Papers by Tian Tian
Detecting Machine-Generated Long-Form Content with Latent-Space Variables (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing zero-shot methods to distinguish machine-generated long-form texts from humans are vulnerable to domain shift including different decoding strategies, variations in prompts, and attacks. |
| Approach: | They propose a method that incorporates abstract elements as key deciding factors by training a latent-space model on sequences of events or topics derived from human-written texts. |
| Outcome: | The proposed method improves on baselines on three domains and significantly improves over existing methods. |
To Forget or Not? Towards Practical Knowledge Unlearning for Large Language Models (2024.findings-emnlp)
Copied to clipboard
Bozhong Tian, Xiaozhuan Liang, Siyuan Cheng, Qingbin Liu, Mengru Wang, Dianbo Sui, Xi Chen, Huajun Chen, Ningyu Zhang
| Challenge: | Existing unlearning paradigms are mired in vague forgetting boundaries, erasing knowledge indiscriminately. |
| Approach: | They propose a benchmark to evaluate if unlearning erases essential knowledge . they propose 'knowUnDo' which uses copyrighted content and privacy domains . |
| Outcome: | The proposed method is superior to existing methods in both precise knowledge unlearning and general knowledge retaining of LLMs. |
Tree-of-Evolution: Tree-Structured Instruction Evolution for Code Generation in Large Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Data synthesis is a key research area in large language models (LLMs). |
| Approach: | They propose a framework that models code instruction synthesis process with a tree structure and optimization-driven evolution to alleviate constraints of unidirectional synthesis and randomness-driven generation. |
| Outcome: | The proposed framework outperforms open-weight code LLMs on five widely-used benchmarks. |
Relation Extraction with Type-aware Map Memories of Word Dependencies (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing studies focus on the dependency connections between words with limited attention paid to exploiting dependency types. |
| Approach: | They propose a neural approach for relation extraction with type-aware map memories . they map all associated words along with dependencies among them to memory slots . |
| Outcome: | The proposed approach achieves state-of-the-art on two English benchmark datasets. |
Rethinking Data Selection at Scale: Random Selection is Almost All You Need (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing data selection techniques are designed for small data pools, a study finds . filtering data by token length is an efficient method for improving results . |
| Approach: | They use self-scoring methods that do not rely on external help to perform fine-tuning . they also find that filtering data by token length offers a stable and efficient method . |
| Outcome: | The proposed methods outperform random selection on large datasets on large data pools. |
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. |
Uncovering the Impact of Chain-of-Thought Reasoning for Direct Preference Optimization: Lessons from Text-to-SQL (2025.acl-long)
Copied to clipboard
| Challenge: | Direct Preference Optimization (DPO) is effective in complex reasoning tasks like math word problems and code generation, but Text-to-SQL datasets often include only final answers (gold SQL queries) without detailed CoT solutions. |
| Approach: | They found that Direct Preference Optimization (DPO) is crucial for unlocking DPO's potential by augmenting Text-to-SQL datasets with synthetic CoT solutions. |
| Outcome: | The proposed method achieves consistent and significant performance improvements on Text-to-SQL datasets. |
ERNIE-Doc: A Retrospective Long-Document Modeling Transformer (2021.acl-long)
Copied to clipboard
| Challenge: | Existing models for document-level language pretraining are not suitable for long documents due to their quadratically increasing memory and time consumption. |
| Approach: | They propose a document-level language pretraining model based on Recurrence Transformers. |
| Outcome: | The proposed model outperforms existing models on language understanding tasks. |
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. |
Encoding Spreadsheets for Large Language Models (2024.emnlp-main)
Copied to clipboard
Haoyu Dong, Jianbo Zhao, Yuzhang Tian, Junyu Xiong, Mengyu Zhou, Yun Lin, José Cambronero, Yeye He, Shi Han, Dongmei Zhang
| Challenge: | Spreadsheets are characterized by their extensive two-dimensional grids, flexible layouts, and varied formatting options, which pose significant challenges for large language models (LLMs). |
| Approach: | They propose a structural-anchor-based compression, inverse index translation, and data-format-aware aggregation module to compress spreadsheets effectively. |
| Outcome: | The proposed method outperforms the existing model in GPT4 and achieves a state-of-the-art 78.9% F1 score. |
Towards Modern Topic Models: A Survey of Taxonomies and Paradigm Shifts from Algorithm-Centric to LLM-Centered Topic Analysis (2026.findings-acl)
Copied to clipboard
| Challenge: | Topic modeling (TM) is a classic unsupervised learning task in the field of natural language processing. |
| Approach: | They propose a new taxonomy that emphasizes the role of LLMs and the design of end-to-end workflows. |
| Outcome: | The proposed taxonomy emphasizes the role of LLMs and the design of end-to-end workflows. |
AGD: Adversarial Game Defense Against Jailbreak Attacks in Large Language Models (2025.acl-long)
Copied to clipboard
Shilong Pan, Zhiliang Tian, Zhen Huang, Wanlong Yu, Zhihua Wen, Xinwang Liu, Kai Lu, Minlie Huang, Dongsheng Li
| Challenge: | Existing defenses, including post-training alignment and prompt engineering, struggle with adaptability to out-of-distribution (OOD) attacks. |
| Approach: | They propose an adversarial game-based defense method that dynamically adjusts LLMs’ internal representations to achieve a balanced trade-off between helpfulness and harmlessness. |
| Outcome: | The proposed method improves LLMs’ safety over all baselines. |
Static Models, Dynamic World: A Unified Perspective on Temporal Perception in Large Language Models (2026.findings-acl)
Copied to clipboard
Chenhao Li, Dandan Song, Changzhi Zhou, Jun Yang, Yuhang Tian, Huipeng Ma, Guangyuan Feng, Luan Zhang, Xudong Li, Ke Duan
| Challenge: | Large language models are trained on static corpora but deployed in a dynamic world . a foundational tension remains between time and the ability to understand it . |
| Approach: | They formalize temporal queries in an information-theoretic framework based on parametric reachability of temporal premises and answers. |
| Outcome: | The proposed framework formalizes temporal queries in an information-theoretic framework based on parametric reachability of temporal premises and answers . the framework induces four temporal information regimes corresponding to internal reasoning, answer recency, premise anchoring, and genuine world indeterminacy . |
QUITO-X: A New Perspective on Context Compression from the Information Bottleneck Theory (2025.findings-emnlp)
Copied to clipboard
Yihang Wang, Xu Huang, Bowen Tian, Yueyang Su, Lei Yu, Huaming Liao, Yixing Fan, Jiafeng Guo, Xueqi Cheng
| Challenge: | Existing methods for compressing context by removing redundant tokens are inconsistent with the objective of retaining the most important tokens when conditioning on a given query. |
| Approach: | They propose a method that uses information bottleneck theory to compress context . they propose to remove redundant tokens using metrics such as self-information or perplexity . |
| Outcome: | The proposed method achieves a 25% increase in compression rate compared to the state-of-the-art . |
Improving Chinese Word Segmentation with Wordhood Memory Networks (2020.acl-main)
Copied to clipboard
| Challenge: | Contextual features are important in Chinese word segmentation (CWS) but it is difficult to integrate wordhood information into existing neural models. |
| Approach: | They propose a neural framework that integrates contextual wordhood information with several popular encoder-decoder combinations for Chinese word segmentation. |
| Outcome: | The proposed framework achieves state-of-the-art performance on five benchmark datasets. |
Dynamic Routing Transformer Network for Multimodal Sarcasm Detection (2023.acl-long)
Copied to clipboard
| Challenge: | Existing methods for multimodal sarcasm detection rely on fixed architectures to capture cross-modal incongruity. |
| Approach: | They propose a method that uses dynamic paths to activate different routing transformer modules with hierarchical co-attention adapting to cross-modal incongruity. |
| Outcome: | The proposed method is compared to state-of-the-art methods on a public dataset. |
ParaMac: A General Unsupervised Paraphrase Generation Framework Leveraging Semantic Constraints and Diversifying Mechanisms (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing unsupervised methods for paraphrase generation are weak in semantic equivalence or expression diversity. |
| Approach: | They propose a framework for unsupervised paraphrase generation that employs multi-aspect equivalence constraints and multi-granularity diversifying mechanisms to achieve good semantic equvalence and expressive diversity. |
| Outcome: | The proposed framework achieves 9.1% and 3.3% absolute gains over previous SOTA on Quora and MSCOCO and can improve to 18.0% and 4.6% on GLUE. |
HASH-RAG: Bridging Deep Hashing with Retriever for Efficient, Fine Retrieval and Augmented Generation (2025.findings-acl)
Copied to clipboard
| Challenge: | Experimental evaluations on NQ, TriviaQA, and HotpotQA datasets demonstrate that our approach achieves a 90% reduction in retrieval time compared to conventional methods while maintaining considerate recall performance. |
| Approach: | They propose a framework that integrates deep hashing techniques with systematic optimizations to address these limitations. |
| Outcome: | The proposed framework outperforms retrieval/non-retrieval baselines by 1.4-4.3% in EM scores on NQ, TriviaQA, and HotpotQA datasets. |
CriticBench: Benchmarking LLMs for Critique-Correct Reasoning (2024.findings-acl)
Copied to clipboard
| Challenge: | CriticBench is a benchmark designed to assess LLMs’ abilities to critique and refine their reasoning across a variety of tasks. |
| Approach: | They propose a benchmark to assess LLMs' ability to critique and correct reasoning across a variety of tasks. |
| Outcome: | The proposed benchmark examines the performance of 17 large language models in generation, critique, and correction reasoning. |
Aspect-based Sentiment Analysis with Type-aware Graph Convolutional Networks and Layer Ensemble (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing studies only leverage dependency relations without considering their dependency types . a valid and effective approach is demonstrated on six English benchmark datasets . |
| Approach: | They propose to explicitly utilize dependency types for ABSA with type-aware graph convolutional networks . attention is used in T-GCN to distinguish different edges in the graph and attentive layer ensemble to comprehensively learn from different layers of T-gCN. |
| Outcome: | The proposed approach performs well on six English benchmark datasets. |
A Mutual Information Perspective on Knowledge Graph Embedding (2025.acl-long)
Copied to clipboard
| Challenge: | Existing knowledge graph embedding techniques suffer from high intra-group similarity, loss of semantic information, and insufficient inference capability, particularly in complex relation patterns such as 1-N and N-1 relations. |
| Approach: | They propose a knowledge graph embedding framework that leverages mutual information maximization to improve the semantic representation of entities and relations. |
| Outcome: | Extensive experiments on benchmark datasets demonstrate the effectiveness of the proposed method, with consistent performance improvements across various baseline models. |
Removing Prompt-template Bias in Reinforcement Learning from Human Feedback (2025.findings-acl)
Copied to clipboard
| Challenge: | Reinforcement Learning from Human Feedback (RLHF) has shown promise for enhancing pre-trained large language models to generate responses that align with human preferences and societal values. |
| Approach: | They propose a method to estimate prompt-template bias term during reward modeling and use it to calibrate reward scores. |
| Outcome: | The proposed method can be flexibly combined with existing algorithms of removing length bias, leading to a further improvement in the aspect of enhancing the quality of generated responses. |
Enhancing Structure-aware Encoder with Extremely Limited Data for Graph-based Dependency Parsing (2022.coling-1)
Copied to clipboard
| Challenge: | Dependency parsing is an important natural language processing task which analyzes the syntactic structure of an input sentence. |
| Approach: | They propose a structure-aware encoder pre-trained on auto-parsed data to improve dependency parsing . they propose combining gold dependency trees with existing parsers to improve parser performance . |
| Outcome: | The proposed approach outperforms baselines under different parsers and dependency standards under different parameters and model architectures. |
CSRP: Chain-of-Thought Reasoning for Chinese Text Correction via Reinforcement Learning with Efficiency-Aware Rewards (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models lack specialized priors for subtle grammatical distinctions, and Supervised Fine-Tuning fails to optimize for precision-focused metrics. |
| Approach: | They propose a framework that builds correction capability through Continual Pre-training on 5.9M balanced samples to internalize domain knowledge. |
| Outcome: | The proposed framework outperforms existing models on the NACGEC benchmark with 50.99 F0.5 and 57.17 precision while mitigating over-correction bias. |
DMHM: Density-aware Manifold Learning and Hybrid Mahalanobis Energy for LLMs-generated Text Detection (2026.acl-long)
Copied to clipboard
Tianle Liu, Zhiliang Tian, Zhen Huang, Tianlun Liu, Jingyuan Huang, Zhaoning Zhang, Chengcheng Shao, Dongsheng Li
| Challenge: | Existing methods for LGT detection assume that it is a single homogeneous distribution. |
| Approach: | They propose a framework for LGT detection based on density-aware manifold learning and hybrid Mahalanobis energy. |
| Outcome: | The proposed framework outperforms baselines in detecting LLM-generated text (LGT) it is based on density-aware manifold learning and hybrid Mahalanobis energy . |
Enhancing Aspect-level Sentiment Analysis with Word Dependencies (2021.eacl-main)
Copied to clipboard
| Challenge: | Existing approaches to enhance aspect-level sentiment analysis have omitted syntactic information . experimental results show that our approach outperforms baseline models on all datasets . |
| Approach: | They propose to leverage word dependencies to enhance aspect-level sentiment analysis . they propose to use key-value memory networks to leverage different dependency results . |
| Outcome: | The proposed approach outperforms baseline models on all datasets and achieves state-of-the-art performance on three of them. |
FanLoRA: Fantastic LoRAs and Where to Find Them in Large Language Model Fine-tuning (2024.emnlp-industry)
Copied to clipboard
| Challenge: | Lowrank adaptation and its variants introduce significant latency in multi-tenant settings, hindering their applications in the industry. |
| Approach: | They propose a framework to fine-tune LoRA modules on a large-scale instruction tuning dataset. |
| Outcome: | The proposed framework outperforms existing PEFT methods and significantly reduces inference latency. |
Learning from Mistakes: Negative Reasoning Samples Enhance Out-of-Domain Generalization (2026.acl-long)
Copied to clipboard
Tian Xueyun, MingHua Ma, Bingbing Xu, Nuoyan Lyu, Wei Li, Heng Dong, Zheng Chu, Yuanzhuo Wang, Huawei Shen
| Challenge: | Recent studies show that supervised fine-tuning (SFT) is a common approach for reasoning in large language models. |
| Approach: | They propose to use supervised fine-tuning (SFT) on chain-of-thought trajectories demonstrations . they find that incorporating negative traxories yields substantial OOD generalization gains . |
| Outcome: | The proposed scheme yields 5.51% OOD gain over positive-only training. |
Detoxifying Large Language Models via the Diversity of Toxic Samples (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for analyzing and utilizing toxic samples are limited . current methods fail to fully harness their potential . |
| Approach: | They propose a diverse detoxification framework that leverages toxic samples' diversity . they propose MPSG strategy and SC-DPO approach to elicit personalized toxic responses . |
| Outcome: | The proposed framework could be used to optimize large language models for user safety . it incorporates two components: MPSG strategy and SC-DPO approach . |
WikiDiverse: A Multimodal Entity Linking Dataset with Diversified Contextual Topics and Entity Types (2022.acl-long)
Copied to clipboard
| Challenge: | Multimodal Entity Linking (MEL) is an essential task for many multimodal applications. |
| Approach: | They propose to use a human-annotated Wikipedia-based multimodal entity linking dataset to improve the quality of existing MEL models. |
| Outcome: | The proposed model uses the visual information of images more effectively than existing models. |
Introducing Graph Context into Language Models through Parameter-Efficient Fine-Tuning for Lexical Relation Mining (2025.acl-long)
Copied to clipboard
| Challenge: | Pre-trained language models can effectively mine lexical relations between word pairs . however, graph features and semantic knowledge of pre-tried models are lacking in the task. |
| Approach: | They propose a parameter-efficient fine-tuning method which integrates graph features and semantic representations for lexical relation classification and lexic entailment tasks. |
| Outcome: | The proposed method integrates graph features and semantic representations for lexical relation mining tasks. |
Cross-Lingual Phrase Retrieval (2022.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to cross-lingual phrase retrieval learn word or sentence representations in word or sentences. |
| Approach: | They propose a cross-lingual phrase retrieval model that extracts phrase representations from unlabeled example sentences. |
| Outcome: | The proposed model outperforms state-of-the-art methods on a large-scale cross-lingual phrase retrieval dataset, showing it can perform in an unseen language pair during training. |
ReviewRL: Towards Automated Scientific Review with RL (2025.emnlp-main)
Copied to clipboard
Sihang Zeng, Kai Tian, Kaiyan Zhang, Yuru Wang, Junqi Gao, Runze Liu, Sa Yang, Jingxuan Li, Xinwei Long, Jiaheng Ma, Biqing Qi, Bowen Zhou
| Challenge: | Existing automated review systems struggle with factual accuracy, rating consistency, and analytical depth. |
| Approach: | They propose a framework for generating comprehensive and factually grounded scientific paper reviews using supervised fine-tuning and reinforcement learning. |
| Outcome: | The proposed framework outperforms existing methods on ICLR 2025 papers. |
MDPO: Customized Direct Preference Optimization with a Metric-based Sampler for Question and Answer Generation (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods for QA data generation are limited by the dependence of existing evaluation metrics on ground truth labels. |
| Approach: | They propose a set of unsupervised evaluation metrics for QA data that enable multidimensional assessment based on the relationships among context,question and answer. |
| Outcome: | The proposed method outperforms state-of-the-art methods on public datasets and shows that it produces high-quality and domain-specific QA pairs. |
ParroT: Translating during Chat using Large Language Models tuned with Human Translation and Feedback (2023.findings-emnlp)
Copied to clipboard
Wenxiang Jiao, Jen-tse Huang, Wenxuan Wang, Zhiwei He, Tian Liang, Xing Wang, Shuming Shi, Zhaopeng Tu
| Challenge: | Large language models (LLMs) like ChatGPT are only accessible through restricted APIs, which creates barriers to new research and advancements in the field. |
| Approach: | They propose a framework to enhance and regulate the translation abilities during chat . they reformulate translation data into the instruction-following style and introduce a "Hint" field . |
| Outcome: | The proposed framework enhances and regulates the translation abilities during chat . it reformulates translation data into the instruction-following style and introduces a "Hint" field . |
GCML: Gradient Coherence Guided Meta-Learning for Cross-Domain Emerging Topic Rumor Detection (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing domain adaptation rumor detection methods ignore the data generalization differences and rely on a large amount of unlabeled target domain samples to achieve domain adaptation. |
| Approach: | They propose a Gradient Coherence guided Meta-Learning approach for emerging topics rumor detection that selectively learns more "generalizable" tasks that are more beneficial in adapting to the target domain. |
| Outcome: | The proposed method outperforms baselines on real-world datasets and significantly outperformed traditional methods on the in-domain condition. |
ImaRA: An Imaginative Frame Augmented Method for Low-Resource Multimodal Metaphor Detection and Explanation (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods for multimodal metaphor detection neglect cross-domain and attribute similarity characteristics underlying multimodal understanding. |
| Approach: | They propose an Imaginative FRame Augmented method for multimodal metaphor detection and explanation . they use a cross-modal imagination dataset rich in multimodal multimodal expressions . |
| Outcome: | The proposed method outperforms existing methods with training data on two datasets. |
BANER: Boundary-Aware LLMs for Few-Shot Named Entity Recognition (2025.coling-main)
Copied to clipboard
| Challenge: | Named Entity Recognition (NER) is a fundamental task in Natural Language Processing (NLP) that aims to detect the entity spans of text and classify them into pre-defined set of entity types. |
| Approach: | They propose a boundary-aware contrastive learning strategy to enhance the LLM’s ability to perceive entity boundaries for generalized entity spans. |
| Outcome: | The proposed framework outperforms prior methods and validates its effectiveness across a range of LLM architectures. |
PaddleSpeech: An Easy-to-Use All-in-One Speech Toolkit (2022.naacl-demo)
Copied to clipboard
Hui Zhang, Tian Yuan, Junkun Chen, Xintong Li, Renjie Zheng, Yuxin Huang, Xiaojie Chen, Enlei Gong, Zeyu Chen, Xiaoguang Hu, Dianhai Yu, Yanjun Ma, Liang Huang
| Challenge: | PaddleSpeech is an open-source speech toolkit that supports speech-to-text and text-to speech tasks. |
| Approach: | They describe the design philosophy and core architecture of PaddleSpeech to support several essential speech-to-text and text-to speech tasks. |
| Outcome: | The proposed framework achieves competitive or state-of-the-art performance on various speech datasets and implements the most popular methods. |
Draft Model Knows When to Stop: Self-Verification Speculative Decoding for Long-Form Generation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Conventional speculative decoding methods use a predefined length policy for proposing drafts, but the reality deviates from this assumption. |
| Approach: | They propose a self-verification length policy that adaptively determines the lengths of draft sequences by referring to the draft entropy. |
| Outcome: | The proposed method achieves 17% speedup on MT-Bench and 22% speedup in long-form reasoning. |
MentalSeek-Dx: Towards Progressive Hypothetico-Deductive Reasoning for Real-world Psychiatric Diagnosis (2026.acl-long)
Copied to clipboard
Xiao Sun, null Ymyang, Xinyi Jiang, Yu Tian, Junnan Zhu, Jiang Zhong, Qin Lei, Jingwang Huang, Haoyang Zeng, Xinyu Zhou, Xin Xiao, Kaiwen Wei
| Challenge: | Mental health disorders represent a burgeoning global public health challenge . lack of ecological validity and fine-grained diagnostic supervision limits their utility . |
| Approach: | They propose a medical-specialized LLM trained to internalize clinical reasoning process through supervised trajectory construction and curriculum-based reinforcement learning. |
| Outcome: | The proposed model achieves state-of-the-art with only 14B parameters, establishing a clinically grounded framework for reliable psychiatric diagnosis. |
Improving Image Captioning via Predicting Structured Concepts (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies on image captioning ignore the relationship between concepts . current methods for image caption generation ignore this relationship . |
| Approach: | They propose a structured concept predictor to predict concepts and their structures . they integrate these predictions into captioning to enhance visual signals . |
| Outcome: | The proposed approach improves image captioning performance by using semantic concepts as a bridge between images and texts. |
When Correct Beliefs Collapse: Epistemic Resilience of LLMs under Clinical Pressure (2026.acl-long)
Copied to clipboard
| Challenge: | Existing models exhibit severe multi-turn sycophancy in clinical dialogue . high initial diagnostic capability does not imply high belief stability . |
| Approach: | They propose a stress test framework that evaluates belief stability under escalating pressure. |
| Outcome: | The proposed stress test framework reduces the risk of multi-turn sycophancy in clinical dialogue . it eliminates belief change and improves robustness in training time . |
Learning Personalized Alignment for Evaluating Open-ended Text Generation (2024.emnlp-main)
Copied to clipboard
| Challenge: | Traditional evaluation metrics rely heavily on lexical similarity with human-written references, showing poor correlation with human judgments and failing to account for alignment with the diversity of human preferences. |
| Approach: | They propose an interpretable evaluation framework that evaluates alignment with specific human preferences by providing detailed comments and fine-grained scoring. |
| Outcome: | The proposed framework outperforms GPT-4 in Kendall correlation and accuracy with zero-shot reviewers. |
