medical hallucinations and make accurate diagnoses in noisy environments. |
| Outcome: | The proposed benchmark can be used to evaluate LLMs’ ability to detect medical hallucinations, make accurate diagnoses in noisy conditions, and provide plausible explanations. |
APT: Improving Specialist LLM Performance with Weakness Case Acquisition and Iterative Preference Training (2025.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models often require domain-specific fine-tuning to address targeted tasks, which risks degrading their general capabilities. |
| Approach: | They propose to use self-generated dis-preferred weakness data to enhance model performance with a targeted training approach that minimizes interference with existing knowledge base. |
| Outcome: | The proposed approach ensures no reduction in generic capacity and achieves superior performance on downstream tasks compared to existing methods. |
Efficient KL Divergence Estimation via Truncated Top-K Integration for Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for estimating KL divergence using only top-k tokens suffer from high variance or systematic bias. |
| Approach: | They propose a top-k Importance-weighted KL Estimator that exploits the Zipfian structure of language model distributions by integrating only the top-K tokens. |
| Outcome: | The proposed estimator outperforms existing estimators on multiple benchmarks while exhibiting lower variance. |
MIND Your Reasoning: A Meta-Cognitive Intuitive-Reflective Network for Dual-Reasoning in Multimodal Stance Detection (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods operate by learning to fuse modalities, leading to frequent misjudgments. |
| Approach: | They propose a paradigm shift from *learning to fuse* to *learning the reason's process' inspired by the dual-process theory of human cognition, MIND operationalizes a self-improving loop. |
| Outcome: | The proposed model significantly outperforms baseline models and exhibits strong generalization. |
Semantically Consistent Data Augmentation for Neural Machine Translation via Conditional Masked Language Model (2022.coling-1)
Copied to clipboard
| Challenge: | Neural network models have a large number of parameters to train, but data augmentation is relatively under-explored in natural language processing. |
| Approach: | They propose a bi-directional conditional Masked Language Model (CMLM) that can be conditional on both left and right contexts and the label. |
| Outcome: | The proposed method achieves the best performance on four translation datasets and yields up to 1.90 BLEU points over the baseline. |
Graph Attention Network with Memory Fusion for Aspect-level Sentiment Analysis (2020.aacl-main)
Copied to clipboard
| Challenge: | Recent studies ignored the syntactic relationship between the aspect and its corresponding context words, leading the model to focus on syntaktically unrelated words mistakenly. |
| Approach: | They propose to extend the graph convolutional network by assigning different weights to edges of connected words. |
| Outcome: | The proposed method can improve on five datasets showing that it learns and exploits multiword relations and draws different weights of words to improve performance. |
KEEP CHATTING! An Attractive Dataset for Continuous Conversation Agents (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing works about persona dialogue such as PersonaChat have greatly facilitated the chatbot with configurable and persistent personalities. |
| Approach: | They propose to collect a dataset called ContinuousChat and rewrite it in style-specific ways to increase users' willingness to continue chatting. |
| Outcome: | The proposed model increases users' willingness to continue talking to the chatbot by increasing their personas to detailed-personas through experiences, daily life, future plans, or interesting stories. |
Improving Model Factuality with Fine-grained Critique-based Evaluator (2025.acl-long)
Copied to clipboard
Yiqing Xie, Wenxuan Zhou, Pradyot Prakash, Di Jin, Yuning Mao, Quintin Fettes, Arya Talebzadeh, Sinong Wang, Han Fang, Carolyn Rose, Daniel Fried, Hejia Zhang
| Challenge: | Factuality evaluation aims to detect factual errors produced by language models and guide the development of more factual models. |
| Approach: | They propose a framework that leverages FenCE to improve the factuality of LM generators by constructing training data. |
| Outcome: | The proposed framework improves the factuality of LM generators by enhancing their training data. |
Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extraction (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods to extract event records from text decompose complex structure prediction task into multiple subtasks. |
| Approach: | They propose a sequence-to-structure generation paradigm that can extract events from text . they propose unified event extraction, constrained decoding algorithm and curriculum learning algorithm . |
| Outcome: | The proposed method can achieve competitive performance using record-level annotations in both supervised learning and transfer learning settings. |
Internal Value Alignment in Large Language Models through Controlled Value Vector Activation (2025.acl-long)
Copied to clipboard
| Challenge: | Existing LLMs do not possess consistent values, but many have been developed to align them at the behavioral level, including supervised fine-tuning (SFT) and reinforcement learning from human feedback (RLHF). |
| Approach: | They propose a Controlled Value Vector Activation method that directly aligns the internal values of Large Language Models by interpreting how a value is encoded in their latent representations. |
| Outcome: | The proposed method achieves highest success rate across 10 basic values without hurting model performance and fluency, and ensures target values even with opposite and potentially malicious input prompts. |
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. |
Implicit Discourse Relation Recognition using Neural Tensor Network with Interactive Attention and Sparse Learning (C18-1)
Copied to clipboard
| Challenge: | Existing methods for implicit discourse relation recognition ignore bidirectional interactions between two arguments and sparsity of pair patterns. |
| Approach: | They propose a neural Tensor network framework with interactive attention and sparse learning for implicit discourse relation recognition. |
| Outcome: | The proposed framework is effective on PDTB and can be used in text summarization, conversation system and so on. |
AudioStealer: Extracting Audio Prompts via Shapley Value-Guided Query Search (2026.findings-acl)
Copied to clipboard
| Challenge: | prompt stealing is a new form of attack that aims to reconstruct high-value prompts that guide music generation. |
| Approach: | They propose a method to steal music prompts from audio domains using a black-box attack framework. |
| Outcome: | The proposed method recovers prompts with high textual consistency to the ground truth while maintaining strong perceptual similarity to the target recordings. |
PACHAT: Persona-Aware Speech Assistant for Multi-party Dialogue (2025.emnlp-main)
Copied to clipboard
| Challenge: | Extensive research on spoken dialogue systems has advanced the development of intelligent voice assistants, but integration of role information within speech remains an underexplored area. |
| Approach: | They propose a language-based spoken dialogue system that integrates role information within speech to generate contextually appropriate responses. |
| Outcome: | The proposed architecture achieves speaker-specific responses, character understanding, and the generation of targeted replies in multi-party dialogue scenarios, surpassing existing spoken dialogue systems. |
ReStyle-TTS: Relative and Continuous Style Control for Zero-Shot Speech Synthesis (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent controllable zero-shot text-to-speech systems can synthesize speech for unseen speakers from a short reference audio clip, but they also inherit the speaking style present in the reference. |
| Approach: | They propose a framework that enables continuous and reference-relative style control in zero-shot text-to-speech systems by combining style-specific LoRAs with Orthogonal LoRA Fusion. |
| Outcome: | The proposed framework reduces the model's dependence on reference style while preserving text fidelity while maintaining intelligibility and speaker timbre. |
Attractive Storyteller: Stylized Visual Storytelling with Unpaired Text (2023.acl-long)
Copied to clipboard
| Challenge: | Xu et al., 2015; Guo e t al, 2022a) focus on generating objective and neutral descriptions of image content without considering style characteristics. |
| Approach: | They propose a task of Stylized Visual Storytelling to generate attractive stylized stories for a photo stream. |
| Outcome: | The proposed framework can generate attractive stories with different styles . it surpasses state-of-the-art methods on automatic and human evaluation metrics. |
WordArt Designer: User-Driven Artistic Typography Synthesis using Large Language Models (2023.emnlp-industry)
Copied to clipboard
Jun-Yan He, Zhi-Qi Cheng, Chenyang Li, Jingdong Sun, Wangmeng Xiang, Xianhui Lin, Xiaoyang Kang, Zengke Jin, Yusen Hu, Bin Luo, Yifeng Geng, Xuansong Xie
| Challenge: | Existing typography solutions lack adaptability, creativity, and computational efficiency. |
| Approach: | They propose a user-driven framework for artistic typography synthesis based on the Large Language Model (LLM) the LLM Engine interprets user inputs and generates actionable prompts for the other modules, transforming abstract concepts into tangible designs. |
| Outcome: | The proposed framework incorporates four key modules: the LLM Engine, SemTypo, StyTyPo, and TexTyPO. |
Web Sitemap Knowledge Can Enhance Autonomous Browsing (2026.findings-acl)
Copied to clipboard
Yuyao Zhang, Hongyu Lu, Jiajie Jin, Hongjin Qian, Shiyu Li, Zhao Yang, Yutao Zhu, Ji-Rong Wen, Zhicheng Dou
| Challenge: | Existing web agents suffer from limited robustness, efficiency and task success due to lack of structural understanding of websites and lack of browsing priors in pre-trained models. |
| Approach: | They propose an agent-oriented sitemap protocol that integrates structured website knowledge into web agents. |
| Outcome: | The proposed agent-oriented sitemap improves robustness, efficiency and effectiveness without extra training. |
TriPlay-RL: Tri-Role Self-Play Reinforcement Learning for LLM Safety Alignment (2026.acl-long)
Copied to clipboard
Zhewen Tan, Wenhan Yu, Jianfeng Si, Tongxin Liu, Kaiqi Guan, Huiyan Jin, Jiawen Tao, Xiaokun Yuan, Xiangzheng Zhang, Duohe Ma, Tong Yang, Lin Sun
| Challenge: | Existing approaches to safety alignment of large language models rely on costly manual annotations or human review. |
| Approach: | They propose a closed-loop reinforcement learning framework called TriPlay-RL that enables iterative collaboration among three roles with near-zero manual annotation. |
| Outcome: | The proposed framework achieves 20%–50% improvement in adversarial effectiveness while preserving high output diversity while achieving 10%–30% gains in safety performance without degrading general reasoning capability. |
Instruction Tuning with Retrieval-based Examples Ranking for Aspect-based Sentiment Analysis (2024.findings-acl)
Copied to clipboard
| Challenge: | Aspect-based sentiment analysis (ABSA) identifies sentiment information related to specific aspects . previous studies have proposed using fixed examples for instruction tuning . |
| Approach: | They propose an instruction learning method with retrieval-based example ranking for ABSA tasks. |
| Outcome: | The proposed method is superior to existing models on three ABSA subtasks. |
From Capabilities to Performance: Evaluating Key Functional Properties of LLM Architectures in Penetration Testing (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have been explored for automating or enhancing penetration testing tasks, but their effectiveness and reliability remain open questions. |
| Approach: | They evaluate multiple LLM-based agents across realistic penetration testing scenarios . they also examine impact of core functional capabilities on agent success . |
| Outcome: | The proposed models improve agent performance in multi-step and real-time penetration testing scenarios. |
OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agents (2026.acl-long)
Copied to clipboard
Bowen Yang, Kaiming Jin, Zhenyu Wu, Zhaoyang Liu, Qiushi Sun, Zehao Li, JingJing Xie, Zhoumianze Liu, Fangzhi Xu, Kanzhi Cheng, Yian Wang, Qingyun Li, Yu Qiao, Zun Wang, Zichen Ding
| Challenge: | Vision-Language Models (VLMs) lack visual-aware tutorial retrieval and historical visual context curation and pruning. |
| Approach: | They propose a framework that integrates an orchestrator and a Reflection-Memory Agent for robust automation. |
| Outcome: | Experimental results show that OS-Symphony delivers substantial performance gains across model scales. |
HTMR: Hybrid Token Masking Reinforcement Learning with Verifiable Rewards for Event Argument Extraction with Multi-Perspective Reasoning (2026.acl-long)
Copied to clipboard
| Challenge: | Recent work formulates EAE with large language models as a structured conditional generation task and applies Reinforcement Learning with Verifiable Rewards (RLVR) to optimize sequence-level event structures. |
| Approach: | They propose a method that selectively updates policy gradients on high-entropy forking tokens and event-critical tokens that define event structure. |
| Outcome: | The proposed method outperforms full-token and high-entropy only methods and transfers effectively as a plug-and-play approach to other tasks such as named entity recognition and relation classification. |
Pan More Gold from the Sand: Refining Open-domain Dialogue Training with Noisy Self-Retrieval Generation (2022.coling-1)
Copied to clipboard
| Challenge: | Existing methods for generating open-domain dialogue systems underutilize training data. |
| Approach: | They propose a retrieval-generation training framework that takes advantage of heterogeneous training data by considering them as "evidence" they use BERTScore retrieval framework which gives better qualities of the training data, they show . |
| Outcome: | The proposed method performs well on zero-shot experiments and is more robust to real-world data. |
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. |
YouMakeup: A Large-Scale Domain-Specific Multimodal Dataset for Fine-Grained Semantic Comprehension (D19-1)
Copied to clipboard
| Challenge: | Multimodal semantic comprehension has attracted increasing research interest recently such as visual question answering and caption generation. |
| Approach: | They propose to use a large-scale multimodal instructional video dataset to support fine-grained comprehension research in specific domain. |
| Outcome: | The proposed dataset contains 2,800 videos from YouTube, spanning more than 420 hours in total. |
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. |
Solver-Independent Automated Problem Formulation via LLMs for High-Cost Simulation-Driven Design (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to translating ambiguous design requirements into a mathematical optimization formulation are expensive and time-consuming. |
| Approach: | They propose a solver-independent framework that converts engineers’ natural language requirements into executable optimization models. |
| Outcome: | The proposed framework outperforms existing methods in the accuracy of requirement formalization and quality of resulting radiation efficiency curves on antenna design. |
Enhancing Language Model with Unit Test Techniques for Efficient Regular Expression Generation (2023.emnlp-industry)
Copied to clipboard
| Challenge: | Recent studies have shown that generative language models lack functional correctness, which is a critical aspect of regular expressions. |
| Approach: | They propose a method that takes functional correctness into account and transforms it into a differentiable gradient feedback using policy gradient techniques. |
| Outcome: | The proposed method has been used in a regulatory scenario to ensure that all online content is free from non-compliant elements, thereby significantly reducing the workload of relevant personnel. |
Can We Trust the Performance Evaluation of Uncertainty Estimation Methods in Text Summarization? (2024.emnlp-main)
Copied to clipboard
| Challenge: | Text summarization is a key natural language generation task, but the high cost of inaccurate summaries raises concerns about the reliability of uncertainty estimation on text summarisation (UE-TS) evaluation methods. |
| Approach: | They propose a UE-TS benchmark that evaluates the uncertainty estimation capabilities of two large language models and one pre-trained language model on three datasets. |
| Outcome: | The proposed benchmark evaluates the uncertainty estimation capabilities of two large language models and one pre-trained language model on three datasets, with human-annotation analysis incorporated where applicable. |
Trigger is Not Sufficient: Exploiting Frame-aware Knowledge for Implicit Event Argument Extraction (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods to extract event arguments focus on learning pair-wise information between arguments and the given trigger. |
| Approach: | They propose a framework to extract event-related arguments from a given event frame-level scope. |
| Outcome: | The proposed method achieves state-of-the-art on the RAMS dataset. |
Analysis of the Neglect-Zero Effect in Large Language Models (2026.acl-srw)
Copied to clipboard
| Challenge: | a neglect-zero effect is a human cognitive bias in language processing . it is unclear whether LLMs also exhibit this effect . |
| Approach: | They focus on a human cognitive bias called the *neglect-zero effect* . they propose a paradigm where exposure to a preceding sentence facilitates processing of a subsequent sentence due to their similarity. |
| Outcome: | The proposed paradigm based on priming facilitates processing of a subsequent sentence due to their similarity to the target. |
Data Augmentation for Voice-Assistant NLU using BERT-based Interchangeable Rephrase (2021.eacl-main)
Copied to clipboard
| Challenge: | a data augmentation technique is used to boost performance on spoken language understanding tasks. |
| Approach: | They propose a data augmentation technique based on byte pair encoding and a BERT-like self-attention model to boost performance on spoken language understanding tasks. |
| Outcome: | The proposed method performs well on domain and intent classification tasks for a voice assistant and in a user-study focused on utterance naturalness and semantic similarity. |
VeriLocc: End-to-End Cross-Architecture Register Allocation via LLM (2025.emnlp-main)
Copied to clipboard
| Challenge: | Modern GPUs evolve rapidly, yet production compilers still rely on hand-crafted register allocation heuristics that require substantial re-tuning for each hardware generation. |
| Approach: | They propose a framework that combines large language models with compiler techniques to enable generalizable and verifiable register allocation across GPU architectures. |
| Outcome: | The framework outperforms expert-tuned libraries on matrix multiplication and multi-head attention and a verifier-guided regeneration loop to ensure correctness. |
FlexiGPT: Pruning and Extending Large Language Models with Low-Rank Weight Sharing (2025.naacl-long)
Copied to clipboard
James Seale Smith, Chi-Heng Lin, Shikhar Tuli, Haris Jeelani, Shangqian Gao, Yilin Shen, Hongxia Jin, Yen-Chang Hsu
| Challenge: | Empirical evaluations demonstrate substantial performance gains over existing methods . |
| Approach: | They propose a method to prune LLMs that selectively prunes model blocks based on an importance score and replaces them with a low-parameter replacement strategy. |
| Outcome: | The proposed method achieves state-of-the-art performance on 5/6 and 6/6 benchmarks with a compression rate of 30% and 40%. |
Toward Beginner-Friendly LLMs for Language Learning: Controlling Difficulty in Conversation (2026.findings-eacl)
Copied to clipboard
| Challenge: | Practicing conversations with large language models is a promising alternative to traditional in-person language learning. |
| Approach: | They propose a new token-level evaluation metric, Token Miss Rate, that measures the proportion of incomprehensible tokens per utterance and correlates strongly with human judgments. |
| Outcome: | The proposed methods improve comprehensibility for beginner speakers from 39.4% to 83.3%, compared with prompting alone and a token-level evaluation metric, Token Miss Rate (TMR). |
Fusion-in-T5: Unifying Variant Signals for Simple and Effective Document Ranking with Attention Fusion (2024.lrec-main)
Copied to clipboard
| Challenge: | Current document ranking pipelines involve multiple ranking layers to integrate different information step-by-step. |
| Approach: | They propose a novel re-ranker Fusion-in-T5 which integrates text matching information, ranking features, and global document information into one single unified model via templated-based input and global attention. |
| Outcome: | The proposed model significantly improves ranking performance over complex cascade pipelines. |
Collaborative Policy Learning for Open Knowledge Graph Reasoning (D19-1)
Copied to clipboard
| Challenge: | Existing models of knowledge graph reasoning suffer from limited performance when working on sparse and incomplete graphs due to the lack of evidential paths that can reach target entities. |
| Approach: | They propose a framework to train two collaborative agents to reason for missing facts over a graph augmented by a text corpus. |
| Outcome: | Experiments on two public datasets show the proposed approach is effective on a knowledge graph reasoning task. |
RAG-Critic: Leveraging Automated Critic-Guided Agentic Workflow for Retrieval Augmented Generation (2025.acl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have demonstrated remarkable performance across a wide range of downstream tasks. |
| Approach: | They propose a framework that leverages a critic-guided agentic workflow to improve RAG capabilities autonomously. |
| Outcome: | The proposed framework improves RAG capabilities autonomously by leveraging a critic-guided agentic workflow. |
Best Practices for Distilling Large Language Models into BERT for Web Search Ranking (2025.coling-industry)
Copied to clipboard
| Challenge: | Recent studies have highlighted the potential of Large Language Models (LLMs) as zero-shot relevance rankers. |
| Approach: | They propose to use a ranking loss to transfer ranking knowledge from LLMs to smaller models like BERT. |
| Outcome: | The proposed model has been successfully integrated into a commercial web search engine as of February 2024. |
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. |
Revisit Self-Debugging with Self-Generated Tests for Code Generation (2025.acl-long)
Copied to clipboard
Xiancai Chen, Zhengwei Tao, Kechi Zhang, Changzhi Zhou, Xinyu Zhang, Wanli Gu, Yuanpeng He, Mengdi Zhang, Xunliang Cai, Haiyan Zhao, Zhi Jin
| Challenge: | Large language models (LLMs) have made significant advances in code generation, but they still face challenges when tackling complex programming tasks beyond their basic capabilities. |
| Approach: | They propose to integrate self-generated tests into the code generation process . they propose to use post-execution and in-exection self-debugging to mitigate test bias . |
| Outcome: | The proposed method improves the performance of large language models in code generation tasks by leveraging execution feedback from tests. |
Enhancing Transformation from Natural Language to Signal Temporal Logic Using LLMs with Diverse External Knowledge (2025.findings-acl)
Copied to clipboard
| Challenge: | Temporal Logic (STL) is a formal specification tool for cyber-physical systems . but it is difficult to transform ambiguous and complex data into STL, a paper argues . |
| Approach: | They propose a NL-STL dataset with 16,000 samples enriched with diverse patterns . they propose KGST framework to transform natural language into STL using a generate-then-refine process . |
| Outcome: | The proposed dataset outperforms baseline models in diversity and accuracy . the proposed dataset contains 16,000 samples enriched with diverse patterns . |
Navigating Ethical Challenges in NLP: Hands-on strategies for students and researchers (2025.acl-tutorials)
Copied to clipboard
Luciana Benotti, Fanny Ducel, Karën Fort, Guido Ivetta, Zhijing Jin, Min-Yen Kan, Seunghun J. Lee, Minzhi Li, Margot Mieskes, Adriana Pagano
| Challenge: | This tutorial will equip participants with basic guidelines for thinking deeply about ethical issues . participants will gain practical experience on when to flag a paper for ethics review . |
| Approach: | This tutorial will equip participants with basic guidelines for thinking deeply about ethical issues . participants will gain practical experience on when to flag a paper for ethics review . |
| Outcome: | This tutorial will equip participants with basic guidelines for thinking deeply about ethical issues . participants will gain practical experience on when to flag a paper for ethics review . |
Fast Domain Adaptation of Semantic Parsers via Paraphrase Attention (D19-61)
Copied to clipboard
| Challenge: | Semantic parsers are used to convert user’s natural language commands to executable logical form in intelligent personal agents. Labeled datasets required to train such parser are expensive to collect, and are never comprehensive. |
| Approach: | They propose to use a sequence-to-sequence/tree attention based attention-based sequence-based parsers which support fast near real time retraining. |
| Outcome: | The proposed parsers can maintain high accuracy and fast retraining time while leveraging paraphrases already present in the training dataset. |
UI-Copilot: Advancing Long-Horizon GUI Automation via Tool-Integrated Policy Optimization (2026.acl-long)
Copied to clipboard
Zhengxi Lu, Fei Tang, Guangyi Liu, Jin Ma, Kaitao Song, Xu Tan, Wenqi Zhang, Weiming Lu, Jun Xiao, Yueting Zhuang, Yongliang Shen
| Challenge: | Experimental results show that UI-Copilot-7B achieves state-of-the-art performance on challenging MemGUI-Bench, outperforming strong 7B-scale GUI agents such as GUI-Owl-7B and UITARS-1.5-7B. |
| Approach: | They propose a collaborative framework where the GUI agent focuses on task execution while a lightweight copilot provides on-demand assistance for memory retrieval and numerical computation. |
| Outcome: | The proposed framework outperforms GUI-Owl-7B and UI-TARS-1.5-7B on MemGUI-Bench and delivers 17.1% improvement on AndroidWorld over the base Qwen model. |
Discovery and Reinforcement of Tool-Integrated Reasoning Chains via Rollout Trees (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to augment Large Language Models (LLMs) with computational capabilities have focused on short Chain-of-thought (CoT) integrating tool-use into long CoT remains underexplored due to the scarcity of training data and the challenge of integrating it without compromising the model’s intrinsic long-chain reasoning. |
| Approach: | They propose a framework that enables spontaneous tool-use during long CoT reasoning without additional human annotation. |
| Outcome: | Experiments on AIME and GPQA-Diamond show that DART significantly outperforms existing methods, successfully harmonizing tool execution with long CoT reasoning. |
LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding (2022.acl-long)
Copied to clipboard
| Challenge: | Existing structured document understanding models only deal with document data of specific language(s) this is extremely limited for other languages, especially in the case of lacking pre-training structured document data. |
| Approach: | They propose a language-independent Layout Transformer (LiLT) for structured document understanding . they propose to pre-train structured documents in a single language and fine-tune them on other languages . |
| Outcome: | The proposed model achieves competitive or even superior performance on diverse downstream benchmarks on eight languages. |
Co-DETECT: Collaborative Discovery of Edge Cases in Text Classification (2025.emnlp-demos)
Copied to clipboard
Chenfei Xiong, Jingwei Ni, Yu Fan, Vilém Zouhar, Donya Rooein, Lorena Calvo-Bartolomé, Alexander Miserlis Hoyle, Zhijing Jin, Mrinmaya Sachan, Markus Leippold, Dirk Hovy, Mennatallah El-Assady, Elliott Ash
| Challenge: | Social scientists often need to develop codebooks that can be reliable but require significant human effort. |
| Approach: | They propose a mixed-initiative annotation framework that integrates human expertise with automatic annotation guided by large language models. |
| Outcome: | The proposed framework integrates human expertise with automatic annotation guided by large language models. |
A Semantically Consistent and Syntactically Variational Encoder-Decoder Framework for Paraphrase Generation (2020.coling-main)
Copied to clipboard
| Challenge: | Paraphrase generation is a longstanding problem in natural language processing (NLP) Neural network-based methods have shown great progress on paraphrase generation. |
| Approach: | They propose a framework that integrates variational inference on a target-related latent variable to introduce the diversity. |
| Outcome: | The proposed framework outperforms baseline models on the metrics based on n-gram matching and semantic similarity, and it can generate multiple different paraphrases by assembling different syntactic variables. |
Sign2Vis: Automated Data Visualization from Sign Language (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to translate natural language descriptions into visualization queries focus on spoken languages, not sign languages. |
| Approach: | They propose a sign language interface that enables the DHH community to engage more fully with data analysis. |
| Outcome: | The proposed interface can be used by the deaf and hard-of-hearing community. |
DICA: Dual-Indicator Guided Contrastive Alignment in Multimodal Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Multimodal large language models may deviate from this pattern due to attention drift and underutilization of visual evidence. |
| Approach: | They propose a Dual-Indicator Guided Contrastive Alignment (DICA) that tracks visual attention and output image correlations to improve visual grounding. |
| Outcome: | The proposed model outperforms existing approaches and significantly reduces hallucinations. |
OpticE: A Coherence Theory-Based Model for Link Prediction (2022.coling-1)
Copied to clipboard
| Challenge: | Knowledge representation learning is a key step required for link prediction tasks with knowledge graphs (KGs). |
| Approach: | They propose a new embedding approach based on the physical phenomenon of optical interference to reduce the semantic ambiguity in KGs. |
| Outcome: | The proposed model can compete with existing methods on KG benchmarks. |
Semantic Structure Enhanced Event Causality Identification (2023.acl-long)
Copied to clipboard
| Challenge: | Existing methods for Event Causality Identification (ECI) capture implicit associations between events, which are difficult because they lack the ability to understand the associations between two events. |
| Approach: | They propose a model that captures the implicit associations between two events and integrates the event-centric structure information into a GNN-based event aggregator. |
| Outcome: | The proposed model improves on three widely used datasets showing that it integrates event-centric and event-associated semantic elements and captures event associations. |
PromptKeeper: Safeguarding System Prompts for LLMs (2025.findings-emnlp)
Copied to clipboard
| Challenge: | PromptKeeper is a defense mechanism designed to safeguard system prompts . adversarial and regular queries can exploit LLM vulnerabilities to expose hidden prompts. |
| Approach: | PromptKeeper is a defense mechanism designed to safeguard system prompts . it detects both explicit and subtle leakage and regenerates responses using a dummy prompt . |
| Outcome: | PromptKeeper detects and mitigates side-channel vulnerabilities when prompts are exposed . it regenerates responses using a dummy prompt, ensuring outputs remain indistinguishable from typical interactions . |
Contrastive Token-Wise Meta-Learning for Unseen Performer Visual Temporal-Aligned Translation (2023.findings-acl)
Copied to clipboard
| Challenge: | a novel generalization framework for visual temporal-aligned translation is proposed to transfer recognition skills to unseen performers . ambiguity in the visual sequence can hinder current methods for visual language translation . |
| Approach: | They propose a generalizable framework to transfer recognition skills to unseen performers . they use visual temporal-aligned translation to generate multiple words autoregressively . |
| Outcome: | The proposed framework is generalized to transfer recognition skills to unseen performers . it is compared with existing methods on lipreading and fingerspelling datasets . |