Diversify Question Generation with Continuous Content Selectors and Question Type Modeling (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to generate questions based on answers and relevant contexts are not suitable for all questions . |
| Approach: | They propose a method to generate questions from a given answer and its relevant context. |
| Outcome: | The proposed method achieves a better trade-off between generation quality and diversity compared with existing approaches. |
Continual Learning Long Short Term Memory (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to prevent catastrophic forgetting in neural networks are based on the stability-plasticity dilemma, but only a limited size of old data is available. |
| Approach: | They propose a Continual Learning Long Short Term Memory cell in Recurrent Neural Network (RNN) that considers the state of each individual task's output gates and the correlation of the states between tasks. |
| Outcome: | The proposed method significantly improves on spoken language understanding tasks over state-of-the-art approaches. |
SKEP: Sentiment Knowledge Enhanced Pre-training for Sentiment Analysis (2020.acl-main)
Copied to clipboard
| Challenge: | sentiment knowledge is ignored in sentiment analysis, despite its use in pretraining. |
| Approach: | They propose to use sentiment knowledge to learn a unified sentiment representation for multiple sentiment analysis tasks. |
| Outcome: | The proposed method outperforms strong pre-training baseline on three kinds of sentiment tasks. |
Optimizing Conversational Quality in Spoken Dialogue Systems with Reinforcement Learning from AI Feedback (2026.findings-acl)
Copied to clipboard
Siddhant Arora, Jinchuan Tian, Jiatong Shi, Hayato Futami, Yosuke Kashiwagi, Emiru Tsunoo, Shinji Watanabe
| Challenge: | Existing studies on reinforcement learning from human or AI feedback have focused on semantic rewards at the utterance level. |
| Approach: | They propose a multi-reward RLAIF framework for speech-in/speech-out dialogue systems . they combine semantic, audio-quality, and emotion-consistency rewards . |
| Outcome: | The proposed framework improves speech-in/speech-out dialogue system quality . it combines semantic, audio-quality, and emotion-consistency rewards . the proposed framework is available to download from the cdc. |
SDC-LoRA: Singular-Subspace Drift Controlled LoRA to Mitigate Knowledge Forgetting (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to adapt LLMs to new tasks focus on limiting knowledge forgetting . et al., 2023b) suggest a solution to this problem by limiting update energy in the principal singular subspace of W0 . |
| Approach: | They propose a low-rank Adaptation (LoRA) that steers early updates away from principal directions and mitigates forgetting by constraining update energy in the principal singular subspace of W0. |
| Outcome: | The proposed model mitigates forgetting on MMLU, TruthfulQA, and HellaSwag while keeping minor-subspace updates unchanged. |
Self-Evolving Multi-Agent Systems via Textual Backpropagation (2026.findings-acl)
Copied to clipboard
Xiaowen Ma, Yunpu Ma, Chenyang Lin, Sikuan Yan, Jinhe Bi, Zixuan Cao, Yijun Tian, Volker Tresp, Hinrich Schuetze
| Challenge: | Large Language Models (LLMs) have proven effective for addressing complex, high-dimensional tasks, but current approaches rely on static, manually engineered multi-agent configurations. |
| Approach: | They propose a framework that conceptualizes multi-agent collaboration as a layered neural network architecture. |
| Outcome: | The proposed framework surpasses leading multi-agent baselines under the same configurations, showing consistent performance improvements. |
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. |
Q-TOD: A Query-driven Task-oriented Dialogue System (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing pipelined task-oriented dialogue systems have difficulties adapting to unseen domains . end-to-end systems are plagued by large-scale knowledge bases in practice . |
| Approach: | They propose a query-driven task-oriented dialogue system that extracts dialogue context information into a natural language query. |
| Outcome: | The proposed system outperforms strong baselines and establishes a new state-of-the-art performance on three publicly available task-oriented dialogue datasets. |
DEED: Dynamic Early Exit on Decoder for Accelerating Encoder-Decoder Transformer Models (2024.findings-naacl)
Copied to clipboard
| Challenge: | Encoder-decoder transformer models suffer from high inference latency due to auto-regressive decoding . Typically, the decoder takes up most of the latency because of the auto-decoding - a problem that is not solved by the current model. |
| Approach: | They propose an approach to perform Dynamic Early Exit on Decoder to reduce inference latency by 20%-74% by using a multi-exit encoder-decoder transformer model trained with deep supervision. |
| Outcome: | The proposed model reduces inference latency by 20%-74% with comparable or even higher accuracy compared to baseline models. |
ZoFia: Zero-Shot Fake News Detection with Entity-Guided Retrieval and Multi-LLM Interaction (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) are limited by knowledge cutoff and can generate factual hallucinations when handling time-sensitive news. |
| Approach: | They propose a two-stage zero-shot fake news detection framework that uses a hierarchical salience and saliency-calibrated minimum margin of relevance algorithm to extract core entities accurately. |
| Outcome: | The proposed framework outperforms existing zero-shot baselines and even most few-shot methods on two public datasets. |
ChiMed-GPT: A Chinese Medical Large Language Model with Full Training Regime and Better Alignment to Human Preferences (2024.acl-long)
Copied to clipboard
| Challenge: | Current large language models (LLMs) are ineffective in learning domain knowledge and aligning with human preference. |
| Approach: | They propose a benchmark LLM for Chinese medical domain that uses pre-training, supervised fine-tuning and RLHF to train LLMs. |
| Outcome: | The proposed LLM performs better than existing LLMs in the Chinese medical domain. |
Modeling Conceptual Attribute Likeness and Domain Inconsistency for Metaphor Detection (2023.emnlp-main)
Copied to clipboard
| Challenge: | Metaphor detection aims to distinguish between metaphorical and literal expressions in text. |
| Approach: | They propose an attribute likeness and domain inconsistency learning framework for wordpair metaphor detection based on conceptual metaphor theory . they model attribute likeity with an attribute siamese network and devise a domain contrastive learning strategy to learn semantic inconsistentness of concepts in source and target domains . |
| Outcome: | The proposed framework outperforms existing word-pair and token-level methods on four datasets. |
Investigating Robustness and Interpretability of Link Prediction via Adversarial Modifications (N19-1)
Copied to clipboard
| Challenge: | Existing approaches focus on improving accuracy and overlook other aspects such as robustness and interpretability. |
| Approach: | They propose adversarial modifications for link prediction models that identify influential facts and evaluate their sensitivity to addition of fake facts. |
| Outcome: | The proposed model evaluates the robustness of the model to the addition of fake facts and the interpretability of the models. |
A Static Evaluation of Code Completion by Large Language Models (2023.acl-industry)
Copied to clipboard
Hantian Ding, Varun Kumar, Yuchen Tian, Zijian Wang, Rob Kwiatkowski, Xiaopeng Li, Murali Krishna Ramanathan, Baishakhi Ray, Parminder Bhatia, Sudipta Sengupta
| Challenge: | Large language models trained on code have shown great potential to increase productivity of software developers. |
| Approach: | They propose a static evaluation framework to quantify static errors in Python code completions by leveraging Abstract Syntax Trees. |
| Outcome: | The proposed framework is more efficient and applicable to code in the wild. |
Know Your Place: Diagnosing Implicit Social Adaptation Failures in Chinese Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Existing studies suggest that failures of large language models in social contexts are not due to limited linguistic competence, but to inappropriate recognition. |
| Approach: | They propose a framework that decomposes social adaptation into three orthogonal dimensions and conduct controlled comparisons across multiple Chinese LLMs under implicit and explicit conditions. |
| Outcome: | The proposed framework decomposes social adaptation into three orthogonal dimensions and conducts controlled comparisons across multiple Chinese LLMs under implicit and explicit conditions. |
Retrieval Enhanced Data Augmentation for Question Answering on Privacy Policies (2023.eacl-main)
Copied to clipboard
| Challenge: | Existing labeled datasets are heavily imbalanced, limiting the QA performance in this domain. |
| Approach: | They propose a question answering task that captures relevant text segments from unlabeled policy documents and expands the positive examples in the training set. |
| Outcome: | The proposed framework elevates the baseline by a large margin (10% F1) and achieves a new state-of-the-art F1 score of 50%. |
Automatic Evaluation for Text-to-image Generation: Task-decomposed Framework, Distilled Training, and Meta-evaluation Benchmark (2025.acl-long)
Copied to clipboard
| Challenge: | Existing MLLMs rely on commercial models such as GPT-4o for evaluations, but they are not universally accessible. |
| Approach: | They propose a task decomposition evaluation framework based on GPT-4o to automatically construct a specialized training dataset to break down the multifaceted evaluation process into simpler sub-tasks. |
| Outcome: | The proposed framework outperforms the current state-of-the-art GPT-4o evaluation framework with over 4.6% improvement in Spearman and Kendall correlations with human judgments. |
Ponder & Press: Advancing Visual GUI Agent towards General Computer Control (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing multimodal large language models (MLLMs) lack visual inputs to ground objects, limiting flexibility across diverse software environments and platforms. |
| Approach: | They propose a divide-and-conquer framework for general computer control that uses only visual inputs to create a purely human-like interaction paradigm. |
| Outcome: | The proposed framework outperforms existing models by +22.5% on the ScreenSpot GUI grounding benchmark. |
Automatic Comment Generation for Chinese Student Narrative Essays (2022.emnlp-demos)
Copied to clipboard
| Challenge: | Existing studies focus on giving discrete scores for holistic quality or distinct traits, but real-world teachers usually provide detailed comments in natural language, which are more informative than single scores. |
| Approach: | They propose a model which generates comments for specified segments from given student narrative essays using a human-written Chinese dataset. |
| Outcome: | The proposed model outperforms baselines and has 91% success rate. |
Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training (2025.acl-long)
Copied to clipboard
Youliang Yuan, Wenxiang Jiao, Wenxuan Wang, Jen-tse Huang, Jiahao Xu, Tian Liang, Pinjia He, Zhaopeng Tu
| Challenge: | Large Language Models exhibit a level of intelligence that is both impressive and everevolving, but their ability to refuse generating unsafe content is a double-edged sword. |
| Approach: | They propose a method to tackle a refusal position bias within safety tuning data that compromises the models’ ability to appropriately refuse generating unsafe content. |
| Outcome: | The proposed method significantly improves model safety without compromising performance and surpasses baseline methods in defending against attacks. |
Make-A-Voice: Revisiting Voice Large Language Models as Scalable Multilingual and Multitask Learners (2024.acl-long)
Copied to clipboard
Rongjie Huang, Chunlei Zhang, Yongqi Wang, Dongchao Yang, Jinchuan Tian, Zhenhui Ye, Luping Liu, Zehan Wang, Ziyue Jiang, Xuankai Chang, Jiatong Shi, Chao Weng, Zhou Zhao, Dong Yu
| Challenge: | Large language models (LLMs) have been used for general-purpose interfaces across multiple tasks and languages. |
| Approach: | They propose to use large language models as a general-purpose interface across multiple tasks and languages. |
| Outcome: | The proposed model performs better on 200K hours of 6-language data for voice generation applications. |
ToolBeHonest: A Multi-level Hallucination Diagnostic Benchmark for Tool-Augmented Large Language Models (2024.emnlp-main)
Copied to clipboard
Yuxiang Zhang, Jing Chen, Junjie Wang, Yaxin Liu, Cheng Yang, Chufan Shi, Xinyu Zhu, Zihao Lin, Hanwen Wan, Yujiu Yang, Tetsuya Sakai, Tian Feng, Hayato Yamana
| Challenge: | Currently, tool-augmented large language models (LLMs) only achieve total scores of 45.3 and 37.0, respectively, on a scale of 100. |
| Approach: | They propose a multi-level diagnostic process to assess the LLM's hallucinations through two perspectives: depth and breadth. |
| Outcome: | The proposed diagnostic process assesses the hallucinations of large language models through two perspectives: depth and breadth. |
Advancing Collaborative Debates with Role Differentiation through Multi-Agent Reinforcement Learning (2025.acl-long)
Copied to clipboard
| Challenge: | Multi-agent collaborative tasks exhibit exceptional capabilities in natural language applications and generation. |
| Approach: | They propose a multi-LLM Cooperation framework with automatic role assignment capabilities that allows multiple agents to embed roles in turn-based speaking. |
| Outcome: | The proposed framework improves collaboration and expertise among agents and teams by enabling them to share roles and develop complementary strengths from the optimization level. |
Attn-GS: Attention-Guided Context Compression for Efficient Personalized LLMs (2026.acl-long)
Copied to clipboard
Shenglai Zeng, Tianqi Zheng, Chuan Tian, Dante Everaert, Yau-Shian Wang, Yupin Huang, Michael J. Morais, Rohit Patki, Jinjin Tian, Xinnan Dai, Kai Guo, Monica Xiao Cheng, Hui Liu
| Challenge: | Existing approaches to personalize large language models (LLMs) rely on heuristic methods to compress user profiles but they ignore how LLMs process and prioritize different profile components. |
| Approach: | They propose an attention-guided context compression framework that leverages attention feedback from a marking model to mark important personalization sentences and guides a compression model to generate task-relevant compressed user contexts. |
| Outcome: | The proposed framework outperforms baselines across tasks, token limits, and settings while reducing token usage by 50 times. |
Conditional Supervised Contrastive Learning for Fair Text Classification (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Recent advances in natural language processing have demonstrated societal bias in existing NLP models. |
| Approach: | They propose to use contrastive learning to learn fair representations for text classification . they conduct experiments on two text datasets to demonstrate their methods are stable . |
| Outcome: | The proposed methods balancing task performance and bias mitigation are stable in different hyperparameter settings. |
BlendFilter: Advancing Retrieval-Augmented Large Language Models via Query Generation Blending and Knowledge Filtering (2024.emnlp-main)
Copied to clipboard
Haoyu Wang, Ruirui Li, Haoming Jiang, Jinjin Tian, Zhengyang Wang, Chen Luo, Xianfeng Tang, Monica Cheng, Tuo Zhao, Jing Gao
| Challenge: | Retrieval-augmented Large Language Models struggle with complex inputs and noisy knowledge retrieval hindering model effectiveness. |
| Approach: | They propose a query generation method that integrates query generation blending with knowledge filtering to enhance retrieval-augmented LLMs. |
| Outcome: | The proposed approach surpasses state-of-the-art benchmarks on open-domain question answering benchmarks. |
SafeSteer: A Decoding-level Defense Mechanism for Multimodal Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing defense methods rely on fine-tuning or inefficient post-hoc interventions, limiting their ability to address novel attacks. |
| Approach: | They propose a decoding-level defense mechanism that employs a lightweight discriminator to iteratively steer the decoding process toward safety. |
| Outcome: | The proposed method improves safety performance by up to 33.40% without fine-tuning on multiple MLLMs. |
MIKE: A New Benchmark for Fine-grained Multimodal Entity Knowledge Editing (2024.findings-acl)
Copied to clipboard
Jiaqi Li, Miaozeng Du, Chuanyi Zhang, Yongrui Chen, Nan Hu, Guilin Qi, Haiyun Jiang, Siyuan Cheng, Bozhong Tian
| Challenge: | Current benchmarks focus on coarse-grained knowledge, leaving the intricacies of fine-grounded knowledge unexplored. |
| Approach: | They propose a benchmark and dataset specifically designed for FG multimodal entity knowledge editing. |
| Outcome: | The proposed benchmark underscoring the complexity of FG knowledge editing in MLLMs. |
Sequential Fusion of Text-close and Text-far Representations for Multimodal Sentiment Analysis (2025.coling-main)
Copied to clipboard
| Challenge: | Multimodal Sentiment Analysis (MSA) aims to identify human attitudes from diverse modalities such as visual, audio and text. |
| Approach: | They propose a framework to combine text-close and text-far representations to refine multimodal representations from multimodal data. |
| Outcome: | The proposed framework explores similarities and differences between text and audio/visual modalities and fuses extracted representations more effectively. |
Chain of Ideas: Revolutionizing Research Via Novel Idea Development with LLM Agents (2025.findings-emnlp)
Copied to clipboard
Long Li, Weiwen Xu, Jiayan Guo, Ruochen Zhao, Xingxuan Li, Yuqian Yuan, Boqiang Zhang, Yuming Jiang, Yifei Xin, Ronghao Dang, Yu Rong, Deli Zhao, Tian Feng, Lidong Bing
| Challenge: | Existing methods for idea generation either trivially prompt LLMs or expose LLM to extensive literature without indicating useful information. |
| Approach: | They propose a chain-of-ideas agent that organizes literature in a chains structure . they propose evaluating idea-generation methods from different perspectives . |
| Outcome: | The proposed agent outperforms existing methods and matches human quality in idea generation. |
A Survey on LLMs for Story Generation (2025.findings-emnlp)
Copied to clipboard
Maria Teleki, Vedangi Bengali, Xiangjue Dong, Sai Tejas Janjur, Haoran Liu, Tian Liu, Cong Wang, Ting Liu, Yin Zhang, Frank Shipman, James Caverlee
| Challenge: | Methods for story generation with Large Language Models (LLMs) have come into the spotlight recently. |
| Approach: | They propose a novel taxonomy of LLMs for story generation consisting of two major paradigms: independent story generation by an LLM, and author-assistance for story creation . |
| Outcome: | The proposed taxonomy compares existing work on the topic with those of novel author-assistance models. |
CodeJudge-Eval: Can Large Language Models be Good Judges in Code Understanding? (2025.coling-main)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have showcased impressive code generation capabilities, primarily evaluated through language-to-code benchmarks. |
| Approach: | They propose a benchmark to assess LLMs’ code understanding abilities from the perspective of code judging rather than code generation. |
| Outcome: | The proposed benchmark evaluates 12 well-known large language models to determine the correctness of provided code solutions. |
Paper2Rebuttal: A Multi-Agent Framework for Transparent Author Response Assistance (2026.acl-long)
Copied to clipboard
| Challenge: | Current approaches to writing effective rebuttals are limited by the direct-to-text generation problem . authors must accurately decipher reviewer intent while ensuring every response is firmly anchored in verifiable manuscript details. |
| Approach: | They propose a framework that reframes rebuttal generation as an evidence-centric planning task. |
| Outcome: | The proposed framework outperforms baselines in coverage, faithfulness, and strategic coherence. |
GEMS: Generation-Based Event Argument Extraction via Multi-perspective Prompts and Ontology Steering (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for event argument extraction rely on a single prompt . existing methods ignore complex structural and dynamic interdependencies between event arguments . |
| Approach: | They propose a multi-prompt learning framework that generates event arguments via multi-perspective prompts and ontology steering. |
| Outcome: | The proposed framework captures interrelationships between arguments and ontology steering . it uses multiple unfilled prompts for each sentence to generate event arguments . |
Bootstrapping meaning through listening: Unsupervised learning of spoken sentence embeddings (2022.findings-emnlp)
Copied to clipboard
| Challenge: | a new study addresses the challenge of learning semantic representations from speech signals . speech-based semantic representation can be used for speech mining and spoken language understanding . |
| Approach: | They propose a multimodal sequential autoencoder that converts speech signals into hidden units . they propose s-HuBERT to induce meaning through knowledge distillation . |
| Outcome: | The proposed model achieves a moderate correlation with human judgments without labels or transcriptions. |
Formally Specifying the Intended Behavior of the Program: LLM-Driven Neuro-Symbolic Program Specification Synthesis (2026.acl-demo)
Copied to clipboard
Cheng Wen, Hu Junjie, YiKun Hu, Jie Su, Bin Yu, Dugang Liu, Zhiwu Xu, Weidi Sun, Shengchao Qin, Cong Tian
| Challenge: | Formal verification typically requires developers to write detailed formal specifications . a formal verification system that generates candidate specifications is costly and error-prone . |
| Approach: | They propose an LLM-driven neuro-symbolic demonstration system that reframes specification writing as constrained structured synthesis. |
| Outcome: | The proposed system reduces hallucinations and produces proof-ready annotations. |
R^3AG: Retriever Routing for Retrieval-Augmented Generation (2026.acl-long)
Copied to clipboard
| Challenge: | Retrieval-augmented generation (RAG) is often bottlenecked by the “one-size-fits-all” retrieval paradigm, as different queries exhibit distinct preferences for different retrievers. |
| Approach: | They propose a novel routing framework that explicitly models the dynamic alignment between queries and retriever capabilities and decomposes retriever capability into two learnable dimensions: retrieval quality and generation utility. |
| Outcome: | Experiments on knowledge-intensive tasks show that R3AG outperforms both the best individual retrievers and state-of-the-art static routing methods. |
AdapShot: Adaptive Many-Shot In-Context Learning with Semantic-Aware KV Cache Reuse (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for In-Context Learning (ICL) rely on a predetermined number of shots, leading to insufficient context or noise. |
| Approach: | They propose a probe-based evaluation mechanism that utilizes output entropy to determine the optimal number of shots and leverages KV cache reuse for efficient inference. |
| Outcome: | The proposed model achieves an average performance gain of 10% and a 4.64 speedup compared to state-of-the-art DBSA. |
Interpretable Composition Attribution Enhancement for Visio-linguistic Compositional Understanding (2024.emnlp-main)
Copied to clipboard
| Challenge: | Despite promising progress, vision-language models still exhibit significant challenges in understanding visio-linguistic concepts beyond object terms. |
| Approach: | They propose a framework that encourages the model to pay greater attention to composition words denoting relationships and attributes within the text. |
| Outcome: | The proposed framework improves the ability to discern intricate details and construct more sophisticated interpretations of combined visual and linguistic elements. |
Retrieve, Discriminate and Rewrite: A Simple and Effective Framework for Obtaining Affective Response in Retrieval-Based Chatbots (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing work on retrieval-based chatbots has low-quality affect response . Existing frameworks for obtaining affective response are based on Retrieve-and-Rerank . |
| Approach: | They propose a retrieval-based framework which provides affective response for retrieval chatbots by using a new discriminate-and-rewrite mechanism. |
| Outcome: | The proposed framework outperforms existing baselines and can guarantee the quality of the response and satisfy the affect label. |
AgentInit: Initializing LLM-based Multi-Agent Systems via Diversity and Expertise Orchestration for Effective and Efficient Collaboration (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing MAS initialization methods do not fully account for the collaborative needs of the generated agents in subsequent stages. |
| Approach: | They propose to use a Natural Language to Format mechanism to optimize the structure of agent teams and incorporate a natural language to format mechanism to ensure consistency and standardization. |
| Outcome: | The proposed method outperforms state-of-the-art initialization methods and pre-defined strategies across various frameworks and tasks while reducing token consumption. |
Improving Preference Alignment of LLM with Inference-Free Self-Refinement (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models (LLMs) develop in-context learning capability through pretraining and instruction tuning. |
| Approach: | Large language models (LLMs) develop in-context learning capability through pretraining and instruction tuning. |
| Outcome: | Experiments show that incorporating IFSR into preference alignment yields performance improvement over 10%. |
Tracing and Dissecting How LLMs Recall Factual Knowledge for Real World Questions (2025.acl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models have shown promising ability to perform commonsense reasoning. |
| Approach: | They propose a two-dimensional analysis framework that incorporates token back-tracing and token decoding to uncover how LLMs conduct factual knowledge recall. |
| Outcome: | The proposed framework shows that LLMs lack relevant knowledge but struggle to select the most accurate information based on context during the retrieval and rerank phase. |
Learning a Multi-Domain Curriculum for Neural Machine Translation (2020.acl-main)
Copied to clipboard
| Challenge: | Existing data selection methods do not work well for multiple domains . multiple aspects need to be considered for training a multi-domain model . |
| Approach: | They propose a dynamic data selection method to multi-domain NMT that incorporates instance-level domain-relevance features and a curriculum to gradually focus on multi- domain relevant data batches. |
| Outcome: | The proposed model outperforms no-curriculum training on multiple domains and reaches or outperformed individual performance. |
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. |
Syntax-driven Approach for Semantic Role Labeling (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing studies focus on auto-generated syntactic knowledge to enhance semantic role labeling . experimental results show that map memories can enhance SRL . |
| Approach: | They propose to map memories to enhance semantic role labeling by encoding auto-generated syntactic knowledge from off-the-shelf toolkits. |
| Outcome: | The proposed model outperforms baselines and achieves state-of-the-art results on two English benchmark datasets. |
Context-aware Watermark with Semantic Balanced Green-red Lists for Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent research suggests that watermarking methods cause degradation of text quality due to semantic disparities between the watermarked text and the unwatermarked text. |
| Approach: | They propose a semantic-aware watermark method that generates a watermark key considering contexts to split a green/red list for watermark injection. |
| Outcome: | The proposed method reduces performance drop due to adding bias on green lists . it also allows green lists to cover almost all semantics . |
Generative Text Modeling through Short Run Inference (2021.eacl-main)
Copied to clipboard
| Challenge: | Latent variable models for text capture global semantic and syntactic features when trained correctly. |
| Approach: | They propose a short run dynamics for inference that initializes from the prior distribution of the latent variable and runs a small number of Langevin dynamics steps guided by its posterior distribution. |
| Outcome: | The proposed model is able to generate coherent sentences with smooth transition and shows no sign of posterior collapse. |
Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge (2025.emnlp-main)
Copied to clipboard
Tianhao Wu, Weizhe Yuan, Olga Golovneva, Jing Xu, Yuandong Tian, Jiantao Jiao, Jason E Weston, Sainbayar Sukhbaatar
| Challenge: | Existing methods for improving large language models have focused on improving model responses rather than judgment capabilities, resulting in rapid saturation during iterative training. |
| Approach: | They propose an iterative Meta-Rewarding step where the model judges its own judgements and uses that feedback to refine its judgment skills. |
| Outcome: | The proposed model improves Llama-3-8B-Instruct from 22.9% to 39.4% on AlpacaEval 2 and 20.6% to 29.1% on Arena-Hard. |
PairCoder: Pair Programming-Inspired Two-Agent Collaboration for Code Generation (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing multi agent frameworks for large language models are brittle on code generation tasks. |
| Approach: | They propose a framework that brings pair programming to autonomous LLM collaboration. |
| Outcome: | Using PairCoder, large language models achieve better results on code generation tasks and reduce token usage by 40% to 70% on eight representative backbones. |
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. |
Train Once, and Decode As You Like (2020.coling-main)
Copied to clipboard
| Challenge: | Existing approaches to machine translation support autoregressive, semi-autoregressive and refinement-based non-auto-regressives. |
| Approach: | They propose a unified approach for supporting different generation manners of machine translation including autoregressive, semi-autoregressive and refinement-based non-auto-regressives. |
| Outcome: | The proposed approach achieves better or competitive translation performance compared with strong baseline models in all the settings. |
Do Multi-hop Readers Dream of Reasoning Chains? (D19-58)
Copied to clipboard
| Challenge: | Existing models for multihop reasoning are limited in their performance . multi-hop reasoning requires the ability to gather information from multiple passages . |
| Approach: | They propose a method that provides the full reasoning chain of multiple passages instead of just one final passage where the answer appears. |
| Outcome: | The proposed model improves on existing models by providing the full reasoning chain of multiple passages instead of just one final passage where the answer appears. |
TMFN: A Target-oriented Multi-grained Fusion Network for End-to-end Aspect-based Multimodal Sentiment Analysis (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods for multimodal aspect-based sentiment analysis focus on fusing image regional information and textual words. |
| Approach: | They propose a multimodal aspect-based sentiment analysis method that integrates regional and global image information with global image data. |
| Outcome: | Experiments show that the proposed method outperforms state-of-the-art methods on two benchmark datasets. |
Visual Evidence Prompting Mitigates Hallucinations in Large Vision-Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | LVLMs have shown impressive progress by integrating visual perception with linguistic understanding to produce contextually grounded outputs. |
| Approach: | They propose a visual evidence prompting method to mitigate hallucinations in large vision-language models by using small visual models to complement them. |
| Outcome: | The proposed method reduces hallucinations by reducing false activation and enhancing correct ones. |
MiLoRA: Efficient Mixture of Low-Rank Adaptation for Large Language Models Fine-tuning (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Low-rank adaptation and its mixture-of-experts (MOE) methods are highly effective but introduce significant latency in multi-tenant settings due to the LoRA modules and MOE routers added to multiple linear modules. |
| Approach: | They propose a low-rank adaptation variant that considers each LoRA module as an expert and employs a prompt-aware routing mechanism. |
| Outcome: | Extensive analysis on commonsense reasoning tasks and math reasoning tasks show that MiLoRA outperforms strong PEFT baselines with comparable tunable parameter budgets. |
Combinatory Grammar Tells Underlying Relevance among Entities (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches focus on dependencies among words while paying limited attention to other types of syntactic structure. |
| Approach: | They propose an alternative approach that takes advantage of combinatory categorial grammar to detect the relation between entities. |
| Outcome: | The proposed model performs state-of-the-art on two widely used English benchmark datasets. |
ReAttn: Improving Attention-based Re-ranking via Attention Re-weighting (2026.findings-eacl)
Copied to clipboard
| Challenge: | Attention-based re-ranking methods are highly concentrated a small subset of tokens within a few documents, making others indistinguishable. |
| Approach: | They propose a post-hoc re-weighting strategy that uses attention weights to reduce lexical bias and emphasize distinctive terms. |
| Outcome: | The proposed method reduces lexical bias and emphasizes distinctive terms across documents, while maintaining a balanced distribution across informative tokens. |
M2PA: A Multi-Memory Planning Agent for Open Worlds Inspired by Cognitive Theory (2025.findings-acl)
Copied to clipboard
YanfangZhou YanfangZhou, Xiaodong Li, Yuntao Liu, Yongqiang Zhao, Xintong Wang, Zhenyu Li, Jinlong Tian, Xinhai Xu
| Challenge: | Open-world planning poses a challenge due to complex environments and task diversity . recent work shows that large language models (LLMs) lack the ability to connect to agents' experiences . |
| Approach: | They propose an open-world multi-memory planning agent that combines large language models with human-like multi-mesh systems to leverage their strengths. |
| Outcome: | The proposed agent outperforms state-of-the-art agents on 50 Minecraft tasks in zero-shot learning. |
Reason in Chains, Learn in Trees: Self-Rectification and Grafting for Multi-turn Agent Policy Optimization (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to reinforcement learning for Large Language Models treat trajectories as independent chains and ignore critical steps that may disproportionally impact reasoning outcome. |
| Approach: | They propose a framework that recovers latent correlated reward structure across seemingly independent trajectories by identifying and merging functionally similar steps/nodes. |
| Outcome: | The proposed framework recovers latent correlated reward structure across seemingly independent trajectories. |
Enhancing Hindi Feature Representation through Fusion of Dual-Script Word Embeddings (2024.lrec-main)
Copied to clipboard
| Challenge: | Pretrained language models often neglect the integration of different scripts within a language, constraining their ability to capture richer semantic information. |
| Approach: | They propose a dual-script enhanced feature representation method for Hindi . they combine features from Devanagari and Romanized Hindi Roberta . |
| Outcome: | The proposed method improves model performance across multiple natural language processing tasks. |
Integrating Data Validation with Large Language Models for Regulation-Guided Tabular Anomaly Detection (2026.acl-long)
Copied to clipboard
| Challenge: | Existing tabular anomaly detection methods focus on detecting anomalies based on data distribution without considering regulatory compliance. |
| Approach: | They propose a task that leverages regulations to detect anomalies in tabular data . they also develop three new datasets to address this task . |
| Outcome: | The proposed method outperforms baselines on three new datasets. |
ALDEN: Reinforcement Learning for Active Navigation and Evidence Gathering in Long Documents (2026.acl-long)
Copied to clipboard
| Challenge: | Visually rich documents (VRDs) combine text, tables, and figures within complex, semantically structured layouts. |
| Approach: | They propose a multi-turn reinforcement learning framework that fine-tunes VLMs as interactive agents capable of actively navigating long, visually rich documents. |
| Outcome: | The proposed framework achieves state-of-the-art on five long-document benchmarks. |
Learning VAE-LDA Models with Rounded Reparameterization Trick (2020.emnlp-main)
Copied to clipboard
| Challenge: | No reparameterization form of Dirichlet distributions is known to date for topic models . |
| Approach: | They propose a method to reparameterize Dirichlet distributions for the learning of VAE-LDA models by using a latent Dirichlets prior. |
| Outcome: | The proposed method outperforms existing neural topic models on benchmark datasets and on a synthetic dataset. |
CTCC: A Robust and Stealthy Fingerprinting Framework for Large Language Models via Cross-Turn Contextual Correlation Backdoor (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for fingerprinting model ownership traces are vulnerable to illegal plagiarism and are not reliable. |
| Approach: | They propose a rule-driven fingerprinting framework that encodes contextual correlations across multiple dialogue turns. |
| Outcome: | The proposed framework achieves stronger stealth and robustness than previous work. |
DUCK: Rumour Detection on Social Media by Modelling User and Comment Propagation Networks (2022.naacl-main)
Copied to clipboard
| Challenge: | Social media rumours can cause significant economic and social disruption. |
| Approach: | They propose a rumour detection algorithm that leverages transformers and graph attention networks to jointly model social media conversations and the network of users who engaged in them. |
| Outcome: | The proposed algorithm produces superior performance over four widely used benchmark rumour datasets in English and Chinese. |
An Iterative Emotion Interaction Network for Emotion Recognition in Conversations (2020.coling-main)
Copied to clipboard
| Challenge: | Emotion recognition in conversations (ERC) is a task that aims to recognize the emotion of each utterance in conversations. |
| Approach: | They propose an iterative emotion interaction network which uses iterativly predicted emotion labels instead of gold emotion labels to explicitly model the emotion interaction. |
| Outcome: | The proposed method retains state-of-the-art performance on two datasets and achieves high accuracy. |
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. |
FastClass: A Time-Efficient Approach to Weakly-Supervised Text Classification (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent research shows keyword-driven methods can achieve state-of-the-art performance on various tasks. |
| Approach: | They propose an efficient weakly-supervised text classification approach using unlabeled data . they use dense text representation to retrieve class-relevant documents from unlabed corpus . |
| Outcome: | The proposed weakly-supervised classification method outperforms keyword-driven models on a wide range of classification tasks. |
Table-as-Search: Agentic Information Seeking is Table Completion (2026.findings-acl)
Copied to clipboard
Tian Lan, Felix Henry, Bin Zhu, Qianghuai Jia, Junyang Ren, Qihang PU, Haijun Li, Longyue Wang, Zhao Xu, Weihua Luo
| Challenge: | Current Information Seeking (InfoSeeking) agents struggle to maintain focus and coherence during long-horizon exploration, as tracking search states within one plain-text context is inherently fragile. |
| Approach: | They propose a structured planning framework that reformulates the InfoSeeking task as a Table Completion task. |
| Outcome: | The proposed framework outperforms state-of-the-art frameworks across three kinds of benchmarks, including multi-agent framework and commercial systems. |
Intent-Aware and Hate-Mitigating Counterspeech Generation via Dual-Discriminator Guided LLMs (2024.lrec-main)
Copied to clipboard
| Challenge: | Hate speech is an aggressive expression that incites hatred towards specific groups based on their group identity. |
| Approach: | They propose an LLMs-based framework for counterspeech generation that uses intent-aware discriminators to decode intents of LLM models. |
| Outcome: | The proposed framework matches intents with hate mitigation intents and performs well. |
End-to-end Aspect-based Sentiment Analysis with Combinatory Categorial Grammar (2023.findings-acl)
Copied to clipboard
| Challenge: | End-to-end aspect-based sentiment analysis (EASA) is a natural language processing task that requires a deep understanding of the running text. |
| Approach: | They propose a method to improve EASA with CCG supertags that carry syntactic and semantic information of the associated words. |
| Outcome: | The proposed approach outperforms baselines and achieves state-of-the-art results on all datasets. |
AgentCPM-GUI: Building Mobile-Use Agents with Reinforcement Fine-Tuning (2025.emnlp-demos)
Copied to clipboard
Zhong Zhang, Yaxi Lu, Yikun Fu, Yupeng Huo, Shenzhi Yang, Yesai Wu, Han Si, Xin Cong, Haotian Chen, Yankai Lin, Xie Xie, Wei Zhou, Wang Xu, Zhou Su, Zhongwu Zhai, Xiaoming Liu, null Meiyudong, Jianming Xu, Hongyan Tian, Chongyi Wang, Chi Chen, Yuan Yao, Zhiyuan Liu, Maosong Sun
| Challenge: | Large language model agents have enabled GUI-based automation, but their deployment is limited by noisy data, poor generalization, and lack of support for non-English GUIs. |
| Approach: | They propose an 8B-parameter GUI agent built for robust and efficient on-device GUI interaction. |
| Outcome: | The proposed GUI agent achieves promising performance on five public benchmarks and proposed Chinese benchmark CAGUI. |
D-Artemis: A Deliberative Cognitive Framework for Mobile GUI Multi-Agents (2026.findings-acl)
Copied to clipboard
Hongze Mi, Yibo Feng, WenJie Lu, Yuqi Wang, Jinyuan Li, Song Cao, He Cui, Tengfei Tian, Xuelin Zhang, Haotian Luo, Di Sun, Jun Fang, Hua Chai, Naiqiang Tan, Gang Pan
| Challenge: | Graphical User Interface (GUI) agents aim to automate a wide spectrum of human tasks by emulating user interaction. |
| Approach: | They propose a deliberative framework that leverages a fine-grained tip retrieval mechanism to inform its decision-making process. |
| Outcome: | The proposed framework achieves SOTA among open-source general models on AndroidWorld and ScreenSpot-V2 . it leverages a fine-grained, app-specific tip retrieval mechanism to inform its decision-making process . |
WkNER: Enhancing Named Entity Recognition with Word Segmentation Constraints and kNN Retrieval (2024.lrec-main)
Copied to clipboard
| Challenge: | Named Entity Recognition (NER) tasks require detecting the span and category of the entity from the text block. |
| Approach: | They propose a kNN retrieval enhancement algorithm that incorporates word segmentation information to enhance the model’s generalization ability and alleviate the problem of missing entity tokens in prediction. |
| Outcome: | The proposed method improves the performance of baseline models and achieves better or compared recognition accuracy than previous state-of-the-art models in multiple public Chinese and English datasets. |
Measuring Large Language Models’ Adversarial Behavior in Social Deduction Games (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing safety evaluations focus on refusal-based methods that test whether models avoid responding to inappropriate or violent requests, leaving open questions about how models behave in interactive social settings. |
| Approach: | They propose to use a meta-LLM to construct a closed behavioral taxonomy from a multi-agent simulation to examine adversarial behavior of large language models. |
| Outcome: | The proposed model-based model-driven model-model-based taxonomy shows that the model-led model-learning model exhibits distinct behavioral profiles and influences social stability and competitive success. |
Depth Growing for Neural Machine Translation (P19-1)
Copied to clipboard
| Challenge: | Neural machine translation models with tens and even more than a hundred blocks have shown effectiveness in image recognition. |
| Approach: | They propose a two-stage approach with three specially designed components to construct deeper NMT models. |
| Outcome: | The proposed approach improves on WMT14 EnglishGerman and EnglishFrench translation tasks. |
Exploring In-Image Machine Translation with Real-World Background (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing models for IIMT focus on simplified scenarios, which is far from reality and impractical for applications in the real world. |
| Approach: | They propose a model that separates the background and text-image from the source image and performs translation on the text- image directly. |
| Outcome: | The proposed model improves translation quality and visual effect in complex scenarios . it separates background and text-image from source image and performs translation on the text- image directly . |
PRIM: Towards Practical In-Image Multilingual Machine Translation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Current research on in-image machine translation focuses on synthetic data with simple background, single font, fixed text position, and bilingual translation. |
| Approach: | They propose an end-to-end model to handle the challenge of practical conditions in PRIM . they annotate a real-world one-line text image with complex background, fonts, diverse text positions . |
| Outcome: | The proposed model improves translation quality and visual effect compared to other models. |
Scene Restoring for Narrative Machine Reading Comprehension (2020.emnlp-main)
Copied to clipboard
| Challenge: | Narrative passages describe a chain of events, which helps the machine understand the passage comprehensively. |
| Approach: | They propose a method to let machine read narrative passages with their prior knowledge . they build a scene graph using Atomic as external knowledge and encode it with GDIN . |
| Outcome: | The proposed method achieves state-of-the-art on a Story Cloze Test and CosmosQA datasets. |
Improving Arabic Diacritization with Regularized Decoding and Adversarial Training (2021.acl-short)
Copied to clipboard
| Challenge: | Existing studies regard auto-generated knowledge instances as gold references, which limits their effectiveness since they are not always accurate and inferior instances can lead to incorrect predictions. |
| Approach: | They propose to use regularized decoding and adversarial training to appropriately learn from noisy knowledge instances for Arabic diacritization. |
| Outcome: | The proposed model outperforms existing models on two benchmark datasets even with flawed auto-generated knowledge. |
Translation or Recitation? Calibrating Evaluation Scores for Machine Translation of Extremely Low-Resource Languages (2026.acl-short)
Copied to clipboard
| Challenge: | Existing studies show that performance across low-resource settings is variable, resulting in a significant barrier for the MT community. |
| Approach: | They propose to use FRED Difficulty Metrics to contextualize reported performance across different language pairs to determine whether breakthroughs reported in other contexts are artifacts of benchmark collection. |
| Outcome: | The proposed metrics explain a significant portion of result variability rather than model capability. |
Multi-Condition Guided Diffusion Network for Multimodal Emotion Recognition in Conversation (2025.findings-naacl)
Copied to clipboard
| Challenge: | Current research emphasizes contextual factors, the speaker’s influence, and extracting complementary information across different modalities. |
| Approach: | They propose a diffusion-based approach to address the challenges posed by redundant information and redundant information at the semantic level while robustly capturing shared semantics. |
| Outcome: | The proposed model outperforms existing state-of-the-art models on two multimodal datasets and is generalizable and effective. |
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. |
From Fallback to Frontline: When Can LLMs be Superior Annotators of Human Perspectives? (2026.findings-acl)
Copied to clipboard
| Challenge: | large language models are often used as annotators at scale, but are not faithful estimators of human perspectives. |
| Approach: | They characterize the conditions under which large language models outperform human annotators . they find they are statistically superior frontline estimators based on low variance . |
| Outcome: | The proposed model outperforms human annotators when predicting subgroup opinions on subjective tasks. |
Multi-Agent Collaboration via Cross-Team Orchestration (2025.findings-acl)
Copied to clipboard
Zhuoyun Du, Chen Qian, Wei Liu, Zihao Xie, YiFei Wang, Rennai Qiu, Yufan Dang, Weize Chen, Cheng Yang, Ye Tian, Xuantang Xiong, Lei Han
| Challenge: | Large Language Models (LLMs) have significantly impacted various domains, especially through organized LLM-driven autonomous agents. |
| Approach: | They propose a framework that enables orchestrated teams to jointly propose various task-oriented solutions and interact with their insights in a self-independence while cross-team collaboration environment for superior solutions generation. |
| Outcome: | Experiments show that the framework can generate better software quality compared to state-of-the-art frameworks. |
DNA: Denoised Neighborhood Aggregation for Fine-grained Category Discovery (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to learn compact cluster representations from coarsely labeled data are noisy and degrade the quality of learning. |
| Approach: | They propose a framework that encodes semantic structures of data into the embedding space . they retrieve k-nearest neighbors of a query as positive keys to capture similarities . |
| Outcome: | The proposed framework can retrieve more accurate neighbors and outperform state-of-the-art models by a large margin. |
Amphista: Bi-directional Multi-head Decoding for Accelerating LLM Inference (2025.naacl-long)
Copied to clipboard
Zeping Li, Xinlong Yang, Ziheng Gao, Ji Liu, Guanchen Li, Zhuang Liu, Dong Li, Jinzhang Peng, Lu Tian, Emad Barsoum
| Challenge: | Existing methods such as Medusa lack adequate information interaction between different drafting heads. |
| Approach: | They propose an enhanced speculative decoding framework that builds upon Medusa and integrates a drafting block capable of parallel inference. |
| Outcome: | The proposed framework outperforms Medusa in terms of head accuracy and latency. |
Improving English-Arabic Transliteration with Phonemic Memories (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing neural approaches to transliterate names from English to Arabic are limited and focus on leveraging the phonemic association between English and Arabic. |
| Approach: | They propose a model for English-Arabic transliteration using a memory module modeling the phonemic association between English and Arabic to guide the transliterations process. |
| Outcome: | The proposed model improves on EANames corpus, which better represents names in the general public than linked Wikipedia entries that are always names of famous people. |
BOSE: A Systematic Evaluation Method Optimized for Base Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing evaluation methods for large language models (LLMs) are inadequate to provide solid conclusions for key experiments such as data ablation and scaling law. |
| Approach: | They propose a method specifically designed to optimize the evaluation of base models by incorporating two innovations: In-Context Light-instruction Prompt and Blank-ppl for multi-choice tasks with candidate options. |
| Outcome: | The proposed method significantly improves stability and consistency of evaluations during pre-training and consistency between base and instruct models. |
Towards Database-Free Text-to-SQL Evaluation: A Graph-Based Metric for Functional Correctness (2025.coling-main)
Copied to clipboard
Yi Zhan, Longjie Cui, Han Weng, Guifeng Wang, Yu Tian, Boyi Liu, Yingxiang Yang, Xiaoming Yin, Jiajun Xie, Yang Sun
| Challenge: | Existing metrics for evaluating functional correctness of SQL queries are prone to false positives due to inadequately prepared test databases. |
| Approach: | They propose a graph-based metric that uses a relational operator tree to extract rich semantic information from the logical execution plan of SQL queries and embed it into a diagram. |