Single LLM, Multiple Roles: A Unified Retrieval-Augmented Generation Framework Using Role-Specific Token Optimization (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies have optimized retrieval-augmented generation (RAG) across sub-tasks, but integrating these optimizations into a unified framework remains challenging. |
| Approach: | They propose a unified retrieval-augmented generation framework that optimizes role-specific tokens for multi-task processing. |
| Outcome: | The proposed framework achieves efficient multi-task processing through role-specific token optimization. |
Towards Event Extraction with Massive Types: LLM-based Collaborative Annotation and Partitioning Extraction (2025.emnlp-main)
Copied to clipboard
| Challenge: | Event Extraction (EE) is a long-standing target, but lacks an efficient and effective annotation framework to construct the corresponding datasets. |
| Approach: | They propose an LLM-based collaborative annotation framework that refines annotations of triggers from distant supervision and carries out argument annotation. |
| Outcome: | The proposed framework outperforms state-of-the-art methods on the largest EE dataset to date . it achieves the F1 scores of 90% and 85.3% on the human-annotated test set . |
Comparing Neighbors Together Makes it Easy: Jointly Comparing Multiple Candidates for Efficient and Effective Retrieval (2024.emnlp-main)
Copied to clipboard
| Challenge: | Experimental results show that using only bi-encoders as an intermediate reranker can improve top-1 accuracy with negligible slowdown (7%). |
| Approach: | They propose a framework that compares a query and multiple embeddings of similar candidates through shallow self-attention layers, delivering rich representations contextualized to each other. |
| Outcome: | The proposed framework compares a query and multiple embeddings of similar candidates through shallow self-attention layers, delivering rich representations contextualized to each other. |
PedagogyBench: A Cognitive-Driven Benchmark for Multimodal Instructional Video Understanding (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing video understanding benchmarks do not adequately capture the pedagogical logic embedded in instructional videos. |
| Approach: | They propose a pedagogy-driven segmentation strategy and a dual-stream semantic injection pipeline that combines machine pre-annotation with expert refinement. |
| Outcome: | The proposed model performs well on discriminative tasks but degrades on higher-order pedagogical diagnosis, relying on parametric memory rather than grounded visual perception. |
Multi-Scale Spectral Selection and Entropy-Guided Uncertainty Fusion for Multimodal Rumor Detection (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for multimodal content detection fail to capture cross-modal semantic inconsistencies and ignore inherent noise in multimodal features. |
| Approach: | They propose a multimodal rumor detection method based on a frequency domain spectral selection method and entropy-guided uncertainty fusion method to capture cross-modal semantic inconsistencies. |
| Outcome: | The proposed method outperforms state-of-the-art methods in multimodal rumor detection . it shows stronger detection capability and robustness on multiple datasets . |
STRUX: An LLM for Decision-Making with Structured Explanations (2025.naacl-short)
Copied to clipboard
| Challenge: | a new LLM decision-making framework is designed to help users understand how and why decisions are made. |
| Approach: | They introduce a new LLM decision-making framework called STRUX that provides structured explanations for LLM decisions. |
| Outcome: | The proposed framework improves decision-making by providing structured explanations . it has been evaluated on the task of forecasting stock investment decisions based on earnings call transcripts - superior performance against strong baselines compared with previous frameworks based upon earnings call transcriptions demonstrating superior performance . |
MLeVLM: Improve Multi-level Progressive Capabilities based on Multimodal Large Language Model for Medical Visual Question Answering (2024.findings-acl)
Copied to clipboard
Dexuan Xu, Yanyuan Chen, Jieyi Wang, Yue Huang, Hanpin Wang, Zhi Jin, Hongxing Wang, Weihua Yue, Jing He, Hang Li, Yu Huang
| Challenge: | Existing MVQA models ignore multi-level progressive capabilities due to unspecific data and plain architecture. |
| Approach: | They propose a multi-level visual language model for medical visual question answering (MVQA) which covers multi- level questions and answers as well as reasoning processes from visual clues to semantic cognition. |
| Outcome: | The proposed model outperforms existing medical multimodal large language models on a multi-level instruction dataset and a feature alignment module. |
Modeling Human-Like Cognition for Stance Detection: Integrating Intuitive Judgment and Analytical Reasoning (2026.acl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have revolutionized stance detection, enabling complex reasoning strategies such as chain-of-thought prompting. |
| Approach: | They propose Cognitive-Driven Stance Detection (CDSD) that integrates fast intuitive judgment and analytical reasoning enhanced by three key modules: attention-based cognitive alignment to compare system focus, uncertainty-aware belief update using Bayesian inference, and self-doubt-triggered counterfactual reasoning for re-evaluation under low consistency or high uncertainty. |
| Outcome: | The proposed method outperforms state-of-the-art methods on SEM16, P-Stance, and VAST. |
S2-MAD: Breaking the Token Barrier to Enhance Multi-Agent Debate Efficiency (2025.naacl-long)
Copied to clipboard
Yuting Zeng, Weizhe Huang, Lei Jiang, Tongxuan Liu, XiTai Jin, Chen Tianying Tiana, Jing Li, Xiaohua Xu
| Challenge: | Large language models exhibit limitations when handling complex mathematical reasoning and logical inference tasks. |
| Approach: | They propose a sparsification strategy to reduce token costs within Multi-agent Debate (MAD) this strategy minimizes ineffective exchanges of information and unproductive discussions among agents . |
| Outcome: | The proposed approach reduces token costs by up to 94.5% while maintaining performance degradation below 2.0%. |
Generic Temporal Reasoning with Differential Analysis and Explanation (2023.acl-long)
Copied to clipboard
| Challenge: | Existing temporal reasoning models drop to random guessing on TODAY, suggesting that they heavily rely on spurious information rather than proper reasoning for temporal predictions. |
| Approach: | They propose a task called TODAY that evaluates whether systems can correctly understand the effect of incremental changes in temporal relation distributions. |
| Outcome: | The proposed task outperforms existing models, including GPT-3.5, on in-domain benchmarks while allowing for more appropriate annotations. |
Med-MoE: Mixture of Domain-Specific Experts for Lightweight Medical Vision-Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Recent advances in multimodal large language models have seen remarkable progress for medical decision-making, however, they are designated for specific classification or generative tasks and require model training or finetuning on large-scale datasets with sizeable parameters and tremendous computing. |
| Approach: | They propose a framework that tackles discriminative and generative multimodal medical tasks using multimodal alignment, instruction tuning and routing. |
| Outcome: | The proposed model can achieve superior performance to or on par with state-of-the-art baselines while only requiring 30%-50% of activated model parameters. |
Focused-DPO: Enhancing Code Generation Through Focused Preference Optimization on Error-Prone Points (2025.findings-acl)
Copied to clipboard
| Challenge: | Current code generation models produce errors concentrated at specific error-prone points, affecting accuracy of code. |
| Approach: | They propose a framework that focuses preference optimization on error-prone areas . focused-DPO improves the accuracy and reliability of code generation by reducing common errors . |
| Outcome: | The proposed framework improves code generation by focusing on error-prone areas. |
Numerical Optimizations for Weighted Low-rank Estimation on Language Models (2022.emnlp-main)
Copied to clipboard
| Challenge: | Singular value decomposition (SVD) is one of the most popular methods for estimating a target matrix with smaller matrices. |
| Approach: | They propose a method that approximates a target matrix with smaller matrices by two smaller . they also propose metric to predict when the SVD may introduce a significant performance drop. |
| Outcome: | The proposed method can perform better than current SOTA methods in compressing Transformer-based language models. |
Multimodal Language Models See Better When They Look Shallower (2025.emnlp-main)
Copied to clipboard
Haoran Chen, Junyan Lin, Xinghao Chen, Yue Fan, Jianfeng Dong, Xin Jin, Hui Su, Jinlan Fu, Xiaoyu Shen
| Challenge: | Existing studies show that multimodal large language models extract visual features from the final layers of a pretrained Vision Transformer. |
| Approach: | They propose a feature fusion method that strategically incorporates shallower layers . they propose MLLMs that extract visual features from the final layers of a pretrained Vision Transformer . |
| Outcome: | The proposed method outperforms deep layers on fine-grained visual tasks . it is the first comprehensive study of visual layer selection for MLLMs . |
Crafting Adversarial Inputs for Large Vision-Language Models Using Black-Box Optimization (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing white-box jailbreak methods require full model accessibility and require computational costs. |
| Approach: | They propose a black-box jailbreak attack using Zeroth-Order optimization using ZO-SPSA. |
| Outcome: | The proposed method achieves highest jailbreak success rate on three LVLMs, including InstructBLIP, LLaVA and MiniGPT-4. |
Saber: Efficient Sampling with Adaptive Acceleration and Backtracking Enhanced Remasking for Diffusion Language Model in Code Generation (2026.acl-long)
Copied to clipboard
| Challenge: | Diffusion language models (DLMs) offer advantages in parallel generation and bidirectional context modeling, but they face a critical trade-off between inference speed and output quality for tasks with strict structural constraints such as code generation. |
| Approach: | They propose an efficient sampling algorithm that reduces the number of tokens unmasked per step based on the model’s evolving confidence. |
| Outcome: | The proposed method improves Pass@1 accuracy by 1.9% while achieving 251.4% inference speedup. |
Persuading across Diverse Domains: a Dataset and Persuasion Large Language Model (2024.acl-long)
Copied to clipboard
| Challenge: | Persuasive dialogue requires multi-turn following and planning abilities to achieve the goal of persuating users. |
| Approach: | They propose a general method to learn a persuasive model based on LLMs through intent-to-strategy reasoning, which summarizes the intent of user’s utterance and reasons next strategy to respond. |
| Outcome: | The proposed method outperforms baselines on automatic evaluation metric Win-Rate and human evaluation on two datasets. |
Can You Tell Me How to Get Past Sesame Street? Sentence-Level Pretraining Beyond Language Modeling (P19-1)
Copied to clipboard
Alex Wang, Jan Hula, Patrick Xia, Raghavendra Pappagari, R. Thomas McCoy, Roma Patel, Najoung Kim, Ian Tenney, Yinghui Huang, Katherin Yu, Shuning Jin, Berlin Chen, Benjamin Van Durme, Edouard Grave, Ellie Pavlick, Samuel R. Bowman
| Challenge: | State-of-the-art models in natural language processing (NLP) often incorporate sentence encoder functions which generate a sequence of vectors intended to represent the in-context meaning of each word in an input text. |
| Approach: | They conduct the first large-scale systematic study of candidate pretraining tasks, comparing 19 different tasks as alternatives and complements to language modeling. |
| Outcome: | The proposed model can be used to train sentences on language modeling tasks. |
LangNav: Language as a Perceptual Representation for Navigation (2024.findings-naacl)
Copied to clipboard
| Challenge: | Existing approaches to vision-and-language navigation use visual features as the perceptual representation of a visual representation of an agent's egocentric panoramic view. |
| Approach: | They propose to use off-the-shelf vision systems to convert an agent’s egocentric panoramic view into natural language descriptions. |
| Outcome: | The proposed approach improves on the R2R VLN benchmark by using synthetic trajectories from a prompted language model and domain transfer where a policy learned on one simulated environment (ALFRED) is transferred to another (more realistic) environment and combining both vision- and language-based representations. |
GOME: Grounding-based Metaphor Binding With Conceptual Elaboration For Figurative Language Illustration (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing Large Language Models (LLMs) and multimodal models are unable to illustrate figurative language based on literal objects, ignoring the underlying groundings and associations across disparate metaphorical domains. |
| Approach: | They propose a grounding-based method for metaphor illustration that integrates metaphorical knowledge into systematic instructions for existing large language models. |
| Outcome: | The proposed method is superior to existing LLMs, diffusion models, or their direct collaboration. |
Act as you think: Reinforcing Consistent Reasoning in Medical Visual Question Answering (2026.acl-long)
Copied to clipboard
Songtao Jiang, Yuan Wang, Ruizhe Chen, Yan Zhang, Ruilin Luo, Bohan Lei, Yeying Jin, Sibo Song, ZhiBo Yang, Jimeng Sun, Jian Wu, Zuozhu Liu
| Challenge: | Recent advances have improved the accuracy of medical visual question answering (Med-VQA) however, the high stakes nature of the medical domain has precipitated a shift towards interpretability and transparency of reasoning processes. |
| Approach: | They propose a reinforcement learning from verifiable rewards framework that rewards internal consistency and logical coherence. |
| Outcome: | The proposed framework rewards internal consistency and logical coherence, and is highly versatile, the authors show. |
Rewarding Semantic Similarity under Optimized Alignments for AMR-to-Text Generation (2022.acl-short)
Copied to clipboard
| Challenge: | Automatic evaluation metrics score natural language generation systems based on how well they lexically align to humanannotated references. |
| Approach: | They propose to replace greedy alignments in BERTScore with optimized ones that replace the n-gram matching BERTAcore metrics with a token embedding to prevent domain mismatch. |
| Outcome: | The proposed metrics outperform cross-entropy and BLEU reward baselines on AMR-to-text generation. |
WeDef: Weakly Supervised Backdoor Defense for Text Classification (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing backdoor defense methods are only effective for limited trigger types . Existing methods only work against certain types of triggers . |
| Approach: | They propose a weakly supervised backdoor defense framework WeDef to defend different trigger types at once . they define reliability of samples based on whether predictions agree with their labels . |
| Outcome: | The proposed framework outperforms existing backdoor defense methods against popular trigger-based attacks. |
TrustAgent: Towards Safe and Trustworthy LLM-based Agents (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing LLMs are primarily used for simple text-related tasks, but LLM-based agents can undertake more complex tasks that require planning and interaction with the physical world and humans. |
| Approach: | They propose an Agent-Constitution-based agent framework with a particular focus on improving the LLM-based agents' safety. |
| Outcome: | The proposed framework can enhance an LLM agent’s safety across multiple domains by identifying and mitigating potential dangers during the planning process. |
OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis (2025.acl-long)
Copied to clipboard
Qiushi Sun, Kanzhi Cheng, Zichen Ding, Chuanyang Jin, Yian Wang, Fangzhi Xu, Zhenyu Wu, Chengyou Jia, Liheng Chen, Zhoumianze Liu, Ben Kao, Guohao Li, Junxian He, Yu Qiao, Zhiyong Wu
| Challenge: | Graphical User Interface (GUI) agents powered by Vision-Language Models (VLMs) have demonstrated human-like computer control capability. |
| Approach: | They propose a GUI data synthesis pipeline that reverse engineers GUI trajectory construction process by executing pre-defined tasks. |
| Outcome: | The proposed GUI data synthesis pipeline overcomes the bottlenecks of previous methods that rely on pre-defined tasks and limited data diversity. |
AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension (2024.acl-long)
Copied to clipboard
Qian Yang, Jin Xu, Wenrui Liu, Yunfei Chu, Ziyue Jiang, Xiaohuan Zhou, Yichong Leng, Yuanjun Lv, Zhou Zhao, Chang Zhou, Jingren Zhou
| Challenge: | Existing benchmarks for audio-centric interaction have impeded advancements in this field . AIR-Bench evaluates LALMs' ability to understand audio signals and interact with humans . |
| Approach: | They propose a benchmark to evaluate the ability of large audio-language models to understand audio signals . they use 19 tasks with approximately 19k single-choice questions to examine single-task ability . |
| Outcome: | The proposed framework evaluates the ability of large audio-language models to understand audio signals and interact with humans in the textual format. |
CTFN: Hierarchical Learning for Multimodal Sentiment Analysis Using Coupled-Translation Fusion Network (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods for multimodal sentiment analysis require all modalities as input, thus are sensitive to missing modality at predicting time. |
| Approach: | They propose to model bi-direction interplay via couple learning and exploit multiple bi-directional translations to exploit multimodal fusion embeddings. |
| Outcome: | The proposed framework achieves state-of-the-art or often competitive performance on two multimodal benchmarks with extensive ablation studies. |
Persona-E²: A Human-Grounded Dataset for Personality-Shaped Emotional Responses to Textual Events (2026.acl-long)
Copied to clipboard
Yuqin Yang, Haowu Zhou, Haoran Tu, Zhiwen Hui, Shiqi Yan, HaoYang Li, Dong She, Xianrong Yao, Yang Gao, Zhanpeng Jin
| Challenge: | A critical bottleneck is the lack of ground-truth human data to link personality traits to emotional shifts. |
| Approach: | They propose a large-scale dataset to capture reader-based emotional variations across news, social media, and life narratives. |
| Outcome: | The proposed model captures reader-based emotional variations across news, social media, and life narratives. |
Reframing Responsibility: Framing-Aware Event Causality Identification (2026.acl-long)
Copied to clipboard
| Challenge: | Causal explanations in political narratives are often framed and contested. |
| Approach: | They propose a framing-aware extension of ECI that models causal explanations as structured claims including responsibility targets, evaluative frams, source type, and epistemic modality. |
| Outcome: | The proposed model enables quantitative analysis of divergent causal attribution across narratives. |
G2S: A General-to-Specific Learning Framework for Temporal Knowledge Graph Forecasting with Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent studies have introduced Large Language Models (LLMs) for this task to enhance the models’ generalization abilities. |
| Approach: | They propose a General-to-Specific learning framework that disentangles the learning processes of two kinds of knowledge in a temporal temporal structure. |
| Outcome: | The proposed framework disentangles the learning processes of the above two kinds of knowledge and improves their generalization abilities. |
TransFace: Unit-Based Audio-Visual Speech Synthesizer for Talking Head Translation (2024.findings-acl)
Copied to clipboard
Xize Cheng, Rongjie Huang, Linjun Li, Zehan Wang, Tao Jin, Aoxiong Yin, Chen Feiyang, Xinyu Duan, Baoxing Huai, Zhou Zhao
| Challenge: | Existing methods for talking head translation rely on cascading, resulting in delays and cascadic errors. |
| Approach: | They propose a model for talking head translation, TransFace, which can translate audio-visual speech into audio-visual speech in other languages. |
| Outcome: | The proposed model can translate audio-visual speech into audio-visual speech in other languages. |
MASSW: A New Dataset and Benchmark Tasks for AI-Assisted Scientific Workflows (2025.findings-naacl)
Copied to clipboard
Xingjian Zhang, Yutong Xie, Jin Huang, Jinge Ma, Zhaoying Pan, Qijia Liu, Ziyang Xiong, Tolga Ergen, Dongsub Shim, Honglak Lee, Qiaozhu Mei
| Challenge: | Scientific innovation is driven by detailed workflows, which include critical steps such as contextualizing literature, generating ideas, validating ideas, and planning new research. |
| Approach: | They propose to use large language models to extract five key aspects from scientific publications to optimize scientific workflows. |
| Outcome: | The proposed dataset includes more than 152,000 peer-reviewed publications from 17 leading computer science conferences spanning the past 50 years. |
Automatic Reconstruction of Ancient Chinese Pronunciations (2024.findings-emnlp)
Copied to clipboard
| Challenge: | A human language is comprised of a pronunciation system and a writing system, both evolving and changing over time. |
| Approach: | They reformulate existing phonetic rules into a dataset of 70,943 entries for 17,001 Chinese characters and use it to perform a temporal prediction task. |
| Outcome: | The transformer-based model significantly advances the digitization and computational reconstruction of ancient Chinese phonology, providing a more complete and temporally contextualized resource for computational linguistics and historical research. |
Rapid Diffusion: Building Domain-Specific Text-to-Image Synthesizers with Fast Inference Speed (2023.acl-industry)
Copied to clipboard
Bingyan Liu, Weifeng Lin, Zhongjie Duan, Chengyu Wang, Wu Ziheng, Zhang Zipeng, Kui Jia, Lianwen Jin, Cen Chen, Jun Huang
| Challenge: | Text-to-Image Synthesis (TIS) aims to generate images based on textual inputs . but, current diffusion-based models lack entity knowledge and low inference speed . |
| Approach: | They propose a framework for training and deploying latent diffusion models with rich entity knowledge injected and optimized networks. |
| Outcome: | The proposed framework improves image quality and inference speed and can be used in industrial applications. |
Rethinking Repetition Problems of LLMs in Code Generation (2025.acl-long)
Copied to clipboard
| Challenge: | Recent studies have focused on content repetition, but structural repetition is a more prevalent problem in code generation. |
| Approach: | They propose a decoding approach that eliminates repetition problems in code generation by identifying grammar rules and strategically decaying the likelihood of critical tokens that contribute to repetitions. |
| Outcome: | The proposed approach outperforms baselines and humanEval benchmarks on CodeRepetEval dataset and MBPP benchmarks, effectively reducing repetitions and enhancing the quality of generated code. |
GPT-HateCheck: Can LLMs Write Better Functional Tests for Hate Speech Detection? (2024.lrec-main)
Copied to clipboard
| Challenge: | HateCheck test cases are generic and have simplistic sentence structures that do not match the real-world data. |
| Approach: | They propose a framework to generate more diverse and realistic functional tests from scratch by instructing large language models. |
| Outcome: | The proposed framework generates more diverse and realistic functional tests from scratch by instructing large language models (LLMs). |
Leveraging Information Bottleneck for Scientific Document Summarization (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to extract salient sentences from document are unsupervised and rely on graph-based methods for sentence ranking. |
| Approach: | They propose an unsupervised extractive approach to document level summarization based on the Information Bottleneck principle. |
| Outcome: | The proposed framework can be extended to a multi-view framework by different signals. |
InternalInspector I2: Robust Confidence Estimation in LLMs through Internal States (2024.findings-emnlp)
Copied to clipboard
Mohammad Beigi, Ying Shen, Runing Yang, Zihao Lin, Qifan Wang, Ankith Mohan, Jianfeng He, Ming Jin, Chang-Tien Lu, Lifu Huang
| Challenge: | Large Language Models (LLMs) often struggle with generating reliable outputs, often producing high-confidence inaccuracies known as hallucinations. |
| Approach: | They propose a framework that leverages contrastive learning on internal states including attention states, feed-forward states, and activation states of all layers to enhance confidence estimation in LLMs. |
| Outcome: | The framework outperforms existing methods in the hallucination detection benchmark HaluEval and the previous methods at the same time. |
A Bi-Model Based RNN Semantic Frame Parsing Model for Intent Detection and Slot Filling (N18-2)
Copied to clipboard
| Challenge: | Intent detection and slot filling are two main tasks for building a spoken language understanding system. |
| Approach: | They propose to use a sequence to sequence model to generate both intent and slot filling tasks together to perform the two tasks jointly. |
| Outcome: | The proposed model achieves 0.5% intent accuracy improvement and 0.9 % slot filling improvement on the ATIS benchmark data. |
D-RAG: Differentiable Retrieval-Augmented Generation for Knowledge Graph Question Answering (2025.emnlp-main)
Copied to clipboard
Guangze Gao, Zixuan Li, Chunfeng Yuan, Jiawei Li, Wu Jianzhuo, Yuehao Zhang, Xiaolong Jin, Bing Li, Weiming Hu
| Challenge: | Existing approaches to Knowledge Graph Question Answering (KGQA) use Retrieval-Augmented Generation (RAG) but subgraph selection process is non-differentiable, preventing end-to-end training of the retriever and the generator. |
| Approach: | They propose a Differentiable RAG approach that optimizes the retriever and the generator for KGQA. |
| Outcome: | The proposed approach outperforms state-of-the-art approaches on WebQSP and CWQ. |
Transformer over Pre-trained Transformer for Neural Text Segmentation with Enhanced Topic Coherence (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models for text segmentation use supervised and unsupervised learning to perform tasks such as text summarization and keyword extraction. |
| Approach: | They propose a transformer over transformer framework to perform neural text segmentation. |
| Outcome: | The proposed framework outperforms state-of-the-art models in terms of semantic coherence measure . bottom-level sentence encoders pre-trained on specific languages yield better performance . |
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. |
Multi-News+: Cost-efficient Dataset Cleansing via LLM-based Data Annotation (2024.emnlp-main)
Copied to clipboard
| Challenge: | Various attempts to correct noisy data in the construction process have been made, but human annotation is expensive and time-consuming. |
| Approach: | They propose to use large language models for data annotation to imitate human annotation and classify unrelated documents from a multi-document summarization task. |
| Outcome: | The proposed method imitates human annotation and classifies unrelated documents from the Multi-News dataset. |
Overcoming Catastrophic Forgetting in Massively Multilingual Continual Learning (2023.findings-acl)
Copied to clipboard
Genta Winata, Lingjue Xie, Karthik Radhakrishnan, Shijie Wu, Xisen Jin, Pengxiang Cheng, Mayank Kulkarni, Daniel Preotiuc-Pietro
| Challenge: | Existing methods to handle catastrophic forgetting fail to retain knowledge learnt in the past when sudden shifts occur in training data distributions. |
| Approach: | They propose a learning rate scheduling method that preserves new information without strongly overwriting past knowledge. |
| Outcome: | The proposed method preserves new information without overwriting past knowledge in a multilingual continuous learning framework. |
Unlocking the Future: Exploring Look-Ahead Planning Mechanistic Interpretability in Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies have shown that large language models may possess preliminary planning capabilities. |
| Approach: | They examine the look-ahead planning mechanism in large language models from the perspectives of information flow and internal representations. |
| Outcome: | The proposed model can decode the decision from the output of MHSA in the middle layers at the last token. |
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 . |
Learning Only from Relevant Keywords and Unlabeled Documents (D19-1)
Copied to clipboard
| Challenge: | Existing methods for document classification are limited due to labeling and privacy concerns. |
| Approach: | They propose a super-vised text classification framework that provides keywords as a hint for classifying a document to a target class. |
| Outcome: | The proposed framework is simple to implement and has flexible choices of models, e.g., linear models or neural networks. |
Document Embedding Enhanced Event Detection with Hierarchical and Supervised Attention (P18-2)
Copied to clipboard
| Challenge: | Existing methods for event detection use sentence-level contextual information. |
| Approach: | They propose a document embedding enhanced bi-RNN model to detect events in sentences . they use hierarchical and supervised attention based RNN to learn document embeds . |
| Outcome: | The proposed model compares with state-of-the-art models on a ACE-2005 dataset. |
Large-Scale Corpus Construction and Retrieval-Augmented Generation for Ancient Chinese Poetry: New Method and Data Insights (2025.findings-naacl)
Copied to clipboard
| Challenge: | Ancient Chinese poetry presents unique challenges for Large Language Models due to data scarcity and limited ability of general LLMs when dealing with ACP. |
| Approach: | They propose a specialized Retrieval-Augmented Generation framework to improve LLMs' performance . they use 1.1 million ancient poems and 990K related texts to address hallucination issues . |
| Outcome: | The proposed framework improves performance of LLMs in ancient Chinese poetry domain from 49.2% to 89.0%. |
Augmenting NLP models using Latent Feature Interpolations (2020.coling-main)
Copied to clipboard
| Challenge: | Existing data augmentation methods with a large number of parameters are prone to over-fitting and often fail to capture the underlying input distribution. |
| Approach: | They propose a data augmentation technique that uses embeddings and hidden layer representations to construct virtual examples. |
| Outcome: | The proposed method outperforms existing methods in terms of accuracy and robustness to weight pruning. |
SEAL: Scaling to Emphasize Attention for Long-Context Retrieval (2025.acl-long)
Copied to clipboard
| Challenge: | Recent studies show that advanced LLMs suffer from degradation when processing longer context data. |
| Approach: | They propose a learning-based mechanism that leverages generated data to emphasize attention heads for long-context retrieval. |
| Outcome: | The proposed approach improves retrieval performance over long contexts while maintaining high reliability. |
DynaMo: Accelerating Language Model Inference with Dynamic Multi-Token Sampling (2024.naacl-long)
Copied to clipboard
| Challenge: | Rapid explosion in model sizes has resulted in high inference times . open-source LLMs are democratizing research in natural language processing . |
| Approach: | They propose a suite of multi-token prediction language models that reduce net inference times by leveraging traditional autoregressive weights. |
| Outcome: | The proposed model achieves same-quality generated text as baseline (Pythia-6.9B) with only 5.87% and 2.67% parameter and training time overheads. |
Multi-Task Label Embedding for Text Classification (D18-1)
Copied to clipboard
| Challenge: | Existing work treats labels of each task as independent and meaningless one-hot vectors, which cause a loss of potential label information. |
| Approach: | They propose to combine multi-task learning with semantic vectors to convert labels into vectors . their results are based on extensive experiments on five benchmark datasets based in chinese . |
| Outcome: | The proposed model can improve performance on five benchmark datasets on text classification tasks. |
Evolution in Simulation: AI-Agent School with Dual Memory for High-Fidelity Educational Dynamics (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models (LLMs) based Agents are increasingly pivotal in simulating complex human systems and interactions. |
| Approach: | They propose an AI-Agent School system that leverages agents for simulating educational dynamics. |