| Outcome: | The proposed method eliminates the need for extensive test database preparation and performs graph matching on unseen SQL queries. |
FLAT-LLM: Fine-grained Low-rank Activation Space Transformation for Large Language Model Compression (2026.findings-eacl)
Copied to clipboard
| Challenge: | Low-rank decomposition methods suffer from accuracy degradation and expensive calibration procedures. |
| Approach: | They propose a fast and accurate, training-free structural compression method based on fine-grained low-rank transformations in the activation space. |
| Outcome: | The proposed method outperforms pruning baselines in generalization and downstream performance while delivering inference speedups. |
Improving Meta-learning for Low-resource Text Classification and Generation via Memory Imitation (2022.acl-long)
Copied to clipboard
Yingxiu Zhao, Zhiliang Tian, Huaxiu Yao, Yinhe Zheng, Dongkyu Lee, Yiping Song, Jian Sun, Nevin Zhang
| Challenge: | Building models of natural language processing (NLP) is challenging in low-resource scenarios where limited data are available. |
| Approach: | They propose a memory imitation meta-learning method that enhances the model’s reliance on support sets for task adaptation. |
| Outcome: | The proposed method outperforms baselines on both text classification and generation tasks. |
TabularMath: Understanding Math Reasoning over Tables with Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Mathematical reasoning has long been a key benchmark for evaluating large language models. |
| Approach: | They propose a framework that transforms math word problems into scalable tabular reasoning tasks. |
| Outcome: | The proposed framework transforms math word problems into scalable and verified tabular reasoning tasks. |
Mitigating Boundary Ambiguity and Inherent Bias for Text Classification in the Era of Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | a new text classification framework for large language models addresses the problem of boundary ambiguity and inherent biases in LLMs. |
| Approach: | They propose a two-stage classification framework for large language models to mitigate bottlenecks . their approach uses pairwise comparisons to efficiently narrow down options . |
| Outcome: | The proposed framework reduces the number of options and improves on four datasets. |
Towards Safer Large Language Models through Machine Unlearning (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing work attempted to implement a gradient ascent based approach to prevent LLMs from producing harmful output when faced with problematic prompts. |
| Approach: | They propose a gradient ascent based approach to prevent LLMs from producing harmful output when faced with problematic prompts. |
| Outcome: | The proposed approach eliminates harmful knowledge while preserving utility on normal prompts. |
Investigating Transfer Learning in Multilingual Pre-trained Language Models through Chinese Natural Language Inference (2021.findings-acl)
Copied to clipboard
| Challenge: | Multilingual transformers have been shown to have remarkable transfer skills in zero-shot settings. |
| Approach: | They investigate cross-lingual transfer abilities of XLM-R for Chinese and English natural language inference using a large scale Chinese dataset. |
| Outcome: | The proposed model trains on Chinese and English natural language inference datasets. |
FineSteer: A Unified Framework for Fine-Grained Inference-Time Steering in Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for inference-time steering fail to be effective, utility-preserving and training-efficient due to rigid, one-size-fits-all designs and limited adaptability. |
| Approach: | They propose a steering framework that decomposes inference-time steering into two stages . they propose 'conditional steering' mechanism that preserves model utility by avoiding unnecessary steering . a 'mixture-of-Steering-Experts' mechanism captures multimodal nature of desired steering behaviors . |
| Outcome: | The proposed framework outperforms the state-of-the-art methods on safety and truthfulness benchmarks. |
Tree of Agents: Improving Long-Context Capabilities of Large Language Models through Multi-Perspective Reasoning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models face persistent challenges when handling long-context tasks . existing methods that reduce input have the risk of discarding key information . |
| Approach: | To address this issue, we propose a multi-agent reasoning framework called Tree of Agents . the framework segments input into chunks processed by independent agents . |
| Outcome: | The proposed model outperforms baseline models on long-context tasks. |
Semi-Supervised Lifelong Language Learning (2022.findings-emnlp)
Copied to clipboard
Yingxiu Zhao, Yinhe Zheng, Bowen Yu, Zhiliang Tian, Dongkyu Lee, Jian Sun, Yongbin Li, Nevin L. Zhang
| Challenge: | Existing methods to learn languages only focus on supervised learning, and unlabeled data is underexplored. |
| Approach: | They propose a semi-supervised lifelong language learning setting where a model learns sequentially arriving language tasks with both labeled and unlabeled data. |
| Outcome: | The proposed model outperforms baseline models on various language tasks and is effective and superior to existing models. |
How Are Idioms Processed Inside Transformer Language Models? (2023.starsem-1)
Copied to clipboard
| Challenge: | idioms are prevalent in natural language, but how do they be processed? |
| Approach: | They analyze the embeddings of idiomatic and literal expressions across all layers of the networks at both the sentence and word levels. |
| Outcome: | The proposed models represent idioms distinctively compared to literal language, the study finds . |
MMAC: A Multilingual, Multimodal Alignment Framework for Cultural Grounding Evaluation (2026.acl-long)
Copied to clipboard
Weihua Zheng, Zhengyuan Liu, Tanmoy Chakraborty, Weiwen Xu, Xiaoxue Gao, Bryan Chen Zhengyu Tan, Bowei Zou, Chang Liu, Yujia Hu, Xing Xie, Xiaoyuan Yi, Jing Yao, Chaojun Wang, Long Li, Rui Liu, Huiyao Liu, Koji Inoue, Ryuichi Sumida, Tatsuya Kawahara, Fan Xu, Lingyu Ye, Wei Tian, Dongjun Kim, Jimin Jung, Jaehyung Seo, Nadya Yuki Wangsajaya, Pham Minh Duc, Ojasva Saxena, Palash Nandi, Xiyan Tao, Wiwik Karlina, Tuan Luong, Keertana Arun Vasan, Roy Ka-Wei Lee, Nancy F. Chen
| Challenge: | Existing models lack cultural alignment across modalities and languages . a new framework to assess cultural awareness across linguistics and languages is needed . |
| Approach: | They propose a framework that integrates tri-modally aligned cultural benchmarks and a five-dimensional evaluation protocol to assess cross-country awareness disparities. |
| Outcome: | The proposed framework assesses cultural awareness disparities across modalities and languages . it is the first dataset aligned at the input level across text, image, and speech . |
Path-enhanced Pre-trained Language Model for Knowledge Graph Completion (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Pre-trained language models have achieved remarkable knowledge graph completion (KGC) success. |
| Approach: | They propose a path-enhanced pre-trained language model-based knowledge graph completion method which uses multi-view generation to infer missing facts in triple-level and path-level simultaneously. |
| Outcome: | The proposed method significantly improves the performance of the knowledge graph completion task. |
POMP: Probability-driven Meta-graph Prompter for LLMs in Low-resource Unsupervised Neural Machine Translation (2024.acl-long)
Copied to clipboard
| Challenge: | Low-resource languages (LRLs) face challenges in supervised neural machine translation due to limited parallel data. |
| Approach: | They propose a method that uses a dynamic graph to organize auxiliary languages in prompts to improve LRL translations. |
| Outcome: | The proposed method improves translation accuracy in low-resource languages (LRLs) using auxiliary language pairs and synthetic pseudo-parallel data. |
MixTEA: Semi-supervised Entity Alignment with Mixture Teaching (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to learn informative entity embeddings are insufficient for semi-supervised entity alignment. |
| Approach: | They propose a semi-supervised method which guides the model learning with an end-to-end mixture teaching of manually labeled mappings and probabilistic pseudo mappings. |
| Outcome: | The proposed method is superior to existing methods on benchmark datasets and further analyses. |
Prompt Conditioned VAE: Enhancing Generative Replay for Lifelong Learning in Task-Oriented Dialogue (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing generative replay methods use only a single task-specific token to control their models. |
| Approach: | They propose a method to capture task-specific distributions with a conditional variational autoencoder, conditioned on natural language prompts to guide the pseudo-sample generation. |
| Outcome: | The proposed method outperforms baselines on natural language understanding tasks of advanced task-oriented dialogue (ToD) systems. |
McBE: A Multi-task Chinese Bias Evaluation Benchmark for Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing datasets on bias evaluation for large language models focus on English and North American culture and are limited to one task. |
| Approach: | They propose to evaluate Chinese language models' biases from multiple perspectives using a multi-task Chinese Bias Evaluation Benchmark. |
| Outcome: | The proposed model covers 12, 82 subcategories and 5 evaluation tasks covering a wide range of categories and content diversity. |
Text-to-TrajVis: Enabling Trajectory Data Visualizations from Natural Language Questions (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing datasets for this task are limited and there is no suitable one available. |
| Approach: | They propose a new visualization language called Trajectory Visualization Language (TVL) to facilitate querying trajectory data and generating visualizations. |
| Outcome: | The proposed language can be used to query and generate trajectory data and generate visualizations with large language models. |
TencentPretrain: A Scalable and Flexible Toolkit for Pre-training Models of Different Modalities (2023.acl-demo)
Copied to clipboard
Zhe Zhao, Yudong Li, Cheng Hou, Jing Zhao, Rong Tian, Weijie Liu, Yiren Chen, Ningyuan Sun, Haoyan Liu, Weiquan Mao, Han Guo, Weigang Gou, Taiqiang Wu, Tao Zhu, Wenhang Shi, Chen Chen, Shan Huang, Sihong Chen, Liqun Liu, Feifei Li, Xiaoshuai Chen, Xingwu Sun, Zhanhui Kang, Xiaoyong Du, Linlin Shen, Kimmo Yan
| Challenge: | Several pre-training models of different modalities are showing a rising trend of homogeneity in their model structures. |
| Approach: | They propose a toolkit that supports pre-training models of different modalities. |
| Outcome: | The proposed toolkit can match the performance of the original implementations on text, vision, and audio benchmarks. |
Probabilistic Tree-of-thought Reasoning for Answering Knowledge-intensive Complex Questions (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models (LLMs) are capable of answering knowledge-intensive complex questions with chain-of-thought reasoning. |
| Approach: | They propose a method to solve complex questions with a tree-of-thought approach using parametric knowledge and retrieved external knowledge to augment CoT reasoning. |
| Outcome: | The proposed approach outperforms SOTA methods on three Complex QA datasets under the open-domain setting. |
The Devil is in the Distributions: Explicit Modeling of Scene Content is Key in Zero-Shot Video Captioning (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing methods for zero-shot video captioning focus on one key aspect of the scene and ignore the rest of the visual input. |
| Approach: | They propose a novel textual prompting strategy for zero-shot video captioning that uses a category-aware retrieval mechanism to promote prompt diversity while ensuring visual relevance. |
| Outcome: | The proposed method outperforms existing methods on in-domain and cross-domain settings. |
PlanGenLLMs: A Modern Survey of LLM Planning Capabilities (2025.acl-long)
Copied to clipboard
| Challenge: | Existing studies have focused on developing LLMs to automate complex planning tasks. |
| Approach: | They propose to provide a comprehensive overview of current LLM planners to fill this gap . they examine performance criteria including completeness, executability, optimality, representation, generalization, and efficiency . |
| Outcome: | The proposed survey examines performance criteria for LLM planners and highlights their strengths and weaknesses. |
CoRe-MMRAG: Cross-Source Knowledge Reconciliation for Multimodal RAG (2025.acl-long)
Copied to clipboard
| Challenge: | Recent advances in Multimodal Large Language Models have significantly improved reasoning and generation tasks by leveraging joint vision-language representations. |
| Approach: | They propose a framework that reconciles inconsistencies across knowledge sources . they use a four-stage pipeline to generate an internal response from parametric knowledge . |
| Outcome: | Experiments on KB-VQA show that CoRe-MMRAG achieves performance gains of 5.6% and 9.3% over baseline methods. |
Are Large Language Models Capable of Generating Human-Level Narratives? (2024.emnlp-main)
Copied to clipboard
Yufei Tian, Tenghao Huang, Miri Liu, Derek Jiang, Alexander Spangher, Muhao Chen, Jonathan May, Nanyun Peng
| Challenge: | a recent HCI study has pointed to gaps in machine storytelling ability at the global level . authors show that LLMs have less suspense and less tension than human stories . |
| Approach: | They propose a computational framework to analyze narratives through three discourse-level aspects. |
| Outcome: | The proposed framework analyzes narratives through three discourse-level aspects . it shows that LLMs fall short of human abilities in discourse understanding . |
CARL: Constraint-Aware Reinforcement Learning for Planning with LLMs (2026.findings-acl)
Copied to clipboard
Qiuyi Qi, Jinjian Zhang, Mutian Bao, Tian Liang, Guocong Li, Dongnan Liu, Wei Zhou, Jie Liu, Ming Kong, Linjian Mo, Feng Zhang, Qiang Zhu
| Challenge: | Existing approaches to constraint-aware planning fail to enhance the model’s intrinsic focus on constraints. |
| Approach: | They propose a constraint-aware reinforcement learning framework that encourages constraint focus and penalizes neglect of LLMs. |
| Outcome: | The proposed framework outperforms existing frameworks and state-of-the-art reasoning models in a number of real-world applications. |
A Framework of Knowledge Graph-Enhanced Large Language Model Based on Question Decomposition and Atomic Retrieval (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to enhance LLMs with knowledge graphs have limited results . knowledge graph question answering (KGQA) provides interpretable reasoning for large language models . |
| Approach: | They propose a framework for KG-enhanced LLM based on question decomposition and atomic retrieval . they propose question decomposing tree as framework for LLM reasoning . |
| Outcome: | The proposed framework outperforms existing reasoning-based baselines on KGQA datasets. |
Multi-Hop Knowledge Editing via Critic-Guided Multi-Agent Reasoning (2026.findings-acl)
Copied to clipboard
Xudong Li, Yuhang Tian, Dandan Song, Zhijing Wu, Shuhao Zhang, Jun Yang, Yongyu Huo, Changzhi Zhou, Xinyu Zhang, Chenhao Li, Huipeng Ma, Luan Zhang, Yan Xu, Qian Liu
| Challenge: | Existing knowledge editing methods rely on unidirectional, feed-forward pipelines . a minor retrieval error or logical mismatch at an early hop can become a silent failure . |
| Approach: | They propose a framework for closed-loop post-edit reasoning that uses a Critic agent to verify coherence and step-wise correctness. |
| Outcome: | Experiments on MQuAKE-2002 and MQuADE-hard show that CARE effectively mitigates error propagation . a minor retrieval error or logical mismatch at an early hop can become a silent failure . |
A Study of Reinforcement Learning for Neural Machine Translation (D18-1)
Copied to clipboard
| Challenge: | Recent studies have shown that reinforcement learning (RL) is an effective approach for improving the performance of neural machine translation systems. |
| Approach: | They propose to leverage reinforcement learning to boost the performance of NMT systems trained with monolingual data. |
| Outcome: | The proposed method achieves competitive results on translation tasks in English-German, Chinese-English and English-English systems. |
A Fast and High-quality Text-to-Speech Method with Compressed Auxiliary Corpus and Limited Target Speaker Corpus (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods to generate high-quality speech with limited target speaker corpus require extensive training data. |
| Approach: | They propose an auxiliary corpus compression algorithm that reduces the training cost while the naturalness of synthesized speech is not significantly degraded. |
| Outcome: | The proposed method significantly reduces training costs while maintaining the naturalness of synthesized speech. |
CogGen: A Cognitively Inspired Recursive Framework for Deep Research Report Generation (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to deep research report generation rely on rigid predefined linear workflows, which cause error accumulation and limit in-depth multimodal fusion and report quality. |
| Approach: | They propose a Cognitively inspired recursive framework for deep research report Generation that simulates cognitive writing and abstract visual representation (AVR) they also propose CLEF, a cognitive load evaluation framework, and a benchmark from our world in data. |
| Outcome: | The proposed framework achieves state-of-the-art among open-source systems, surpassing Gemini Deep Research. |
LLM-based Rumor Detection via Influence Guided Sample Selection and Game-based Perspective Analysis (2025.acl-long)
Copied to clipboard
Zhiliang Tian, Jingyuan Huang, Zejiang He, Zhen Huang, Menglong Lu, Linbo Qiao, Songzhu Mei, Yijie Wang, Dongsheng Li
| Challenge: | Existing methods for rumor detection on social media are limited by limited modeling capacity and insufficient training corpora. |
| Approach: | They propose an SFT-based rumor detection model with Influence guided Sample selection and Game-based multi-perspective analysis to address these issues. |
| Outcome: | The proposed model outperforms existing SOTA on three datasets. |
Named Entity Recognition for Social Media Texts with Semantic Augmentation (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches for named entity recognition suffer from data sparsity problems when conducted on short and informal texts. |
| Approach: | They propose a neural-based approach to named entity recognition for social media texts . they obtain augmented semantic information from a large-scale corpus and encode it . |
| Outcome: | The proposed approach outperforms existing approaches on three social media datasets. |
CharacterEval: A Chinese Benchmark for Role-Playing Conversational Agent Evaluation (2024.acl-long)
Copied to clipboard
| Challenge: | CharacterEval is a benchmark for comprehensive RPCA assessment in Chinese . authors show that Chinese LLMs exhibit more promising capabilities than GPT-4 in role-playing conversation. |
| Approach: | They propose a Chinese benchmark for comprehensive RPCA assessment . they use a dataset of Chinese role-playing dialogues and character profiles . |
| Outcome: | The proposed benchmark demonstrates that Chinese LLMs exhibit more promising capabilities than GPT-4 in Chinese role-playing conversation. |
Friendly Topic Assistant for Transformer Based Abstractive Summarization (2020.emnlp-main)
Copied to clipboard
| Challenge: | Abstractive document summarization is a comprehensive task in natural language processing. |
| Approach: | They propose a topic assistant that rearranges and learns document semantics . they propose TA that is compatible with Transformer-based models and user-friendly . |
| Outcome: | The proposed model is compatible with Transformer-based models and user-friendly. |
Towards Trustworthy Smart Contract Synthesis: A Multi-Agent Framework with Lean-Based Verification (2026.acl-long)
Copied to clipboard
| Challenge: | Smart Contracts are the foundation of Decentralized Finance (DeFi), executing financial logic without trusted intermediaries. |
| Approach: | They propose a framework that integrates LLM-based generation with Lean-based auto-formalization and verification. |
| Outcome: | LeVer is the first trustworthy smart contract synthesis framework that integrates LLM-based generation with Lean-based auto-formalization and verification. |
Self-Improvement in Multimodal Large Language Models: A Survey (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Using data and data, self-improvement for Large Language Models has improved model capabilities without significantly increasing costs. |
| Approach: | This survey provides a comprehensive overview of self-improvement for Large Language Models . it includes commonly used evaluations and downstream applications . |
| Outcome: | The authors provide a comprehensive overview of self-improvement in Multimodal LLMs. |
F²Bench: An Open-ended Fairness Evaluation Benchmark for LLMs with Factuality Considerations (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing fairness evaluation benchmarks for large language models rely on closed-ended evaluation formats that overlook factuality considerations rooted in historical, social, physiological, and cultural contexts. |
| Approach: | They propose an open-ended fairness evaluation benchmark for large language models . they incorporate factuality considerations and multi-turn reasoning into the benchmark . |
| Outcome: | The proposed benchmark incorporates factual grounding and text generation to better reflect the complexities of real-world model usage. |
A Simple and Effective Method to Improve Zero-Shot Cross-Lingual Transfer Learning (2022.coling-1)
Copied to clipboard
Kunbo Ding, Weijie Liu, Yuejian Fang, Weiquan Mao, Zhe Zhao, Tao Zhu, Haoyan Liu, Rong Tian, Yiren Chen
| Challenge: | Existing zero-shot cross-lingual transfer methods rely on parallel corpora or bilingual dictionaries . however, its effect is limited by the gap between embedding clusters of different languages . |
| Approach: | They propose Embedding-Push, Attention-Pull, and Robust targets to transfer English embeddings to virtual multilingual embedders without semantic loss. |
| Outcome: | Experimental results show that the proposed method outperforms existing methods on cross-lingual tasks and can achieve a better multilingual alignment. |
CLUE: A Chinese Language Understanding Evaluation Benchmark (2020.coling-main)
Copied to clipboard
Liang Xu, Hai Hu, Xuanwei Zhang, Lu Li, Chenjie Cao, Yudong Li, Yechen Xu, Kai Sun, Dian Yu, Cong Yu, Yin Tian, Qianqian Dong, Weitang Liu, Bo Shi, Yiming Cui, Junyi Li, Jun Zeng, Rongzhao Wang, Weijian Xie, Yanting Li, Yina Patterson, Zuoyu Tian, Yiwen Zhang, He Zhou, Shaoweihua Liu, Zhe Zhao, Qipeng Zhao, Cong Yue, Xinrui Zhang, Zhengliang Yang, Kyle Richardson, Zhenzhong Lan
| Challenge: | Existing language evaluation benchmarks for English are limited to English . lack of such benchmarks makes it difficult to replicate success in other languages . |
| Approach: | They introduce a large-scale Chinese language understanding evaluation benchmark . the benchmark uses a set of current state-of-the-art pre-trained Chinese models . |
| Outcome: | The first large-scale Chinese Language Understanding Evaluation (CLUE) benchmark is released . the benchmark evaluates models across a wide range of tasks on original Chinese text . existing language evaluation benchmarks are mostly limited to English . |
Summarizing Medical Conversations via Identifying Important Utterances (2020.coling-main)
Copied to clipboard
| Challenge: | Applying natural language processing (NLP) techniques to the medical field is a prevailing trend nowadays and has great potential in many applications, such as key information extraction in medical literature. |
| Approach: | They propose to use a hierarchical encoder-tagger model to generate medical conversation summarization by identifying important utterances. |
| Outcome: | The proposed model outperforms baseline models and models and adds conversation-related features to improve performance. |
Dual Capsule Attention Mask Network with Mutual Learning for Visual Question Answering (2022.coling-1)
Copied to clipboard
| Challenge: | Visual Question Answering (VQA) models extract features from images and questions independently, but these methods fail to capture fine-grained key features and include much unnecessary information. |
| Approach: | They propose a dual capsule attention mask network with mutual learning for visual question answering (VQA) it contains two branches processing coarse-grained features and fine-grain features, respectively. |
| Outcome: | The proposed model outperforms baselines in terms of performance and interpretability and achieves new SOTA performance on the VQA-v2 dataset. |
Measuring Bargaining Abilities of LLMs: A Benchmark and A Buyer-Enhancement Method (2024.findings-acl)
Copied to clipboard
| Challenge: | Using a novel approach, we can evaluate an agent’s bargaining abilities as an asymmetric incomplete information game. |
| Approach: | They propose an approach that integrates a deterministic Offer Generator and an LLM Narrator to create natural language sentences for generated offers. |
| Outcome: | The proposed approach improves the buyer’s deal rates from 26.67% to 88.88% and brings a ten times multiplication of profits on all baselines, even a model that has not been aligned. |
Clip-Tuning: Towards Derivative-free Prompt Learning with a Mixture of Rewards (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing work does not take full advantage of over-parameterized characteristics of large pre-trained language models. |
| Approach: | They propose a method that uses frozen "thinned" networks to obtain a mixture of rewards and advance the derivative-free prompt learning. |
| Outcome: | The proposed method outperforms previous gradient-free prompt learning methods and achieves parity with gradient-based counterparts on seven language understanding benchmarks under few-shot settings. |
Facilitating Long Context Understanding via Supervised Chain-of-Thought Reasoning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models (LLMs) have enabled them to process increasingly longer sequences, ranging from 2K to 2M tokens and even beyond. |
| Approach: | They propose a synthetic dataset in the financial domain that integrates Chain-of-Thought reasoning into LLMs in a supervised manner to facilitate effective long-context understanding. |
| Outcome: | The proposed model outperforms standard GPT-4o-mini on the Loong benchmark and fine tunes LLaMA-3.1-8B-Instruct on the model, achieving a 28.0% gain on the financial subset. |
REFFLY: Melody-Constrained Lyrics Editing Model (2025.naacl-long)
Copied to clipboard
| Challenge: | Automatic melody-to-lyric (M2L) generation aims to create lyrics that align with a given melody. |
| Approach: | They propose a framework for automatic melody-to-lyric generation that allows for a more flexible approach to creating lyrics from plain text. |
| Outcome: | The proposed framework outperforms baselines Lyra and GPT-4 in musicality and text quality. |
Attention Consistency for LLMs Explanation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing interpretability methods face limitations such as low resolution and high computational cost. |
| Approach: | They propose a multi-layer attention consistency score to estimate the importance of input tokens in large language models. |
| Outcome: | The proposed heuristic achieves a favorable trade-off between interpretability quality and computational efficiency . |
Hierarchical Text Classification with Reinforced Label Assignment (D19-1)
Copied to clipboard
| Challenge: | Existing hierarchical text classification methods make local decisions regarding labels or ignore hierarchy information during inference. |
| Approach: | They propose to learn a Label Assignment Policy via deep reinforcement learning to determine where to place an object and when to stop the assignment process. |
| Outcome: | The proposed method outperforms state-of-the-art methods on five datasets and four base models and achieves an average improvement of 33.4% over flat classifiers. |
Context-Fidelity Boosting: Enhancing Faithful Generation through Watermark-Inspired Decoding (2026.findings-acl)
Copied to clipboard
Weixu Zhang, Fanghua Ye, Qiang Gao, Jian Li, Haolun Wu, Yuxing Tian, Sijing Duan, Nan Du, Xiaolong Li
| Challenge: | Large language models produce content that contradicts or overlooks information provided in the input context, a phenomenon known as faithfulness hallucination. |
| Approach: | They propose a lightweight framework that boosts the generation probability of context-relevant tokens by boosting the generation of tokens. |
| Outcome: | The proposed framework improves faithfulness metrics with minimal generation overhead. |
A Symbolic Adversarial Learning Framework for Evolving Fake News Generation and Detection (2025.emnlp-main)
Copied to clipboard
| Challenge: | Rapid LLM advancements heighten fake news risks by enabling the automatic generation of increasingly sophisticated misinformation. |
| Approach: | They propose a framework that implements an adversarial training paradigm by an agent symbolic learning optimization process rather than numerical updates. |
| Outcome: | The proposed framework generates sophisticated fake news that degrades state-of-the-art detection performance by 53.4% in Chinese and 34.2% in English on average. |
Multi-step Entity-centric Information Retrieval for Multi-Hop Question Answering (D19-58)
Copied to clipboard
Rajarshi Das, Ameya Godbole, Dilip Kavarthapu, Zhiyu Gong, Abhishek Singhal, Mo Yu, Xiaoxiao Guo, Tian Gao, Hamed Zamani, Manzil Zaheer, Andrew McCallum
| Challenge: | Multi-hop question answering (QA) requires an information retrieval system that can find multiple supporting evidence needed to answer the question. |
| Approach: | They propose a technique that uses information of entities present in the initial retrieved evidence to learn to ‘hop’ onto other relevant evidence. |
| Outcome: | The proposed method boosts retrieval performance on a multi-hop question answering dataset with 5 million Wikipedia paragraphs and a model without training increases its performance by 10.59 F1. |
Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback (2023.emnlp-main)
Copied to clipboard
Katherine Tian, Eric Mitchell, Allan Zhou, Archit Sharma, Rafael Rafailov, Huaxiu Yao, Chelsea Finn, Christopher Manning
| Challenge: | Recent studies have shown that unsupervised pre-training produces large language models whose conditional probabilities are remarkably well-calibrated. |
| Approach: | They propose to use verbalized confidences to extract confidence from large language models with reinforcement learning from human feedback to improve their accuracy. |
| Outcome: | The proposed methods reduce the expected calibration error by 50% for RLHF-LMs such as ChatGPT, GPT-4, and Claude. |
CoDraw: Collaborative Drawing as a Testbed for Grounded Goal-driven Communication (P19-1)
Copied to clipboard
Jin-Hwa Kim, Nikita Kitaev, Xinlei Chen, Marcus Rohrbach, Byoung-Tak Zhang, Yuandong Tian, Dhruv Batra, Devi Parikh
| Challenge: | a goal-driven collaborative drawing task combines language, perception, and actions in a partially observable environment . et al., 1990: 138K messages exchanged between human players. |
| Approach: | They propose a goal-driven collaborative task that combines language, perception, and action . they collect a clip art dataset and use it to build an image-drawing game between two agents . |
| Outcome: | The proposed task integrates language, perception, and action in a virtual world . it is based on a dataset of 10K dialogs and 138K messages exchanged between humans . |
SeCuRepair: Semantics-Aligned, Curriculum-Driven, and Reasoning-Enhanced Vulnerability Repair Framework (2026.acl-long)
Copied to clipboard
Chengran Yang, Ting Zhang, Jinfeng Jiang, Xin Zhou, Haoye Tian, Mingzhe Du, Jieke Shi, Junkai Chen, Yikun Li, Eng Lieh Ouh, Lwin Khin Shar, David Lo
| Challenge: | Existing methods for automating vulnerability repair suffer from syntactic overfitting . nvd published 49,230 Common Vulnerabilities and Exposures (CVE) records in 2025 alone . |
| Approach: | They propose a semantic-aware reward framework that optimizes for code semantic equivalence rather than lexical mimicry. |
| Outcome: | The proposed framework outperforms state-of-the-art frameworks on repository-level splits . it incorporates expert-aligned reasoning mechanism that grounds patch generation in structured diagnosis. |
PLATO-XL: Exploring the Large-scale Pre-training of Dialogue Generation (2022.findings-aacl)
Copied to clipboard
Siqi Bao, Huang He, Fan Wang, Hua Wu, Haifeng Wang, Wenquan Wu, Zhihua Wu, Zhen Guo, Hua Lu, Xinxian Huang, Xin Tian, Xinchao Xu, Yingzhan Lin, Zheng-Yu Niu
| Challenge: | Experimental results show PLATO-XL achieves state-of-the-art results across multiple conversational tasks. |
| Approach: | They propose to train PLATO-XL models with up to 11 billion parameters, trained on Chinese and English social media conversations. |
| Outcome: | The proposed model achieves state-of-the-art on multiple conversational tasks, verifying its potential as a foundation model of conversational AI. |
Token Alignment via Character Matching for Subword Completion (2024.findings-acl)
Copied to clipboard
Ben Athiwaratkun, Shiqi Wang, Mingyue Shang, Yuchen Tian, Zijian Wang, Sujan Kumar Gonugondla, Sanjay Krishna Gouda, Robert Kwiatkowski, Ramesh Nallapati, Parminder Bhatia, Bing Xiang
| Challenge: | Generative models struggle with prompts corresponding to partial tokens due to tokenization, where partial token is out-of-distribution during inference. |
| Approach: | They propose a method to alleviate tokenization artifact on text completion by backtracking to the last complete tokens and aligning subsequent generations to match with the prompt. |
| Outcome: | The proposed method shows that it improves on partial token scenarios with only a minor time increase. |
Specialization without Sparsity: Efficient and Expressive Split-Path Experts for LLM Fine-Tuning (2026.findings-acl)
Copied to clipboard
| Challenge: | Parameter-efficient fine-tuning (PEFT) is a low-cost alternative to full fine-timing due to the massive overhead. |
| Approach: | They propose a Mixture-of-Experts approach that enhances specialization while maintaining low resource overhead. |
| Outcome: | The proposed approach outperforms or matches state-of-the-art methods on GLUE, GSM8K, MBPP, and a text rewriting task from SmolTalk. |
Evaluating Large Language Models on Controlled Generation Tasks (2023.emnlp-main)
Copied to clipboard
Jiao Sun, Yufei Tian, Wangchunshu Zhou, Nan Xu, Qian Hu, Rahul Gupta, John Wieting, Nanyun Peng, Xuezhe Ma
| Challenge: | Recent studies have looked into the ability of large language models in various benchmark tasks, including question generation, reading comprehension, multilingual and etc. However, few studies investigate the controllability of large languages. |
| Approach: | They propose to compare large language models with state-of-the-start finetuned smaller models to find that large language model controls are comparable to smaller models. |
| Outcome: | The proposed model can meet hard constraints and perform better than state-of-the-art models. |
Lunar-Bench: Towards Evaluating Task-Oriented Reasoning of LLMs in Lunar Exploration Scenarios (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing benchmarks focus on static, context-independent reasoning tasks and fail to capture constraints and dependencies of lunar missions. |
| Approach: | They propose a benchmark to assess the task-oriented reasoning and decision-making performance of large language models through 3,000 tasks derived from mission procedures and documentation. |
| Outcome: | The proposed model achieves 47.8% accuracy compared with 65.1% for human experts on 36 representative missions. |
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. |
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. |
CORAL: Learning Consistent Representations across Multi-step Training with Lighter Speculative Drafter (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods that focus on training and inference suffer from misalignment . speculative decoding is a powerful technique that accelerates large language models . |
| Approach: | They propose a framework that improves both accuracy and efficiency in speculative drafting by using cross-step representational alignment. |
| Outcome: | The proposed framework outperforms existing methods on three LLM families and three benchmark datasets. |
Relation Extraction with Word Graphs from N-grams (2021.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies for relation extraction (RE) leverage the dependency tree of the input sentence to improve performance. |
| Approach: | They propose to use a graph convolutional network to build a context graph without dependency parsers. |
| Outcome: | The proposed approach improves neural RE methods without dependency parsers on English benchmark datasets. |
TamEdit: Trajectory-Aware Meta-Learning for Specificity-Preserving Continual Knowledge Editing (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for continual knowledge editing focus on single edits or preventing knowledge forgetting. |
| Approach: | They propose a meta-learning method that preserves specificity for continual knowledge editing by capturing relationships between different single edits within the trajectory. |
| Outcome: | Experiments show that TamEdit outperforms baselines in continual editing while preserving general capabilities. |
Dictionaries to the Rescue: Cross-Lingual Vocabulary Transfer for Low-Resource Languages Using Bilingual Dictionaries (2025.findings-acl)
Copied to clipboard
Haruki Sakajo, Yusuke Ide, Justin Vasselli, Yusuke Sakai, Yingtao Tian, Hidetaka Kamigaito, Taro Watanabe
| Challenge: | Existing approaches to cross-lingual vocabulary transfer face challenges when dealing with low-resource languages. |
| Approach: | They propose a dictionary-based crosslingual vocabulary transfer method that leverages bilingual dictionaries, which are available for many languages thanks to descriptive linguists. |
| Outcome: | The proposed method outperforms existing methods for low-resource languages. |
Cross-Modal Masked Compositional Concept Modeling for Enhancing Visio-Linguistic Compositionality (2026.acl-long)
Copied to clipboard
| Challenge: | a contrastive learning approach for vision-language models is needed to capture compositional information. |
| Approach: | They propose a framework that masks compositional concepts in one modality and reconstructs them conditioned on full contextual information from the other . |
| Outcome: | The proposed framework enhances compositionality in visual language models and improves their ability to capture syntactic structure and linguistic information. |
mOthello: When Do Cross-Lingual Representation Alignment and Cross-Lingual Transfer Emerge in Multilingual Models? (2024.findings-naacl)
Copied to clipboard
| Challenge: | Pretrained multilingual models exhibit cross-lingual transfer ability, which is often attributed to a learned language-neutral representation during pretraining. |
| Approach: | They propose a synthetic task, Multilingual Othello, as a testbed to investigate the factors that contribute to the learning of a language-neutral representation. |
| Outcome: | The proposed approach induces the learning of language-neutral representation and facilitates cross-lingual transfer. |
Does Vision-and-Language Pretraining Improve Lexical Grounding? (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Large pretrained language models (LMs) have been criticized for lack of grounding, i.e., connecting words to their meanings in the physical world. |
| Approach: | They compare vision-and-language (VL) models trained jointly on text and image or video data to find out how they compare to text-only counterparts. |
| Outcome: | The proposed model outperforms the text-only variants on a commonsense question answering task. |
Offensive Language Detection Using Brown Clustering (2020.lrec-1)
Copied to clipboard
| Challenge: | a recent study shows that Brown clustering is of little use when distinguishing word polarity in sentiment analysis tasks. |
| Approach: | They investigate the use of Brown clustering for offensive language detection . they train Brown clusters separately on positive and negative sentiment data, then combine it into a single complex feature per word . |
| Outcome: | The proposed method improves offensive language detection when used as the only feature or with words or character n-grams. |
Chain-of-Memory: Lightweight Memory Construction with Dynamic Evolution for LLM Agents (2026.acl-long)
Copied to clipboard
| Challenge: | Existing paradigms for large language model (LLM) agents use memory construction and retrieval-augmented generation. |
| Approach: | They propose a framework that advocates for a paradigm shift toward lightweight construction paired with sophisticated utilization. |
| Outcome: | Experiments show that CoM outperforms baselines with accuracy gains of 7.5%–10.4% while reducing computational overhead to approximately 2.7% of token consumption and 6.0% of latency compared to complex memory architectures. |
SEE: Signal Embedding Energy for Quantifying Noise Interference in Large Audio Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Existing studies on noise lack quantitative analysis and rely on intuition and empirical observation, thus failing to understand practical robustness. |
| Approach: | They propose a method for quantifying the impact of noise intensity on LALM inputs by using a structured activation subspace derived from the model's internal representations. |
| Outcome: | The proposed method outperforms existing denoising methods and demonstrates that noise is perceived more accurately than raw audio features. |
Alignment-Augmented Speculative Decoding with Alignment Sampling and Conditional Verification (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to accelerate autoregressive generation of large language models require training costs. |
| Approach: | They propose a training-free alignment-augmented speculative decoding algorithm . it leverages the output distribution obtained in the prefilling phase to provide more aligned draft candidates . |
| Outcome: | The proposed method increases the average generation score by 3.3 points for the LLaMA3 model. |
MathCanvas: Intrinsic Visual Chain-of-Thought for Multimodal Mathematical Reasoning (2026.acl-long)
Copied to clipboard
Weikang Shi, Aldrich Yu, Rongyao Fang, Houxing Ren, Ke Wang, Aojun Zhou, Changyao Tian, Xinyu Fu, Yuxuan Hu, Zimu Lu, Linjiang Huang, Si Liu, Rui Liu, Hongsheng Li
| Challenge: | Existing approaches to visual chain-of-thought are limited by external tools or fail to generate high-fidelity diagrams. |
| Approach: | They propose a framework to enable large multimodal models with VCoT capabilities . they pre-train a model on a 15.2M-pair corpus and teach it how to leverage visual aids . |
| Outcome: | The proposed framework unlocks complex, human-like visual reasoning in large language models . it pre-trains the model on a 15.2M-pair corpus and fine-tunes it on MathCanvas-Instruct . |
Intuitive Fine-Tuning: Towards Simplifying Alignment into a Single Process (2025.acl-long)
Copied to clipboard
| Challenge: | Supervised Fine-Tuning (SFT) and Preference Optimization (PO) are key processes for aligning Language Models with human preferences post pre-training. |
| Approach: | They propose to combine Supervised Fine-Tuning and Preference Optimization (PO) with two sub-processes defined at token level within the Markov Decision Process (MDP) |
| Outcome: | The proposed process performs comparably or even superiorly to SFT and some typical PO methods across several tasks, particularly those requires generation, reasoning, and fact-following abilities. |
Exploring the Capability Boundaries of LLMs in Mastering of Chinese Chouxiang Language (2026.findings-acl)
Copied to clipboard
Dianqing Lin, Tian Lan, Jiali Zhu, Jiang Li, Wei Chen, Xu Liu, null Aruukhan, Xiangdong Su, Hongxu Hou, Guanglai Gao
| Challenge: | Current state-of-the-art LLMs exhibit clear limitations on multiple tasks, while performing well on tasks that involve contextual semantic understanding. |
| Approach: | They propose a mouse-based benchmark to evaluate LLMs' performance on NLP tasks involving Chouxiang Language. |
| Outcome: | The proposed benchmark evaluates the performance of LLMs on six NLP tasks involving Chouxiang Language. |
Tracing the Light of Thought: A Probabilistic Self- and Cross-Consistency Verification Mechanism Improving Mathematical Reasoning in LLMs (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for evaluating reasoning paths are not efficient, but they are prone to errors. |
| Approach: | They propose a probabilistic self- and cross-consistency framework for mathematical reasoning that employs an accept-reject mechanism to encourage high-quality reasoning paths. |
| Outcome: | The proposed framework improves on 9 LLMs across 4 challenging benchmarks. |
Interactive Key-Value Memory-augmented Attention for Image Paragraph Captioning (2020.coling-main)
Copied to clipboard
| Challenge: | Existing approaches to image paragraph captioning ignore the past alignment information, resulting in repetitive captioning and incomplete captioning. |
| Approach: | They propose an Interactive key-value Memory-augmented Attention model for image paragraph captioning to keep track of attention history along with update-chain of decoder state. |
| Outcome: | Extensive experiments on a benchmark dataset demonstrate the effectiveness of the proposed model. |
Dovetail: A CPU/GPU Heterogeneous Speculative Decoding for LLM inference (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) are demanding more memory and computational resources . however, these devices typically feature weaker GPUs and stronger CPUs . |
| Approach: | They propose a lossless inference acceleration method that leverages the characteristics of heterogeneous devices and the advantages of speculative decoding. |
| Outcome: | The proposed method achieves speedups ranging from 1.79 to 10.1 across different devices . it uses a draft model on the GPU to perform preliminary predictions, while a target model on CPU validates these outputs . |
Unlocking Black-Box Prompt Tuning Efficiency via Zeroth-Order Optimization (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Prompt optimization is an important technique for adapting Large Language Models (LLMs) to specific tasks. |
| Approach: | They propose a zeroth-order approach which enables efficient prompt tuning solely via inference APIs. |
| Outcome: | The proposed approach outperforms existing black-box prompt tuning methods in terms of performance and convergence speed. |
OD-Stega: LLM-Based Relatively Secure Steganography via Optimized Distributions (2026.eacl-long)
Copied to clipboard
| Challenge: | In coverless steganography, secret bits are embedded in as few language tokens as possible . stego-texts can be decoded by eavesdroppers, but are difficult to detect . |
| Approach: | They propose a method to embed secret bits in language tokens using a Large Language Model . they propose maximizing the entropy of a replacement probability distribution . |
| Outcome: | The proposed method should embed secret bits in as few language tokens as possible while keeping the stego-text as natural as possible. |
Can We Edit Multimodal Large Language Models? (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to edit multimodal models have been used to incrementally infuse a language model with a new set of facts. |
| Approach: | They construct a benchmark for editing multimodal Large Language Models and establish metrics for evaluation. |
| Outcome: | The proposed benchmarks show that editing multimodal models is not as difficult as editing single-modal models. |
ERNIE-M: Enhanced Multilingual Representation by Aligning Cross-lingual Semantics with Monolingual Corpora (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for pretraining cross-lingual models are limited in their size due to the limited amount of parallel corpora. |
| Approach: | They propose a method that encourages the model to align multiple languages with monolingual corpora to overcome the constraint of the parallel corpus size. |
| Outcome: | The proposed method outperforms existing cross-lingual models and delivers new state-of-the-art results in various cross-linguistic downstream tasks. |
Interpretable and Compositional Relation Learning by Joint Training with an Autoencoder (P18-1)
Copied to clipboard
| Challenge: | Embedding models for entities and relations are useful for recovering missing facts in knowledge bases. |
| Approach: | They propose a dimension reduction technique by training relations jointly with an autoencoder to capture compositional constraints. |
| Outcome: | The proposed model improves on Knowledge Base Completion tasks with a significantly higher mean rank and better compositional training. |
SALT: Step-level Advantage Assignment for Long-horizon Agents via Trajectory Graph (2026.findings-eacl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable capabilities, but their application to complex, multi-step, and long-horizon tasks remains challenging. |
| Approach: | They propose a framework that provides a finer-grained advantage assignment derived solely from outcome rewards. |
| Outcome: | The proposed framework provides a finer-grained advantage assignment, derived solely from outcome rewards. |
Editing Large Language Models: Problems, Methods, and Opportunities (2023.emnlp-main)
Copied to clipboard
Yunzhi Yao, Peng Wang, Bozhong Tian, Siyuan Cheng, Zhoubo Li, Shumin Deng, Huajun Chen, Ningyu Zhang
| Challenge: | Recent advances in model editing for LLMs have created challenges and opportunities for the community. |
| Approach: | They propose to alter the behavior of LLMs efficiently within a specific domain without negatively impacting performance across other inputs. |
| Outcome: | The proposed method alters behavior of LLMs efficiently within a specific domain without negatively impacting performance across other inputs. |
FAER: Benchmarking VLMs for Failure-Aware Embodied Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Visual-language models (VLMs) are the core component of embodied agents in perceiving the environment and making decisions. |
| Approach: | They propose a failure-aware benchmark to evaluate the performance of visual language models (VLMs) in long-horizon tasks. |
| Outcome: | The proposed benchmark evaluates the performance of 16 widely utilized VLMs and 4 LLMs for FAER tasks. |
Speech-Hands: A Self-Reflection Voice Agentic Approach to Speech Recognition and Audio Reasoning with Omni Perception (2026.acl-long)
Copied to clipboard
Zhen Wan, Chao-Han Huck Yang, Jinchuan Tian, Hanrong Ye, Ankita Pasad, Szu-Wei Fu, Arushi Goel, Ryo Hachiuma, Shizhe Diao, Kunal Dhawan, Sreyan Ghosh, Yusuke Hirota, Zhehuai Chen, Rafael Valle, Chenhui Chu, Shinji Watanabe, Boris Ginsburg, Yu-Chiang Frank Wang
| Challenge: | naively fine-tuning an omni-model on speech recognition and external sound understanding tasks often degrades performance . Xie and Wu's framework, Speech-Hands, recasts the problem as an explicit self-reflection decision. |
| Approach: | They propose a voice-agentic framework that learns one critical omni-understanding skill: trusting itself versus external audio perception. |
| Outcome: | The proposed framework outperforms baseline models on the OpenASR leaderboard by 12.1% WER and high F1 on audio QA decisions. |
Relation-Specific Attentions over Entity Mentions for Enhanced Document-Level Relation Extraction (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing document-level relation extraction methods do not distinguish between mention-level features and entity-level feature . document-based methods are more challenging because of multiple mentions of entities. |
| Approach: | They propose a method which selectively attentions different entity mentions with respect to candidate relations and performs relation-specific representations of entities. |
| Outcome: | The proposed method improves relation-specific representations of entities on two benchmark datasets. |
Harnessing Black-Box Control to Boost Commonsense in LM’s Generation (2023.emnlp-main)
Copied to clipboard
| Challenge: | Recent years have seen remarkable progress in massively Pre-Trained Language Models such as GPT-3 . however, their generated outputs lack commonsense at times . |
| Approach: | They propose a framework that steers a frozen Pre-Trained Language Model towards more commonsense generation by training an auxiliary model. |
| Outcome: | The proposed framework produces plausible outputs that incorporate concepts in a meaningful way. |