| Outcome: | The proposed system can simulate complex educational dynamics in simulated schools. |
ArgGenBench: Benchmarking the Complex Controlled Argument Generation Capability of Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Existing studies focus on limited control signals such as topic, stance, length, style, strategy, audience, and key aspects, failing to capture this complexity. |
| Approach: | They propose a benchmark that integrates multi-dimensional control into a single instruction to evaluate LLMs' ability to produce persuasive arguments. |
| Outcome: | The proposed benchmarks show that existing models fail to capture multifaceted argumentative control signals. |
Machine Unlearning of Pre-trained Large Language Models (2024.acl-long)
Copied to clipboard
| Challenge: | Using curated datasets, we establish a robust benchmark for unlearning performance, demonstrating that these methods are over 105 times more computationally efficient than retraining. |
| Approach: | They propose a framework for machine unlearning in pre-trained LLMs and integrate gradient ascent with gradient descent on in-distribution data to achieve robustness. |
| Outcome: | The proposed framework is over 105 times more efficient than retraining on in-distribution data and provides detailed guidelines for efficient hyperparameter tuning in the unlearning process. |
Distilling Structured Knowledge for Text-Based Relational Reasoning (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing text-based relational reasoning models lack a symbolic representation of text . performance gap between NLP models and structured models remains . |
| Approach: | They first pre-train a GNN on a reasoning task using structured inputs and then incorporate its knowledge into an NLP model. |
| Outcome: | The proposed model improves on two state-of-the-art NLP models on 13 different inductive reasoning datasets from the CLUTRR benchmark. |
Mitigating Biases in Language Models via Bias Unlearning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent debiasing approaches target different demographic groups, harming fairness and discrimination. |
| Approach: | They propose a model debiasing framework which targets stereotypes by unlearning stereotype forgetting and anti-stereotype retention. |
| Outcome: | The proposed framework outperforms existing methods in mitigating bias while retaining language modeling capabilities. |
MultiChallenge: A Realistic Multi-Turn Conversation Evaluation Benchmark Challenging to Frontier LLMs (2025.findings-acl)
Copied to clipboard
Kaustubh Deshpande, Ved Sirdeshmukh, Johannes Baptist Mols, Lifeng Jin, Ed-Yeremai Hernandez-Cardona, Dean Lee, Jeremy Kritz, Willow E. Primack, Summer Yue, Chen Xing
| Challenge: | Existing evaluation frameworks for large language models have limited coverage for multi-turn conversations . multi-turned conversations require accurate instruction following, context allocation, and in-context reasoning at the same time. |
| Approach: | They propose a benchmark to evaluate large language models' ability to conduct multi-turn conversations with humans. |
| Outcome: | The proposed benchmarks achieve near perfect scores on existing benchmarks but only a 41.4% accuracy on the frontier models. |
FRAME: Feedback-Refined Agent Methodology for Enhancing Medical Research Insights (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to automate scientific research are limited by human cognitive constraints and timeintensive workflows. |
| Approach: | They propose a framework that enhances medical paper generation through iterative refinement and structured feedback. |
| Outcome: | The proposed framework achieves significant improvements over conventional methods across multiple models and evaluation dimensions. |
CDA: A Contrastive Data Augmentation Method for Alzheimer’s Disease Detection (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for detecting AD are challenging and time-consuming due to lack of data and generalizability of the models. |
| Approach: | They propose a contrastive data augmentation method which simulates the cognitive impairment of a patient by randomly deleting a proportion of text from the transcript to create negative samples. |
| Outcome: | The proposed method achieves the best performance among language-based models on the benchmark ADReSS Challenge dataset. |
CycleOIE: A Low-Resource Training Framework For Open Information Extraction (2025.coling-main)
Copied to clipboard
Zhihong Jin, Chunhong Zhang, Zheng Hu, Jibin Yu, Ruiqi Ma, Qingyun Chen, Xiaohao Liao, Yanxing Zhang
| Challenge: | Open Information Extraction (OpenIE) models rely heavily on large amounts of annotated data. |
| Approach: | They propose a training framework that maximizes data efficiency through a cycle-consistency mechanism. |
| Outcome: | The proposed approach improves the quality of training data by curating low-quality datasets annotated by a large language model. |
Rethinking the Multimodal Correlation of Multimodal Sequential Learning via Generalizable Attentional Results Alignment (2024.acl-long)
Copied to clipboard
| Challenge: | Existing studies have focused on the alignment of multimodal sequential learning using transformers. |
| Approach: | They propose a constrained scheme to align the multiple attentional results from both local and global perspectives. |
| Outcome: | The proposed scheme could align the multiple attentional results from both local and global perspectives, making the information capture more efficient. |
SeaPO: Strategic Error Amplification for Robust Preference Optimization of Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for preference optimization of large language models use pairs of positive and negative samples, but the quality of positive samples may become similar during training, complicating preference learning. |
| Approach: | SeaPO introduces error types commonly occurring in large language models to improve preference learning. |
| Outcome: | SeaPO introduces error types into model Preference Optimization to improve model performance . negative samples are more erroneous than positive samples, and preference-based training mitigates errors . |
Beyond Dialogue Time: Temporal Semantic Memory for Personalized LLM Agents (2026.findings-acl)
Copied to clipboard
Miao Su, Yucan Guo, Zhongni Hou, Long Bai, Zixuan Li, Yufei Zhang, Guojun Yin, Wei Lin, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng
| Challenge: | Existing methods focus on point-wise memory, losing durative information that captures persistent states and evolving patterns. |
| Approach: | They propose a memory framework that models semantic time for point-wise memory and supports the construction and utilization of durative memory. |
| Outcome: | Experiments on LongMemEval and LoCoMo show that the proposed method outperforms existing methods and achieves up to 12.2% improvement in accuracy. |
M3ED: Multi-modal Multi-scene Multi-label Emotional Dialogue Database (2022.acl-long)
Copied to clipboard
| Challenge: | Existing data resources to support multimodal affective analysis in dialogues are limited in scale and diversity. |
| Approach: | They propose a multimodal multi-scene multi-label Emotional Dialogue dataset, M3ED, which contains 990 dyadic emotional dialogues from 56 different TV series. |
| Outcome: | The proposed dataset contains 990 dyadic emotional dialogues from 56 different TV series, a total of 9,082 turns and 24,449 utterances. |
A Survey of Deep Learning for Geometry Problem Solving (2026.acl-long)
Copied to clipboard
| Challenge: | Recent surge in deep learning technologies has significantly accelerated research in this area. |
| Approach: | They propose a comprehensive summary of the relevant tasks in geometry problem solving and a review of related deep learning methods. |
| Outcome: | The proposed method is based on a systematic review of related methods and evaluation metrics and methods. |
DiPT: Enhancing LLM Reasoning through Diversified Perspective-Taking (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing work on improving language model reasoning typically explores a single solution path, which can be prone to errors. |
| Approach: | They propose a novel approach that incorporates diversified viewpoints into existing reasoning methods to improve their reasoning performance. |
| Outcome: | The proposed approach can be flexibly integrated into existing models that focus on a single reasoning approach, enhancing their reasoning performance and stability when presented with paraphrased problems. |
AgentReview: Exploring Peer Review Dynamics with LLM Agents (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods of peer review analysis do not address multivariate nature of the process, account for latent variables, and are constrained by privacy concerns due to the sensitive nature of data. |
| Approach: | They propose a large language model based peer review simulation framework which effectively disentangles the impacts of multiple latent factors and addresses the privacy issue. |
| Outcome: | The proposed framework disentangles the impacts of multiple latent factors and addresses privacy concerns. |
Empowering parameter-efficient transfer learning by recognizing the kernel structure in self-attention (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods to fine-tune pre-trained language models are parameter efficient . fine- tuning the models requires multiple copies of the parameters, which is inefficient. |
| Approach: | They propose to use kernel-based adapters to tune only a few parameters while freezing the rest of the parameters. |
| Outcome: | The proposed methods achieve or improve strong performance over a diverse set of natural language generation and understanding tasks. |
Locally Aggregated Feature Attribution on Natural Language Model Understanding (2022.naacl-main)
Copied to clipboard
| Challenge: | a growing popularity of deep-learning models makes model understanding more important . feature attribution methods have shown promising results in computer vision but are not trivial . |
| Approach: | They propose a gradient-based feature attribution method that smooths gradients by aggregating similar reference texts derived from language model embeddings. |
| Outcome: | The proposed method outperforms existing methods on public datasets and key words detection tasks. |
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. |
When Do Language Models Endorse Limitations on Human Rights Principles? (2026.findings-eacl)
Copied to clipboard
Keenan Samway, Miu Nicole Takagi, Rada Mihalcea, Bernhard Schölkopf, Ilias Chalkidis, Daniel Hershcovich, Zhijing Jin
| Challenge: | a recent study evaluated how large language models navigate trade-offs involving the Universal Declaration of Human Rights. |
| Approach: | They evaluate how large language models navigate trade-offs involving the Universal Declaration of Human Rights (UDHR) they use 1,152 synthetically generated scenarios across 24 rights articles and eight languages . |
| Outcome: | The proposed models accept limiting economic, social, and cultural rights more often than political and civil rights, the authors show . their models show significant cross-linguistic variation with elevated endorsement rates of rights-limiting actions in Chinese and Hindi compared to English or Romanian . |
Traces in the Brain: Neural Evidence for Syntactic Movement in English and Chinese (2026.findings-acl)
Copied to clipboard
Yuhan Huang, Zhengwu Ma, Yuqi Jin, Beth Chan, Zheng Shen, Jackie Yan-Ki Lai, John T. Hale, Jixing Li
| Challenge: | Syntactic movement is a core concept in generative linguistics to account for word-order variation and long-distance dependencies. |
| Approach: | They annotated every sentence in the audiobook The Little Prince using X-bar style tree annotations. |
| Outcome: | The proposed model shows that deep structure significantly predicts neural responses in English but not in Chinese. |
Integrating Deep Event-Level and Script-Level Information for Script Event Prediction (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies only consider a single event sequence corresponding to one common protagonist. |
| Approach: | They propose a Transformer-based model which integrates deep event-level and script-level information for script event prediction. |
| Outcome: | The proposed model is superior to existing models on the New York Times corpus . it utilizes rich information in the text to obtain more comprehensive representations . |
MSD: Saliency-aware Knowledge Distillation for Multimodal Understanding (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Current knowledge distillation models are limited and lack performance on multimodal datasets. |
| Approach: | They propose a multimodal knowledge distillation framework to transfer knowledge from a teacher on multimodal tasks by learning the teacher's behavior within each modality. |
| Outcome: | The proposed framework achieves better performance than KD on four multimodal datasets. |
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 . |
Empowering Multi-Turn Tool-Integrated Agentic Reasoning with Group Turn Policy Optimization (2026.acl-long)
Copied to clipboard
Yifeng Ding, Hung Le, Songyang Han, Kangrui Ruan, Zhenghui Jin, Varun Kumar, Zijian Wang, Anoop Deoras
| Challenge: | Current reinforcement learning methods suffer from coarse-grained, trajectory-level rewards that provide insufficient learning signals for complex multi-turn interactions, leading to training stagnation. |
| Approach: | They propose a novel RL algorithm for training large language models for multi-turn tool-integrated reasoning (TIR) that incorporates three innovations: turn-level reward assignment that provides fine-grained feedback for individual turns, return-based advantage estimation where normalized discounted returns are calculated as advantages, and self-supervised reward shaping that exploits self-supervision signals from generated code to densify sparse binary outcome-based rewards. |
| Outcome: | The proposed algorithm outperforms GRPO by 3.0% across diverse math reasoning benchmarks and improves grepo by 3.9% on commonsense reasoning and program synthesis tasks. |
DPDV: Dual-Pathway and Dual-View Representation Learning for Bridging Information Asymmetry in Text-Video Retrieval (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for text-based person anomaly search fail to address the pose-semantic gap . asymmetric cross-modal information poses a challenge to accurately establishing retrieval relationships . |
| Approach: | They propose a video retrieval framework that partitions visual features into two categories based on relevance to the text query and performs effective interaction. |
| Outcome: | The proposed framework achieves leading retrieval performance on five benchmark datasets. |
Dynamic Augmentation Data Selection for Few-shot Text Classification (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Data augmentation is a popular method for fine-tuning pre-trained language models to increase model robustness and performance. |
| Approach: | They propose a dynamic data selection method to select effective augmentation data from different augmentation sources according to the model’s learning stage by identifying a set of augmentation samples that optimally facilitates the learning process of the most current model. |
| Outcome: | The proposed method outperforms strong baselines on a variety of sentence classification tasks. |
To Intervene or Not: Guiding Inference-time Alignment with Probabilistic Model Blending (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to inference-time alignment are expensive and only offer guidances during output generation. |
| Approach: | They propose an inference-time alignment framework that shifts from binary decisions to creating hybrid distributions integrating both models’ knowledge. |
| Outcome: | The proposed framework reduces the number of inference-time alignment interventions and improves performance on challenging model pairs. |
Fast or Slow? Integrating Fast Intuition and Deliberate Thinking for Enhancing Visual Question Answering (2025.acl-short)
Copied to clipboard
| Challenge: | Current approaches generate visual markers for all questions, generating excessive visual markers. |
| Approach: | They propose a plug-and-play approach that adapts to the complexity of questions . they propose combining fast intuitive judgments with deliberate analytical reasoning . |
| Outcome: | The proposed approach improves performance on four benchmarks on ScienceQA, TextQA, VizWiz, and MME. |
Text Classification by Contrastive Learning and Cross-lingual Data Augmentation for Alzheimer’s Disease Detection (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods for AD detection are too expensive and time-consuming to cover all potential patients. |
| Approach: | They propose a contrastive learning method to obtain effective text representations based on monolingual embeddings of BERT and a cross-lingual data augmentation method by building autoencoders to learn the text representation shared by both languages. |
| Outcome: | The proposed method outperforms other methods on a Mandarin AD corpus and achieves 81.6% detection accuracy. |
Diagnosing the First-Order Logical Reasoning Ability Through LogicNLI (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies have focused on diagnosing LMs' reasoning abilities in natural language understanding tasks. |
| Approach: | They propose a diagnostic method for first-order logic reasoning with a proposed benchmark, LogicNLI. |
| Outcome: | The proposed method disentangles the target FOL reasoning from commonsense inference and can be used to diagnose LMs from four perspectives: accuracy, robustness, generalization, and interpretability. |
DiffChat: Learning to Chat with Text-to-Image Synthesis Models for Interactive Image Creation (2024.findings-acl)
Copied to clipboard
| Challenge: | a novel method to align Large Language Models to "chat" with prompt-as-input Text-to-Image Synthesis models is proposed . a user-specified instruction can be used to create a high quality image . |
| Approach: | They propose a method to align Large Language Models to "chat" with prompt-as-input Text-to-Image Synthesis models for interactive image creation. |
| Outcome: | The proposed method can exhibit superior performance than baseline models and strong competitors based on automatic and human evaluations. |
CORE: Measuring Multi-Agent LLM Interaction Quality under Game-Theoretic Pressures (2026.eacl-long)
Copied to clipboard
| Challenge: | Game-theoretic interactions between agents with large language models (LLMs) have revealed many emergent capabilities, yet the linguistic diversity of these interactions has not been quantified. |
| Approach: | They propose a metric to quantify the effectiveness of language use within multi-agent systems across different game-theoretic interactions. |
| Outcome: | The proposed metric measures the effectiveness of language use within multi-agent systems across game-theoretic interactions. |
Mondrian: A Framework for Logical Abstract (Re)Structuring (2025.emnlp-main)
Copied to clipboard
| Challenge: | Using the ABT structure, academic abstracts are structured to provide clear and concise prose, but a lack of clarity and logical coherence is a challenge for authors struggling with English proficiency or academic writing conventions. |
| Approach: | They propose a framework that identifies the key components of an abstract and reorients itself to properly reflect the ABT logical progression. |
| Outcome: | The proposed framework improves comprehensibility of academic writing, particularly for non-native English speakers, and is based on a human evaluation and automated metrics. |
RISER: Orchestrating Latent Reasoning Skills for Adaptive Activation Steering (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for domain-specific reasoning with large language models require updating parameter updates. |
| Approach: | They propose a plug-and-play intervention framework that adaptively steers LLM reasoning in activation space. |
| Outcome: | The proposed framework achieves zero-shot accuracy improvements of 3.4–6.5% over the base model while outperforming chain-of-thought-style reasoning with 2–3 higher token efficiency and robust accuracy gains. |
Draft, Verify, Restore: Self-Refining Historical Inscription Restoration with a Unified MLLM (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for end-to-end historical inscription restoration rely on task-separated pipelines with irreversible error accumulation and patch-based generation that sacrifices page-level consistency. |
| Approach: | They propose a unified MLLM for end-to-end historical inscription restoration that integrates draft-guided localization and Hierarchical self-refinement to enable accurate damage localization. |
| Outcome: | The proposed model achieves superior performance in both text restoration accuracy and appearance restoration quality. |
ReasonRec: A Reasoning-Augmented Multimodal Agent for Unified Recommendation (2026.findings-acl)
Copied to clipboard
Yihua Zhang, Mingfu Liang, Jiyan Yang, Rong Jin, Wen-Yen Chen, Yiping Han, Huayu Li, Buyun Zhang, Liang Luo, Luke Simon, Sijia Liu, Tianlong Chen, Xi Liu
| Challenge: | Recent advances in multimodal recommenders lack explicit reasoning and self-awareness of uncertainty. |
| Approach: | They propose a reasoning-augmented multimodal agent structured around a three-stage explicit reasoning pipeline. |
| Outcome: | The proposed agent improves ranking metrics and performance on four standard recommendation tasks across five real-world datasets. |
LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context Inference (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Long-context Multimodal Large Language Models (MLLMs) require substantial computational resources for inference . the growth of their multimodal Key-Value (KV) cache challenges memory and time efficiency. |
| Approach: | They propose a fine-tuning-free approach that efficiently reduces the multimodal KV cache size while maintaining performance comparable to a full cache. |
| Outcome: | The proposed method reduces the multimodal KV cache size while maintaining performance comparable to a full cache. |
Enhancing Document Ranking with Task-adaptive Training and Segmented Token Recovery Mechanism (2021.emnlp-main)
Copied to clipboard
| Challenge: | Document Retrieval (DR) requires the machine to retrieve and rank documents according to their relevance with the query. |
| Approach: | They propose a ranking model DR-BERT which improves the Document Retrieval task by a task-adaptive training process and a Segmented Token Recovery Mechanism. |
| Outcome: | The proposed ranking model keeps in the top three on the MS MARCO leaderboard since 2020. |
DynamicNER: A Dynamic, Multilingual, and Fine-Grained Dataset for LLM-based Named Entity Recognition (2025.emnlp-main)
Copied to clipboard
Hanjun Luo, Yingbin Jin, Yiran Wang, Xinfeng Li, Tong Shang, Xuecheng Liu, Ruizhe Chen, Kun Wang, Hanan Salam, Qingsong Wen, Zuozhu Liu
| Challenge: | Existing datasets designed for Named Entity Recognition methods are inadequate for LLMs. |
| Approach: | They propose a dataset that is multilingual and multi-granular and enables LLMs to be applied to Named Entity Recognition methods. |
| Outcome: | The proposed dataset is multilingual and multi-granular, covering 8 languages and 155 entity types, with corpora spanning a diverse range of domains. |
Plug and Play Knowledge Distillation for kNN-LM with External Logits (2022.aacl-short)
Copied to clipboard
| Challenge: | Despite the promising evaluation results by knowledge distillation (KD) in natural language understanding (NLU) and sequence-to-sequence (seq2sequ) tasks, KD for causal language modeling (LM) remains a challenge. |
| Approach: | They propose to use external logits to improve a student's kNN-LM by leveraging teacher's knowledge at test time. |
| Outcome: | The proposed method improves a student's kNN-LM in multiple language modeling datasets and improves perplexity. |
WebQuality: A Large-scale Multi-modal Web Page Quality Assessment Dataset with Multiple Scoring Dimensions (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing studies on web page quality assessment neglect the aspect of web page content. |
| Approach: | They propose a Chinese dataset for web page quality assessment . the dataset includes over 65,000 detailed an-notations spanning four sub-dimensions . |
| Outcome: | The proposed dataset includes over 65,000 detailed an-notations spanning four sub-dimensions and incorporates elements such as HTML+CSS, text, and visual screenshot. |
Class-Incremental Few-Shot Event Detection (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods to deal with new class of events with only a few labeled instances are challenging . old knowledge forgetting and new class overfitting are two problems in this task. |
| Approach: | They propose a task called class-incremental few-shot event detection to solve old knowledge forgetting and new class overfitting problems. |
| Outcome: | The proposed method reduces old knowledge forgetting and new class overfitting problems on two benchmark datasets. |
Learning a Grammar Inducer from Massive Uncurated Instructional Videos (2022.emnlp-main)
Copied to clipboard
| Challenge: | aims to find more accurate syntactic grammars for accompanying text using video data. |
| Approach: | They build a video-aided grammar induction model that can learn video-span correlation without manual features. |
| Outcome: | The proposed model can learn video-span correlation without manual features adopted by previous systems. |
Don’t Be Misled by Style: A Style-Adaptive Reranker for Capturing Effective Knowledge in Retrieval-Augmented Generation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing rerankers are mainly trained on well-edited texts, but stylistic features can be misled by reranked models. |
| Approach: | They propose a style-augmented multi-task framework that prioritizes effective knowledge over stylistic perturbations by using an LLM to derive passage-level supervision on whether a passage helps or harms answer correctness. |
| Outcome: | Extensive experiments show that SARK improves generation performance across multiple LLMs under mixed-style conditions. |
Revisiting 3D LLM Benchmarks: Are We Really Testing 3D Capabilities? (2025.findings-acl)
Copied to clipboard
| Challenge: | Current 3D LLMs are evaluated on Q&A or captioning tasks rather than specific downstream tasks like object detection. |
| Approach: | They propose principles for better assessing genuine 3D understanding by explicitly separating 3D abilities from 1D or 2D aspects when evaluating 3D LLMs. |
| Outcome: | The proposed methods are based on the “2D-Cheating” problem in 3D LLM evaluation, suggesting that they are ineffective . |
Tab-CoT: Zero-shot Tabular Chain of Thought (2023.findings-acl)
Copied to clipboard
| Challenge: | Recent efforts to encourage more structured reasoning procedures to be captured have shown that chain-of-though (CoT) prompting methods can be effective in NLP tasks. |
| Approach: | They propose a tabular-format CoT prompting method that allows the complex reasoning process to be explicitly modeled in a highly structured manner. |
| Outcome: | The proposed method shows impressive performance improvements on a range of reasoning tasks. |
Integrating Physician Diagnostic Logic into Large Language Models: Preference Learning from Process Feedback (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing studies have shown that large language models can enhance response richness and coherence, but there is a pressing need to bolster the model’s capacity for diagnostic logic to ensure patient safety. |
| Approach: | They propose an approach termed preference learning from process feedback (PLPF) that integrates the doctor’s diagnostic logic into LLMs. |
| Outcome: | The proposed approach improves the diagnostic accuracy of the baseline model in medical conversations by 17.6%, surpassing the performance of traditional approaches. |
Explainable Slot Type Attentions to Improve Joint Intent Detection and Slot Filling (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods analyze and compute features collectively for all slot types, and have no way to explain slot filling model decisions. |
| Approach: | They propose a method that learns to generate additional slot type specific features to improve accuracy and provides explanations for slot filling decisions for the first time in a joint NLU model. |
| Outcome: | The proposed model improves on two widely used datasets and provides an explanation for slot filling decisions for the first time. |
Narrative Order Aware Story Generation via Bidirectional Pretraining Model with Optimal Transport Reward (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing storytelling systems suffer from insufficient understanding of event correlations and inadequate awareness of event temporal order. |
| Approach: | They propose a narrative order aware framework to generate coherent stories with flashbacks . they propose 'bidirectional pretraining model with Optimal Transport Reward' to improve quality . |
| Outcome: | The proposed framework generates coherent stories with flashbacks with a novel optimal transport reward. |
Highway Transformer: Self-Gating Enhanced Self-Attentive Networks (2020.acl-main)
Copied to clipboard
| Challenge: | Self-attention mechanisms have made striking state-of-the-art (SOTA) progress in various sequence learning tasks, attending to all the global contexts at different locations. |
| Approach: | They propose a gated component self-dependency units (SDU) that incorporates LSTM-styled gating units to replenish internal semantic importance within the multi-dimensional latent space of individual representations. |
| Outcome: | The proposed system could boost the performance of the Transformer modules by allowing them to skip connections and step towards suboptimal points during the optimization process. |
Rethinking Table Pruning in TableQA: From Sequential Revisions to Gold Trajectory-Supervised Parallel Search (2026.acl-long)
Copied to clipboard
Yu Guo, Shenghao Ye, Shuangwu Chen, Zijian Wen, Tao Zhang, Bai Qirui, Dong Jin, Yunpeng Hou, Huasen He, null Jianyang, Xiaobin Tan
| Challenge: | Existing pruning methods rely on sequential revisions and unreliable critique signals . Existing methods fail to detect the loss of answer-critical data . |
| Approach: | They propose a table pruning framework which transforms table pruning to gold trajectory-supervised parallel search. |
| Outcome: | The proposed framework outperforms the strongest baseline pruning framework by 3.2% on various tabular reasoning tasks. |
TCSinger 2: Customizable Multilingual Zero-shot Singing Voice Synthesis (2025.findings-acl)
Copied to clipboard
Yu Zhang, Wenxiang Guo, Changhao Pan, Dongyu Yao, Zhiyuan Zhu, Ziyue Jiang, Yuhan Wang, Tao Jin, Zhou Zhao
| Challenge: | Existing zero-shot singing voice synthesis models depend on phoneme and note boundary annotations, limiting their robustness and producing poor transitions between phonemes and notes. |
| Approach: | They propose a multi-task multilingual zero-shot SVS model with style transfer and style control based on various prompts. |
| Outcome: | Experimental results show that TCSinger 2 outperforms baseline models in subjective and objective metrics across multiple related tasks. |
AliGATr: Graph-based layout generation for form understanding (2024.findings-emnlp)
Copied to clipboard
| Challenge: | State of the art forms understanding models often rely on poorly calibrated output probabilities and low performance on relation extraction tasks. |
| Approach: | They propose a graph-based model that uses a generative objective to represent complex grid-like layouts that are often found in forms. |
| Outcome: | The proposed model performs better on the KIE and RE tasks and is more accurate than existing models. |
Large Language Model-Based Event Relation Extraction with Rationales (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods for ERE rely on large language models, but they face limitations. |
| Approach: | They propose an LLM-based approach with rationales for the ERE task . LLMERE transforms ERE into a question-and-answer task that may have multiple answers . |
| Outcome: | Experimental results show that LLMERE improves over existing methods. |
HearSay Benchmark: Do Audio LLMs Leak What They Hear? (2026.findings-acl)
Copied to clipboard
Jin Wang, Kaiwen Luo, Liang Lin, Weiliu Wang, Yitian Chen, Moayad Aloqaily, Xuehai Tang, Zhenhong Zhou, Kun Wang, Li Sun, Qingsong Wen
| Challenge: | Recent advances in audio large language models have led to their potential privacy implications unexplored. |
| Approach: | They propose a benchmark to examine whether ALLMs leak user privacy through acoustic voiceprints. |
| Outcome: | The proposed benchmark is constructed from over 22,000 real-world audio clips. |
100-LongBench: Are de facto Long-Context Benchmarks Literally Evaluating Long-Context Ability? (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing benchmarks for long-context capability are too synthetic and do not represent the real world usage of LLMs. |