Enhancing Relation Extraction via Adversarial Multi-task Learning (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing studies have focused on re-modeling the given NEs and thus lead to inferior results when NE is sometimes ambiguous. |
| Approach: | They propose a relation extraction model with two training stages that uses adversarial multi-task learning to recover the given NEs. |
| Outcome: | The proposed model improves on two English benchmark datasets and shows state-of-the-art performance. |
P-React: Synthesizing Topic-Adaptive Reactions of Personality Traits via Mixture of Specialized LoRA Experts (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing studies on personalized large language models focus on modeling explicit character profiles, while ignoring the underlying personality traits that truly shape behaviors and decision-making. |
| Approach: | They propose a personalized large language model (LLM) that captures implicit Big Five personality traits and integrates a Personality Specialization Loss to capture individual trait expressions. |
| Outcome: | The proposed model improves on Big Five personality traits and integrates a Personality Specialization Loss (PSL) to capture individual trait expressions. |
SpeechIQ: Speech-Agentic Intelligence Quotient Across Cognitive Levels in Voice Understanding by Large Language Models (2025.acl-long)
Copied to clipboard
Zhen Wan, Chao-Han Huck Yang, Yahan Yu, Jinchuan Tian, Sheng Li, Ke Hu, Zhehuai Chen, Shinji Watanabe, Fei Cheng, Chenhui Chu, Sadao Kurohashi
| Challenge: | SIQ quantifies voice understanding abilities and provides unified comparisons between cascaded methods and end-to-end models. |
| Approach: | They propose a human cognition-inspired evaluation pipeline for voice understanding large language models (LLM_Voice) that quantifies voice understanding abilities and provides unified comparisons between cascaded methods and end-to-end models. |
| Outcome: | The proposed framework quantifies voice understanding abilities and provides unified comparisons between cascaded methods and end-to-end models, identifies annotation errors in existing benchmarks, and detects hallucinations in LLM_Voice. |
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. |
PLUE: Language Understanding Evaluation Benchmark for Privacy Policies in English (2023.acl-short)
Copied to clipboard
| Challenge: | Existing efforts to understand privacy policies are limited by processing the language in a way exclusive to a single task focusing on certain privacy practices. |
| Approach: | They propose a privacy policy language understanding evaluation benchmark to evaluate the understanding of privacy policies across multiple tasks. |
| Outcome: | The proposed framework improves the understanding of privacy policies across multiple tasks. |
SDAR: A Synergistic Diffusion-AutoRegression Paradigm for Scalable Sequence Generation (2026.findings-acl)
Copied to clipboard
Shuang Cheng, Yihan Bian, Dawei Liu, Yuhua Jiang, Yihao Liu, Linfeng Zhang, Qian Yao, Zhongbo Tian, Wenhai Wang, Qipeng Guo, Kai Chen, Biqing Qi, Bowen Zhou
| Challenge: | Autoregressive (AR) language models are a dominant paradigm in the field of parallelism and non-causal modeling. |
| Approach: | They propose a blockwise discrete diffusion model that preserves AR-compatible serving while enabling parallel intra-block generation. |
| Outcome: | The proposed model achieves theoretical speedups over 5 and wall-clock speedup of 2.3 on H200 GPUs in latency-critical regimes. |
RGL: A Simple yet Effective Relation Graph Augmented Prompt-based Tuning Approach for Few-Shot Learning (2022.findings-naacl)
Copied to clipboard
| Challenge: | Pre-trained language models (PLMs) are a good starting point for downstream applications, but it is difficult to generalize them to new tasks given a few labeled samples. |
| Approach: | They propose to use Relation Graph augmented learning to improve the performance of few-shot natural language understanding tasks by rewriting the input sequence into a cloze question with masks. |
| Outcome: | Extensive experiments show that Relation Graph augmented learning (RGL) improves performance of prompt-based tuning strategies. |
Supertagging Combinatory Categorial Grammar with Attentive Graph Convolutional Networks (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies have focused on supertagging but have not tapped into contextual information. |
| Approach: | They propose to build a graph from chunks extracted from a lexicon and apply attention over it to enhance supertagging by leveraging contextual information. |
| Outcome: | The proposed approach outperforms previous studies in terms of supertagging and parsing. |
Reinforcement Learning for Self-Improving Agent with Skill Library (2026.acl-long)
Copied to clipboard
Jiongxiao Wang, Qiaojing Yan, Yawei Wang, Yijun Tian, Soumya Smruti Mishra, Zhichao Xu, Megha Gandhi, Panpan Xu, Lin Lee Cheong
| Challenge: | Large Language Model (LLM)-based agents have demonstrated remarkable capabilities in complex reasoning and multi-turn interactions but struggle to continuously improve and adapt when deployed in new environments. |
| Approach: | They propose a Reinforcement Learning-based approach to enhance agents’ self-improvement capabilities with a skill library. |
| Outcome: | The proposed framework achieves 8.9% higher Scenario Goal Completion when applied to supervised-finetuned model with expert experience while requiring 26% fewer interaction steps and generating 59% fewer tokens. |
DPN-LE: Dual Personality Neuron Localization and Editing for Large Language Models (2026.findings-acl)
Copied to clipboard
Lifan Zheng, Xue Yang, Jiawei Chen, Chenyan WU, Jingyuan Zhang, Fanheng Kong, Xinyi Zeng, Xiang Chen, Yu Tian
| Challenge: | Current methods for editing personality traits in large language models can change personalities but reduce performance. |
| Approach: | They propose a novel paradigm for personality editing that locates and edits LLM neurons and enables competitive personality control at inference time. |
| Outcome: | Experiments on LLaMA-3-8B-Instruct and Qwen2.5-7B-instruct show that the proposed approach can improve performance and improve 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. |
RethinkingTMSC: An Empirical Study for Target-Oriented Multimodal Sentiment Classification (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Recent studies have shown that current TMSC systems rely on textual information, and the progress in tackling this task has slowed down. |
| Approach: | They propose to integrate both visual and textual information to improve the performance of TMSC by considering multimodal information. |
| Outcome: | The proposed model integrates both visual and textual information to improve performance. |
Learning Multimodal Contrast with Cross-modal Memory and Reinforced Contrast Recognition (2024.findings-acl)
Copied to clipboard
| Challenge: | Using a memory module, we learn multimodal contrast using encoding-decoding paradigm . multimodal information are used in many applications, including news feeding, social media, etc. |
| Approach: | They propose an LLM-based approach for learning multimodal contrast following the encoding-decoding paradigm . they use a memory module with reinforced contrast recognition to enhance learning . |
| Outcome: | The proposed approach outperforms baseline and state-of-the-art studies on four English and Chinese benchmark datasets. |
Explicit Alignment and Many-to-many Entailment Based Reasoning for Conversational Machine Reading (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Recent research has explored how to improve the abilities of decision-making and question generation. |
| Approach: | They propose a pipeline framework that aligns the document and user-provided information in an explicit way, makes decisions using a lightweight many-to-many entailment reasoning module and generates follow-up questions based on the document. |
| Outcome: | The proposed framework achieves state-of-the-art in micro-accuracy and ranks the first place on the public leaderboard of the CMR benchmark dataset ShARC. |
Beyond True or False: Retrieval-Augmented Hierarchical Analysis of Nuanced Claims (2025.acl-long)
Copied to clipboard
| Challenge: | Claims are often nuanced and cannot be clearly labeled as “true” or “false” . however, a claim can be dissected into integral aspects and sub-aspects that are individually easier to validate . |
| Approach: | They propose a retrieval-augmented generation-based framework for deconstructing nuanced claims . claim can be dissected into integral aspects and sub-aspects, which are easier to validate . |
| Outcome: | The proposed framework can be easily deconstructed into integral aspects and sub-aspects, which are easier to validate. |
Dialogue Summarization with Mixture of Experts based on Large Language Models (2024.acl-long)
Copied to clipboard
| Challenge: | Existing studies for dialogue summarization use one model at a time or treat it as a black box. |
| Approach: | They propose an LLM-based approach with role-oriented routing and fusion generation to utilize mixture of experts for dialogue summarization. |
| Outcome: | The proposed approach produces informative and accurate dialogue summarization on widely used datasets. |
HiGoE: Hierarchical Graph of Evidence to Enhance Retrieval-Augmented Generation for Long-context Summarization (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for long-context summarization fail to capture high-level thematic structures and long-range dependencies. |
| Approach: | They propose a hierarchical Graph of Evidence to reduce hallucination and attention dilution by replacing unreliable chunk-based methods with a filtered proposition–evidence graph. |
| Outcome: | Experiments show that HiGoE surpasses baselines in quality and efficiency. |
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. |
Emergence of Abstract State Representations in Embodied Sequence Modeling (2023.emnlp-main)
Copied to clipboard
| Challenge: | Sequence modeling is a simple yet versatile task that can be applied to more complex decision-making domains. |
| Approach: | They build a sequence modeling Transformer which takes a language instruction, actions, and environmental observations as inputs and then trains a model to reconstruct environmental layouts. |
| Outcome: | The proposed model can reconstruct environmental layouts from the inputs of the model and language instructions play a role in the reconstruction accuracy. |
A Large-Scale Chinese Multimodal NER Dataset with Speech Clues (2021.acl-long)
Copied to clipboard
| Challenge: | Using a large-scale dataset, we explore Chinese named entity recognition (NER) with both textual and acoustic contents. |
| Approach: | They propose a Chinese multimodal named entity recognition dataset . their corpus contains 42,987 annotated sentences and 71 hours of speech data . |
| Outcome: | The proposed model yields state-of-the-art (SoTA) results on Chinese multimodal named entity recognition (NER) based on 42,987 annotated sentences and 71 hours of speech data. |
AutoBreach: Universal and Adaptive Jailbreaking with Efficient Wordplay-Guided Optimization via Multi-LLMs (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing jailbreak research exhibits limitations in universality, validity, and efficiency . Existing methods for jailbreaking LLMs have limited validity and effectiveness . |
| Approach: | They propose a black-box approach that uses wordplay-guided mapping rule sampling to create universal adversarial prompts. |
| Outcome: | The proposed method efficiently identifies security vulnerabilities across various LLMs, achieving an average success rate of over 80% with fewer than 10 queries. |
BSCodec: A Band-Split Neural Codec for High-Quality Universal Audio Reconstruction (2026.findings-eacl)
Copied to clipboard
| Challenge: | Neural audio codecs have enabled high-fidelity reconstruction of speech, music and sound . however, speech-optimized codec systems suffer degradation on music or sound if they ignore spectral differences . |
| Approach: | They propose a neural audio codec that splits the spectral dimension into separate bands and compresses each band independently. |
| Outcome: | Experimental results show that BSCodec achieves better reconstruction quality on music and sound compared to existing codecs. |
Understanding User Resistance Strategies in Persuasive Conversations (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Persuasive dialog systems have various usages, such as donation persuation and physical exercise persulasion. |
| Approach: | They adopt a preliminary framework on persuasion resistance in psychology and build a fine-grained resistance strategy annotation scheme to analyze the persuitee's resistance strategies. |
| Outcome: | The proposed system can understand and address user resistance strategies appropriately. |
Confidence-Calibrated Small-Large Language Model Collaboration for Cost-Efficient Reasoning (2026.eacl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have superior reasoning capabilities compared to small language models, but incur substantially higher inference costs. |
| Approach: | They propose a system that cascades an LLM with an SLM to achieve a balance between accuracy and cost in complex reasoning tasks. |
| Outcome: | The proposed system improves the SLM’s reasoning ability and confidence calibration across diverse datasets and model backbones. |
Local Additivity Based Data Augmentation for Semi-supervised NER (2020.emnlp-main)
Copied to clipboard
| Challenge: | Named Entity Recognition (NER) is one of the first stages in deep language understanding yet current NER models heavily rely on human-annotated data. |
| Approach: | They propose a Local Additivity based Data Augmentation method for semi-supervised Named Entity Recognition (NER) that creates virtual samples by interpolating sequences close to each other. |
| Outcome: | The proposed method improves both entity and context learning by adding to training data and extending it to semi-supervised setting. |
SAMP: A Model Inference Toolkit of Post-Training Quantization for Text Processing via Self-Adaptive Mixed-Precision (2023.emnlp-industry)
Copied to clipboard
| Challenge: | Existing methods for quantization of models are too complicated and can cause performance damage. |
| Approach: | They propose a self-adaptive mixed-precision (SAMP) toolkit to automatically control quantization rate by a mixed-presence architecture to balance model accuracy and efficiency. |
| Outcome: | The proposed toolkit has a higher speedup than PyTorch and FasterTransformer while ensuring the required accuracy. |
R3 Prompting: Review, Rephrase and Resolve for Chain-of-Thought Reasoning in Large Language Models under Noisy Context (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies have evaluated LLMs under noise-free context but the dilemma for LLM to produce inaccurate results under noisy context has not been fully investigated. |
| Approach: | They propose a new method for CoT reasoning using Chain-of-Thought prompting that interacts with LLMs to perform key sentence extraction, variable declaration and answer prediction. |
| Outcome: | The proposed method outperforms existing CoT prompting methods on five reasoning tasks under noisy context. |
Joint Chinese Word Segmentation and Part-of-speech Tagging via Multi-channel Attention of Character N-grams (2020.coling-main)
Copied to clipboard
| Challenge: | Chinese word segmentation and part-of-speech tagging can be performed in a sequential order . existing studies have shown that jointly performing them can be effective . |
| Approach: | They propose a character-based neural model enhanced by multi-channel attention of n-grams. |
| Outcome: | The proposed model outperforms baseline models on five benchmark datasets. |
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. |
ChatMusician: Understanding and Generating Music Intrinsically with LLM (2024.findings-acl)
Copied to clipboard
Ruibin Yuan, Hanfeng Lin, Yi Wang, Zeyue Tian, Shangda Wu, Tianhao Shen, Ge Zhang, Yuhang Wu, Cong Liu, Ziya Zhou, Liumeng Xue, Ziyang Ma, Qin Liu, Tianyu Zheng, Yizhi Li, Yinghao Ma, Yiming Liang, Xiaowei Chi, Ruibo Liu, Zili Wang, Chenghua Lin, Qifeng Liu, Tao Jiang, Wenhao Huang, Wenhu Chen, Jie Fu, Emmanouil Benetos, Gus Xia, Roger Dannenberg, Wei Xue, Shiyin Kang, Yike Guo
| Challenge: | Despite LLMs' impressive capabilities in musical knowledge, music reasoning remains an unsolved task. |
| Approach: | They propose an open-source large language model (LLM) that integrates intrinsic musical abilities into LLaMA2 and GPT-3.5. |
| Outcome: | The proposed model can understand and generate music with a pure text tokenizer without external multi-modal neural structures or tokenizers. |
Don’t Get Lost in the Trees: Streamlining LLM Reasoning by Overcoming Tree Search Exploration Pitfalls (2025.acl-long)
Copied to clipboard
Ante Wang, Linfeng Song, Ye Tian, Dian Yu, Haitao Mi, Xiangyu Duan, Zhaopeng Tu, Jinsong Su, Dong Yu
| Challenge: | Recent advances in tree search algorithms guided by verifiers have significantly enhanced the reasoning capabilities of large language models (LLMs), but at the cost of increased computational resources. |
| Approach: | They propose an e ffici ent tree sear ch framework that is a plug-and-play system compatible with various tree search algorithms. |
| Outcome: | The proposed framework reduces computational costs and prioritizes resource allocation to harder tasks (Levels 3-4) over simpler ones (Level 1-2), addressing both over-exploration in basic problems and under-exploation in complex cases. |
Training Language Models to Critique With Multi-agent Feedback (2025.findings-emnlp)
Copied to clipboard
Tian Lan, Wenwei Zhang, Chengqi Lyu, Shuaibin Li, Chen Xu, Heyan Huang, Dahua Lin, Xian-Ling Mao, Kai Chen
| Challenge: | utilizing human annotations can enhance critique ability, but model-generated critiques suffer from inherent flaws due to complexity of critique . a new framework that leverages multi-agent feedback improves critique ability . |
| Approach: | They propose a framework that leverages multi-agent feedback to improve critique ability . they propose to use supervised fine-tuning and reinforcement learning to improve this capability . |
| Outcome: | The proposed framework improves critique ability in both supervised fine-tuning and reinforcement learning stages. |
Task-oriented Word Embedding for Text Classification (C18-1)
Copied to clipboard
| Challenge: | Existing word embeddings only consider contextual information, which is suboptimal when used in various tasks due to a lack of task-specific features. |
| Approach: | They propose a task-oriented word embedding method that regularizes the distribution of words to enable a clear classification boundary. |
| Outcome: | The proposed method outperforms the state-of-the-art methods on a text classification task. |
TUNA: Comprehensive Fine-grained Temporal Understanding Evaluation on Dense Dynamic Videos (2025.acl-long)
Copied to clipboard
Fanheng Kong, Jingyuan Zhang, Hongzhi Zhang, Shi Feng, Daling Wang, Linhao Yu, Xingguang Ji, Yu Tian, V. W., Fuzheng Zhang
| Challenge: | Existing benchmarks for video understanding often focus on specific aspects, overlooking the holistic nature of video content. |
| Approach: | They propose a temporal-oriented benchmark for fine-grained understanding on dense dynamic videos with two complementary tasks: captioning and QA. |
| Outcome: | The proposed model performs well on diverse video scenarios and dynamic videos, with interpretable and robust evaluation criteria. |
Zero-shot Sonnet Generation with Discourse-level Planning and Aesthetics Features (2022.naacl-main)
Copied to clipboard
| Challenge: | a sonnet is a fourteen-line poem with rigorous meter-and-rhyme constraints. |
| Approach: | They propose a framework which plans the poem sketch before decoding a sonnet without training on poems . they use a rhyme module, polishing module and a constrained decoding algorithm to impose the meter-and-rhyme constraint . |
| Outcome: | The proposed framework generates sonnets that are coherent and poetic without training on poems . the proposed framework is based on a framework that plans the poem sketch before decoding . |
The Medium Is Not the Message: Deconfounding Document Embeddings via Linear Concept Erasure (2025.emnlp-main)
Copied to clipboard
| Challenge: | Embedding-based similarity metrics can be influenced by content dimensions and spurious attributes like the text’s source or language. |
| Approach: | They propose a debiasing algorithm that removes observed confounders from encoder representations and removes them from the encoder. |
| Outcome: | The proposed method improves on out-of-distribution benchmarks and on benchmarks, but performance is not affected. |
GLTW: Joint Improved Graph Transformer and LLM via Three-Word Language for Knowledge Graph Completion (2025.findings-acl)
Copied to clipboard
Kangyang Luo, Yuzhuo Bai, Cheng Gao, Shuzheng Si, Zhu Liu, Yingli Shen, Zhitong Wang, Cunliang Kong, Wenhao Li, Yufei Huang, Ye Tian, Xuantang Xiong, Lei Han, Maosong Sun
| Challenge: | Existing knowledge graphs lack the ability to integrate structural information into LLMs and output predictions deterministically. |
| Approach: | They propose a method which encodes structural information of KGs and merges it with LLMs to enhance KGC performance. |
| Outcome: | The proposed method improves the performance of KG Completion datasets on KGs by integrating structural information with LLMs. |
In-Image Neural Machine Translation with Segmented Pixel Sequence-to-Sequence Model (2023.findings-emnlp)
Copied to clipboard
| Challenge: | In-Image Machine Translation (IIMT) aims to convert images containing texts from one language to another. |
| Approach: | They propose an end-to-end model instead of the traditional cascade methods which use optical character recognition followed by neural machine translation and text rendering. |
| Outcome: | The proposed model outperforms both cascade methods and current model in translation quality and robustness across various dimensions. |
Go Back in Time: Generating Flashbacks in Stories with Event Temporal Prompts (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing systems that generate *flashbacks* are monotonic and lack explicit guidance on how to insert them. |
| Approach: | They propose to use event temporal orders to encode events as temporal prompts . they leverage a Plan-and-Write framework enhanced by reinforcement learning to generate storylines . |
| Outcome: | The proposed method generates more interesting stories with *flashbacks* while maintaining textual diversity, fluency, and temporal coherence. |
Premise-based Multimodal Reasoning: Conditional Inference on Joint Textual and Visual Clues (2022.acl-long)
Copied to clipboard
Qingxiu Dong, Ziwei Qin, Heming Xia, Tian Feng, Shoujie Tong, Haoran Meng, Lin Xu, Zhongyu Wei, Weidong Zhan, Baobao Chang, Sujian Li, Tianyu Liu, Zhifang Sui
| Challenge: | Existing work in vision language cross-modal reasoning uses binary or multi-choice classification based on source image and textual query. |
| Approach: | They propose a task where a textual premise is the background presumption on each source image. |
| Outcome: | The proposed task is based on a dataset of 15,360 movie screenshots and human-curated premise templates from 6 pre-defined categories. |
SCAN: Structured Capability Assessment and Navigation for LLMs (2026.acl-long)
Copied to clipboard
| Challenge: | Existing research has focused on approximating model rankings, but such benchmarks fail to provide users and developers with a comprehensive and fine-grained understanding of a specific model’s capabilities. |
| Approach: | They propose a framework that enables detailed characterization of LLM capabilities through comprehensive and fine-grained evaluation. |
| Outcome: | The proposed framework enables detailed characterization of large language models through comprehensive and fine-grained evaluation. |
PUPPET: Neural-Symbolic Standardized Patients for Mental Health (2026.acl-long)
Copied to clipboard
Chen Xu, Yu ji, Zhenyu Lv, Yang Yi, Yizhe Yang, Luyao Ji, Chaoyi Chen, Xianyang Wang, Tian Lan, Zhihua Wang, Juan Wang, Xunde Dong, Fuze Tian, Qunxi Dong, Bin Hu
| Challenge: | Existing LLM-based training approaches lack faithful responses to clinical errors and explainable feedback. |
| Approach: | They propose a neural-symbolic virtual standardized patient governed by an OBSERVE-THINK-BEHAVE architecture that embeds LLM reasoning into a symbolic system where experts implant causal associations between intervention logic and patient mental states. |
| Outcome: | The proposed model outperforms baselines in faithfulness and pedagogical value. |
Improving Constituency Parsing with Span Attention (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Constituency parsing is a fundamental task for natural language understanding . n-grams are a conventional type of feature for contextual information . experimental results show that neural parsers with no grammar rules outperform statistical ones . |
| Approach: | They propose to incorporate n-grams into span representations by weighting them according to their contributions to the parsing process. |
| Outcome: | The proposed approach outperforms existing statistical grammar-based models on Arabic, Chinese, and English datasets. |
OSCaR: Object State Captioning and State Change Representation (2024.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods to extrapolate and comprehend changes in object states are limited . relying on a small set of symbolic words to represent changes has restricted expressiveness of language. |
| Approach: | They propose a dataset and benchmark to evaluate multimodal large language models . they investigate causal relations between a concrete action and the change . |
| Outcome: | The proposed method achieves near parity with GPT-4V ratings across helpfulness, accuracy, reasoning, and other key metrics. |
Fine-Tuning Large Language Models for Stock Return Prediction Using Newsflow (2024.emnlp-industry)
Copied to clipboard
| Challenge: | Quantitative investing relies on extracting quantitative features or signals from various data sources including market prices, economic indicators, financial text, etc. |
| Approach: | They propose to integrate LLMs’ token-level embeddings into a forecasting module and compare their results to those of encoder-only and decoder-based models. |
| Outcome: | The proposed model outperforms conventional sentiment scores on multiple investment universes and is based on encoder-only and decoder-based models. |
Multi-stage Distillation Framework for Cross-Lingual Semantic Similarity Matching (2022.findings-naacl)