| Approach: | They propose a length-controllable, real-life reflective benchmark that disentangles baseline knowledge from long-context capabilities. |
| Outcome: | Experiments show that the proposed benchmarks disentangle baseline knowledge from long-context capabilities. |
Where is this coming from? Making groundedness count in the evaluation of Document VQA models (2025.findings-naacl)
Copied to clipboard
| Challenge: | Document Visual Question Answering (VQA) models have come close to or matching human performance on some benchmarks. |
| Approach: | They propose a method that accounts for the semantic and multimodal groundedness of a model’s outputs and can be parameterized so that users can configure the score according to their preferences. |
| Outcome: | The proposed method produces scores that are a better indicator of a model’s robustness and tends to give higher rewards to better-calibrated answers. |
Meeseeks: A Feedback-Driven, Iterative Self-Correction Benchmark evaluating LLMs’ Instruction Following Capability (2026.findings-acl)
Copied to clipboard
Jiaming Wang, Yunke Zhao, Peng Ding, Jun Kuang, Yibin Shen, Zhe Tang, Yilin Jin, ZongYu Wang, Xiaoyu Li, Xuezhi Cao
| Challenge: | Existing models lack the ability to adhere to instructions, resulting in suboptimal performance. |
| Approach: | They propose an automated iterative instruction-following benchmark with integrated feedback mechanism. |
| Outcome: | The proposed benchmark identifies erroneous components in model responses and provides feedback accurately. |
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. |
Character-based PCFG Induction for Modeling the Syntactic Acquisition of Morphologically Rich Languages (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models for syntactic acquisition are word-based and do not inspect functional affixes. |
| Approach: | They propose a computer-based induction model that allows a clean ablation of the influence of subword information in grammar induction. |
| Outcome: | The proposed model is more accurate in morphologically richer languages with subword information than word-based models. |
Generalization or Memorization: Data Contamination and Trustworthy Evaluation for Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Considering the vast size and wide-ranging sources of LLMs’ training data, it could explicitly or implicitly include test data. |
| Approach: | They propose a Contamination Detection via output Distribution (CDD) which detects data contamination only by identifying the peakedness of LLM's output distribution. |
| Outcome: | The proposed method improves performance by 21.8%-30.2% on humanEval and TED: trustworthy evaluation via output distribution. |
BENTO: A Visual Platform for Building Clinical NLP Pipelines Based on CodaLab (2020.acl-demos)
Copied to clipboard
| Challenge: | CodaLab has limited support for creating reusable tools that can be easily applied to different datasets and composed into pipelines. |
| Approach: | They propose a workflow management platform with a graphic user interface built on top of CodaLab to facilitate the process of building clinical NLP pipelines. |
| Outcome: | The proposed workflow management platform, BENTO, is designed for clinical NLP tasks and can be easily used by researchers and developers. |
Do Large Language Models Mirror Cognitive Language Processing? (2025.coling-main)
Copied to clipboard
| Challenge: | Large language models have demonstrated remarkable abilities in text comprehension and logical reasoning. |
| Approach: | They employ Representational Similarity Analysis to measure alignment between 23 LLMs and fMRI signals of the brain. |
| Outcome: | The results show that training strategies affect the LLM-brain alignment. |
Stress-Testing Emotional Support Models: Moving from Homogeneous to Diverse Help Seekers (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing simulators fail to capture behavioral diversity of real-world seekers . lack of reliable automated evaluation frameworks hinders field's establishment . |
| Approach: | They propose a controllable seeker simulator driven by nine psychological and linguistic features that underpin seeker behavior. |
| Outcome: | The proposed model achieves superior profile adherence and behavioral diversity compared to existing approaches. |
Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphs (2024.findings-acl)
Copied to clipboard
Bowen Jin, Chulin Xie, Jiawei Zhang, Kashob Kumar Roy, Yu Zhang, Zheng Li, Ruirui Li, Xianfeng Tang, Suhang Wang, Yu Meng, Jiawei Han
| Challenge: | Existing studies suggest augmenting LLMs with external text corpora to alleviate hallucination problems. |
| Approach: | They propose to augment large language models with text units retrieved from external knowledge corpora to alleviate the issue. |
| Outcome: | The proposed framework outperforms baselines on GRBench with three LLMs and shows that iterative reasoning outperformed the baselines. |
HUE: Pretrained Model and Dataset for Understanding Hanja Documents of Ancient Korea (2022.findings-naacl)
Copied to clipboard
| Challenge: | Historical records in Korea before the 20th century were primarily written in Hanja, an extinct language based on Chinese characters. |
| Approach: | They present a dataset that includes tasks for attribution, topic classification, named entity recognition and summary retrieval for classical Hanja documents. |
| Outcome: | The proposed models improve on the Annals of the Joseon Dynasty and Diaries of the Royal Secretariats datasets. |
Using In-Context Learning to Improve Dialogue Safety (2023.findings-emnlp)
Copied to clipboard
Nicholas Meade, Spandana Gella, Devamanyu Hazarika, Prakhar Gupta, Di Jin, Siva Reddy, Yang Liu, Dilek Hakkani-Tur
| Challenge: | Recent work has highlighted safety issues with large neural-based conversational models. |
| Approach: | They propose a retrieval-based approach for reducing bias and toxicity in chatbot responses . they retrieve demonstrations of safe responses to similar dialogue contexts to generate a response . |
| Outcome: | The proposed method reduces bias and toxicity in three chatbot models . it can be used in compliment to existing dialogue safety approaches, such as RLHF. |
TalkLoRA: Communication-Aware Mixture of Low-Rank Adaptation for Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Existing LoRA methods assume that experts operate independently, leading to unstable routing, expert dominance. |
| Approach: | They propose a communication-aware MoELoRA framework that relaxes this assumption by introducing expert-level communication prior to routing. |
| Outcome: | The proposed framework outperforms vanilla LoRA and MoELoRA on diverse language understanding tasks while maintaining expert dominance. |
Chat-Driven Text Generation and Interaction for Person Retrieval (2025.emnlp-main)
Copied to clipboard
| Challenge: | Text-based person search (TBPS) aims to retrieve images of a target individual from large-scale databases using natural language descriptions. |
| Approach: | They propose two modules to improve retrieval accuracy and usability . they generate rich pseudo-labels through simulated dialogues with MLLMs . |
| Outcome: | The proposed method achieves competitive or superior results while eliminating the need for manual captions. |
Can GRPO Boost Complex Multimodal Table Understanding? (2025.emnlp-main)
Copied to clipboard
Xiaoqiang Kang, Shengen Wu, Zimu Wang, Yilin Liu, Xiaobo Jin, Kaizhu Huang, Wei Wang, Yutao Yue, Xiaowei Huang, Qiufeng Wang
| Challenge: | Existing table understanding methods struggle with low initialization accuracy and coarse rewards in tabular contexts. |
| Approach: | They propose a three-stage RL framework that enhances multimodal table understanding through: (1) Warm-up that prompts initial perception and reasoning capabilities; (2) Perception Alignment GRPO (PA-GRPO); (3) Hint-Completion GR PO (HC-GRP); |
| Outcome: | The proposed framework outperforms existing models on held-in and held-out datasets, outperforming SFT and GRPO largely. |
SAGE: An Agentic Explainer Framework for Interpreting SAE Features in Language Models (2026.eacl-industry)
Copied to clipboard
| Challenge: | Large language models (LLMs) have achieved remarkable progress, yet their internal mechanisms remain largely opaque. |
| Approach: | They propose an agent-based framework that recasts feature interpretation from a passive, single-pass generation task into an explanation-driven process. |
| Outcome: | The proposed framework produces explanations with significantly higher generative and predictive accuracy compared to state-of-the-art baselines. |
Hyperparameter-free Continuous Learning for Domain Classification in Natural Language Understanding (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing continual learning approaches suffer from low accuracy and performance fluctuation when the distributions of old and new data are significantly different. |
| Approach: | They propose a hyperparameter-free continual learning model for text data that can stably produce high performance under various environments. |
| Outcome: | The proposed model outperforms the best state-of-the-art method by 20% in average accuracy and each component contributes effectively to overall performance. |
Exploring the Vulnerability of the Content Moderation Guardrail in Large Language Models via Intent Manipulation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Prior work has shown that intent detection enhances LLMs’ moderation guardrails, but the robustness of these guardrail mechanisms under malicious manipulations remains under-explored. |
| Approach: | They propose a two-stage intent-based prompt-refinement framework that first transforms harmful inquiries into structured outlines and further reframes them into declarative-style narratives. |
| Outcome: | The proposed framework outperforms several cutting-edge jailbreak methods and evades even advanced Intent Analysis (IA) and Chain-of-Thought (CoT)-based defenses. |
Prejudge-Before-Think: Enhancing Large Language Models at Test-Time by Process Prejudge Reasoning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Experimental results from competition-level complex reasoning demonstrate that bootstrapping with process prejudge can significantly enhance the reasoning ability of LLMs. |
| Approach: | They propose a new process prejudge strategy for LLM reasoning that bootstraps with process prejudgment . |
| Outcome: | The proposed method can be bootstrapped with process prejudge in LLM reasoning . it allows the model to anticipate errors rather than relying on trial and error. |
QuantAgents: Towards Multi-agent Financial System via Simulated Trading (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing LLM-based agent models exhibit significant deviations from real-world fund companies. |
| Approach: | They propose a multi-agent financial system that incorporates simulated trading . they propose simulated trades are evaluated without assuming actual risks . |
| Outcome: | The proposed system evaluates various investment strategies without assuming actual risks without involving real-world investors. |
Mining the Cause of Political Decision-Making from Social Media: A Case Study of COVID-19 Policies across the US States (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies on political responsiveness focus on long-term policies collected over decades . recent COVID-19 pandemic has given rise to a new political phenomenon, where political leaders make frequent short-term decisions on the same controlled topic. |
| Approach: | They propose to use Twitter data to classify the sentiments toward governors of each state and conduct controlled studies and comparisons. |
| Outcome: | The proposed model focuses on the COVID-19 pandemic, where political leaders make frequent short-term decisions on the same controlled topic. |
Contextual Modeling for Document-level ASR Error Correction (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing work on document-level ASR error correction ignores contextual information . however, there are limited studies on incorporating contextual information into AEC . |
| Approach: | They propose a context-aware method that retrieves contextual information from a datastore . they use two English and two Chinese datasets to model document-level AEC . |
| Outcome: | The proposed model can utilize contextual information to improve document-level AEC . the data store containing contextual information provides even better results . |
Rethinking the Reversal Curse of LLMs: a Prescription from Human Knowledge Reversal (2024.emnlp-main)
Copied to clipboard
Zhicong Lu, Li Jin, Peiguang Li, Yu Tian, Linhao Zhang, Sirui Wang, Guangluan Xu, Changyuan Tian, Xunliang Cai
| Challenge: | Existing methods for large language models (LLMs) are limited by their aggressive sample permutation and lack a detailed understanding of the underlying reasons for the reversal curse. |
| Approach: | They propose a method which enhances bidirectional entity correlation modeling and pairwise relationship reasoning to overcome the reversal curse. |
| Outcome: | The proposed method overcomes the reversal curse by augmenting the samples with entity order-reversals and semantically preserved question-answer pairs. |
Zero-Shot Cross-Lingual Document-Level Event Causality Identification with Heterogeneous Graph Contrastive Transfer Learning (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing studies focus on sentence-level ECI with high-resource languages, leaving document-level DECI with low-resourced languages under-explored. |
| Approach: | They propose a Heterogeneous Graph Interaction Model with Multi-granularity Contrastive Transfer Learning for zero-shot cross-lingual ECI. |
| Outcome: | The proposed model outperforms the state-of-the-art model on monolingual and multilingual scenarios by 9.4% and 8.2% of average F1 score. |
Correcting Pronoun Homophones with Subtle Semantics in Chinese Speech Recognition (2024.lrec-main)
Copied to clipboard
| Challenge: | Chinese speech recognition is becoming prevalent due to the similar semantic context of the entities and the overlap of Chinese pronunciation. |
| Approach: | They propose three models to address common confusion issues in Chinese speech recognition . they implement a language model, a LSTM model with semantic features and a rule-based assisted Ngram model . |
| Outcome: | The proposed models achieve highest recognition rate for “T” correction with improvements from 70% in the popular voice input methods up to 90%. |
SOP-Maze: Evaluating Large Language Models on Complicated Business Standard Operating Procedures (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) are widely deployed as domain-specific agents, but evaluation of their capabilities in such contexts has not been fully explored. |
| Approach: | They propose a benchmark to evaluate LLMs' ability to follow instructions and make decisions in real-world scenarios. |
| Outcome: | The proposed benchmark is constructed from real-world business data and adapted into 23 complex SOP scenarios. |
Prototypical Reward Network for Data-Efficient Model Alignment (2024.acl-long)
Copied to clipboard
| Challenge: | Reinforcement Learning from Human Feedback (RLHF) is a reward model that fine-tunes Large Language Models (LLMs) by utilizing Prototypical Networks. |
| Approach: | They propose a framework utilizing Prototypical Networks to enhance reward models under limited human feedback, enabling more stable and reliable structural learning from fewer samples. |
| Outcome: | The proposed framework improves reward models under limited human feedback, surpassing traditional methods, especially in data-limited scenarios. |
Identifying Collective Intelligence Factor in LLM Agent Groups for Generalizable Multi-Agent System Design (2026.findings-acl)
Copied to clipboard
| Challenge: | Prior studies have focused on designing customized MAS for specific tasks . a critical research question remains: do LLM agent groups exhibit a form of "general intelligence" |
| Approach: | They find a Collective Intelligence factor in human groups that captures their general capability. |
| Outcome: | The proposed model predicts the ACI factor based on the features of LLM agent groups and can improve generalization abilities. |
Can AI Revise Research Papers with Human Review Feedback? An Empirical Study and Benchmark (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are fundamentally reshaping the scientific landscape, transitioning the role of AI from passive tools to active partners within a new paradigm of Human-AI collaboration. |
| Approach: | They propose a benchmark to evaluate the ability of Large Language Models to improve papers with human feedback. |
| Outcome: | The proposed benchmark tests the skills of Large Language Models (LLMs) on paper interpretation, experimental implementation, and paper formulation, using authors’ camera-ready versions as natural human baselines. |
Protein Large Language Models: A Comprehensive Survey (2025.findings-emnlp)
Copied to clipboard
Yijia Xiao, Wanjia Zhao, Junkai Zhang, Yiqiao Jin, Han Zhang, Zhicheng Ren, Renliang Sun, Haixin Wang, Guancheng Wan, Pan Lu, Xiao Luo, Yu Zhang, James Zou, Yizhou Sun, Wei Wang
| Challenge: | Existing studies focus on specific aspects or applications, but this study provides a comprehensive overview of Protein-specific large language models. |
| Approach: | This paper proposes a structured taxonomy of state-of-the-art ProteinLLMs . they analyze how they leverage large-scale protein sequence data for improved accuracy . |
| Outcome: | The proposed model covers their architectures, training datasets, evaluation metrics, and diverse applications. |
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. |
Visually Grounded Continual Learning of Compositional Phrases (2020.emnlp-main)
Copied to clipboard
| Challenge: | Modern NLP systems rely on offline training and are inefficient for new tasks. |
| Approach: | They propose a visually grounded ContinuaL learning task which simulates the continual acquisition of compositional phrases from streaming visual scenes. |
| Outcome: | The proposed system improves on existing systems, but it's infeasible to store all possible compositions. |
DVD: Dynamic Contrastive Decoding for Knowledge Amplification in Multi-Document Question Answering (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) generate information with hallucinations due to uneven retrieval quality and irrelevant contents. |
| Approach: | They propose a decoding strategy which dynamically amplifies knowledge from selected documents during the generation phase. |
| Outcome: | The proposed method outperforms other decoding strategies on ALCE-ASQA, NQ, TQA and PopQA benchmarks. |
KCVR: Knowledge-Centric Video Reconstruction for Structured Pedagogical Summarization via Dynamic Graph Planning (2026.acl-long)
Copied to clipboard
Jingjiang Liu, Jia Zhu, Hanghui Guo, Weijie Shi, Yue Cui, Xiaokang Jin, Yilin Wang, Qingyu Niu, Jiawei Shen, Guoqing Ma, Yidan Liang, Shimin Di, Jiajie Xu
| Challenge: | Existing summarization methods compress content for gist browsing, but they break prerequisite logic in instructional videos. |
| Approach: | They propose a framework that decouples epistemic planning from content generation. |
| Outcome: | The proposed framework outperforms strong end-to-end baselines on Knowledge Progression Consistency and Learning Objective Coverage. |
Inductive Link Prediction in N-ary Knowledge Graphs (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods to predict missing elements in NKGs are fixed and therefore cannot be used in real-world situations. |
| Approach: | They propose a task to predict missing elements in unseen facts involving unseent entities and roles in emerging NKGs by embedding unseense entities and role-encoding neural networks. |
| Outcome: | The proposed task outperforms representative models across all datasets. |
Membership Inference Attacks against Language Models via Neighbourhood Comparison (2023.findings-acl)
Copied to clipboard
Justus Mattern, Fatemehsadat Mireshghallah, Zhijing Jin, Bernhard Schoelkopf, Mrinmaya Sachan, Taylor Berg-Kirkpatrick
| Challenge: | Existing membership inference attacks aim to predict whether a data sample was present in training data of a machine learning model. |
| Approach: | They propose to compare model scores to neighbour texts to eliminate access to training data by comparing model scores with a given sample. |
| Outcome: | The proposed attacks outperform reference-based attacks with perfect knowledge of the training data distribution and outperformed reference-free attacks with imperfect knowledge. |
Wikipedia2Vec: An Efficient Toolkit for Learning and Visualizing the Embeddings of Words and Entities from Wikipedia (2020.emnlp-demos)
Copied to clipboard
Ikuya Yamada, Akari Asai, Jin Sakuma, Hiroyuki Shindo, Hideaki Takeda, Yoshiyasu Takefuji, Yuji Matsumoto
| Challenge: | Existing tools for learning the embeddings of words and entities from Wikipedia are not yet available. |
| Approach: | They propose a Python-based tool for learning Wikipedia embeddings from Wikipedia . they use a Wikipedia dump file as an argument to issue a single command . |
| Outcome: | The proposed tool achieves state-of-the-art results on the KORE entity relatedness dataset and competitive results on benchmark datasets. |
Enhancing Code Generation Performance of Smaller Models by Distilling the Reasoning Ability of LLMs (2024.lrec-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have made significant advances in code generation through the ‘Chain-of-Thought’ prompting technique. |
| Approach: | They propose a framework which aims to transfer LLMs’ reasoning capabilities to smaller models through distillation. |
| Outcome: | The proposed framework improves the smaller model's code generation performance by over 130% on the APPS benchmark. |
Uni-Dubbing: Zero-Shot Speech Synthesis from Visual Articulation (2024.acl-long)
Copied to clipboard
Songju Lei, Xize Cheng, Mengjiao Lyu, Jianqiao Hu, Jintao Tan, Runlin Liu, Lingyu Xiong, Tao Jin, Xiandong Li, Zhou Zhao
| Challenge: | Multimodal speech synthesis is a key challenge due to the scarcity of datasets that pair audio with corresponding video. |
| Approach: | They propose a method that incorporates modality alignment during the pre-training phase on multimodal datasets and freezes the video modality extraction component and the encoder module within the pretrained weights. |
| Outcome: | The proposed method achieves a reduced word error rate (WER) of 31.73%, surpassing the previous best of 33.9% with single-modality audio. |
Plug-in and Fine-tuning: Bridging the Gap between Small Language Models and Large Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) are renowned for their extensive linguistic knowledge and strong generalization capabilities, but their high computational demands make them unsuitable for resource-constrained environments. |
| Approach: | They propose a framework that integrates a single frozen layer from an LLM into a SLM and fine-tunes the combined model for specific tasks. |
| Outcome: | The proposed framework improves performance across a range of natural language processing tasks, including both natural language understanding and generation. |
Learning to Conceal Risk: Controllable Multi-turn Red Teaming for LLMs in the Financial Domain (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are increasingly deployed in high-stakes domains such as finance where unsafe behavior can lead to serious regulatory risks. |
| Approach: | They propose a black-box multi-turn risk-concealed redteaming framework that progressively conceals surface-level risk while exploiting regulatory-violating behaviors. |
| Outcome: | Experiments on nine widely used LLMs show that the proposed framework achieves 93.19% average attack success rate (ASR) and improves the average ASR to 95.00%. |
Knowledge Distillation with Reptile Meta-Learning for Pretrained Language Model Compression (2022.coling-1)
Copied to clipboard
| Challenge: | Knowledge distillation (KD) can transfer knowledge from the original model into a compact model to achieve model compression. |
| Approach: | They propose a knowledge distillation method with reptile meta-learning to facilitate the transfer of knowledge from the teacher to the student. |
| Outcome: | Extensive experiments on the GLUE benchmark show the proposed method performs better than previous methods. |
CEMT:Controllable Element-Oriented Machine Translation via Structured Linguistic Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models suffer from paraphrasing errors, omissions, or hallucinations when input contains translation-specific elements that require strict preservation or controlled transformation. |
| Approach: | They propose a Controllable Element-Oriented Machine Translation framework that decomposes the translation process into a linguistically grounded analysis, strategy formulation, and final generation. |
| Outcome: | The proposed framework improves on the WMT23/24 Chinese–English benchmarks while significantly reducing element-level constraint violations. |
Beyond Good Intentions: Reporting the Research Landscape of NLP for Social Good (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Recent advances in natural language processing (NLP) have created a vast number of applications that are aimed at social good applications. |
| Approach: | They propose a dataset with three tasks that can help identify NLP4SG papers and characterize the NLP landscape by: (1) identifying the papers that address a social problem, (2) mapping them to the corresponding UN Sustainable Development Goals, and (3) identifying their methods. |
| Outcome: | The proposed dataset can help identify NLP4SG papers and characterize the NLP landscape by: (1) identifying the papers that address a social problem, (2) mapping them to the corresponding UN Sustainable Development Goals (SDGs), and (3) identifying their methods. |
Causal Denoising Prototypical Network for Few-Shot Multi-label Aspect Category Detection (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent methods that learn robust prototypes to represent aspects with limited support samples address noise categories in the support set that hinder their models from effective prototype generation. |
| Approach: | They propose a causal denoising prototypical network for few-shot MACD by learning robust prototypes to represent categories with limited support samples. |
| Outcome: | The proposed model outperforms baseline models and can prevent models from overly predicting more categories and mitigate semantic ambiguity issues among categories. |
SAME: Signer-Aware Mixture-of-Experts for Test-Time Adaptation in Sign Language Translation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for supervised fine-tuning are limited due to labeled data . existing methods require long adaptation times and batch statistics are unavailable in streaming settings . |
| Approach: | They propose a plug-and-play, signer-aware Mixture-of-Experts (MoE) TTA architecture for SLT . they use a combination of lightweight MoE modules and unsupervised regularizers to decouple domain shift . |
| Outcome: | The proposed test-time adaptation outperforms existing TTA methods in sign language translation . the proposed architecture can be used in real-world deployments without labeling . |
Adversarial Robustness for Large Language NER models using Disentanglement and Word Attributions (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Named Entity Recognition (NER) tasks are becoming more challenging due to the introduction of complex tagsets, which often leads to the failure of existing NER systems in accurately recognizing these entities. |
| Approach: | They propose a novel attack which relies on disentanglement and word attribution techniques to learn an embedding and identifying important words across both components. |
| Outcome: | The proposed approach improves the F1 score over the original LLM model by 8% and 18% on CoNLL-2003 and Ontonotes 5.0 datasets respectively. |
Rethinking Positional Encoding in Tree Transformer for Code Representation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent works have proposed novel tree Transformers to capture the syntactic structure in source code. |
| Approach: | They propose a novel tree Transformer encoding node positions based on a description method for tree structures to incorporate inductive bias into Transformer. |
| Outcome: | The proposed model outperforms baselines on code summarization and completion tasks across two languages, and it is able to perform better on both local and global paradigms. |
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. |
Exploring Fine-Grained Human Motion Video Captioning (2025.coling-main)
Copied to clipboard
Bingchan Zhao, Xinyi Liu, Zhuocheng Yu, Tongchen Yang, Yifan Song, Mingyu Jin, Sujian Li, Yizhou Wang
| Challenge: | Existing video captioning models fail to capture nuanced semantics of videos . existing models generate coarse descriptions of human motions, resulting in poor quality . |
| Approach: | They construct a fine-grained human motion video captioning dataset named BoFiT and a model that generates fine-grain descriptions of human motions via prompting. |
| Outcome: | The proposed model outperforms existing models on comprehensive metrics. |
CogIE: An Information Extraction Toolkit for Bridging Texts and CogNet (2021.acl-demo)
Copied to clipboard
| Challenge: | CogNet is a knowledge base that integrates three types of knowledge: linguistic knowledge, world knowledge and commonsense knowledge. |
| Approach: | They propose an information extraction toolkit called CogIE that is a bridge connecting raw texts and CogNet. |
| Outcome: | The proposed toolkit can ground raw texts to CogNet and leverage different types of knowledge to enrich extracted results. |
CRUISE: Cold-Start New Skill Development via Iterative Utterance Generation (P18-4)
Copied to clipboard
| Challenge: | Existing systems require developers to manually generate and annotate a large number of utterances. |
| Approach: | They propose a system that guides ordinary software developers to build a high quality NLU engine from scratch. |
| Outcome: | The proposed system shows that iterative pruning of incorrect utterances reduces human workload and cognitive load. |
Reviving Cultural Heritage: A Novel Approach for Comprehensive Historical Document Restoration (2025.acl-long)
Copied to clipboard
Yuyi Zhang, Peirong Zhang, Zhenhua Yang, Pengyu Yan, Yongxin Shi, Pengwei Liu, Fengjun Guo, Lianwen Jin
| Challenge: | Existing methods for historical document restoration focus on single modality or limited-size restoration, failing to meet practical needs. |
| Approach: | They propose a full-page HDR dataset and an automated HDR solution to replace manual restoration methods. |
| Outcome: | The proposed solution improves OCR accuracy from 46.83% to 84.05% when processing severely damaged documents, with enhancement to 94.25% through human-machine collaboration. |
Do Vision-Language Models Have Internal World Models? Towards an Atomic Evaluation (2025.findings-acl)
Copied to clipboard
Qiyue Gao, Xinyu Pi, Kevin Liu, Junrong Chen, Ruolan Yang, Xinqi Huang, Xinyu Fang, Lu Sun, Gautham Kishore, Bo Ai, Stone Tao, Mengyang Liu, Jiaxi Yang, Chao-Jung Lai, Chuanyang Jin, Jiannan Xiang, Benhao Huang, Zeming Chen, David Danks, Hao Su, Tianmin Shu, Ziqiao Ma, Lianhui Qin, Zhiting Hu
| Challenge: | Recent studies have evaluated and shown limitations in specific capabilities such as visual understanding, but a systematic evaluation of VLMs’ fundamental WM abilities remains absent. |
| Approach: | They propose a framework that assesses perception and prediction to provide an atomic evaluation of VLMs as WMs. |
| Outcome: | The proposed framework assesses perception and prediction abilities on 15 latest VLMs and compares them to human-level 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. |
Variance of Average Surprisal: A Better Predictor for Quality of Grammar from Unsupervised PCFG Induction (P19-1)
Copied to clipboard
| Challenge: | In unsupervised grammar induction, data likelihood is only weakly correlated with parsing accuracy, especially at convergence after multiple runs. |
| Approach: | They propose to use VAS instead of data likelihood to find better grammars by examining linguistically-motivated constraints related to syntax. |
| Outcome: | The proposed model is better suited for word order typology classification than data likelihood. |
Fine-Grained Entity Typing via Hierarchical Multi Graph Convolutional Networks (D19-1)
Copied to clipboard
| Challenge: | Existing methods for inferring the fine-grained type of an entity from knowledge base are incomplete and lack type information. |
| Approach: | They propose a novel Deep Learning architecture to infer the fine-grained type of an entity from a knowledge base. |
| Outcome: | The proposed method significantly outperforms four state-of-the-art methods on two large-scale datasets. |
TMID: A Comprehensive Real-world Dataset for Trademark Infringement Detection in E-Commerce (2023.emnlp-industry)
Copied to clipboard