Copied to clipboard
Kunbo Ding, Weijie Liu, Yuejian Fang, Zhe Zhao, Qi Ju, Xuefeng Yang, Rong Tian, Zhu Tao, Haoyan Liu, Han Guo, Xingyu Bai, Weiquan Mao, Yudong Li, Weigang Guo, Taiqiang Wu, Ningyuan Sun
| Challenge: | Existing studies have shown that cross-lingual knowledge distillation can improve the performance of pre-trained models for cross-linguistic similarity matching tasks. |
| Approach: | They propose a multi-stage distillation framework for constructing a small-size but high-performance cross-lingual model using contrastive learning, bottleneck, and parameter recurrent strategies. |
| Outcome: | The proposed model can compress the size of XLM-R and MiniLM by more than 50% while the performance is only reduced by about 1%. |
OPeRA: A Dataset of Observation, Persona, Rationale, and Action for Evaluating LLMs on Human Online Shopping Behavior Simulation (2026.acl-long)
Copied to clipboard
Ziyi Wang, Yuxuan Lu, Wenbo Li, Amirali Amini, Bo Sun, Yakov Bart, Weimin Lyu, Jiri Gesi, Tian Wang, Jing Huang, Yu Su, Upol Ehsan, Malihe Alikhani, Toby Jia-Jun Li, Lydia Chilton, Dakuo Wang
| Challenge: | evaluating LLMs' ability to mimic real user behavior remains an open challenge due to the lack of high-quality, publicly available datasets that capture both the observable actions and the internal reasoning of an actual user. |
| Approach: | They propose a dataset of Observation, Persona, Rationale, and Action collected from real human participants during online shopping sessions. |
| Outcome: | The proposed dataset is the first to evaluate how well current LLMs can accurately simulate the next web action of a specific user. |
Dual Context-Guided Continuous Prompt Tuning for Few-Shot Learning (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing prompt-based paradigms have shown their competitive performance in many NLP tasks, but their effectiveness varies upon the model and training data. |
| Approach: | They propose a dual context-guided continuous prompt tuning method that integrates contextual information into the input input. |
| Outcome: | The proposed method outperforms existing prompt tuning methods in the few-shot setting and can be used in many NLP tasks. |
You Only Query Twice: Multimodal Rumor Detection via Evidential Evaluation from Dual Perspectives (2025.coling-main)
Copied to clipboard
| Challenge: | Existing rumor detectors exhibit limitations in fully exploiting responses to the source tweet as essential public opinions, and in explaining and indicating the reliability of the results obtained. Existing research mainly combats this with content and response-based detection methods. |
| Approach: | They propose a Large Language Model with both multimodal source content and the corresponding response set to extract contrasting evidence to enable maximal utilization of informative responses. |
| Outcome: | The proposed approach can indicate the model’s uncertainty (i.e., reliability) of the results. |
VCSearch: Bridging the Gap Between Well-Defined and Ill-Defined Problems in Mathematical Reasoning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies have improved the performance of Large language models on well-defined mathematical benchmarks, but they often overlook ill-defined problems. |
| Approach: | They develop a large-scale benchmark that contains over 5,000 ill-defined mathematical problems. |
| Outcome: | The proposed framework improves the accuracy of identifying unsolvable problems by at least 12% across different LLMs, thus achieving stronger robust mathematical reasoning ability. |
TACO: Enhancing Multimodal In-context Learning via Task Mapping-Guided Sequence Configuration (2025.emnlp-main)
Copied to clipboard
| Challenge: | Multimodal in-context learning (ICL) is a key mechanism for harnessing the capabilities of large vision–language models. |
| Approach: | They propose a transformer-based model with task-aware attention that dynamically configures ICL sequences. |
| Outcome: | Experiments on five LVLMs and nine datasets show that TACO surpasses baselines across diverse ICL tasks. |
MM-CRITIC: A Holistic Evaluation of Large Multimodal Models as Multimodal Critique (2025.findings-emnlp)
Copied to clipboard
| Challenge: | e MM-CRITIC is a holistic benchmark for evaluating the critique ability of Large Multimodal Models (LMMs) covering 8 main task types and over 500 tasks, covering 4471 samples. |
| Approach: | They introduce a holistic benchmark for evaluating the critique ability of Large Multimodal Models across multiple dimensions: basic, correction, and comparison. |
| Outcome: | The proposed benchmark covers 8 main task types and over 500 tasks and is composed of 4471 samples. |
Fine-grained Category Discovery under Coarse-grained supervision with Hierarchical Weighted Self-contrastive Learning (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for novel category discovery focus on the scenario where known and novel categories are of the same granularity. |
| Approach: | They propose a novel scenario for fine-grained category discovery under coarse-grain supervision that allows for adapting models to categories of different granularity from known ones. |
| Outcome: | The proposed model can adapt models to categories of different granularity from known ones and reduce labeling cost. |
NOTA: Multimodal Music Notation Understanding for Visual Large Language Model (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing general-domain visual language models lack ability of music notation understanding . Symbolic music is represented in two distinct forms: auditory music and symbolic music . |
| Approach: | They propose to train a multimodal music notation model using a large-scale dataset . they use cross-modal alignment to train the model for music notations analysis . |
| Outcome: | The proposed model improves on music understanding by training with a multimodal music notation model. |
Self-Evolution Learning for Mixup: Enhance Data Augmentation on Few-Shot Text Classification Tasks (2023.emnlp-main)
Copied to clipboard
Haoqi Zheng, Qihuang Zhong, Liang Ding, Zhiliang Tian, Xin Niu, Changjian Wang, Dongsheng Li, Dacheng Tao
| Challenge: | Text classification tasks often encounter few-shot scenarios with limited labeled data, and addressing data scarcity is crucial. |
| Approach: | They propose a self-evolution learning (SE) based mixup approach for data augmentation in text classification which generates more adaptive and model-friendly pseudo samples for the model training. |
| Outcome: | The proposed approach can generate more adaptive and model-friendly pseudo samples for the model training. |
Beyond Literal Mapping: Benchmarking and Improving Non-Literal Translation Evaluation (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have advanced machine translation (MT) a meta-evaluation dataset focused on non-literal translations is lacking . experimental results show the inaccuracies of traditional MT metrics and the limitations of LLM-as-a-Judge. |
| Approach: | They propose a meta-evaluation framework that leverages sub-agents to evaluate machine translation metrics. |
| Outcome: | The proposed framework improves on the knowledge cutoff and score inconsistency problem. |
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. |
A Localized Geometric Method to Match Knowledge in Low-dimensional Hyperbolic Space (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for entity alignment are limited to Euclidean space and hyperbolic embedding can represent hierarchical structure in knowledge graphs. |
| Approach: | They propose a localized geometric method to find equivalent entities in hyperbolic space using a hyperbolical neural network. |
| Outcome: | The proposed method outperforms the state-of-the-art by a large margin. |
MMInA: Benchmarking Multihop Multimodal Internet Agents (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing benchmarks fail to assess embodied agents in a realistic, evolving environment for compositional Internet tasks. |
| Approach: | They propose a multihop and multimodal benchmark to evaluate embodied agents for compositional Internet tasks. |
| Outcome: | The proposed protocol significantly improves the performance of both the single-hop and multihop web browsing abilities. |
Reasoning over Hierarchical Question Decomposition Tree for Explainable Question Answering (2023.acl-long)
Copied to clipboard
| Challenge: | Existing XQA methods focus on reasoning on a single knowledge source, e.g., structured knowledge bases, unstructured corpora, etc. Existing work in XQA focuses on integrating information from heterogeneous knowledge sources. |
| Approach: | They propose to leverage question decomposing for heterogeneous knowledge integration by breaking down a complex question into simpler ones and selecting the appropriate knowledge source for each sub-question. |
| Outcome: | The proposed framework outperforms SOTA methods on complex QA datasets. |
Smart-Searcher: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learning (2025.findings-emnlp)
Copied to clipboard
Huatong Song, Jinhao Jiang, Wenqing Tian, Zhipeng Chen, Yuhuan Wu, Jiahao Zhao, Yingqian Min, Xin Zhao, Lei Fang, Ji-Rong Wen
| Challenge: | Large Language Models (LLMs) are powerful but prone to hallucinations due to static knowledge. Retrieval-augmented generation (RAG) helps by injecting external information, but current methods are costly, generalize poorly, or ignore the model’s internal knowledge. |
| Approach: | They propose a framework to train large language models to leverage both internal and external knowledge sources. |
| Outcome: | The proposed framework outperforms existing methods and achieves efficient retrieval-augmented reasoning. |
Enhancing Recommendation Explanations through User-Centric Refinement (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing explanations for user reviews often fail to meet user-centric aspects, reducing their usefulness to users. |
| Approach: | They propose a paradigm that refines initial explanations generated by existing models during the inference stage to enhance their quality in multiple aspects. |
| Outcome: | The proposed model improves explanations generated by existing models during the inference stage to enhance their quality in multiple aspects. |
DivScene: Towards Open-Vocabulary Object Navigation with Large Vision Language Models in Diverse Scenes (2025.findings-emnlp)
Copied to clipboard
Zhaowei Wang, Hongming Zhang, Tianqing Fang, Ye Tian, Yue Yang, Kaixin Ma, Xiaoman Pan, Yangqiu Song, Dong Yu
| Challenge: | Large Vision-Language Models (LVLMs) have achieved significant progress in tasks like visual question answering and document understanding. |
| Approach: | They introduce DivScene, a large-scale dataset with 4,614 houses across 81 scene types and 5,707 kinds of target objects. |
| Outcome: | The proposed dataset provides a much greater diversity of target objects and scene types than existing datasets, enabling a comprehensive task evaluation. |
TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space (2024.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) sometimes produce untruthful responses despite knowing the correct knowledge. |
| Approach: | They propose an inference-time intervention method to activate the truthfulness of Large Language Models (LLMs) by editing the features within LLM’s internal representations that govern the truthful. |
| Outcome: | The proposed method improves the truthfulness of 13 advanced LLMs by an average of 20% on TruthfulQA benchmark. |
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. |
Self-Tuning: Instructing LLMs to Effectively Acquire New Knowledge through Self-Teaching (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to keeping large language models current involve continued pre-training on new documents. |
| Approach: | They propose a learning framework that augments documents with knowledge-intensive tasks created in a self-supervised manner, focusing on memorization, comprehension, and self-reflection. |
| Outcome: | The proposed learning framework improves an LLM’s ability to acquire new knowledge from unseen raw documents through self-teaching. |
Intent Classification and Slot Filling for Privacy Policies (2021.acl-long)
Copied to clipboard
| Challenge: | Sentences written in privacy policies explain privacy practices and the constituent text spans convey further specific information. |
| Approach: | They propose an English corpus of 5,250 intent and 11,788 slot annotations . they propose two alternative neural approaches to model the corpus as a sequence-to-sequence learning task. |
| Outcome: | The proposed corpus predicts intent classification and slot filling, while the sequence tagging method outperforms slot filler by a large margin. |
CTTA-T: Continual Test-Time Adaptation for Text Understanding via Teacher-Student with a Domain-aware and Generalized Teacher (2026.acl-long)
Copied to clipboard
Tianlun Liu, Zhiliang Tian, Zhen Huang, Xingzhi Zhou, Wanlong Yu, Tianle Liu, Feng Liu, Dongsheng Li
| Challenge: | Existing models for text understanding fail to adapt to domain shifts in real-world applications . current models do not improve themselves as they are applied to new domains . |
| Approach: | They propose a continual test-time adaptation framework that adapts to evolving domains . they propose accumulating domains and a refine-then-filter framework to calibrate teacher predictions . |
| Outcome: | The proposed model excels in a teacher-student framework adaptable to evolving domains. |
STAMP: Selective Task-Aware Mechanism for Text Privacy (2026.eacl-long)
Copied to clipboard
| Challenge: | Experimental evaluations on SQuAD, Yelp, and AG News datasets demonstrate that STAMP achieves superior privacy–utility trade-offs across varying per-token privacy budgets. |
| Approach: | They propose a new framework for task-aware text privatization that selectively allocates privacy budgets across tokens by jointly considering (i) each token’s importance to the downstream task and (ii) its privacy sensitivity. |
| Outcome: | The proposed framework achieves superior privacy–utility trade-offs on SQuAD, Yelp, and AG News datasets. |
Truth-Aware Context Selection: Mitigating Hallucinations of Large Language Models Being Misled by Untruthful Contexts (2024.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are easily misled by untruthful contexts provided by users or knowledge augmentation tools, leading to hallucinations. |
| Approach: | They propose a lightweight method to adaptively recognize and mask untruthful context from the inputs and a new evaluation metric to further study the LLMs’ ability to accept truthful information and resist untrusted information. |
| Outcome: | The proposed method can detect and mask untruthful context from the inputs and significantly improve the quality of LLMs’ responses when presented with misleading information. |
StereoRel: Relational Triple Extraction from a Stereoscopic Perspective (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods for relational triple extraction still face challenges, including information loss and error propagation. |
| Approach: | They propose a model which maps relational triples to a three-dimensional space and leverages three decoders to extract them. |
| Outcome: | The proposed model outperforms the baselines on five public datasets. |
Augmenting Reasoning Capabilities of LLMs with Graph Structures in Knowledge Base Question Answering (2024.findings-emnlp)
Copied to clipboard
Yuhang Tian, Dandan Song, Zhijing Wu, Changzhi Zhou, Hao Wang, Jun Yang, Jing Xu, Ruanmin Cao, HaoYu Wang
| Challenge: | Recent work uses Large Language Models (LLMs) for semantic parsing to address Knowledge Base Question Answering tasks. |
| Approach: | They propose a framework that augments reasoning capabilities of LLMs with Graph Structures in Knowledge Base Question Answering to retrieve question-related graph structures. |
| Outcome: | The proposed framework outperforms existing methods on GrailQA and WebQSP under the few-shot setting. |
Timeline Summarization based on Event Graph Compression via Time-Aware Optimal Transport (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for timeline summarization ignore the events’ intra-structures and inter-structure connections. |
| Approach: | They propose to represent news articles as an event-graph, thus compressing the whole graph to its salient sub-graph. |
| Outcome: | The proposed method significantly improves on the state-of-the-art on three real-world datasets, including two public benchmarks and a Timeline100 dataset. |
DYNTEXT: Semantic-Aware Dynamic Text Sanitization for Privacy-Preserving LLM Inference (2025.findings-acl)
Copied to clipboard
Juhua Zhang, Zhiliang Tian, Minghang Zhu, Yiping Song, Taishu Sheng, Siyi Yang, Qiunan Du, Xinwang Liu, Minlie Huang, Dongsheng Li
| Challenge: | Existing methods to protect privacy of sensitive data are differential privacy (DP) and DP is used to protect users from privacy leakage. |
| Approach: | They propose an LDP-based Dynamic Text sanitization for privacy-preserving LLM inference that dynamically constructs semantic-aware adjacency lists of sensitive tokens to sample non-sensitive tokens for perturbation. |
| Outcome: | The proposed model excels on three datasets. |
Challenging Large Language Models with New Tasks: A Study on their Adaptability and Robustness (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing evaluation approaches for large language models (LLMs) rely on existing tasks and benchmarks, raising concerns about test set contamination and the genuine comprehension abilities of LLMs. |
| Approach: | They propose to evaluate LLMs by designing new tasks, automatically generating evaluation datasets for the tasks, and conducting detailed error analyses to scrutinize LLM's adaptability to new tasks. |
| Outcome: | The proposed method examines LLMs’ adaptability to new tasks, their sensitivity to prompt variations, and their error tendencies. |
Self-adaptive Context and Modal-interaction Modeling For Multimodal Emotion Recognition (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to predict emotion label for a given utterance lack modeling of diverse dependency ranges and inconsistent treatment of contribution for various modalities. |
| Approach: | They propose a multimodal emotion recognition in conversation task that uses context and multiple modalities to predict emotion label for a given utterance. |
| Outcome: | The proposed method outperforms the state-of-the-art methods on three multimodal datasets. |
Optimal Expert-Attention Allocation in Mixture-of-Experts: A Scalable Law for Dynamic Model Design (2026.acl-industry)
Copied to clipboard
| Challenge: | a novel extension of neural scaling laws to Mixture-of-Experts models is proposed . a ratio of expert-attention compute is crucial for efficient MoE models . |
| Approach: | They propose an extension of neural scaling laws to Mixture-of-Experts (MoE) models . they define the ratio r as the fraction of total FLOPs per token dedicated to expert and attention layers . |
| Outcome: | The proposed model can be tuned beyond size and data with the proposed model. |
Does it Make Sense? And Why? A Pilot Study for Sense Making and Explanation (P19-1)
Copied to clipboard
| Challenge: | Existing benchmarks measure common sense knowledge indirectly or without reasoning. |
| Approach: | They propose a benchmark to test whether a system can differentiate natural language statements that make sense from those that do not make sense. |
| Outcome: | The proposed benchmarks show that models trained on large corpora perform better than humans on some benchmarks. |
LAM SIMULATOR: Advancing Data Generation for Large Action Model Training via Online Exploration and Trajectory Feedback (2025.findings-acl)
Copied to clipboard
Thai Quoc Hoang, Kung-Hsiang Huang, Shirley Kokane, Jianguo Zhang, Zuxin Liu, Ming Zhu, Jake Grigsby, Tian Lan, Michael S Ryoo, Chien-Sheng Wu, Shelby Heinecke, Huan Wang, Silvio Savarese, Caiming Xiong, Juan Carlos Niebles
| Challenge: | Large Action Models (LAMs) face challenges due to the need for high-quality training data, especially for multi-steps tasks that involve planning, executing tool calls, and responding to feedback. |
| Approach: | They propose a framework for online exploration of agentic tasks with high-quality feedback . they use a dynamic task query generator and an extensive collection of tools to create a high-level feedback environment for LLM Agents. |
| Outcome: | The proposed framework achieves 49.3% performance improvement over baselines on toolbench and CRMArena. |
MTAVG-Bench: A Diagnostic Benchmark for Multi-Talker Dialogue-Centric Audio-Video Generation (2026.acl-long)
Copied to clipboard
Yanghao Zhou, Haitian Li, Rexar Lin, Heyan Huang, Jinxing Zhou, Changsen Yuan, Tian Lan, Ziqin Zhou, Yudong Li, Jiajun Xu, Jingyun Liao, YiMing Cheng, Xuefeng Chen, Xian-Ling Mao, Yousheng Feng
| Challenge: | Existing evaluation benchmarks for text-to-audio-video (T2AV) generation are largely designed for human-recorded videos or single-speaker settings. |
| Approach: | They propose a failure-driven diagnostic benchmark for multi-talker dialogue-centric audio-video generation. |
| Outcome: | The benchmark evaluates multi-speaker dialogue generation at four levels: audio-visual signal fidelity, temporal attribute consistency, social interaction, and cinematic expression. |
Attention Optimization for Abstractive Document Summarization (D19-1)
Copied to clipboard
| Challenge: | Abstractive summarization models require attention to reproduce the most salient information. |
| Approach: | They propose to use local and global variances to augment the vanilla attention model to reproduce the most salient information and avoid repetitions. |
| Outcome: | The proposed attention refinement unit can reproduce the most salient information and avoid repetitions on CNN/Daily Mail dataset. |
MCMH: Learning Multi-Chain Multi-Hop Rules for Knowledge Graph Reasoning (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing work on knowledge graphs infers a missing relationship between entities with a multi-hop rule . Empirical results show that our multi-chain multi-homing (MCMH) rules yield superior results compared to the standard single-chain approaches. |
| Approach: | They propose to use a generalized form of multi-hop rules to learn generalized rules efficiently . they propose to select a small set of relation chains as a rule and evaluate confidence . |
| Outcome: | The proposed method outperforms the existing methods and the existing frameworks. |
DaMSTF: Domain Adversarial Learning Enhanced Meta Self-Training for Domain Adaptation (2023.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to domain adaptation only use reliable pseudo instances, i.e., pseudo instances with high prediction confidence, to retrain the model. |
| Approach: | They propose a domain adversarial learning enhanced self-training framework that uses meta-learning to estimate the importance of each pseudo instance and a meta constructor to construct the meta-validation set. |
| Outcome: | The proposed framework reduces label noise and preserves hard examples while maintaining accuracy. |
Task and Sentiment Adaptation for Appraisal Tagging (2023.eacl-main)
Copied to clipboard
| Challenge: | Appraisal framework in linguistics defines the framework for fine-grained evaluations and opinions. |
| Approach: | They propose to use language models to automatically identify and annotate text segments for appraisal. |
| Outcome: | The proposed model achieves superior performance than baseline adapter-based models and other neural classification models for cross-domain and cross-language settings. |
RESEMO: A Benchmark Chinese Dataset for Studying Responsive Emotion from Social Media Content (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing studies on social media text processing do not focus on responsive emotion analysis. |
| Approach: | They propose a Chinese dataset named ResEmo for responsive emotion analysis, including 3813 posts with 68,781 comments collected from Weibo, the largest social media platform in China. |
| Outcome: | The proposed dataset includes 3813 posts with 68,781 comments collected from weibo, the largest social media platform in China. |
Uni-MMMU: A Massive Multi-discipline Multimodal Unified Benchmark (2026.acl-long)
Copied to clipboard
Kai Zou, Ziqi Huang, Yuhao Dong, Shulin Tian, Dian Zheng, Hongbo Liu, Jingwen He, Bin Liu, Yu Qiao, Ziwei Liu
| Challenge: | Existing evaluations treat visual understanding and generation in isolation or overlook tasks that inherently couple them. |
| Approach: | They propose a benchmark that examines the bidirectional synergy between generation and understanding across eight reasoning-centric domains. |
| Outcome: | The proposed model systematically unfolds the bidirectional synergy between generation and understanding across eight reasoning-centric domains. |
Coarse-to-Fine: Hierarchical Multi-task Learning for Natural Language Understanding (2022.coling-1)
Copied to clipboard
Zhaoye Fei, Yu Tian, Yongkang Wu, Xinyu Zhang, Yutao Zhu, Zheng Liu, Jiawen Wu, Dejiang Kong, Ruofei Lai, Zhao Cao, Zhicheng Dou, Xipeng Qiu
| Challenge: | Existing methods to learn downstream tasks by stitches skill block lack rationality and interpretation. |
| Approach: | They propose a hierarchical framework with a coarse-to-fine paradigm for generalized text representations from the large-scale corpus. |
| Outcome: | The proposed model learns basic language properties from all tasks and boosts performance on relevant tasks. |
EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Models (2024.acl-demos)
Copied to clipboard
Peng Wang, Ningyu Zhang, Bozhong Tian, Zekun Xi, Yunzhi Yao, Ziwen Xu, Mengru Wang, Shengyu Mao, Xiaohan Wang, Siyuan Cheng, Kangwei Liu, Yuansheng Ni, Guozhou Zheng, Huajun Chen
| Challenge: | Large Language Models (LLMs) suffer from knowledge cutoff or fallacy issues, which means they are unaware of unseen events or generate text with incorrect facts owing to outdated/noisy data. |
| Approach: | They propose an easy-to-use knowledge editing framework for Large Language Models that allows users to easily edit updated knowledge and adjust undesired behavior while minimizing the impact on unrelated inputs. |
| Outcome: | The proposed framework surpasses traditional fine-tuning in terms of reliability and generalization. |
PolicyQA: A Reading Comprehension Dataset for Privacy Policies (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Privacy policy documents are long and verbose. Hence, a question answering system can help users find the information that is relevant and important to them. |