| Challenge: | Annually, e-commerce platforms incur substantial financial losses due to trademark infringements. |
| Approach: | They propose a dataset to detect trademark infringement in merchant registrations . they use legal rules and contextual information from Alipay to gather contextual information with annotations from legal experts. |
| Outcome: | The proposed dataset is sourced from Alipay, one of the world’s largest e-commerce and digital payment platforms. |
Prompt-Singer: Controllable Singing-Voice-Synthesis with Natural Language Prompt (2024.naacl-long)
Copied to clipboard
Yongqi Wang, Ruofan Hu, Rongjie Huang, Zhiqing Hong, Ruiqi Li, Wenrui Liu, Fuming You, Tao Jin, Zhou Zhao
| Challenge: | Recent singing-voice-synthesis methods lack ability to control style attributes of synthesized singing. |
| Approach: | They propose a singing-voice-synthesis method that enables attribute controlling on singer gender, vocal range and volume with natural language. |
| Outcome: | The proposed method achieves favorable control ability and audio quality. |
MetaSLRCL: A Self-Adaptive Learning Rate and Curriculum Learning Based Framework for Few-Shot Text Classification (2022.coling-1)
Copied to clipboard
| Challenge: | Existing few-shot text classification methods lack labeled data in many scenarios. |
| Approach: | They propose a meta learning framework that obtains different learning rates for different tasks and neural network layers to enable the meta learner to quickly adapt to new training data. |
| Outcome: | The proposed framework can obtain different learning rates for different tasks and neural network layers so as to enable the meta learner to quickly adapt to new tasks. |
What Matters in Evaluating Book-Length Stories? A Systematic Study of Long Story Evaluation (2025.acl-long)
Copied to clipboard
| Challenge: | a new study examines the effectiveness of automated evaluations of book-length stories . aggregation-based and summary-based evaluations excel in detail assessment, the study finds . |
| Approach: | They propose a system for automatic evaluation of book-length stories based on human-centered criteria . they propose aggregation-based and summary-based evaluations to improve accuracy . |
| Outcome: | The proposed evaluation criteria outperforms commercial models like GPT-4o in evaluating human-written or machine-generated stories. |
Analyzing the Role of Semantic Representations in the Era of Large Language Models (2024.naacl-long)
Copied to clipboard
Zhijing Jin, Yuen Chen, Fernando Gonzalez Adauto, Jiarui Liu, Jiayi Zhang, Julian Michael, Bernhard Schölkopf, Mona Diab
| Challenge: | Existing studies show the benefits of semantic representations in NLP tasks . Existing work using AMR is concerned with trainable models . |
| Approach: | They propose an AMR-driven chain-of-thought prompting method that uses AMR . they propose to use it to predict which input examples AMR may help or hurt on . |
| Outcome: | The proposed method hurts performance more than it helps on five different tasks. |
Multi-granularity Textual Adversarial Attack with Behavior Cloning (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing adversarial attack models are vulnerable to adversarials crafted by human-imperceptible perturbations. |
| Approach: | They propose a multi-granularity adversarial attack model that generates high-quality adversarials with fewer queries to victim models. |
| Outcome: | The proposed model generates high-quality adversarial samples with fewer queries to victim models compared to baseline models . the proposed model also reduces query times for black-box models that only output labels without confidence scores . |
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. |
Salience Allocation as Guidance for Abstractive Summarization (2022.emnlp-main)
Copied to clipboard
Fei Wang, Kaiqiang Song, Hongming Zhang, Lifeng Jin, Sangwoo Cho, Wenlin Yao, Xiaoyang Wang, Muhao Chen, Dong Yu
| Challenge: | Abstractive summarization models implicitly learn to capture the salient information from scratch. |
| Approach: | They propose a method that uses salience expectation to guide abstractive summarization by averaging salient content to a fixed threshold. |
| Outcome: | The proposed method can be easily adapted to documents with various abstractiveness and achieves high performance. |
Two-Step Question Retrieval for Open-Domain QA (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing question retrieval models have shown a significant increase in inference speed but at the cost of lower QA performance compared to the retriever-reader pipeline. |
| Approach: | They propose a two-step question retrieval model with distant supervision to improve inference speed. |
| Outcome: | The proposed model significantly increases the performance of existing question retrieval models with a negligible loss on inference speed. |
Perceptions to Beliefs: Exploring Precursory Inferences for Theory of Mind in Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | While theory of mind (ToM) is naturally developed for humans in childhood, large language models (LLMs) exhibit inconsistency in ToM tasks, despite early reports of successful cases. |
| Approach: | They propose to evaluate human ToM precursors-perception inference and perception-to-belief inference-in large language models (LLMs) by annotating characters’ perceptions on ToMi and FANToM. |
| Outcome: | The proposed method significantly improves LLMs’ performance in false belief scenarios. |
Reusing Transferable Weight Increments for Low-resource Style Generation (2024.emnlp-main)
Copied to clipboard
| Challenge: | Text style transfer (TST) is crucial in natural language processing, aiming to endow text with a new style without altering its meaning. |
| Approach: | They propose a framework to use style features in weight increments to transfer low-resource styles effectively. |
| Outcome: | The proposed framework achieves remarkable performance across different backbones, achieving particularly effective results in low-resource scenarios. |
Pushing the Limits of LLM Tool Calling via Experiential Knowledge Integration and Activation (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches treat tool use as a problem of prompt design, API documents specification, or supervised or unsupervised alignment. |
| Approach: | They propose a knowledge-augmented tool execution framework that integrates experiential knowledge with reasoning-width-expanded inference and knowledge-aware training. |
| Outcome: | The proposed framework improves on BFCL-V3 and AppWorld on three model scales. |
Reasoning Is Not All You Need: Examining LLMs for Multi-Turn Mental Health Conversations (2026.acl-long)
Copied to clipboard
| Challenge: | Existing evaluation frameworks focus on diagnostic accuracy and win-rates and often overlook alignment with patient-specific goals, values, and personalities required for meaningful conversations. |
| Approach: | They propose a framework for synthetically generating realistic, multi-turn mental health sensemaking conversations and a dataset to examine their models in healthcare settings. |
| Outcome: | The proposed framework synthesizes a dataset comprising over 2,200 patient–LLM conversations and evaluates them using human-centric criteria. |
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 . |
Knowledge-Infused Prompting: Assessing and Advancing Clinical Text Data Generation with Large Language Models (2024.findings-acl)
Copied to clipboard
Ran Xu, Hejie Cui, Yue Yu, Xuan Kan, Wenqi Shi, Yuchen Zhuang, May Dongmei Wang, Wei Jin, Joyce Ho, Carl Yang
| Challenge: | Clinical natural language processing (NLP) is a subfield that requires the extraction, analysis, and interpretation of unstructured clinical text. |
| Approach: | They propose a model which infuses knowledge into clinical text generation with LLMs for clinical NLP tasks. |
| Outcome: | The proposed model improves performance across 8 clinical NLP tasks and 18 datasets by 7.7%-8.7% on average. |
Probabilistic Soundness Guarantees in LLM Reasoning Chains (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for detecting propagated errors in reasoning chains are inadequate . author et al. (2017) show that initial errors propagate and undermine reliability of final conclusion . |
| Approach: | They propose a framework that evaluates each reasoning step based solely on previously-verified premises and provides certified statistical guarantees of its soundness. |
| Outcome: | ARES achieves state-of-the-art performance across four benchmarks and demonstrates superior robustness on very long synthetic reasoning chains. |
Schema-based Data Augmentation for Event Extraction (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing data augmentation methods rely on language models to train event extraction models. |
| Approach: | They propose a schema-based data augmentation method that utilizes event schemas to guide the data generation process. |
| Outcome: | The proposed method produces high-quality generated data and significantly improves model performance. |
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. |
RAM-EHR: Retrieval Augmentation Meets Clinical Predictions on Electronic Health Records (2024.acl-short)
Copied to clipboard
| Challenge: | Existing deep learning models for EHRs rely on knowledge from a single source and do not capture the semantic information for medical codes. |
| Approach: | They propose a Retrieval AugMentation pipeline to augment clinical prediction on EHRs . they use multiple knowledge sources to convert them into text and use consistency regularization to capture complementary information from patient visits and summarized knowledge. |
| Outcome: | Experiments on two EHR datasets show that RAM-EHR improves clinical prediction tasks. |
ESCoT: Towards Interpretable Emotional Support Dialogue Systems (2024.acl-long)
Copied to clipboard
| Challenge: | Emotion-focused and strategy-driven chain-of-thought (ESCoT) is a new paradigm for emotional support dialogues. |
| Approach: | They propose an emotional support response generation scheme to improve interpretability . they generate a dataset and develop a model to generate dialogue responses with better interpretability. |
| Outcome: | The proposed scheme can generate dialogue responses with better interpretability. |
Learning to Generalize to More: Continuous Semantic Augmentation for Neural Machine Translation (2022.acl-long)
Copied to clipboard
| Challenge: | Neural machine translation (NMT) tasks require large amounts of parallel data to augment training. |
| Approach: | They propose a data augmentation paradigm that augments each training instance with an adjacency semantic region that could cover adequate variants of literal expression under the same meaning. |
| Outcome: | The proposed paradigm improves on the state-of-the-art in supervised neural machine translation tasks. |
MPVStance: Mitigating Hallucinations in Stance Detection with Multi-Perspective Verification (2025.acl-long)
Copied to clipboard
| Challenge: | despite advances in large language models, challenges persist due to hallucination-models generating inaccurate content. |
| Approach: | They propose a framework that integrates multi-perspective verification with Retrieval-Augmented Generation to address these challenges. |
| Outcome: | The proposed method outperforms existing models on the SemEval-2016 and VAST datasets. |
Event Causality Extraction via Implicit Cause-Effect Interactions (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies have not exploited the interactions between the cause and effect event that could provide crucial clues for causality reasoning. |
| Approach: | They propose an Implicit Cause-Effect interaction framework which captures the implicit intra- and inter-event interactions by incorporating the privileged information for reasoning. |
| Outcome: | The proposed framework captures the implicit intra- and inter-event interactions by incorporating the privileged information (ground truth event types and arguments) for reasoning. |
From Past To Path: Masked History Learning for Next-Item Prediction in Generative Recommendation (2026.acl-long)
Copied to clipboard
Kaiwen Wei, Kejun he, Xiaomian Kang, Jie Zhang, null Ymyang, Li Jin, Zhenyang Li, Jiang Zhong, Richard He Bai, Junnan Zhu
| Challenge: | Generative recommendation models inherently bias towards local contexts, failing to capture deeper historical dependencies necessary for understanding complex user intents. |
| Approach: | They propose a training framework that shifts the objective from simple next-step prediction to deep comprehension of history by entropy-guided masking policy and a curriculum learning scheduler to enhance the framework. |
| Outcome: | The proposed framework outperforms state-of-the-art generative models on three public datasets and shows that it is more accurate than current models. |
Dunhuang-Bench: How Well Do MLLMs Understand Cultural Heritage? (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in Multimodal Large Language Models (MLLMs) have led to extensive evaluations on Chinese cultural benchmarks. |
| Approach: | They construct a large-scale benchmark comprising 486 images and 22,970 QA pairs to evaluate MLLMs' cultural understanding. |
| Outcome: | The proposed benchmark incorporates three task formats to evaluate MLLMs’ cultural understanding: Question Answering with Text Description, Multi-turn Dialogue, and Question Answers with Choices. |
PPTSER: A Plug-and-Play Tag-guided Method for Few-shot Semantic Entity Recognition on Visually-rich Documents (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for visually-rich document information extraction are limited . Xu et al., 2020: visually rich document information is a vital aspect of document understanding . |
| Approach: | They propose a plug-and-play Tag-guided method for few-shot Semantic Entity Recognition (PPTSER) on visually-rich documents. |
| Outcome: | The proposed method outperforms fine-tuning and few-shot methods on visual-rich documents. |
CAPSTONE: Curriculum Sampling for Dense Retrieval with Document Expansion (2023.emnlp-main)
Copied to clipboard
| Challenge: | Experimental results show that dense retrieval models are better at obtaining query-informed representations. |
| Approach: | They propose a dual-encoder approach that computes latent representations of query and document independently, but inference replaces the real query with a generated one. |
| Outcome: | The proposed approach outperforms previous dense retrieval models on in-domain and out-of-domain datasets. |
Self-Improvement Programming for Temporal Knowledge Graph Question Answering (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods implicitly model time constraints by learning time-aware embeddings of questions and candidate answers, which is far from understanding the question comprehensively. |
| Approach: | They propose a temporal-based temporal programming method that leverages the in-context learning ability of Large Language Models to understand combinatory time constraints in questions. |
| Outcome: | The proposed method outperforms existing methods on multiTQ and CronQuestions datasets and is highly efficient on multi-level questions. |
Vision-Flan: Scaling Human-Labeled Tasks in Visual Instruction Tuning (2024.findings-acl)
Copied to clipboard
Zhiyang Xu, Chao Feng, Rulin Shao, Trevor Ashby, Ying Shen, Di Jin, Yu Cheng, Qifan Wang, Lifu Huang
| Challenge: | Recent vision-language models (VLMs) have shown impressive capabilities as general visual assistants, but there are two challenges to their performance: (1) lacking task diversity in pretraining and visual instruction tuning; (2) annotation error and bias in GPT-4 synthesized instruction tuning data. |
| Approach: | They propose a two-stage instruction tuning framework that fine tunes VLMs firstly and further tuned on GPT-4 synthesized data. |
| Outcome: | The proposed framework outperforms the traditional single-stage visual instruction tuning framework and achieves state-of-the-art performance across a wide range of multi-modal evaluation benchmarks. |
RCTEA: Richness-guided Co-training for Temporal Entity Alignment (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing TEA models fail to capture the orthogonal yet complementary effect between structural and temporal features. |
| Approach: | They propose a framework that jointly models structural and temporal aspects of Temporal Knowledge Graphs for entity alignment. |
| Outcome: | The proposed framework achieves state-of-the-art on public TEA benchmarks. |
CS2W: A Chinese Spoken-to-Written Style Conversion Dataset with Multiple Conversion Types (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing datasets focus on a single type of spoken style, such as disfluencies. |
| Approach: | They propose a Chinese Spoken-to-Written style conversion dataset with 7,237 spoken sentences extracted from transcribed conversational texts. |
| Outcome: | The proposed dataset covers four major conversion problems corresponding to the majority of spoken styles. |
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. |
FashionKLIP: Enhancing E-Commerce Image-Text Retrieval with Fashion Multi-Modal Conceptual Knowledge Graph (2023.acl-industry)
Copied to clipboard
Xiaodan Wang, Chengyu Wang, Lei Li, Zhixu Li, Ben Chen, Linbo Jin, Jun Huang, Yanghua Xiao, Ming Gao
| Challenge: | Recent advances in visual-language pre-trained (VLP) models have greatly improved cross-modal retrieval performance . however, the fine-grained interactions between objects from different modalities are far from well-established . e-commerce domain lacks sufficient training data and fine-granular cross-modulal knowledge . |
| Approach: | They propose a visual-language pre-trained (VLP) image-text retrieval model that integrates cross-modal knowledge into the model to improve performance. |
| Outcome: | The proposed model improves performance on e-commerce image-text retrieval task by a large margin. |
Multimodal Transformers are Hierarchical Modal-wise Heterogeneous Graphs (2025.acl-long)
Copied to clipboard
| Challenge: | Multimodal Sentiment Analysis (MSA) is a rapidly developing field that integrates multimodal information to recognize sentiments. |
| Approach: | They propose a multimodal fusion model that integrates multimodal information to recognize sentiments using multimodal transformers. |
| Outcome: | The proposed model achieves significantly higher performance than MulTs and the existing model is robust. |
Document-Level Text Simplification: Dataset, Criteria and Baseline (2021.emnlp-main)
Copied to clipboard
| Challenge: | Text simplification is a valuable technique, but research on it is limited. |
| Approach: | They propose a document-level simplification task using Wikipedia dumps as a dataset and propose an automatic evaluation metric called D-SARI. |
| Outcome: | The proposed metric is more suitable for document-level simplification task. |
Emotion Recognition in Conversation via Dynamic Personality (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing approaches to ERC focus on conversational contexts, but focus on static personality. |
| Approach: | They propose a model that considers the dynamic personality of speakers during conversations. |
| Outcome: | The proposed model outperforms existing models on three benchmark conversational datasets. |
Generalized Shortest-Paths Encoders for AMR-to-Text Generation (2020.coling-main)
Copied to clipboard
| Challenge: | a recent effort to encode graphs with gated convolutions provides local context, but distance messages travel is limited by number of encoder propagation steps. |
| Approach: | They propose to use generalized shortest-paths to train a graph encoder to learn shortest paths . they show that path diversity affects performance across levels of AMR connectivity . |
| Outcome: | The proposed model achieves a 1.4 BLEU and 1.8 chrF++ margin over a baseline model that encodes only pairwise-unique shortest paths. |
Modeling the Severity of Complaints in Social Media (2021.naacl-main)
Copied to clipboard
| Challenge: | Complaining is a speech act used by humans to communicate a negative mismatch between reality and expectations . recent work on modeling complaints in natural language processing (NLP) has focused on distinguishing complaints from non-complaints in social media. |
| Approach: | They propose to classify complaints into various severity levels based on the face-threat that the complainer is willing to undertake and their purpose. |
| Outcome: | The proposed model achieves 55.7 macro F1 on binary complaint classification and 88.2 macro F1. |
SLiM: Speculative Decoding with Hypothesis Reduction (2024.findings-naacl)
Copied to clipboard
| Challenge: | Speculative decoding has emerged as an alternative to autoregressive decoding for expediting inference in large language models (LLMs). prevailing assumptions focus solely on latency reduction, neglecting the computational expenses. |
| Approach: | They propose a speculative decoding enhancement to reduce the speculation set while validating more effective tokens. |
| Outcome: | The proposed method reduces the speculation set while validating more effective tokens. |
DICP: Deep In-Context Prompt for Event Causality Identification (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing prompt-learning-based methods concatenate in-context examples only at the input layer, limiting the model’s ability to capture abstract semantic cues necessary for identifying complex causal relationships. |
| Approach: | They propose a model that injects in-context examples into the deeper layer of a pre-trained language model (PLM) this model leverages hierarchical semantic representations formed in deeper layers, thereby enhancing its capacity to learn high-level causal abstractions. |
| Outcome: | The proposed model improves on two widely used datasets and shows that it can learn high-level causal abstractions. |
Uncovering Hidden Correctness in LLM Causal Reasoning via Symbolic Verification (2026.eacl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) are increasingly being applied to causal reasoning tasks. |
| Approach: | They propose a symbolic verification framework that checks whether LLM-generated causal expressions are derivable from a given causal graph using do-calculus and probability theory. |
| Outcome: | The proposed framework can recover correct answers that would otherwise be marked incorrect due to superficial differences. |
Interpreting Positional Information in Perspective of Word Order (2023.acl-long)
Copied to clipboard
| Challenge: | Attention mechanism is a powerful and effective method utilized in natural language processing, but it is insensitive to positional information. |
| Approach: | They propose a weight concatenation operation to evaluate its efficacy in machine translation tasks. |
| Outcome: | The proposed operation can encode positional information and confirms our hypothesis. |
CocaCLIP: Exploring Distillation of Fully-Connected Knowledge Interaction Graph for Lightweight Text-Image Retrieval (2023.acl-industry)
Copied to clipboard
| Challenge: | Existing methods for text-image retrieval are limited to edge devices and real-time situations due to the substantial indexing and inference time. |
| Approach: | They propose a fully-Connected knowledge interaction graph technique for cross-modal pre-training distillation. |
| Outcome: | The proposed method achieves SOTA performances on the widely-used Flickr30K and MSCOCO benchmarks under the lightweight setting. |
Dual Low-Rank Multimodal Fusion (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing tensor-based fusion methods make poor use of fine-grained temporal dynamics of multimodal sequential features. |
| Approach: | They propose a novel multimodal fusion method called Fine-Grained Temporal Low-Rank Multimodal Fusion that uses low-rank tensor approximation along dual dimensions of input features. |
| Outcome: | The proposed method outperforms the state-of-the-art tensor-based methods with a similar computational complexity. |
U-Fold: Dynamic Intent-Aware Context Folding for User-Centric Agents (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing context-folding methods are designed for single-query or single-intent scenarios. |
| Approach: | They propose a dynamic context-folding framework tailored to user-centric tasks that preserves fine-grained information through dynamic context folding. |
| Outcome: | The proposed framework outperforms ReAct and previous folding frameworks on long, noisy tasks. |
MA-BERT: Learning Representation by Incorporating Multi-Attribute Knowledge in Transformers (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for incorporating external attribute knowledge into deep neural networks are concatenating multiple attributes to word/text representation or treating them as biases to adjust attention distribution. |
| Approach: | They propose a multi-attribute BERT to incorporate external attribute knowledge into deep neural networks. |
| Outcome: | The proposed method outperforms existing models and models on three benchmark datasets. |
Instilling Type Knowledge in Language Models via Multi-Task QA (2022.findings-naacl)
Copied to clipboard
| Challenge: | Current methods to learn entity types rely on coarse, noisy labels . current methods rely only on text-to-text pre-training on type-centric questions . |
| Approach: | They propose to instill fine-grained type knowledge in language models by pre-training on type-centric questions. |
| Outcome: | The proposed model achieves state-of-the-art in zero-shot dialog state tracking benchmarks and can accurately infer entity types in Wikipedia articles. |
MTR: A Dataset Fusing Inductive, Deductive, and Defeasible Reasoning (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing datasets for logical reasoning focus on monotonic logic and a single form of reasoning. |
| Approach: | They propose to use a dataset to study the human-like reasoning in machine reading comprehension. |
| Outcome: | The proposed dataset shows that state-of-the-art neural models perform noticeably worse than expected. |
KoCo-Bench: Can Large Language Models Leverage Domain Knowledge in Software Development? (2026.acl-long)
Copied to clipboard
Xue Jiang, Ge Li, Jiaru Qian, Xianjie Shi, Chenjie Li, Hao Zhu, Ziyu Wang, Jielun Zhang, Zeyu Zhao, Kechi Zhang, Jia Li, Wenpin Jiao, Zhi Jin, Yihong Dong
| Challenge: | Existing domain-specific code benchmarks focus on assessing what knowledge LLMs possess rather than how they acquire and apply new knowledge. |
| Approach: | They propose a benchmark to evaluate domain specialization methods in real-world software development. |
| Outcome: | KOCO-bench is a new benchmark for evaluating domain specialization methods in real-world software development. |
Knowing-how & Knowing-that: A New Task for Machine Comprehension of User Manuals (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for machine reading comprehension of user manuals have trouble answering complex questions. |
| Approach: | They propose a knowing-how & knowing-that task that requires the model to answer factoid-style, procedure-style and inconsistent questions about user manuals. |
| Outcome: | The proposed model can answer factoid-style, procedure-style and inconsistent questions about user manuals. |
DenseLoRA: Dense Low-Rank Adaptation of Large Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Low-rank adaptation (LoRA) is an efficient approach for adapting large language models (LLMs) but many of the weights in these matrices are redundant, leading to inefficiencies in parameter utilization. |
| Approach: | They propose a low-rank adaptation approach that fine-tunes two low-ranked matrices and adapts them through a dense low-Rank matrix, improving parameter utilization and adaptation efficiency. |
| Outcome: | The proposed approach achieves 83.8% accuracy with only 0.01% of trainable parameters compared to LoRA's 80.8% with 0.70% of trainability parameters on LLaMA3-8B. |
Large Language Models Can Be Contextual Privacy Protection Learners (2024.emnlp-main)
Copied to clipboard
Yijia Xiao, Yiqiao Jin, Yushi Bai, Yue Wu, Xianjun Yang, Xiao Luo, Wenchao Yu, Xujiang Zhao, Yanchi Liu, Quanquan Gu, Haifeng Chen, Wei Wang, Wei Cheng
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable linguistic comprehension and generation capability, but when applied to specialized industries, they face challenges such as hallucination, insufficient domain knowledge, and failing to incorporate the latest domain knowledge. |
| Approach: | They propose a paradigm for fine-tuning LLMs that effectively injects domain-specific knowledge while safeguarding inference-time data privacy. |
| Outcome: | The proposed model protects private data while enhancing the model's knowledge. |
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. |
Can Graph Neural Networks Learn Language with Extremely Weak Text Supervision? (2025.acl-long)
Copied to clipboard
| Challenge: | Graph Neural Networks (GNNs) with CLIP pipeline are difficult because of the scarcity of labeled data and text supervision, different levels of downstream tasks, and conceptual gaps between domains. |
| Approach: | They propose a multi-modal prompt learning paradigm to adapt pre-trained GNNs to downstream tasks with weak text supervision. |
| Outcome: | The proposed model can generalize graphs to unseen classes with weak text supervision. |
DCR: Quantifying Data Contamination in LLMs Evaluation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) memorize evaluation data during training, inflating performance metrics and undermining genuine generalization assessment. |
| Approach: | They propose a framework to detect and quantify benchmark data contamination (BDC) by synthesizing contamination scores via a fuzzy inference system. |
| Outcome: | The proposed framework detects and quantifies BDC risk across semantic, informational, data, and label levels. |
RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment (2025.findings-acl)
Copied to clipboard
Zhuoran Jin, Hongbang Yuan, Tianyi Men, Pengfei Cao, Yubo Chen, Jiexin Xu, Huaijun Li, Xiaojian Jiang, Kang Liu, Jun Zhao
| Challenge: | Existing retrieval augmented language models often overlook effective alignment with human preferences. |
| Approach: | They propose a benchmark to evaluate RMs in retrieval augmented language models . they incorporate 18 RAG subsets, six retrievers, and 24 RALMs to increase diversity . |
| Outcome: | The proposed benchmark combines 18 RAG subsets, six retrievers, and 24 RALMs to increase diversity of data sources. |
Compilable Neural Code Generation with Compiler Feedback (2022.findings-acl)
Copied to clipboard
Xin Wang, Yasheng Wang, Yao Wan, Fei Mi, Yitong Li, Pingyi Zhou, Jin Liu, Hao Wu, Xin Jiang, Qun Liu
| Challenge: | Existing deep-learning approaches model code generation as text generation, but few of them account for compilability of the generated programs. |
| Approach: | They propose a three-stage pipeline utilizing compiler feedback for compilable code generation to improve compilability. |
| Outcome: | The proposed pipeline improves compilability of generated programs by combining compiler feedback, language model fine-tuning, and compilable discrimination. |
ATLAS: Orchestrating Heterogeneous Models and Tools for Multi-Domain Complex Reasoning (2026.findings-acl)
Copied to clipboard
Jinyang Wu, Guocheng Zhai, Ruihan Jin, Jiahao Yuan, Yuhao Shen, Shuai Zhang, Zhengqi Wen, Jianhua Tao
| Challenge: | Existing approaches to optimize large language models with external tools are limited. |
| Approach: | They propose a dual-path framework for dynamic tool usage in cross-domain complex reasoning . they exploit empirical priors for domain-specific alignment and RL-based multi-step routing . |
| Outcome: | The proposed framework outperforms closed-source models and existing methods on in-distribution and out-of-distortion tasks. |
Efficient Prompting for Continual Adaptation to Missing Modalities (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing methods combine various missing cases to train recovery modules or align multimodal features, resulting in suboptimal performance, high computational costs, and catastrophic forgetting. |
| Approach: | They propose a continual multimodal missing modality task that uses prompts to learn modalities . existing methods often aggregate various missing cases to train recovery modules . authors conduct extensive experiments on three public datasets . |
| Outcome: | The proposed method consistently outperforms state-of-the-art methods on three public datasets. |
Examining Temporalities on Stance Detection towards COVID-19 Vaccination (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing studies have highlighted the importance of vaccination as an effective strategy to control the transmission of the COVID-19 virus. |
| Approach: | They evaluate a range of transformer-based models using chronological and random splits of social media data to examine the impact of temporal concept drift on stance detection towards COVID-19 vaccination. |
| Outcome: | The proposed models show that the models performed better with chronological and random splits than with random split models. |
FedID: Federated Interactive Distillation for Large-Scale Pretraining Language Models (2023.emnlp-main)
Copied to clipboard
| Challenge: | federated learning (FL) is widely studied in user-related natural language processing (NLP) but its performance is faded by confirmation bias. |
| Approach: | They propose a decentralized learning paradigm that uses labeled data to rectify local models . they propose federated interactive distillation (FedID) to alleviate communication overhead . |
| Outcome: | The proposed framework achieves the best results in homogeneous and heterogeneously federated scenarios. |
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. |
Unsupervised Morphological Paradigm Completion (2020.acl-main)
Copied to clipboard
| Challenge: | a task of generating morphological paradigms is a challenging unsupervised task for natural language processing systems . acuidados y acciones del idioma es a problem in linguistic annotators. |
| Approach: | They propose a task of unsupervised morphological paradigm completion using raw text and a lemma list. |
| Outcome: | The proposed system outperforms trivial baselines on 14 typologically diverse languages with ease and higher accuracy than minimally supervised systems. |
A Multistage Extraction Pipeline for Long Scanned Financial Documents: An Empirical Study in Industrial KYC Workflows (2026.acl-industry)
Copied to clipboard
| Challenge: | Structured information extraction from long, multilingual scanned financial documents is a core requirement in industrial KYC and compliance workflows. |
| Approach: | They propose a framework for structured information extraction from long, multilingual scanned financial documents . they combine image preprocessing, multilinguistic OCR, hybrid page-level retrieval and VLMs . |
| Outcome: | The proposed pipeline outperforms direct PDF-to-VLM baselines on 120 production KYC documents. |
UMR-Writer: A Web Application for Annotating Uniform Meaning Representations (2021.emnlp-demo)
Copied to clipboard
| Challenge: | Uniform Meaning Representations (UMRs) are graph-based semantic representations that can be used to annotate text. |
| Approach: | They present a web-based application for annotating Uniform Meaning Representations (UMR) they propose to use a graph-based cross-linguistically applicable semantic representation to annotate sentences and documents. |
| Outcome: | The proposed tool is based on a graph-based, cross-linguistically applicable semantic representation that can be used to annotate text. |
NLP for Social Good: A Survey and Outlook of Challenges, Opportunities and Responsible Deployment (2026.eacl-long)
Copied to clipboard
Antonia Karamolegkou, Angana Borah, Eunjung Cho, Sagnik Ray Choudhury, Martina Galletti, Pranav Gupta, Oana Ignat, Priyanka Kargupta, Neema Kotonya, Hemank Lamba, Sun-Joo Lee, Arushi Mangla, Ishani Mondal, Fatima Zahra Moudakir, Deniz Nazar, Poli Nemkova, Dina Pisarevskaya, Naquee Rizwan, Nazanin Sabri, Keenan Samway, Dominik Stammbach, Anna Steinberg Schulten, David Tomás, Steven R Wilson, Bowen Yi, Jessica H Zhu, Arkaitz Zubiaga, Anders Søgaard, Alexander Fraser, Zhijing Jin, Rada Mihalcea, Joel R. Tetreault, Daryna Dementieva
| Challenge: | This paper surveys work in "NLP for Social Good" across nine domains relevant to global development and risk agendas. |
| Approach: | This paper analyzes work in "NLP for Social Good" across nine domains relevant to global development and risk agendas. |
| Outcome: | The paper analyzes work in "NLP for Social Good" across nine domains relevant to global development and risk agendas. |
Discrete Latent Variable Representations for Low-Resource Text Classification (2020.acl-main)
Copied to clipboard
| Challenge: | Several approaches to learning discrete latent variable models for text are available. |
| Approach: | They compare several approaches to learning discrete latent variable models for text in the case where exact marginalization over these variables is intractable. |
| Outcome: | The learned models outperform the previous best models in low-resource settings while learning significantly more compressed representations. |
From Discourse to Narrative: Knowledge Projection for Event Relation Extraction (2021.acl-long)
Copied to clipboard
| Challenge: | Existing event-centric knowledge graphs rely on explicit connectives to extract relations between events. |
| Approach: | They propose a knowledge projection paradigm for event relation extraction using commonalities between events. |
| Outcome: | The proposed method achieves state-of-the-art performance and extrinsic results verify the extracted event relations. |
Can Medical Vision-Language Pre-training Succeed with Purely Synthetic Data? (2025.findings-acl)
Copied to clipboard
Che Liu, Zhongwei Wan, Haozhe Wang, Yinda Chen, Talha Qaiser, Chen Jin, Nikolay Burlutskiy, Fariba Yousefi, Rossella Arcucci
| Challenge: | Medical Vision-Language Pretraining (MedVLP) models typically require large-scale datasets with paired, high-quality image-text data. |
| Approach: | They propose to generate large-scale synthetic image-text pairs using off-the-shelf generative models . they propose to isolate model and training settings, focusing entirely from the data perspective. |
| Outcome: | The proposed pipeline outperforms models trained on real data by 3.8% on averaged AUC on zero-shot classification tasks. |
IMaT: Unsupervised Text Attribute Transfer via Iterative Matching and Translation (D19-1)
Copied to clipboard
| Challenge: | Existing approaches to rewrite sentences with certain attributes are difficult and often result in poor content-preservation and ungrammaticality. |
| Approach: | They propose a method that uses a sequence-to-sequence model to learn attribute transfer . existing approaches try to explicitly disentangle content and attribute information . |
| Outcome: | The proposed method outperforms complex state-of-the-art systems by a large margin in sentiment modification and formality transfer tasks. |
UNICORN: A Unified Causal Video-Oriented Language-Modeling Framework for Temporal Video-Language Tasks (2024.emnlp-main)
Copied to clipboard
Yuanhao Xiong, Yixin Nie, Haotian Liu, Boxin Wang, Jun Chen, Rong Jin, Cho-Jui Hsieh, Lorenzo Torresani, Jie Lei
| Challenge: | Recent advances in large multimodal models have encouraged the development of large multi-modal models . however, it is unclear how to extend these models to the more complex video domain . |
| Approach: | They propose a visual instruction tuning framework to address temporal video-language tasks . they collect a dataset and fine-tune the framework on instruction-following data . |
| Outcome: | The proposed model can perform better on established temporal video-language tasks without training objectives and intensive pre-training. |
Enhancing High-order Interaction Awareness in LLM-based Recommender Model (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to model user-item interactions do not account for high-order interactions. |
| Approach: | They propose to enhance whole-word embeddings to enhance LLMs’ interpretation of graph-constructed interactions for recommendations without requiring graph pre-training. |
| Outcome: | The proposed model outperforms state-of-the-art methods in direct recommendations. |
TinyAlign: Boosting Lightweight Vision-Language Models by Mitigating Modal Alignment Bottlenecks (2026.findings-acl)
Copied to clipboard
Yuanze Hu, Xinyu Wang, Zhichao Yang, Gen Li, Ye Qiu, Zhaoxin Fan, Yifan Sun, Wenjun wu, Jin Dong, Xiaotie Deng
| Challenge: | Lightweight Vision-Language Models (VLMs) are indispensable for resource-constrained applications. |
| Approach: | They propose a framework that retrieves context from a memory bank to enhance alignment . they propose EMI-based approach to align vision and language models . |
| Outcome: | The proposed framework reduces training loss, accelerates convergence, and enhances task performance with negligible computational overhead. |
Claim-Guided Textual Backdoor Attack for Practical Applications (2025.findings-naacl)
Copied to clipboard
| Challenge: | a novel backdoor attack is based on textual claims to trick models into misbehaving on targeted claims. |
| Approach: | a new backdoor attack is designed to trick models into misbehaving on targeted claims . the code and data will be available at https://github.com/minkyoo9/CGBA . |
| Outcome: | a new backdoor attack exploits the power of textual claims to trick models into misbehaving on claims without affecting their performance on clean data. |
DTELS: Towards Dynamic Granularity of Timeline Summarization (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing timeline summarizations lack flexibility to meet diverse granularity needs . a fine-grained timeline showing the technical details is preferred for news topics . |
| Approach: | They propose a new paradigm to construct adaptive timelines based on user instructions or requirements. |
| Outcome: | The proposed timelines are informative and granularly consistent, but they struggle to generate consistent timelines. |
Capturing Conversational Interaction for Question Answering via Global History Reasoning (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing studies have studied history-dependent reasoning for question answering . utilizing global conversation history for enhancement is gaining interest . |
| Approach: | They propose to establish long-distance dependency among global utterances in multi-turn conversation. |
| Outcome: | The proposed method improves on QuAC by 1%, yielding the F1 score of 73.7%. |
Sycophancy Mitigation Through Reinforcement Learning with Uncertainty-Aware Adaptive Reasoning Trajectories (2025.emnlp-main)
Copied to clipboard
Mohammad Beigi, Ying Shen, Parshin Shojaee, Qifan Wang, Zichao Wang, Chandan K. Reddy, Ming Jin, Lifu Huang
| Challenge: | Existing studies show that large language models inadvertently foster sycophancy . scophancies are a tendency of models to blindly conform to user preferences without critical reasoning or self-reflection. |
| Approach: | They propose a method to reduce sycophancy by combining uncertainty-aware Monte Carlo tree search and progress-based reinforcement learning. |
| Outcome: | The proposed model outperforms baseline models in effectively reducing sycophancy while maintaining performance on out-of-distribution inputs. |
Dynamic Low-rank Estimation for Transformer-based Language Models (2023.findings-emnlp)
Copied to clipboard
| Challenge: | RankDyna is a matrix decomposition method that can be used to compress Transformer-based language models. |
| Approach: | They propose a matrix decomposition method that enables dynamic rank resource allocation . they say it can outperform current SOTA methods under various parameter budget levels . |
| Outcome: | The proposed method outperforms current SOTA methods under various budget levels . the proposed method is more efficient with higher compression rates . |
ReInceptionE: Relation-Aware Inception Network with Joint Local-Global Structural Information for Knowledge Graph Embedding (2020.acl-main)
Copied to clipboard
| Challenge: | Existing knowledge graph embedding methods are limited in their expressiveness and lack structural information in the embeddable space. |
| Approach: | They propose to use a relation-aware network to learn query embedding . they first explore the Inception network to further increase interactions between head and relation embedders . |
| Outcome: | The proposed network improves performance on WN18RR and FB15k-237 datasets. |
Lifelong Pretraining: Continually Adapting Language Models to Emerging Corpora (2022.naacl-main)
Copied to clipboard
| Challenge: | Pretrained language models are typically learned over a large, static corpus and fine-tuned for various downstream tasks. |
| Approach: | They propose to continuously update a pretrained language model to adapt to emerging data and to keep track of the model's performance. |
| Outcome: | The proposed model can adapt to new corpora while retaining knowledge in earlier domains. |
Automatic Bug Detection in LLM-Powered Text-Based Games Using LLMs (2024.findings-acl)
Copied to clipboard
| Challenge: | Advancements in large language models (LLMs) are revolutionizing interactive game design, but they may exhibit flaws such as hallucinations, forgetfulness, or misinterpretation of prompts. |
| Approach: | They propose a method for automatically identifying LLM bugs from player game logs . their method surpasses unstructured bug-catching methods and fills the gap . |
| Outcome: | The proposed method surpasses unstructured bug-catching methods and fills the gap in detection of logical and design flaws. |
Towards Explainable Diagnosis: A Self-learned Explanatory Knowledge Base Approach (2026.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have great potential to facilitate explainable diagnosis, but their effectiveness is often constrained by insufficient diagnostic expertise. |
| Approach: | They propose a unified LLM-based framework for faithful and explainable diagnosis that builds a high-quality diagnostic knowledge base through a record-driven explanation learning paradigm. |
| Outcome: | The proposed framework outperforms baselines on the DiReCT and JAMA benchmarks and improves the explanation completeness metric from 64.5% to 76.9% over the best existing methods. |
Empowering GUI Agents via Autonomous Experience Exploration and Hindsight Experience Utilization for Task Planning (2026.acl-long)
Copied to clipboard
| Challenge: | Multimodal web agents are cost-efficient and privacy-preserving, but suffer from weak planning and limited cross-website generalization. |
| Approach: | They propose a method which autonomously explores environments to discover experiences and utilizes hindsight experience to synthesize strictly aligned, high-level training data. |
| Outcome: | The proposed method outperforms Qwen2.5-VL-32B model on real-world benchmarks and demonstrates that mastering low-level atomic skills does not guarantee high-level planning competence. |
Domain-Adaptive Pretraining Methods for Dialogue Understanding (2021.acl-short)
Copied to clipboard
| Challenge: | Recent advances in pretraining methods have achieved promising results on NLP tasks . however, it is unclear which pretraining objective is the most effective for each downstream task . |
| Approach: | They evaluate the effectiveness of domain-adaptive pretraining objectives on downstream tasks . they use open-domain data to pretrain language models like BERT and SpanBERT . |
| Outcome: | The proposed model improves on two dialogue understanding tasks with domain-adaptive pretraining objectives. |
Towards Multi-Relational Multi-Hop Reasoning over Dense Temporal Knowledge Graphs (2024.findings-acl)
Copied to clipboard
| Challenge: | Temporal knowledge graph reasoning is a crucial task for answering time-dependent questions within a knowledge graph (KG). |
| Approach: | They propose a temporal KG reasoning benchmark with over 200k entities and 960k questions that facilitate complex, multi-relational and multi-hop reasoning. |
| Outcome: | The proposed model is able to conduct pattern-aware and time-sensitive reasoning across temporal KGs and is scalable to a wide range of data conditions. |
Using a Human-AI Teaming Approach to Create and Curate Scientific Datasets with the SciLire System (2026.eacl-demo)
Copied to clipboard
Necva Bölücü, Jessica Irons, Changhyun Lee, Brian Jin, Maciej Rybinski, Huichen Yang, Andreas Duenser, Stephen Wan
| Challenge: | rapid growth of scientific literature has made manual extraction of structured knowledge increasingly impractical. |
| Approach: | They propose a system for creating datasets from scientific literature that integrates human-AI teaming principles and iterative workflows. |
| Outcome: | The proposed system improves extraction fidelity and facilitates efficient dataset creation. |
Towards Neural Speaker Modeling in Multi-Party Conversation: The Task, Dataset, and Models (L18-1)
Copied to clipboard
| Challenge: | Existing methods for speaker modeling are based on hand-crafted statistics and ad hoc to a certain application. |
| Approach: | They propose to use speaker classification as a surrogate task for general speaker modeling and collect massive data to facilitate research in this direction. |
| Outcome: | The proposed models outperform the existing models and are feasible with speaker identity information. |
VisKoP: Visual Knowledge oriented Programming for Interactive Knowledge Base Question Answering (2023.acl-demo)
Copied to clipboard
Zijun Yao, Yuanyong Chen, Xin Lv, Shulin Cao, Amy Xin, Jifan Yu, Hailong Jin, Jianjun Xu, Peng Zhang, Lei Hou, Juanzi Li
| Challenge: | Existing knowledge base question answering systems that parse natural language questions into knowledge oriented program language (KoPL) . |
| Approach: | They propose a knowledge base question answering system that integrates human into the loop to edit and debug queries. |
| Outcome: | The proposed system can debug and edit knowledge base questions on a million-entity-level . it provides auto-completion for its knowledge base schema and user interaction can fix a large portion of wrong KoPL programs to acquire the correct answer. |
What Makes an Ideal Quote? Recommending “Unexpected yet Rational” Quotations via Novelty (2026.acl-long)
Copied to clipboard
| Challenge: | Prior systems focus on topical relevance and overlook what makes quotes memorable. |
| Approach: | They propose a system that maps quotations and contexts into deep-meaning labels for label-enhanced retrieval. |
| Outcome: | The proposed system can recommend quotations that are contextually novel while semantically coherent. |
Dimensions of Online Conflict: Towards Modeling Agonism (2023.findings-emnlp)
Copied to clipboard
Matt Canute, Mali Jin, Hannah Holtzclaw, Alberto Lusoli, Philippa Adams, Mugdha Pandya, Maite Taboada, Diana Maynard, Wendy Hui Kyong Chun
| Challenge: | agonism fosters robust discussions, but hateful antagonism undermines constructive dialogue . a new study analyzes Twitter conversations to identify different dimensions of conflict . |
| Approach: | They annotated Twitter conversations related to trending controversial topics to model conflict on a richly annotized dataset. |
| Outcome: | The proposed model can help to moderate online conflicts and improve content monetization. |
AMR-To-Text Generation with Graph Transformer (2020.tacl-1)
Copied to clipboard
| Challenge: | Abstract meaning representation (AMR)-to-text generation is challenging task for natural language processing. |
| Approach: | They propose a graph-to-sequence model that directly encodes AMR graphs and learns node representations. |
| Outcome: | The proposed model outperforms the current state-of-the-art neural approach by 1.5 BLEU points on LDC2015E86 and 4.8 BLUE points on the LDC2017T10 and achieves new state- of-the art performance. |
TabDSR: Decompose, Sanitize, and Reason for Complex Numerical Reasoning in Tabular Data (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models often underperform due to complex queries, noisy data, and limited numerical capabilities. |
| Approach: | They propose a framework that integrates seamlessly with mainstream LLMs to improve tabular reasoning. |
| Outcome: | The proposed framework outperforms existing methods in state-of-the-art analysis. |
Task-Level Thinking Steps Help Large Language Models for Challenging Classification Task (2023.emnlp-main)
Copied to clipboard
| Challenge: | Experimental results prove the superiority of our proposed method on challenging classification tasks. |
| Approach: | They propose a task-level thinking step that eliminates bias introduced by demonstrations . they propose 'progressive revision framework' which can improve the thinking steps by correcting hard demonstrations. |
| Outcome: | The proposed method achieves best performance on three kinds of classification tasks in zero-shot and few-shot settings. |
AGRec: Adapting Autoregressive Decoders with Graph Reasoning for LLM-based Sequential Recommendation (2025.findings-acl)
Copied to clipboard
| Challenge: | Autoregressive decoders in large language models excel at capturing sequential behaviors for generative recommendations, but they lack graph-structured user-item interactions, which are widely recognized as beneficial. |
| Approach: | They propose a novel algorithm that adapts LLMs’ decoders with graph reasoning for recommendation by augmenting the decoding logits with an auxiliary GNN model to optimize token generation. |
| Outcome: | The proposed model outperforms state-of-the-art models in sequential recommendations. |
DeCoRe: Decoding by Contrasting Retrieval Heads to Mitigate Hallucinations (2025.findings-emnlp)
Copied to clipboard
Aryo Pradipta Gema, Chen Jin, Ahmed Abdulaal, Tom Diethe, Philip Alexander Teare, Beatrice Alex, Pasquale Minervini, Amrutha Saseendran
| Challenge: | Large Language Models often produce unfaithful or factually incorrect outputs . masking retrieval heads can induce hallucinations, but decoding by contrast can reduce hallucinosity . |
| Approach: | They propose a training-free decoding strategy that contrasts the outputs of the base LLM and the masked LLM. |
| Outcome: | The proposed decoding strategy reduces hallucinations by contrasting the outputs of the base and masked LLMs. |
InstructoR: Instructing Unsupervised Conversational Dense Retrieval with Large Language Models (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for conversational retrieval only fine-tune on limited supervised data, making it difficult for the retriever to fully grasp the entire conversation. |
| Approach: | They propose a method to instruct unsupervised conversational dense retrieval with large language models (LLMs) they use supervised data to discover the user's query intent from the conversation context . |
| Outcome: | The proposed method can bring significant improvements across various ad-hoc retrievers, surpassing the current state-of-the-art method. |
HypMix: Hyperbolic Interpolative Data Augmentation (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for data augmentation involve performing mathematical operations over the raw input samples or their latent states representations, but these operations are performed in the Euclidean space, simplifying these representations and resulting in noisy interpolations. |
| Approach: | They propose a model-, data-, and modality-agnostic interpolative data augmentation technique operating in the hyperbolic space that captures the complex geometry of input and hidden state hierarchies better than its contemporaries. |
| Outcome: | The proposed technique outperforms state-of-the-art methods on benchmark and low resource datasets across speech, text, and vision modalities. |
Synthesizing Post-Training Data for LLMs through Multi-Agent Simulation (2025.acl-long)
Copied to clipboard
Shuo Tang, Xianghe Pang, Zexi Liu, Bohan Tang, Rui Ye, Tian Jin, Xiaowen Dong, Yanfeng Wang, Siheng Chen
| Challenge: | Extensive experiments demonstrate that our framework effectively generates both general and domain-specific data. |
| Approach: | They propose a multi-agent simulator that automatically generates diverse text-based scenarios, capturing a wide range of real-world human needs. |
| Outcome: | Experiments show that the proposed model outperforms Meta’s Llama-3-8B-Instruct model on AlpacaEval 2 and Arena-Hard benchmarks with just 20K instruction-response pairs. |
CausalNLP Tutorial: An Introduction to Causality for Natural Language Processing (2022.emnlp-tutorials)
Copied to clipboard
| Challenge: | Establishing causal relationships is a fundamental goal of scientific research . lack of clear definitions, notations, benchmark datasets, and challenges remains . |
| Approach: | They introduce the fundamentals of causal discovery and causal effect estimation to the natural language processing audience and provide an overview of causal perspectives to NLP problems. |
| Outcome: | This tutorial introduces the fundamentals of causal discovery and causal effect estimation to the natural language processing audience and provides an overview of causal perspectives to NLP problems. |
DarkBERT: A Language Model for the Dark Side of the Internet (2023.acl-long)
Copied to clipboard
| Challenge: | Recent research suggests that there are clear differences in the language used in the Dark Web compared to that of the Surface Web. |
| Approach: | They propose a language model that is pretrained on Dark Web data to combat extreme lexical diversity. |
| Outcome: | The proposed model outperforms existing models and may be useful for future research on the Dark Web. |
Alignment Precedes Fusion: Open-Vocabulary Named Entity Recognition as Context-Type Semantic Matching (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Continual learning and zero-shot learning approaches have not been adopted to scale to novel-emerging types. |
| Approach: | They propose a method to recognize entities in novel types by their textual names or descriptions. |
| Outcome: | The proposed method outperforms the state-of-the-art methods on three challenging OVNER benchmarks by 9.7%, 9.5%, and 1.8% F1-score of novel types. |
AMQ: Enabling AutoML for Mixed-precision Weight-Only Quantization of Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Weight-only quantization is a powerful optimization technique for large language models . pushing below 4 bits often leads to substantial accuracy degradation due to increased quantization error. |
| Approach: | They propose a framework that assigns layer-wise quantization bit-widths to optimize model quality and memory usage. |
| Outcome: | The proposed framework can optimize for large language models under memory constraints. |
LogicPoison: Logical Attacks on Graph Retrieval-Augmented Generation (2026.acl-long)
Copied to clipboard
Yilin Xiao, Jin Chen, Qinggang Zhang, Yujing Zhang, Chuang Zhou, Longhao Yang, Lingfei Ren, Xin Yang, Xiao Huang
| Challenge: | Graph-based Retrieval-Augmented Generation (GraphRAG) enhances the reasoning capabilities of Large Language Models (LLMs) however, traditional RAG attacks are difficult to pose an effective threat to GraphRAg systems. |
| Approach: | They propose a novel attack framework that targets logical reasoning rather than injecting false contents into GraphRAG systems by grounding their responses in structured knowledge graphs. |
| Outcome: | The proposed framework outperforms state-of-the-art attacks on GraphRAG systems in both effectiveness and stealth. |
VulAgent: Hypothesis-Validation Driven Multi-Agent Architecture for Vulnerability Detection (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent reports indicate that software vulnerabilities caused by insecure coding practices remain a major security threat. |
| Approach: | They propose a multi-agent vulnerability detection framework based on hypothesis validation . they use multi-view analyzers to localize and localize security-sensitive operations . |
| Outcome: | The proposed framework reduces false positives and increases accuracy by 6.6 percentage points on PrimeVul and SVEN. |
SAE-SSV: Supervised Steering in Sparse Representation Spaces for Reliable Control of Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) have impressive capabilities in natural language understanding and generation, but controlling their behavior remains a challenge. |
| Approach: | They propose a supervised steering approach that operates in sparse, interpretable representation spaces. |
| Outcome: | The proposed approach achieves higher success rates with minimal degradation in generation quality compared to existing methods. |
InSerter: Speech Instruction Following with Unsupervised Interleaved Pre-training (2025.acl-long)
Copied to clipboard
Dingdong Wang, Jin Xu, Ruihang Chu, Zhifang Guo, Xiong Wang, Jincenzi Wu, Dongchao Yang, Shengpeng Ji, Junyang Lin
| Challenge: | Recent advances in speech large language models exhibit suboptimal performance in adhering to speech instructions. |
| Approach: | They propose a method to pre-train large-scale unsupervised speech-text sequences . they use text-to-speech conversion to generate textual continuations corresponding to provided speech segments . |
| Outcome: | The proposed model achieves superior or competitive results across diverse speech processing tasks. |
DMix: Adaptive Distance-aware Interpolative Mixup (2022.acl-short)
Copied to clipboard
| Challenge: | Interpolation-based regularisation methods such as Mixup have shown to be effective for various tasks and modalities. |
| Approach: | They propose an adaptive distance-aware interpolative Mixup that selects samples based on their diversity in the embedding space. |
| Outcome: | The proposed method achieves state-of-the-art on sentence classification over existing methods on 8 benchmark datasets across English, Arabic, Turkish, and Hindi languages while achieving benchmark F1 scores in 3 times less number of iterations. |
MedEthicEval: Evaluating Large Language Models Based on Chinese Medical Ethics (2025.naacl-industry)
Copied to clipboard
| Challenge: | Large language models (LLMs) have been used in clinical decision support, medical education and patient communication. |
| Approach: | They propose a benchmark to evaluate large language models in the domain of medical ethics and assess their grasp of medical ethical principles and their application across diverse scenarios. |
| Outcome: | The proposed framework assesses the models’ grasp of medical ethics principles and their ability to apply them across diverse scenarios. |
Neuralizing Regular Expressions for Slot Filling (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to integrate neural networks and symbolic rules have their merits and weaknesses. |
| Approach: | They propose to integrate regular expressions into neural networks for a slot filling task . they use finite-state transducers to convert regular expression into a neural network . their model has superior zero-shot and few-shot performance . |
| Outcome: | The proposed model outperforms rules in zero-shot and few-shot scenarios and is competitive when training data is available. |
Learning Query Adaptive Anchor Representation for Inductive Relation Prediction (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to infer the missing links between entities are limited to the transductive setting . Query Adaptive Anchor Representation (QAAR) model is based on entity-independent features . |
| Approach: | They propose a query adaptive anchor representation model which extracts one opening subgraph and performs reasoning by one time for all candidate triples. |
| Outcome: | The proposed model outperforms state-of-the-art models in relation prediction task. |
CARE: A Clue-guided Assistant for CSRs to Read User Manuals (2024.acl-long)
Copied to clipboard
| Challenge: | Current solutions don't fit the online custom service scenarios well due to the lack of attention to user questions and possible responses. |
| Approach: | They propose to build a clue-guided assistant for customer service representations (CSRs) that can provide accurate responses and explicitly show explainable paths about how to arrive at these responses. |
| Outcome: | The proposed assistant can reduce CSRs' reading burden and keep high service quality, in particular with >35% decrease in time spent and keeping a >0.75 ICC score. |
Entropy-Based Vocabulary Substitution for Incremental Learning in Multilingual Neural Machine Translation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to update a multilingual model with new language pairs are expensive and time-consuming. |
| Approach: | They propose an entropy-based vocabulary substitution method that walks through new language pairs for incremental learning while remaining the size of the original vocabulary. |
| Outcome: | The proposed method achieves better performance and saves excess overhead in a multilingual machine translation task. |
EmojiPrompt: Generative Prompt Obfuscation for Privacy-Preserving Communication with Cloud-based LLMs (2025.naacl-long)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models (LLMs) have substantially expanded their applicability across diverse fields, such as personalized recommendations, health report analysis, and financial decision-making. |
| Approach: | They propose a generative transformation paradigm that obfuscates user data with linguistic and non-linguistic elements before submitting it to cloud-based LLMs. |
| Outcome: | The proposed paradigm obfuscates user private data while maintaining performance compared to the unobflated version. |
Movie101v2: Improved Movie Narration Benchmark (2025.acl-long)
Copied to clipboard
| Challenge: | Automatic movie narration aims to generate video-aligned plot descriptions to assist visually impaired audiences. |
| Approach: | They propose to break down the ultimate goal of automatic movie narration into three stages . they propose a large-scale, bilingual dataset with enhanced data quality . |
| Outcome: | The proposed dataset breaks down the goal of automatic movie narration into three stages . achieving applicable movie narration is a fascinating goal that requires significant research . |
Enhanced Coherence-Aware Network with Hierarchical Disentanglement for Aspect-Category Sentiment Analysis (2024.lrec-main)
Copied to clipboard
| Challenge: | Aspect-category-based sentiment analysis (ACSA) is a popular approach for identifying aspect categories and predicting their sentiments. |
| Approach: | They propose an enhanced coherence-aware network with hierarchical disentanglement (ECAN) to capture contexts across the whole review and to help the implicit aspect and sentiment identification. |
| Outcome: | The proposed network decouples multiple aspects and sentiment features and achieves state-of-the-art (SOTA) performance. |
Hi-ZFO: Hierarchical Zeroth- and First-Order LLM Fine-Tuning via Importance-Guided Tensor Selection (2026.findings-acl)
Copied to clipboard
| Challenge: | generative tasks require a high degree of exploratory capacity, but zeroth-order methods suffer from slow convergence . generative task-specific methods tend to converge toward local minima, causing noise and inefficient estimation . |
| Approach: | They propose a framework that synergizes FO precision with exploratory capability of ZO estimation. |
| Outcome: | The proposed framework synergizes precision of FO gradients with exploratory capability of ZO estimation. |
Align-to-Distill: Trainable Attention Alignment for Knowledge Distillation in Neural Machine Translation (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing knowledge distillation approaches to NMT often rely on heuristics when deciding which teacher layers to distill from. |
| Approach: | They propose an approach to align student attention heads with their teacher counterparts by heuristics to solve a feature mapping problem. |
| Outcome: | The proposed strategy shows gains of +3.61 and +0.63 BLEU points for WMT-2022 DeDsb and WMT-2014 EnDe compared to baselines. |
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. |
Taming the Real-world Complexities in CPT E/M Coding with Large Language Models (2025.emnlp-industry)
Copied to clipboard
Islam Nassar, Yang Lin, Yuan Jin, Rongxin Zhu, Chang Wei Tan, Zenan Zhai, Nitika Mathur, Thanh Tien Vu, Xu Zhong, Long Duong, Yuan-Fang Li
| Challenge: | Evaluation and Management (E/M) coding is performed by physicians and trained human coders who review clinical encounter notes and electronic health record data to assign appropriate codes. |
| Approach: | They propose a framework that automates evaluation and management coding tasks using the Current Procedural Terminology (CPT) taxonomy. |
| Outcome: | The proposed framework achieves an increase in coding accuracy of more than 36% over a commercial CPT E/M coding system and almost 5% over our strongest single-prompt baseline. |
GraphIE: A Graph-Based Framework for Information Extraction (N19-1)
Copied to clipboard
| Challenge: | Most modern Information Extraction (IE) systems are implemented as sequential taggers and model local dependencies. |
| Approach: | They propose a framework that operates over a graph representing a broad set of dependencies between textual units. |
| Outcome: | The proposed framework outperforms the state-of-the-art sequence tagging model on three different tasks. |
ChemActor: Enhancing Automated Extraction of Chemical Synthesis Actions with LLM-Generated Data (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for extracting chemical procedures from literature are insufficient and low-quality due to the inherent ambiguity of chemical language and the high cost of human annotation. |
| Approach: | They propose a fully fine-tuned large language model (LLM) as a chemical executor to convert between unstructured experimental procedures and structured action sequences. |
| Outcome: | The proposed model outperforms the baseline model on R2D and D2A tasks by 10%. |
Establishing Trustworthy LLM Evaluation via Shortcut Neuron Analysis (2025.acl-long)
Copied to clipboard
| Challenge: | Recent studies have focused on building dynamic benchmarks to address data contamination issues. |
| Approach: | They propose a method for identifying shortcut neurons through comparative and causal analysis to suppress shortcut neurons. |
| Outcome: | The proposed method overestimates contaminated models and is highly generalizable across benchmarks and hyperparameter settings. |
MedCite: Can Language Models Generate Verifiable Text for Medicine? (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing LLM-based medical question answering systems lack citation generation and evaluation capabilities, raising concerns about their adoption in practice. |
| Approach: | They propose a framework that facilitates the design and evaluation of LLM citations for medical tasks and a retrieval-citation method that generates high-quality citation. |
| Outcome: | The proposed method achieves superior citation precision and recall improvements compared to strong baseline methods and correlates well with annotation results from professional experts. |
Conflict-Aware Memory for Embodied Agents: Enhancing Vector Data Quality via Detection Rules (2026.acl-long)
Copied to clipboard
| Challenge: | Embodied agents have successfully leveraged large language models (LLMs) to better transform human instructions and images into executable task plans. |
| Approach: | They propose Conflict Detection Rules to identify and manage data quality issues in vector knowledge bases and correct the index structure. |
| Outcome: | Experimental results show that planners with Conflict Detection Rules exceed the basic LLM planner by 15.25% and 14.25% in grammatical accuracy (GA) and interpretation accuracy (IA) on average. |
Translating Hanja Historical Documents to Contemporary Korean and English (2022.findings-emnlp)
Copied to clipboard
| Challenge: | The Annals of Joseon Dynasty contain the daily records of the Kings of Joseont, the 500-year kingdom preceding the modern nation of Korea. |
| Approach: | They propose a neural machine translation model that translates historical documents written in Hanja to more easily understandable Korean and to English. |
| Outcome: | The proposed model outperforms baseline models in terms of BLEU scores for both contemporary Korean and English translations. |
The Vault: A Comprehensive Multilingual Dataset for Advancing Code Understanding and Generation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Open-source dataset of code-text pairs for training large language models to understand code is outperforms other datasets for code generation and understanding tasks. |
| Approach: | They propose to extract high-quality code-text pairs from a dataset of 43 million pairs . they use rules and deep learning to ensure that the code-sampled samples contain high-quality pairs a . |
| Outcome: | The Vault dataset outperforms existing models on common coding tasks . authors hope the results will propel AI research and software development forward . |
Revealing Hidden Mechanisms of Cross-Country Content Moderation with Natural Language Processing (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing knowledge on how and why NLP methods make content moderation decisions is limited . authors examine how and when to use LLMs in content modeation . |
| Approach: | They use Shapley values and LLM-guided explanations to reverse-engineer content moderation decisions across countries. |
| Outcome: | The proposed methods show that they reverse-engineer content moderation decisions across countries and over time. |
GraphLoRA: Structure-Aware Low-Rank Adaptation for Large Language Model Recommendation (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for translating collaborative information into textual prompts or injecting pre-trained embeddings into the LLM treat structural information as static input and fail to capture high-order relational dependencies. |
| Approach: | They propose a framework that generalizes low-rank adaptation from independent to structure-aware propagation by embedding a trainable graph message-passing network within the low-ranked adaptation pathway. |
| Outcome: | Experiments on multiple benchmarks show that GraphLoRA outperforms state-of-the-art recommendation methods and achieves superior generalization. |
MCS-Bench: A Comprehensive Benchmark for Evaluating Multimodal Large Language Models in Chinese Classical Studies (2025.acl-long)
Copied to clipboard
| Challenge: | Multimodal Large Language Models (MLLMs) have advanced visual and language understanding, but their potential in Chinese Classical Studies (CCS) remains underexplored due to the lack of specialized benchmarks. |
| Approach: | They propose to develop a multimodal benchmark specifically designed for Chinese Classical Studies across multiple subdomains to bridge this gap. |
| Outcome: | The proposed benchmark spans seven core subdomains with a total of 45 meticulously designed tasks. |
Dynamics of Cognitive Heterogeneity: Investigating Behavioral Biases in Multi-Stage Supply Chains with LLM-Based Simulation (2026.acl-long)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models (LLMs) allow repeatable experiments in which individual characteristics can be precisely defined. |
| Approach: | They propose a scalable experimental paradigm using Large Language Models to simulate multi-stage supply chain dynamics. |
| Outcome: | The proposed model systematically replicates and validates the results of a behavioral simulation on agents in multi-stage supply chain dynamics. |
Rethinking the Role of LLMs for Document-level Relation Extraction: a Refiner with Task Distribution and Probability Fusion (2025.naacl-long)
Copied to clipboard
| Challenge: | Document-level relation extraction (DocRE) provides a broad context for extracting relations for entities. |
| Approach: | They propose a method that utilizes LLMs as a refiner and task distribution and probability fusion to refine LLM-based relation extraction methods. |
| Outcome: | The proposed method outperforms existing LLM-based methods without fine-tuning by 25.2% F1. |
AICA-Bench: Holistically Examining the Capabilities of VLMs in Affective Image Content Analysis (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent studies have focused on factual correctness, semantic grounding, visual reasoning, or multimodal large language models. |
| Approach: | They propose a benchmark to assess AICA, which integrates perception, reasoning, and generation into a unified framework. |
| Outcome: | The proposed framework corrects intensity errors and significantly enhances descriptive depth. |
Rectifying the Emotional Flow: Aligning Priors and Dynamic Guidance for High-Arousal Text-to-Speech (2026.acl-long)
Copied to clipboard
| Challenge: | Existing systems suffer from linguistic collapse when pursuing high intensity or fail to meet target emotional levels. |
| Approach: | They propose an inference framework that introduces a neutral prosody bias and a uniform Classifier-Free Guidance that distorts the acoustic manifold, leading to artifacts. |
| Outcome: | The proposed framework achieves superior linguistic accuracy and expressiveness without model retraining. |
SEAG: Structure-Aware Event Causality Generation (2023.findings-acl)
Copied to clipboard
Zhengwei Tao, Zhi Jin, Xiaoying Bai, Haiyan Zhao, Chengfeng Dou, Yongqiang Zhao, Fang Wang, Chongyang Tao
| Challenge: | Current methods for extracting event causality are limited by the lack of cross-task dependencies and may cause error propagation. |
| Approach: | They propose an approach for Structure-Aware Event Causality Generation (SEAG) they generate the ECG structure using a pre-trained language model and perform structural discriminative training alongside auto-regressive generation. |
| Outcome: | The proposed method is effective in extracting event causality from text. |
Residual Learning of Neural Text Generation with n-gram Language Model (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Experimental results show that n-gram models can achieve satisfactory performance on a large proportion of testing cases. |
| Approach: | They propose to learn a neural LM that fits the residual between an n-gram LM and the real-data distribution. |
| Outcome: | The proposed model achieves additional performance gains over popular standalone models on three typical language tasks. |
Evaluating Structure-Aware Retrieval and Safety in Statute-Centric Legal QA (2026.acl-long)
Copied to clipboard
Kyubyung Chae, Jewon Yeom, Jeongjae Park, Seunghyun Bae, Ijun Jang, Hyunbin Jin, Jinkwan Jang, Taesup Kim
| Challenge: | Legal QA benchmarks focus on case law, overlooking statute-centric regulatory reasoning . relevant evidence is distributed across hierarchically linked documents, creating statutory retrieval gap . |
| Approach: | They propose a structure- and safety-aware benchmark for statute-centric legal QA . the benchmark assesses whether models can retrieve hierarchically fragmented evidence . |
| Outcome: | The proposed benchmark evaluates whether models can retrieve hierarchically fragmented evidence and safely abstain when statutory context is insufficient. |
Challenges in Context-Aware Neural Machine Translation (2023.emnlp-main)
Copied to clipboard
| Challenge: | despite well-reasoned intuitions, most context-aware neural machine translation models show only modest improvements over sentence-level systems. |
| Approach: | They propose a more realistic setting for document-level translation called paragraph-to-paragraph (PARA2PARA) they collect a dataset of Chinese-English novels to promote future research . |
| Outcome: | The proposed model improves translation quality across document-level metrics and discourse phenomena. |
COIG-CQIA: Quality is All You Need for Chinese Instruction Fine-tuning (2025.findings-naacl)
Copied to clipboard
Yuelin Bai, Xeron Du, Yiming Liang, Leo Jin, Junting Zhou, Ziqiang Liu, Feiteng Fang, Mingshan Chang, Tianyu Zheng, Xincheng Zhang, Nuo Ma, Zekun Moore Wang, Ruibin Yuan, Haihong Wu, Hongquan Lin, Wenhao Huang, Jiajun Zhang, Chenghua Lin, Jie Fu, Min Yang, Shiwen Ni, Ge Zhang
| Challenge: | Existing datasets for Chinese instruction tuning are not well-aligned with Chinese users’ interaction patterns. |
| Approach: | They propose to use Chinese instruction tuning datasets to improve instruction fine-tuning for Chinese users. |
| Outcome: | The proposed dataset shows that Chinese models achieve competitive performance in diverse benchmarks. |
Video-aided Unsupervised Grammar Induction (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing methods of multi-modal grammar induction focus on grammar inducing from text-image pairs, but videos provide even richer information, such as static objects and actions. |
| Approach: | They propose a video-aided grammar induction model which learns a constituency parser from unlabeled text and its corresponding video. |
| Outcome: | The proposed model outperforms existing systems on three benchmarks. |
RDRec: Rationale Distillation for LLM-based Recommendation (2024.acl-short)
Copied to clipboard
| Challenge: | Existing models that bridge users and items through textual prompts for effective semantic reasoning do not consider the underlying rationales behind interactions, such as user preferences and item attributes. |
| Approach: | They propose a rationale distillation recommender model that learns rationales generated by a larger language model (LM) by leveraging reviews related to users and items. |
| Outcome: | The proposed model achieves state-of-the-art (SOTA) performance in top-N and sequential recommendations. |
Missing Modality Imagination Network for Emotion Recognition with Uncertain Missing Modalities (2021.acl-long)
Copied to clipboard
| Challenge: | Existing multimodal fusion models trained on full-modality samples fail when partial modalities are missing. |
| Approach: | They propose a model to deal with the uncertain missing modality problem by learning robust joint multimodal representations that can predict the representation of any missing modal given available modalities under different missing-modality conditions. |
| Outcome: | The proposed model significantly improves performance under uncertain missing-modality testing conditions and full-modalities ideal testing conditions. |
Spotlight and Shadow: Attention-Guided Dual-Anchor Introspective Decoding for MLLM Hallucination Mitigation (2026.findings-acl)
Copied to clipboard
| Challenge: | Multimodal Large Language Models (MLLMs) excel in tasks ranging from image captioning to complex reasoning. |
| Approach: | They propose a contrastive decoding framework that dynamically calibrates each token generation by mining the model’s internal perceptual discrepancies. |
| Outcome: | The proposed framework mitigates hallucination while enhancing general reasoning capabilities. |
CodeDPO: Aligning Code Models with Self Generated and Verified Source Code (2025.acl-long)
Copied to clipboard
| Challenge: | Existing training methods for code generation do not improve code correctness and efficiency. |
| Approach: | They propose a framework that integrates preference learning into code generation to improve code correctness and efficiency. |
| Outcome: | The proposed framework improves code correctness and efficiency by integrating preference learning into code generation. |
A Progressive Model to Enable Continual Learning for Semantic Slot Filling (D19-1)
Copied to clipboard
| Challenge: | Existing approaches to slot filling training on large scale data are inefficient and require multiple trainings. |
| Approach: | They propose a slot filling model that transfers previously learned knowledge to a small size expanded component and enables it to be fast trained to learn from new data. |
| Outcome: | The proposed model outperforms existing models on two benchmark datasets by 4.24% and 3.03% on the same dataset. |
On Construction of the ASR-oriented Indian English Pronunciation Dictionary (2020.lrec-1)
Copied to clipboard
| Challenge: | Indian English (IE) has distinctive characteristics, especially phonologically, from other varieties of English. |
| Approach: | They build a small IE spontaneous speech corpus and use a linguistically-guided IE pronunciation dictionary to apply it to IE. |
| Outcome: | The proposed system performs better on IE spontaneous speech data than the one trained with CMUdict. |
AIRepr: An Analyst-Inspector Framework for Evaluating Reproducibility of LLMs in Data Science (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models are increasingly used to automate data analysis, but data science tasks often admit multiple statistically valid solutions. |
| Approach: | They propose a framework to evaluate LLM-generated code and assess its reproducibility . they introduce two reproducibility-enhancing prompting strategies and benchmark them against standard prompting . |
| Outcome: | The proposed framework improves reproducibility of large language models . it provides a foundation for transparent, reliable, and efficient human–AI collaboration in data science. |
Harnessing the Power of Large Language Model for Uncertainty Aware Graph Processing (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods for graph processing rely on assumptions about data relations that are inadequate when handling large and complex graph data. |
| Approach: | They propose a large language model enhanced by an uncertainty-aware module to provide a confidence score on the generated graph data. |
| Outcome: | The proposed approach surpasses state-of-the-art algorithms by a substantial margin on ten datasets. |
A Good Neighbor, A Found Treasure: Mining Treasured Neighbors for Knowledge Graph Entity Typing (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to infer missing types for knowledge graphs only leverage one-hop neighbor information of the central entity, ignoring multi-hop neighbors that can provide valuable clues for inference. |
| Approach: | They propose a method to infer missing types for knowledge graph entities by using neighbor information and co-occurrence relations between types. |
| Outcome: | The proposed method significantly outperforms existing state-of-the-art methods on two widely used datasets. |
RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation (2023.emnlp-main)
Copied to clipboard
Fengji Zhang, Bei Chen, Yue Zhang, Jacky Keung, Jin Liu, Daoguang Zan, Yi Mao, Jian-Guang Lou, Weizhu Chen
| Challenge: | RepoCoder is a repository-level code completion framework that utilizes the useful information scattered in files. |
| Approach: | They propose a repository-level code completion framework called RepoCoder . it integrates a similarity-based retriever and a pre-trained code language model . they propose 'repoBench' benchmark to validate the framework's effectiveness . |
| Outcome: | The proposed framework outperforms the vanilla retrieval-augmented code completion approach in the real-world. |
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. |
The Authors Matter: Understanding and Mitigating Implicit Bias in Deep Text Classification (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing studies on text classification have focused on the bias towards the individuals mentioned in the text content. |
| Approach: | They propose a framework to mitigate implicit bias in text classification models based on demographic attributes of authors . they propose to use this framework to train deep text classifiers to make predictions on the right features . |
| Outcome: | The proposed framework outperforms existing models significantly in fairness and performance. |
RedundancyLens: Revealing and Exploiting Visual Token Processing Redundancy for Efficient Decoder-Only MLLMs (2025.findings-acl)
Copied to clipboard
| Challenge: | Current decoder-only architectures achieve higher performance but lower efficiency . cross-attention-based architectures skip visual token computations . |
| Approach: | They propose a training-free framework for analyzing trained MLLMs to investigate redundancy . they propose 'probe-activated Dynamic FFN and Hollow Attention' algorithms for visual token reductions and a layer ranking algorithm for inference acceleration. |
| Outcome: | The proposed framework achieves comparable performance to or better than state-of-the-art methods while remaining compatible with them. |
Foot-In-The-Door: A Multi-turn Jailbreak for LLMs (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are increasingly integrated into real-world applications, requiring a high level of safety and alignment. |
| Approach: | They propose a multi-turn jailbreak method that leverages foot-in-the-door principles to escalate malicious intent of user queries through intermediate bridge prompts and aligns the model’s response by itself to induce toxic responses. |
| Outcome: | The proposed method achieves an average attack success rate of 94% across seven widely used models outperforming existing state-of-the-art methods. |
AgentsCourt: Building Judicial Decision-Making Agents with Court Debate Simulation and Legal Knowledge Augmentation (2024.findings-emnlp)
Copied to clipboard
Zhitao He, Pengfei Cao, Chenhao Wang, Zhuoran Jin, Yubo Chen, Jiexin Xu, Huaijun Li, Kang Liu, Jun Zhao
| Challenge: | Recent advances in deep learning have significantly impacted the legal domain. |
| Approach: | They propose a multi-agent framework for judicial decision-making that simulates the court trial process . they propose 420 Chinese judgment documents to support their framework and build a large-scale legal knowledge base . |
| Outcome: | The proposed framework outperforms existing methods in various aspects, especially in generating legal articles. |
A New Concept of Knowledge based Question Answering (KBQA) System for Multi-hop Reasoning (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing knowledge based question answering systems are trained based on labeled reasoning paths, which hinder their performance. |
| Approach: | They propose a KBQA system which leverages multiple reasoning paths’ information and only requires labeled answer as supervision. |
| Outcome: | The proposed system can leverage multiple reasoning paths’ information and only requires labeled answer as supervision. |
Bi-level Finetuning with Task-dependent Similarity Structure for Low-resource Training (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to fine tune a large language model in low-resource settings are limited in their expressiveness or rely on task-independent knowledge. |
| Approach: | They propose a framework where all parameters are finetuned with task-dependent information from the training data only. |
| Outcome: | The proposed framework outperforms baseline models on several classification datasets in low-resource scenarios. |
DialogueEIN: Emotion Interaction Network for Dialogue Affective Analysis (2022.coling-1)
Copied to clipboard
| Challenge: | Emotion Recognition in Conversation (ERC) has attracted increasing research attention in recent years. |
| Approach: | They propose to model the emotional interactions between speakers to simulate the emotional inertia, emotional stimulus, global and local emotional evolution in dialogues. |
| Outcome: | The proposed model can achieve superior performance compared to state-of-the-art methods on four ERC benchmark datasets, IEMOCAP, MELD, EmoryNLP and DailyDialog. |
Your Inference Request Will Become a Black Box: Confidential Inference for Cloud-based Large Language Models (2026.acl-long)
Copied to clipboard
Chung-ju Huang, Huiqiang Zhao, Yuanpeng He, Lijian Li, Wenpin Jiao, Zhi Jin, Peixuan Chen, Leye Wang
| Challenge: | Existing approaches fail to ensure privacy, maintain model performance, and preserve computational efficiency simultaneously. |
| Approach: | They propose a confidential inference framework that partitions the LLM pipeline between a client-verified Confidential Virtual Machine (CVM) and the public cloud to protect client data without compromising the cloud’s model intellectual property or inference quality. |
| Outcome: | The proposed framework can defend against state-of-the-art token inference attacks while preserving model privacy, performance, and efficiency. |
Beneficial Reasoning Behaviors in Agentic Search and Effective Training Methods to Obtain Them (2026.findings-acl)
Copied to clipboard
| Challenge: | Agentic search requires large language models to perform multi-step searches to solve complex information needs. |
| Approach: | They propose a training approach that equips agentic search models with reasoning behaviors before reinforcement learning (RL) they compare successful and failed trajectories and propose supervised fine-tuning and standard RL . |
| Outcome: | The proposed approach outperforms direct RL by 37.2% on three web benchmarks and 6.2% on seven multi-hop QA benchmarks. |
TDNN: A Two-stage Deep Neural Network for Prompt-independent Automated Essay Scoring (P18-1)
Copied to clipboard
| Challenge: | Existing automated essay scoring (AES) models rely on rated essays for the target prompt as training data. |
| Approach: | They propose a shallow deep neural network to learn a prompt-dependent rating model using rated essays for non-target prompts as training data. |
| Outcome: | The proposed model improves on the standard ASAP dataset. |
A Survey of Large Models in Sports (2026.findings-acl)
Copied to clipboard
| Challenge: | Increasing interest in sports has led to the rapid advancement of large models, particularly multimodal large language models (MLLMs) . linguistic intelligence is a key component of large-model-driven sports intelligence . |
| Approach: | They propose to establish a foundation for advancing research and practical development of large-model-driven sports intelligence. |
| Outcome: | The proposed model-driven sports intelligence will be able to process and generate sports-related language effectively and process multiple data modalities. |
Selective In-Context Data Augmentation for Intent Detection using Pointwise V-Information (2023.eacl-main)
Copied to clipboard
Yen-Ting Lin, Alexandros Papangelis, Seokhwan Kim, Sungjin Lee, Devamanyu Hazarika, Mahdi Namazifar, Di Jin, Yang Liu, Dilek Hakkani-Tur
| Challenge: | Intent detection is a fundamental element in task-oriented dialogue systems, usually occurring within the Natural Language Understanding component. |
| Approach: | They propose an in-context data augmentation approach that fine-tunes a pre-trained language model and synthesizes new datapoints that correspond to given intents. |
| Outcome: | The proposed method produces training data that achieves state-of-the-art on three challenging intent detection datasets and performs on par with the state- of-the art in full-shot settings. |
Has It All Been Solved? Open NLP Research Questions Not Solved by Large Language Models (2024.lrec-main)
Copied to clipboard
Oana Ignat, Zhijing Jin, Artem Abzaliev, Laura Biester, Santiago Castro, Naihao Deng, Xinyi Gao, Aylin Ece Gunal, Jacky He, Ashkan Kazemi, Muhammad Khalifa, Namho Koh, Andrew Lee, Siyang Liu, Do June Min, Shinka Mori, Joan C. Nwatu, Veronica Perez-Rosas, Siqi Shen, Zekun Wang, Winston Wu, Rada Mihalcea
| Challenge: | Recent advances in large language models have led to misleading public discourse that “it’s all been solved.” |
| Approach: | They identify 14 research areas encompassing 45 research directions that require new research and are not directly solvable by LLMs. |
| Outcome: | The research areas identified are 45 research directions that require new research and are not directly solvable by LLMs. |
Seed Word Selection for Weakly-Supervised Text Classification with Unsupervised Error Estimation (2021.naacl-srw)
Copied to clipboard
| Challenge: | Weakly-supervised text classification aims to induce text classifiers from only a handful of user-provided seed words. |
| Approach: | They propose to use user-provided seed words to induce text classifiers using only a handful of carefully chosen seed words. |
| Outcome: | The proposed method outperforms baseline model using only category name seed words and achieves comparable performance as a counterpart using expert-annotated seed words. |
A Survey of Link Prediction in N-ary Knowledge Graphs (2025.emnlp-main)
Copied to clipboard
Jiyao Wei, Saiping Guan, Da Li, Zhongni Hou, Miao Su, Yucan Guo, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng
| Challenge: | N-ary Knowledge Graphs (NKGs) capture n-ary facts containing more than two entities. |
| Approach: | They present the first comprehensive survey of link prediction in NKGs . they provide an overview of the field and analyze their performance and application scenarios . |
| Outcome: | The proposed methods provide an overview of the field and analyze performance and application scenarios. |
Original or Translated? A Causal Analysis of the Impact of Translationese on Machine Translation Performance (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing work on translationese neglects important factors and conclusions are mostly correlational but not causal. |
| Approach: | They use a dataset where MT training data are also labeled with human translation directions to examine the impact of translationese on machine translation evaluation. |
| Outcome: | The proposed model learns in the same direction as human translation directions. |
Learning to Reason via Self-Iterative Process Feedback for Small Language Models (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods for enhancing SLMs’ reasoning depend on costly external signals, resulting in SLM overly confident with limited supervision signals. |
| Approach: | They propose to fine-tune and align SLMs using positive and negative feedback signals and introduce process supervision for rewards in preference alignment by sampling-based inference simulation and process reward models. |
| Outcome: | The proposed method improves Gemma-2B's performance on GSM8K and MBPP, and out-of-domain generalization capabilities on MMLU_Math and HumanEval. |
PADO: Personality-induced multi-Agents for Detecting OCEAN in human-generated texts (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods for personality detection are limited due to the latent and relative nature of personality and lack of annotated datasets. |
| Approach: | They propose a method that exploits the inherent knowledge of Large Language Models to capture the relative nature of personality traits by comparing contrasting perspectives. |
| Outcome: | The proposed approach exploits the inherent knowledge of Large Language Models to capture the relative nature of personality traits. |
IntentionESC: An Intention-Centered Framework for Enhancing Emotional Support in Dialogue Systems (2025.findings-acl)
Copied to clipboard
| Challenge: | IntentionESC defines the possible intentions of supporters in emotional support conversations, identifies key emotional state aspects for inferring these intentions, and maps them to appropriate support strategies. |
| Approach: | They propose an Intention-centered Emotional Support Conversation framework which defines the possible intentions of supporters in emotional support conversations, identifies key emotional state aspects for inferring intentions, and maps them to appropriate support strategies. |
| Outcome: | The proposed framework defines the possible intentions of supporters in emotional support conversations, identifies key emotional state aspects for inferring these intentions, and maps them to appropriate support strategies. |
LANTERN in the Event Stream: Training-Free Temporal Knowledge Graph Forecasting by Balancing Inertia and Shifts (2026.findings-acl)
Copied to clipboard
| Challenge: | Temporal knowledge graph forecasting (TKGF) uses long-window strengthscores and short-windowed novelty scores to predict missing entities in future queries. |
| Approach: | They propose a training-freeprompting framework that uses two perspectives of history to predict missing entities in future queries. |
| Outcome: | The proposed framework outperforms the state-of-the-art baselineAnRe framework in ICEWS14, ICEW05-15, and GDELT. |
VC4VG: Optimizing Video Captions for Text-to-Video Generation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in text-to-video generation highlight the critical role of high-quality video-text pairs in training models capable of producing coherent and instruction-aligned videos. |
| Approach: | They propose a caption optimization framework tailored to the needs of T2V models. |
| Outcome: | The proposed framework improves video caption quality and video generation performance. |
A Contextual Alignment Enhanced Cross Graph Attention Network for Cross-lingual Entity Alignment (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods for cross-lingual entity alignment ignore useful pre-aligned links between two KGs. |
| Approach: | They propose a novel method that jointly learns embeddings in different KGs by propagating cross-KG information through pre-aligned seed alignments. |
| Outcome: | The proposed method achieves remarkable performance gains on three benchmark cross-lingual entity alignment datasets. |
CARE-STaR: Constraint-aware Self-taught Reasoner (2025.findings-acl)
Copied to clipboard
Zhiliang Li, Bo Tang, Yijun Niu, Beihong Jin, Qiwen Shi, Yuchen Feng, Zhiyu Li, Jie Hu, Mingchuan Yang, Feiyu Xiong
| Challenge: | Recent research on instruction following has demonstrated that LLMs can handle complex instructions. |
| Approach: | They propose to assign constraints to different levels of constraints in instructions . they use chain-of-thought and self-taught reasoner methods to identify constraints . |
| Outcome: | The proposed method outperforms supervised fine-tuning (SFT) on three instruction-following benchmarks. |
AgentMark: Utility-Preserving Behavioral Watermarking for Agents (2026.acl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have improved text generation and reasoning. |
| Approach: | They propose a behavioral watermarking framework that embeds multi-bit identifiers into planning decisions while preserving utility. |
| Outcome: | The proposed framework embeds multi-bit provenance into planning decisions while preserving utility. |
Supporting Medical Relation Extraction via Causality-Pruned Semantic Dependency Forest (2022.coling-1)
Copied to clipboard
| Challenge: | Medical relation extraction (MRE) tasks aims to extract relations between entities in medical literature. |
| Approach: | They propose to combine semantic and syntactic information from medical texts by using causal explanation theory. |
| Outcome: | Empirically, the proposed model outperforms existing methods on benchmark medical datasets. |
Automatic Identification and Classification of Bragging in Social Media (2022.acl-long)
Copied to clipboard
| Challenge: | Bragging is a speech act employed to build a favorable self-image through positive statements about oneself. |
| Approach: | They propose to use tweets annotated for bragging to build a model that can predict bragging with macro F1 up to 72.42 and 35.95 for binary and multi-class bragging classification tasks respectively. |
| Outcome: | The proposed models predict bragging with macro F1 up to 72.42 and 35.95 in binary and multi-class classification tasks respectively. |
Enhancing Knowledge Selection for Grounded Dialogues via Document Semantic Graphs (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing conversation models treat knowledge selection as a sentence ranking problem where each sentence is handled individually, ignoring the internal semantic connection between sentences. |
| Approach: | They propose to automatically convert background knowledge documents into document semantic graphs and perform knowledge selection over such graphs. |
| Outcome: | The proposed model improves on the knowledge selection task and the response generation task on HollE and generalizes on unseen topics in WoW. |
MUG-Eval: A Proxy Evaluation Framework for Multilingual Generation Capabilities in Any Language (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Evaluating text generation capabilities of large language models (LLMs) is challenging, especially for low-resource languages where methods for direct assessment are scarce. |
| Approach: | They propose a framework that transforms existing benchmarks into conversational tasks and measures LLMs’ accuracies on those tasks. |
| Outcome: | The proposed framework correlates strongly with established benchmarks while enabling standardized comparisons across languages and models. |
PIPER: Benchmarking and Prompting Event Reasoning Boundary of LLMs via Debiasing-Distillation Enhanced Tuning (2025.acl-long)
Copied to clipboard
Zhicong Lu, Changyuan Tian, PeiguangLi PeiguangLi, Li Jin, Sirui Wang, Wei Jia, Ying Shen, Guangluan Xu
| Challenge: | Existing studies on Large Language Models (LLMs) have failed to evaluate their performance in event reasoning with a single event relational type or reasoning format. |
| Approach: | They propose a benchmark to evaluate LLMs' event reasoning capability using a single event relational type or reasoning format. |
| Outcome: | The proposed model improves on 10K diverse instruction-tuning demonstrations to alleviate event reasoning-oriented data scarcity. |
Unsupervised Learning of PCFGs with Normalizing Flow (P19-1)
Copied to clipboard
| Challenge: | Existing induction models unable to incorporate semantics and morphology into induction . current models lack a robust model for generating morphologically rich sentences . |
| Approach: | They propose a PCFG inducer which uses context embeddings to generalize over rare, morphologically rich forms. |
| Outcome: | The proposed model produces grammars with state-of-the-art accuracy on a variety of languages. |
DiningBench: A Hierarchical Multi-view Benchmark for Perception and Reasoning in the Dietary Domain (2026.acl-long)
Copied to clipboard
| Challenge: | Existing vision-language models lack fine-grained classification, single-view imagery, and inaccurate metadata. |
| Approach: | They propose a hierarchical, multi-view benchmark to evaluate VLMs across three levels of cognitive complexity. |
| Outcome: | The proposed benchmark evaluates vision-language models across three levels of complexity . it systematically identifies five primary failure modes . the proposed benchmarks are available on https://github.com/meituan/DiningBench. |
Syntax Controlled Knowledge Graph-to-Text Generation with Order and Semantic Consistency (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing knowledge graph-to-text generation methods focus on sequence-to sequence generation, but the linearized order of KG is obtained through a heuristic search without data-driven optimization. |
| Approach: | They propose to generate easy-to-understand sentences from the knowledge graph . they incorporate part-of-speech syntactic tags to constrain the positions to copy words from the KG and employ a semantic context scoring function to evaluate the semantic fitness for each word in its local context. |
| Outcome: | The proposed method achieves state-of-the-art on two datasets, WebNLG and DART, and achieves high consistency. |
Data-Efficiently Learn Large Language Model for Universal 3D Scene Perception (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods for 3D scene understanding are limited to specific downstream tasks, hindering their practicality in real-world applications. |
| Approach: | They propose a 3D visual perceptual ability and advanced reasoning capabilities for 3D scenes by aligning 3D representations into the feature space of advanced LLMs. |
| Outcome: | The proposed system achieves a 82.2% relative score compared with state-of-the-art methods with limited data. |
Learning Semantic Textual Similarity via Topic-informed Discrete Latent Variables (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent discrete latent variable models have received a surge of interest in both NLP and CV . they are comparable to the continuous counterparts in representation learning, but are more interpretable in their predictions. |
| Approach: | They develop a topic-informed discrete latent variable model for semantic textual similarity . they inject the quantized representation into a transformer-based language model . |
| Outcome: | The proposed model outperforms strong baselines in semantic textual similarity tasks. |
Profiler: Black-box AI-generated Text Origin Detection via Context-aware Inference Pattern Analysis (2025.emnlp-main)
Copied to clipboard
Hanxi Guo, Siyuan Cheng, Xiaolong Jin, Zhuo Zhang, Guangyu Shen, Kaiyuan Zhang, Shengwei An, Guanhong Tao, Xiangyu Zhang
| Challenge: | Existing methods to identify the origin of AI-generated texts fail to identify origin due to the high similarity of different LLMs. |
| Approach: | They propose a black-box AI-generated text origin detection method which accurately predicts the origin of an input text by extracting distinct context inference patterns. |
| Outcome: | The proposed method outperforms 10 state-of-the-art baselines and achieves a 25% increase in AUC score on average across natural language and code datasets. |
Who Is Bragging More Online? A Large Scale Analysis of Bragging in Social Media (2024.lrec-main)
Copied to clipboard
| Challenge: | Social media is a natural platform for users to use bragging to gain admiration, respect, attention and followers from their audiences. |
| Approach: | They employ computational sociolinguistics methods to conduct the first large scale study of bragging behavior on Twitter by focusing on its overall prevalence, temporal dynamics and impact of demographic factors. |
| Outcome: | The proposed study shows that the prevalence of bragging decreases over time within the same population of users and younger, more educated and popular users in the U.S. are more likely to brag. |
RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization (2026.acl-long)
Copied to clipboard
Yihong Dong, Xue Jiang, Yongding Tao, Huanyu Liu, Kechi Zhang, Lili Mou, Rongyu Cao, Yingwei MA, Jue Chen, Binhua Li, Zhi Jin, Fei Huang, Yongbin Li, Ge Li
| Challenge: | Reinforcement Learning with Verifiable Reward (RLVR) has significantly advanced the complex reasoning abilities of Large Language Models (LLMs). |
| Approach: | They propose a hybrid-policy optimization approach that synergizes internal exploitation with external data to achieve stronger reasoning capabilities. |
| Outcome: | The proposed approach achieves state-of-the-art performance on six math reasoning benchmarks and superior performance on out-of distribution reasoning tasks. |
Knowledge Transfer in Incremental Learning for Multilingual Neural Machine Translation (2023.acl-long)
Copied to clipboard
| Challenge: | Existing studies focus on overcoming catastrophic forgetting on original language pairs while lacking encouragement to learn new knowledge from incremental learning. |
| Approach: | They propose a knowledge transfer method that can adapt original MNMT models to diverse incremental language pairs by flexibly introducing knowledge from external models into original models, which encourages the models to learn new language pairs. |
| Outcome: | The proposed method outperforms baselines on multiple languages while maintaining performance on original language pairs. |
UniEvent: Unified Generative Model with Multi-Dimensional Prefix for Zero-Shot Event-Relational Reasoning (2023.acl-long)
Copied to clipboard
| Challenge: | Reasoning about events and their relations is an indispensable ability to fulfill various event-centric or common-sense reasoning tasks. |
| Approach: | They propose a multi-task learning framework that organizes event relational reasoning tasks into a coordinate system with multiple axes, representing inter-event relations and reasoning formulations. |
| Outcome: | The proposed framework achieves state-of-the-art or competitive performance on zero-shot and supervised reasoning tasks. |
ForecastQA: A Question Answering Challenge for Event Forecasting with Temporal Text Data (2021.acl-long)
Copied to clipboard
| Challenge: | Existing automated forecasting studies rely on structured data to predict future events. |
| Approach: | They propose a question-answering task that limits access to unstructured text data . they use a crowdsourced dataset to form a restricted-domain, multiple-choice, question-announcement task . |
| Outcome: | The proposed model achieves 61.0% accuracy on the dataset, which still lags behind human performance by about 19%. |
Improving Personalized Sentiment Representation with Knowledge-enhanced and Parameter-efficient Layer Normalization (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing studies on personalized sentiment classification consider document reviews as overall text unit and incorporate backgrounds (i.e., user and product information) Existing methods for personalized sentiment modeling have quadratic costs that increase with text length and heterogeneous mixes of background information and textual information. |
| Approach: | They propose a knowledge-enhanced and parameter-efficient layer normalization model that leverages pretrained checkpoints and background information into transformer structures. |
| Outcome: | The proposed model can be used to improve pretrained language models in document reviews and incorporate background information with parameter-efficient fine-tuning and knowledge injecting. |
Unlocking Anticipatory Text Generation: A Constrained Approach for Large Language Models Decoding (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models have shown a powerful ability for text generation, but undesired behaviors such as toxicity and hallucinations can manifest. |
| Approach: | They propose to formalize text generation as a future-constrained generation problem to minimize undesirable behaviors and enforce faithfulness to instructions. |
| Outcome: | The proposed approach is effective across three tasks, including keyword-constrained generation, toxicity reduction, and factual correctness in question-answering. |
ECO v1: Towards Event-Centric Opinion Mining (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing studies on event-centric opinion mining focus on entity-centric opinions . entity-centered opinions focus on sentimental polarity of events, while event-centered ones focus on content . |
| Approach: | They propose to perform event-centric opinion mining on event-argument structure and expression categorizing theory and benchmark it against a pioneer corpus. |
| Outcome: | The proposed task is feasible and challenging, and the results are beneficial for future studies. |
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. |
RAP: Efficient Text-Video Retrieval with Sparse-and-Correlated Adapter (2024.findings-acl)
Copied to clipboard
Meng Cao, Haoran Tang, Jinfa Huang, Peng Jin, Can Zhang, Ruyang Liu, Long Chen, Xiaodan Liang, Li Yuan, Ge Li
| Challenge: | Text-Video Retrieval (TVR) aims to align relevant video content with natural language queries. |
| Approach: | They propose to conduct efficient text-video Retrieval with a salient-and-correlated AdaPter . they propose a low-rank modulation module to refine per-image features from frozen CLIP backbone . |
| Outcome: | Experiments on four TVR datasets show that the proposed method performs better than other 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). |
GRADE: Generating multi-hop QA and fine-gRAined Difficulty matrix for RAG Evaluation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Current evaluations of RAG systems overlook structural complexity and multi-step reasoning . GRADE model enables fine-grained analysis of Ragging performance . |
| Approach: | They propose a framework that models retrieval difficulty along two orthogonal dimensions . they extract knowledge graphs and augment them through semantic clustering to recover missing links . |
| Outcome: | The proposed framework models retrieval difficulty along two orthogonal dimensions . error rates correlate with the framework, and it validates its diagnostic utility. |
Enhancing LLM Agent Safety via Causal Influence Prompting (2025.findings-acl)
Copied to clipboard
| Challenge: | Experimental results demonstrate that our method effectively enhances safety in code execution and mobile device control tasks. |
| Approach: | They propose a technique that leverages causal influence diagrams to identify and mitigate risks arising from agent decision-making. |
| Outcome: | The proposed method enhances safety in code execution and mobile device control tasks. |
Safety Alignment via Constrained Knowledge Unlearning (2025.acl-long)
Copied to clipboard
Zesheng Shi, Yucheng Zhou, Jing Li, Yuxin Jin, Yu Li, Daojing He, Fangming Liu, Saleh Alharbi, Jun Yu, Min Zhang
| Challenge: | Existing defense mechanisms have not fully deleted harmful knowledge in large language models (LLMs) Existing methods to address safety alignment have not completely deleted harmful information in LLMs. |
| Approach: | They propose a safety alignment strategy that uses scoring neurons to identify useful knowledge in LLMs and pruning the gradients of neurons in U to preserve beneficial information. |
| Outcome: | The proposed method significantly improves model safety while maintaining utility compared to existing methods. |
Conflict and Overlap Classification in Construction Standards Using a Large Language Model (2025.naacl-industry)
Copied to clipboard
Seong-Jin Park, Youn-Gyu Jin, Hyun-Young Moon, Choi Bong-Hyuck, Lee Seung Hwan, Ohjoon Kwon, Kang-Min Kim
| Challenge: | Current manual approaches to analyzing overlapping or conflicting content are time-consuming, costly, and error-prone. |
| Approach: | They propose a large language model that uses a construction domain-adapted large language for the semantic comparison of sentences in construction standards. |
| Outcome: | The proposed framework achieves 97.9% accuracy and 0.907 macro F1-score in classifying sentences from Korean construction standards as overlapping, conflicting, or neutral. |
A Comparative Study of Explicit and Implicit Gender Biases in Large Language Models via Self-evaluation (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing studies on the explicit and implicit biases in large language models (LLMs) focus on either explicit or implicit bias. |
| Approach: | They propose a self-evaluation-based two-stage measurement of explicit and implicit biases within large language models grounded in social psychology. |
| Outcome: | The proposed model is based on two stages of self-evaluation on state-of-the-art LLMs to measure explicit bias toward social targets, where bias is less likely to be self-recognized by the LLM. |
Enhancing the generalization for Intent Classification and Out-of-Domain Detection in SLU (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods for intent classification are expensive to collect and train . evaluators have shown that the ability to detect out-of-domain utterances is limited . |
| Approach: | They propose to train a model with only IND data while supporting both intent classification and OOD detection. |
| Outcome: | The proposed model improves on existing models and strong baselines on four datasets. |
PlugMed: Improving Specificity in Patient-Centered Medical Dialogue Generation using In-Context Learning (2023.findings-emnlp)
Copied to clipboard
| Challenge: | In-context learning is a key task in health conversational assistants, but it is difficult to guarantee the specificity of the responses. |
| Approach: | They propose a plug-and-play medical dialogue system that provides a patient-centered medical interpretation service to users who are less knowledgeable about medical knowledge. |
| Outcome: | The proposed model improves the specificity of the patient-centered medical dialogues by providing them with real dialogues from similar patients as prompts. |
GPTs Are Multilingual Annotators for Sequence Generation Tasks (2024.findings-eacl)
Copied to clipboard
| Challenge: | Existing methods of data annotation are time-consuming and expensive . complexity of crowdsourcing increases when dealing with low-resource languages . |
| Approach: | They propose an autonomous method to gather unlabeled data and label them using large language models. |
| Outcome: | The proposed method is cost-efficient and applicable for low-resource language annotation. |
CORES: Code-Oriented Reasoning for Complex Text-to-SQL and Generalizable TableQA (2026.findings-acl)
Copied to clipboard
Meng Zhang, Ruochun Jin, Yuanxi Peng, Wenjing Yang, Haotian Wang, Liting Sun, Kun Hu, Silin Yang, Zhang Ke-di
| Challenge: | Text-to-SQL models struggle with complex analytical tasks such as generating simple SQL queries. |
| Approach: | They propose a text-to-sql model that leverages Python as a procedural reasoning pivot to enhance both complex SQL generation and tabular reasoning. |
| Outcome: | The proposed model outperforms baseline models on six text-to-SQL benchmarks by 6.44% on average while maintaining good capability on three tableQA benchmarks. |
HTCCN: Temporal Causal Convolutional Networks with Hawkes Process for Extrapolation Reasoning in Temporal Knowledge Graphs (2024.naacl-long)
Copied to clipboard
| Challenge: | Temporal knowledge graphs (TKGs) are powerful tools for storing and modeling dynamic facts. |
| Approach: | They propose a Hawkes process-based temporal causal convolutional network for temporal reasoning under extrapolation settings. |
| Outcome: | The proposed network is based on Hawkes process-based temporal causal convolutional network and captures the temporal evolution of facts. |
Do LLMs Think Fast and Slow? A Causal Study on Sentiment Analysis (2024.findings-emnlp)
Copied to clipboard
Zhiheng Lyu, Zhijing Jin, Fernando Gonzalez Adauto, Rada Mihalcea, Bernhard Schölkopf, Mrinmaya Sachan
| Challenge: | Sentiment analysis aims to identify the sentiment expressed in a piece of text, often in the form of a review. |
| Approach: | They propose a causal discovery task that distinguishes whether a review "primes" the sentiment and a traditional prediction task to model the sentiment using the review as input. |
| Outcome: | The proposed model improves by 32.13 F1 points on a zero-shot five-class SA. |
Scaling Law for Multimodal Large Language Model Supervised Fine-Tuning (2026.acl-long)
Copied to clipboard
YiFan Zhang, Tao Yu, Feng Li, Chaoyou Fu, Yibo Hu, Kun Wang, Qingsong Wen, Zhang Zhang, Liang Wang, Rong Jin
| Challenge: | supervised fine-tuning (SFT) is crucial for multimodal large language models, yet a comprehensive scaling law is lacking . et al.: scaling laws focus on model size, pre-training tokens, and MLLM SFT data volumes . |
| Approach: | They propose two scaling laws to guide optimal model-data configuration . they propose one applicable when training data volumes are well defined by researchers . |
| Outcome: | The proposed scaling laws provide valuable recommendations for optimal resource allocation . they show that the proposed laws are more accurate than existing models . |
SkillBot: Towards Automatic Skill Development via User Demonstration (N19-4)
Copied to clipboard
| Challenge: | Existing industrial PA products require software developers to build new skills via IDE tools. |
| Approach: | They propose a software that automatically develops a natural language understanding engine and implements the action without the need of coding. |
| Outcome: | The proposed system performs well on both benchmark and in-house datasets. |
AutoAugment Is What You Need: Enhancing Rule-based Augmentation Methods in Low-resource Regimes (2024.eacl-srw)
Copied to clipboard
| Challenge: | Existing methods for text data augmentation suffer from potential semantic damage due to the discrete nature of sentences. |
| Approach: | They propose to adapt AutoAugment to solve this problem by using softEDA to increase text data. |
| Outcome: | The proposed method can boost existing augmentation methods and enhance cutting-edge pretrained language models. |
Evaluating Personalized Tool-Augmented LLMs from the Perspectives of Personalization and Proactivity (2025.acl-long)
Copied to clipboard
| Challenge: | Personalized tool utilization is essential for aligning large language models (LLMs) with user preference in interaction scenarios with various tools. |
| Approach: | They propose a key-point-based LLM evaluation method that mitigates biases by manually annotating key points for each test case and providing them to LLM as the reference. |
| Outcome: | The proposed method mitigates biases in the LLM-as-a-judge system by manually annotating key points for each test case and providing them to LLM as the reference. |
ScriptWriter: Narrative-Guided Script Generation (2020.acl-main)
Copied to clipboard
| Challenge: | Existing systems that generate scripts from a storyline are not available for this purpose. |
| Approach: | They propose a model that generates a story from a narrative and a tool that keeps track of what is said and what is to be said. |
| Outcome: | The proposed model outperforms baselines that use the narrative as a kind of context. |
Context-Driven Index Trimming: A Data Quality Perspective to Enhancing Precision of RALMs (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing research often overlooks the data quality issues within retrieval results, often caused by inaccurate existing vector-distance-based retrieval methods. |
| Approach: | They propose to use Context-Driven Index Trimming framework to capture and regulate consistency between retrieved contexts and modify indexes in the database. |
| Outcome: | Experiments show that the proposed framework can improve answer quality by 3.75% on open-domain question-answering tasks. |
LHMKE: A Large-scale Holistic Multi-subject Knowledge Evaluation Benchmark for Chinese Large Language Models (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing benchmarks for comprehensively evaluating Chinese Large Language Models are insufficient. |
| Approach: | They propose a Large-scale, Holistic, and Multi-subject Knowledge Evaluation benchmark to evaluate Chinese Large Language Models. |
| Outcome: | The proposed benchmark measures the knowledge acquisition capabilities of Chinese Large Language Models across 75 subjects from primary school to professional certification exams. |
PubMedQA: A Dataset for Biomedical Research Question Answering (D19-1)
Copied to clipboard
| Challenge: | PubMedQA is a biomedical question answering dataset based on PubMed abstracts . 68.1% accuracy is achieved, compared to single human performance of 78.0% . |
| Approach: | They propose a biomedical question answering dataset from PubMed abstracts . the dataset is annotated by experts and has 1k instances of QA . |
| Outcome: | The proposed model achieves 68.1% accuracy compared to human performance of 78.0% and majority-baseline of 55.2%. |
Enhancing Semantics in Multimodal Chain of Thought via Soft Negative Sampling (2024.lrec-main)
Copied to clipboard
| Challenge: | Chain of thought (CoT) is used for complex reasoning problems, but hallucinations are a problem in multimodal CoT. |
| Approach: | They propose a method to generate soft negative samples with different semantics to mitigate hallucinations in multimodal CoT. |
| Outcome: | The proposed method mitigates hallucinations in multimodal CoT by using soft negative sampling. |
Different Absorption from the Same Sharing: Sifted Multi-task Learning for Fake News Detection (D19-1)
Copied to clipboard
| Challenge: | Existing methods for detecting fake news use shared features as complementarity features without selection. |
| Approach: | They propose a sifted multi-task learning method with a selected sharing layer for fake news detection. |
| Outcome: | The proposed method boosts the F1-score by more than 0.87%, 1.31% on two public and widely used competition datasets. |
Learn to Not Link: Exploring NIL Prediction in Entity Linking (2023.findings-acl)
Copied to clipboard
| Challenge: | Entity linking models have been successful in capturing semantic features, but the NIL prediction problem has not been addressed. |
| Approach: | They propose an entity linking dataset that categorizes mentions linking to NIL into Missing Entity and Non-Entity Phrases. |
| Outcome: | The proposed dataset categorizes mentions linking to NIL into Missing Entity and Non-Entity Phrase categories and ensures the presence of mentions by human annotation and entity masking. |
LLEOT: A Privacy-Enhancing Offsite Tuning Framework via Loss Landscape Elevation (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to fine-tune large language models are infeasible due to privacy regulations. |
| Approach: | They propose an offsite tuning framework that secures data privacy and model parameter and capability privacy. |
| Outcome: | The proposed framework secures data privacy and model parameter and capability privacy while preserving gradient alignment. |
CodecLM: Aligning Language Models with Tailored Synthetic Data (2024.findings-naacl)
Copied to clipboard
Zifeng Wang, Chun-Liang Li, Vincent Perot, Long Le, Jin Miao, Zizhao Zhang, Chen-Yu Lee, Tomas Pfister
| Challenge: | Recent work on generating diverse instructions and applying LLM to increase instruction complexity neglects downstream use cases. |
| Approach: | They propose a framework for generating high-quality synthetic data for LLM alignment with different downstream instruction distributions and LLMs. |
| Outcome: | Experiments on four open-domain instruction using the proposed framework validate the effectiveness of CodecLM over the current state-of-the-art. |
Now You Hear Me: Audio Narrative Attacks Against Large Audio–Language Models (2026.eacl-long)
Copied to clipboard
| Challenge: | Existing jailbreaks against large audio-language models fall into two categories . early work converted text-based prompts into synthetic speech, while subsequent work introduced minor acoustic variations such as accent shifts, phonetic spellings, or stress patterns. |
| Approach: | They propose a text-to-audio jailbreak that embeds disallowed directives within a narrative-style audio stream. |
| Outcome: | The proposed attack exploits structural and acoustic properties of a text-to-audio model . it achieves 98.26% success rate, significantly exceeding baselines for text-based models . |
HULK: An Energy Efficiency Benchmark Platform for Responsible Natural Language Processing (2021.eacl-demos)
Copied to clipboard
| Challenge: | Pretrained models have been taking the lead of many natural language processing benchmarks such as GLUE, but energy efficiency in the process of model training and inference becomes a critical bottleneck. |
| Approach: | They propose a multi-task energy efficiency benchmarking platform for responsible natural language processing that compares pretrained models’ energy efficiency from the perspectives of time and cost. |
| Outcome: | The proposed model improves on the fine-tuning efficiency of pretrained models from the perspectives of time and cost. |
When TableQA Meets Noise: A Dual Denoising Framework for Complex Questions and Large-scale Tables (2026.acl-long)
Copied to clipboard
Shenghao Ye, Yu Guo, Dong Jin, Yuxiang Wang, Yikai Shen, Yunpeng Hou, Shuangwu Chen, null Jianyang, Xiaofeng Jiang
| Challenge: | Extensive research shows that noisy data significantly degrades the performance of table reasoning in real-world applications. |
| Approach: | They propose a dual denoising framework for complex questions and large-scale tables that uses Tree-guided table pruning to remove irrelevant data step by step. |
| Outcome: | The proposed framework achieves outstanding performance on TableQA tasks with complex questions and large-scale tables. |
Event-Centric Query Expansion in Web Search (2023.acl-industry)
Copied to clipboard
| Challenge: | Existing studies rely on long-term search log mining to improve search experience . EQE system is a novel event retrieval framework that can select the best expansion from a significant amount of potential events quickly and accurately. |
| Approach: | They propose a QE system that uses a four-stage event retrieval framework . they collect news headlines and then refine a dual-tower semantic model to serve as an encoder . |
| Outcome: | The proposed system can select the best expansion from a significant amount of potential events quickly and accurately. |
Adaptively profiling models with task elicitation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Language model evaluations fail to characterize consequential failure modes, forcing experts to inspect outputs and build new benchmarks. |
| Approach: | They propose a method that automatically builds new evaluations to profile model behavior. |
| Outcome: | The proposed method finds that language models fail in hundreds of tasks . it also finds that o3-mini is prone to hallucination when fabrications are repeated . |