| Approach: | They propose to provide users with a short text span from policy documents to search for answers from a long text segment. |
| Outcome: | The proposed question answering system can help users find information relevant to them. |
Beyond Error Propagation in Neural Machine Translation: Characteristics of Language Also Matter (D18-1)
Copied to clipboard
| Challenge: | Neural machine translation suffers from exposure bias and error propagation problem. |
| Approach: | They conduct a series of analyses to deeply understand the accuracy drop problem . they find that the left part of the translated sentence is often better than its right part . |
| Outcome: | The results show that the left part of the translated sentence is often better than its right part in left-to-right decoding models. |
Martingale Foresight Sampling: A Principled Approach to Inference-Time LLM Decoding (2026.eacl-long)
Copied to clipboard
| Challenge: | Standard autoregressive decoding in large language models is short-sighted, often failing to find globally optimal reasoning paths due to token-by-token generation process. |
| Approach: | They propose a principled framework that reformulates LLM decoding as a problem of identifying an optimal stochastic process. |
| Outcome: | The proposed framework surpasses state-of-the-art methods in accuracy while significantly improving computational efficiency. |
Joint Training of Candidate Extraction and Answer Selection for Reading Comprehension (P18-1)
Copied to clipboard
| Challenge: | Various advanced neural models have been proposed for reading comprehension, but most models ignore its relations with other answer candidates. |
| Approach: | They propose to model reading comprehension as an extract-then-select two-stage procedure . they first extract answer candidates from passages, then select the final answer by combining information from all candidates. |
| Outcome: | The proposed approach improves state-of-the-art performance on open-domain reading comprehension datasets. |
SentiX: A Sentiment-Aware Pre-Trained Model for Cross-Domain Sentiment Analysis (2020.coling-main)
Copied to clipboard
| Challenge: | Pre-trained language models have been widely applied to cross-domain NLP tasks like sentiment analysis, but fine-tuning them on the source domain tends to overfit, leading to inferior results on the target domain. |
| Approach: | They propose to pre-train a sentiment-aware language model (SentiX) via domain-invariant sentiment knowledge from large-scale review datasets and utilize it for cross-domain sentiment analysis tasks without fine-tuning. |
| Outcome: | The proposed model achieves state-of-the-art in all the cross-domain sentiment analysis tasks and can be trained with only 1% samples and better than BERT with 90% samples. |
GRACE: Gradient-guided Controllable Retrieval for Augmenting Attribute-based Text Generation (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for controlling the generation of pre-trained language models infuse domain bias into the generation process, making it difficult to generate out-of-domain texts. |
| Approach: | They propose a retrieval-augmented generation framework that uses retrieval to generate fluent sentences with high attribute relevance. |
| Outcome: | The proposed method can generate fluent sentences with high attribute relevance while keeping domain bias out of the model. |
SkillVerse : Assessing and Enhancing LLMs with Tree Evaluation (2025.acl-long)
Copied to clipboard
| Challenge: | Language models evolve to tackle complex, multifaceted tasks, requiring granular evaluations . recent studies have focused on leaderboard and benchmark results, but limited interpretability makes it difficult to compare strengths and weaknesses of models. |
| Approach: | They propose an unsupervised tree-structured diagnosis framework for understanding model proficiency in specific abilities with an LLM as a judge. |
| Outcome: | The proposed framework improves model in-context learning and predicts model weaknesses with a 55% success rate compared to the framework without SkillVerse. |
Distance between Relevant Information Pieces Causes Bias in Long-Context LLMs (2025.findings-acl)
Copied to clipboard
Runchu Tian, Yanghao Li, Yuepeng Fu, Siyang Deng, Qinyu Luo, Cheng Qian, Shuo Wang, Xin Cong, Zhong Zhang, Yesai Wu, Yankai Lin, Huadong Wang, Xiaojiang Liu
| Challenge: | Positional biases in large language models hinder their ability to process long inputs. |
| Approach: | They propose a benchmark to assess positional bias in large language models involving multiple pieces of relevant information. |
| Outcome: | The proposed benchmark assesses the performance of long-context language models by examining their models with different input lengths and tasks. |
Context Length Alone Hurts LLM Performance Despite Perfect Retrieval (2025.findings-emnlp)
Copied to clipboard
Yufeng Du, Minyang Tian, Srikanth Ronanki, Subendhu Rongali, Sravan Babu Bodapati, Aram Galstyan, Azton Wells, Roy Schwartz, Eliu A Huerta, Hao Peng
| Challenge: | Large language models (LLMs) often fail to scale their performance on long-context tasks performance in line with the context lengths they support. |
| Approach: | They propose a model-agnostic mitigation strategy that transforms a long-context task into a short-concept one by prompting the model to recite the retrieved evidence before attempting to solve the problem. |
| Outcome: | The proposed model improves on a long-context task up to 4% on RULER. |
Learning From Free-Text Human Feedback – Collect New Datasets Or Extend Existing Ones? (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing datasets for learning from free-text human feedback are scarce. |
| Approach: | They manually annotate a subset of a popular dialogue dataset with error and user response types using an improved version of the Integrated Error Taxonomy and a newly proposed user response type taxonomies. |
| Outcome: | The proposed dataset provides new insights into dataset composition, error types, user response types, and the relations between them. |
TaCL: Improving BERT Pre-training with Token-aware Contrastive Learning (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing pre-trained MLMs produce an anisotropic distribution of token representations . this is not ideal for tasks that require discriminative semantic meanings of distinct tokens - a problem that exists in pre-training models . |
| Approach: | They propose a continual pre-training approach that encourages BERT to learn an isotropic distribution of token representations. |
| Outcome: | The proposed approach improves on a wide range of English and Chinese benchmarks. |
RecMem: Recurrence-based Memory Consolidation for Efficient and Effective Long-Running LLM Agents (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing memory systems invoke LLMs to extract episodic and semantic memory, and this leads to substantial token consumption. |
| Approach: | They propose a method that stores incoming interactions in a subconscious memory layer and encodes them using lightweight embedding models for retrieval. |
| Outcome: | Experiments show that RecMem reduces the memory construction token cost of three SOTA memory systems by up to 87% while exceeding their accuracy. |
Improving Relation Extraction through Syntax-induced Pre-training with Dependency Masking (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing studies require modifications to existing baseline architectures to leverage syntactic information. |
| Approach: | They propose to leverage syntactic information to improve relation extraction by training a syntax-induced encoder on auto-parsed data through dependency masking. |
| Outcome: | The proposed approach outperforms baseline models and achieves state-of-the-art results on two English datasets. |
Red Teaming Large Reasoning Models (2026.acl-long)
Copied to clipboard
| Challenge: | Large Reasoning Models (LRMs) have emerged as a powerful advancement in multi-step reasoning tasks, but they introduce safety and reliability risks, such as CoT-hijacking and prompt-induced inefficiencies. |
| Approach: | They propose a unified benchmark to assess the trustworthiness of Large Reasoning Models. |
| Outcome: | The proposed benchmark evaluates truthfulness, safety and efficiency on 26 models. |
AscendKernelGen: LLM-Driven Kernel Generation for NPUs (2026.findings-acl)
Copied to clipboard
Xinzi Cao, Jianyang Zhai, Pengfei Li, Zhiheng Hu, Cen Yan, null Mubingxu, Guanghuan Fang, Bin She, Jiayu Li, Yihan Su, Dongyang Tao, Feidiao Yang, Chang-Dong Wang, Yutong Lu, Weicheng Xue, Bin Zhou, Yonghong Tian
| Challenge: | Neural Processing Units (NPUs) are critical for AI infrastructure, but their development remains a bottleneck due to vendor-specific Domain-Specific Languages (DSLs). |
| Approach: | They propose a framework for NPU kernel development that bridges the gap in hardware-specific coding . compiler success on complex Level-2 kernels improves from 0% to 95.5%, they say . |
| Outcome: | The proposed framework bridges the gap in hardware-specific coding, showing a near-zero success rate on complex kernels. |
STRICT: Stress-Test of Rendering Image Containing Text (2025.emnlp-main)
Copied to clipboard
| Challenge: | Despite the advances in diffusion models, the generation of coherent text remains a major bottleneck. |
| Approach: | They propose a benchmark to test the ability of diffusion models to render coherent text in images. |
| Outcome: | The proposed model fails to generate coherent and legible text in images despite its iterative nature . the model fails in both the maximum length of readable text and correctness and legibility of the generated text . |
RiT: Rubrics-in-Thinking Reinforcement Learning for Improved Reasoning in Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Reasoning Models benefit from generating intermediate reasoning steps alongside final answers. |
| Approach: | They propose a framework to introduce thinking-rubric supervision into intermediate reasoning. |
| Outcome: | The proposed framework outperforms outcome-only RL baselines on reasoning-intensive and open-ended tasks. |
Towards Robust Speech Representation Learning for Thousands of Languages (2024.emnlp-main)
Copied to clipboard
William Chen, Wangyou Zhang, Yifan Peng, Xinjian Li, Jinchuan Tian, Jiatong Shi, Xuankai Chang, Soumi Maiti, Karen Livescu, Shinji Watanabe
| Challenge: | XEUS is a cross-lingual encoder for universal speech that can be trained on 1 million hours of data across 4057 languages. |
| Approach: | They propose a Cross-lingual Encoder for Universal Speech that can be trained on 1 million hours of data across 4057 languages and a newly created corpus of 7400+ hours from 4057 . |
| Outcome: | The proposed model outperforms state-of-the-art models on several benchmarks and outperfies MMS 1B and w2v-BERT 2.0 v2 by 0.8% and 4.4% respectively. |
Evaluation Agent: Efficient and Promptable Evaluation Framework for Visual Generative Models (2025.acl-long)
Copied to clipboard
| Challenge: | Existing evaluation methods rely on rigid pipelines that overlook user needs and provide numerical results without clear explanations. |
| Approach: | They propose an evaluation framework that employs human-like strategies for efficient, dynamic, multi-round evaluations using only a few samples per round. |
| Outcome: | The evaluation agent framework reduces evaluation time to 10% of traditional methods while delivering comparable results. |
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. |
FedCSR: A Federated Framework for Multi-Platform Cross-Domain Sequential Recommendation with Dual Contrastive Learning (2025.coling-main)
Copied to clipboard
Dongyi Zheng, Hongyu Zhang, Jianyang Zhai, Lin Zhong, Lingzhi Wang, Jiyuan Feng, Xiangke Liao, Yonghong Tian, Nong Xiao, Qing Liao
| Challenge: | Existing federated frameworks for cross-domain sequential recommendation rely on user alignment, which increases communication costs and privacy risks. |
| Approach: | They propose a federated cross-domain sequential recommendation framework that eliminates the need for user alignment between platforms. |
| Outcome: | The proposed framework eliminates the need for user alignment between platforms. |
To the Globe (TTG): Towards Language-Driven Guaranteed Travel Planning (2024.emnlp-demo)
Copied to clipboard
Da Ju, Song Jiang, Andrew Cohen, Aaron Foss, Sasha Mitts, Arman Zharmagambetov, Brandon Amos, Xian Li, Justine Kao, Maryam Fazel-Zarandi, Yuandong Tian
| Challenge: | a new system that takes natural language requests from users generates and trains optimal travel plans . a user can provide instructions and an agent provides optimal solutions . the system takes 5seconds to reply to the user request with guaranteed itineraries . |
| Approach: | They propose a real-time demo system that takes natural language requests from users . it translates requests to symbolic form and produces optimal travel itineraries with LLM . |
| Outcome: | The proposed system produces optimal travel itineraries with mixed integer linear programming solvers. |
ToHRE: A Top-Down Classification Strategy with Hierarchical Bag Representation for Distantly Supervised Relation Extraction (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods to find relational facts from texts lack hierarchical information of relations. |
| Approach: | They propose a hierarchical classification framework which extracts relation in a top-down manner. |
| Outcome: | The proposed method significantly outperforms state-of-the-art methods on NYT dataset . the proposed method generates large amounts of training data by aligning KBs with unlabeled corpora . |
CMT-Eval: A Novel Chinese Multi-turn Dialogue Evaluation Dataset Addressing Real-world Conversational Challenges (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing evaluation benchmarks fail to capture users’ evolving needs and how their diverse conversation styles affect the dialogue flow. |
| Approach: | They propose to use CMT-Eval to evaluate Chinese multi-turn dialogue systems. |
| Outcome: | The proposed dataset is the first dedicated dataset for fine-grained evaluation of Chinese multi-turn dialogue systems. |
HER: Human-like Reasoning and Reinforcement Learning for LLM Role-playing (2026.findings-acl)
Copied to clipboard
Chengyu Du, Xintao Wang, Aili Chen, Weiyuan Li, Rui Xu, Junteng Liu, Zishan Huang, Rong Tian, Zijun Sun, Yuhao Li, Liheng Feng, Deming Ding, Pengyu Zhao, Yanghua Xiao
| Challenge: | Existing models for LLM role-playing lack high-quality datasets with explicit reasoning traces and reliable reward signals aligned with human preferences. |
| Approach: | They propose a unified framework for cognitive-level persona simulation that strictly distinguishes characters’ first-person thinking processes from LLMs’ third-person reasoning. |
| Outcome: | The proposed framework outperforms the Qwen3-32B baseline model and achieves a 30.26% and 14.97% performance on the minimax benchmarks. |
GraphQ IR: Unifying the Semantic Parsing of Graph Query Languages with One Intermediate Representation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to neural semantic parsing are limited by the semantic gap between natural and formal languages. |
| Approach: | They propose a unified intermediate representation for graph query languages, named GraphQ IR, which has a natural-language-like expression that bridges the semantic gap and formally defined syntax that maintains the graph structure. |
| Outcome: | The proposed representation can convert user queries into graphQ IR, which can later be losslessly compiled into various downstream graph query languages. |
A Theory Guided Scaffolding Instruction Framework for LLM-Enabled Metaphor Reasoning (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing methods for metaphor detection and reasoning struggle to explain the underlying reasoning process behind the metaphorical/literal judgment. |
| Approach: | They propose a Theory guided Scaffolding Instruction framework that instructs an LLM to infer the underlying reasoning process of metaphor detection guided by metaphor theories for the first time. |
| Outcome: | The proposed method significantly outperforms both the LLM-based reasoning methods and the SOTA methods in metaphor detection. |
Shorten After You’re Right: Lazy Length Penalties for Reasoning RL (2026.findings-acl)
Copied to clipboard
Danlong Yuan, Tian Xie, Shaohan Huang, Huishuai Zhang, Zhuocheng Gong, Chong Luo, Furu Wei, Dongyan Zhao
| Challenge: | Existing shortening methods for long reasoning models rely on additional supervision or multi-stage post-training. |
| Approach: | They propose a lazy length penalty that imposes length pressure on models without extra training stages. |
| Outcome: | The proposed method significantly reduces response length without extra training stages while maintaining or improving performance. |
Me-Agent: A Personalized Mobile Agent with Two-Level User Habit Learning for Enhanced Interaction (2026.findings-acl)
Copied to clipboard
Shuoxin Wang, Chang Liu, Gowen Loo, Lifan Zheng, Kaiwen Wei, Huanqian Yan, Xinyi Zeng, Jingyuan Zhang, Yu Tian
| Challenge: | Existing Large Language Model (LLM)-based mobile agents follow explicit user instructions without personalized needs. |
| Approach: | They propose a user preference learning strategy enhanced with a Personal Reward Model to improve personalization performance. |
| Outcome: | The proposed agent achieves state-of-the-art performance while maintaining competitive instruction execution performance. |
AmbiPun: Generating Humorous Puns with Ambiguous Context (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing methods for generating homographic puns are heavy-weighted due to the lack of training data. |
| Approach: | They propose a way to generate pun sentences that does not require training on existing puns. |
| Outcome: | The proposed method outperforms baseline models and state-of-the-art models by a large margin. |
V-Oracle: Making Progressive Reasoning in Deciphering Oracle Bones for You and Me (2025.acl-long)
Copied to clipboard
Runqi Qiao, Qiuna Tan, Guanting Dong, MinhuiWu MinhuiWu, Jiapeng Wang, YiFan Zhang, Zhuoma GongQue, Chong Sun, Yida Xu, Yadong Xue, Ye Tian, Zhimin Bao, Lan Yang, Chen Li, Honggang Zhang
| Challenge: | Deciphering oracle bone scripts using AI technology is not an overnight task due to the evolution of written language over millennia. |
| Approach: | They propose a framework that utilizes Large Multi-modal Models (LMMs) for interpreting Oracle Bone Script (OBS). |
| Outcome: | The proposed framework provides quantitative analyses and superior deciphering capability. |
You Only Use Reactive Attention Slice When Retrieving From Long Context (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing retrieval techniques for language models are limited due to their reliance on lexical similarity and are computationally expensive to train. |
| Approach: | They propose a training-free and fine-tuning-free attention-based retrieval technique that uses a reaction score heuristic to quantify how an LM’s self-attention “reacts” to a user query. |
| Outcome: | The proposed approach improves QA task accuracy by 15% and inference throughput by 31% compared to embedding-based retrieval. |
Correlation-Aware Example Selection for In-Context Learning with Nonsymmetric Determinantal Point Processes (2025.emnlp-main)
Copied to clipboard
Qiunan Du, Zhiliang Tian, Zhen Huang, Kailun Bian, Tianlun Liu, Zhaoning Zhang, Xinwang Liu, Feng Liu, Dongsheng Li
| Challenge: | Existing studies on in-context learning (ICL) focus on the selection of individual examples and ignore correlations among examples. |
| Approach: | They propose a method to capture positive and negative correlations using the determinantal point process . they optimize the method via kernel decomposition-based MLE to fit a constructed pseudo-labeled dataset . |
| Outcome: | The proposed method outperforms baselines in ICL example selection. |
LiCoMemory: Lightweight and Cognitive Agentic Memory for Efficient Long-Term Reasoning (2026.findings-acl)
Copied to clipboard
Zhengjun Huang, Zhoujin Tian, Qintian Guo, Fangyuan Zhang, Yingli Zhou, Di Jiang, Zeying Xie, Xiaofang Zhou
| Challenge: | Large Language Models are constrained by limited context windows and lack of persistent memory . recent efforts address these limitations via external memory architectures . |
| Approach: | They propose an end-to-end agentic memory framework for real-time updating and retrieval that integrates hierarchical and temporal indexing layers. |
| Outcome: | The proposed framework outperforms established benchmarks in temporal reasoning, multi-session consistency, and retrieval efficiency. |
Hard Gate Knowledge Distillation - Leverage Calibration for Robust and Reliable Language Model (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing knowledge distillation schemes focus on a teacher as a source of knowledge and a gauge to detect miscalibration of a student. |
| Approach: | They propose a method that uses a teacher model as a source of knowledge and a model as an error detector to detect miscalibration of a student. |
| Outcome: | The proposed scheme improves model generalization and significantly lowers calibration error. |
LoRATK: LoRA Once, Backdoor Everywhere in the Share-and-Play Ecosystem (2025.findings-emnlp)
Copied to clipboard
Hongyi Liu, Shaochen Zhong, Xintong Sun, Minghao Tian, Mohsen Hariri, Zirui Liu, Ruixiang Tang, Zhimeng Jiang, Jiayi Yuan, Yu-Neng Chuang, Li Li, Soo-Hyun Choi, Rui Chen, Vipin Chaudhary, Xia Hu
| Challenge: | distributing LLMs without a proven track record like ‘meta-llama‘ or ‘qwen‘ rarely gains community traction. |
| Approach: | They propose a simple, efficient, yet specific recipe for a backdoor LoRA to be injected into task-enhancing LoRAs and examine the mechanisms of such infections. |
| Outcome: | The proposed model allows attackers to scale the distribution of compromised LoRAs with minimal effort by leveraging the rich pool of shared LoRA assets. |
KG-Adapter: Enabling Knowledge Graph Integration in Large Language Models through Parameter-Efficient Fine-Tuning (2024.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) are criticized for lack of expertise and knowledge conflict . KG-Adapter is a parameter-level KG integration method for decoder-only LLMs . |
| Approach: | They propose a parameter-level KG integration method based on parameter-efficient fine-tuning . they use KG-Adapter to integrate knowledge graphs with LLMs and perform joint reasoning . |
| Outcome: | The proposed method outperforms the current state-of-the-art method on four datasets for two different tasks. |
Emotion Trajectory-aware Retrieval for Markov-driven Emotion Anticipation in LLM-based Emotional Support Conversation (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing strategies focus on planning the next-turn dialogue strategies, while external strategy planners focus on generating empathetic responses. |
| Approach: | They propose a Markov-driven emotion anticipation framework with emotion trajectory-aware retrieval for LLM-based ESC, which anticipates future emotion states to guide strategy planning and achieve sustained emotional support. |
| Outcome: | The proposed framework can anticipate future emotions and achieve sustained emotional support on two datasets with two models. |
Subgraph-Guided Executable Logical Form Generation for Knowledge Base Question Answering (2026.findings-acl)
Copied to clipboard
Yuhang Tian, Dandan Song, Zhijing Wu, Changzhi Zhou, Jun Yang, Huipeng Ma, Chenhao Li, Luan Zhang, Yading Li, Xudong Li, Shenxi Liu, Jing Jiang
| Challenge: | Existing retrieval-augmented approaches focus on ignoring the structural information of the Knowledge Base (KB) and the question. |
| Approach: | They propose a structure-aware subgraph retrieval stage that ranks candidate subgraphs by aligning them with the question’s structure, along with semantic relevance. |
| Outcome: | Experiments on GrailQA, WebQSP, and GraphQuestions show that the proposed framework achieves state-of-the-art performance. |
League of LLMs: A Benchmark-Free Paradigm for Mutual Evaluation of Large Language Models (2026.acl-long)
Copied to clipboard
Qianhong Guo, Wei Xie, Xiaofang Cai, Enze Wang, Shuoyoucheng Ma, Xiaobing Sun, Tian Xia, Kai Chen, Xiaofeng Wang, Baosheng Wang
| Challenge: | Large language models (LLMs) have shown exceptional capabilities across a wide range of tasks, but reliable evaluation remains a challenge due to data contamination, opaque operation, and subjective preferences. |
| Approach: | They propose a benchmark-free evaluation paradigm that organizes multiple LLMs into a self-governed league for multi-round mutual evaluation. |
| Outcome: | Experiments on eight mainstream LLMs in mathematics and programming show that the proposed model can distinguish capabilities while maintaining high internal ranking stability. |
Hint-Based Training for Non-Autoregressive Machine Translation (D19-1)
Copied to clipboard
| Challenge: | AutoRegressive Translation models have to generate tokens sequentially during decoding and thus suffer from high inference latency. |
| Approach: | They propose to use hidden states and word alignments to help train NART models. |
| Outcome: | The proposed model improves on the WMT14 En-De and De-En datasets but is faster in inference than the current models. |
SENTRA: Selected-Next-Token Transformer for LLM Text Detection (2025.findings-emnlp)
Copied to clipboard
| Challenge: | SENTRA is a general-purpose, supervised LLM text detector . it detects LLM-generated text that is not explicitly declared as such . |
| Approach: | They propose a general-purpose LLM text detector that detects unlabeled text . they use a transformer-based encoder that leverages selected-next-token sequences . |
| Outcome: | The proposed classifier outperforms baselines on 24 domains of text. |
MacGyver: Are Large Language Models Creative Problem Solvers? (2024.naacl-long)
Copied to clipboard
Yufei Tian, Abhilasha Ravichander, Lianhui Qin, Ronan Le Bras, Raja Marjieh, Nanyun Peng, Yejin Choi, Thomas Griffiths, Faeze Brahman
| Challenge: | a new study examines the creative problem-solving capabilities of modern LLMs . it provides insight into the constrained problem- solving capabilities of both humans and AI . |
| Approach: | They use an automatically generated dataset to compare and contrast LLMs and humans to find out their creative problem-solving abilities. |
| Outcome: | The proposed dataset compares LLMs and humans in a constrained setting . it shows that humans excel in tasks they are familiar with but struggle with domain-specific knowledge . |
CodeAgent: Autonomous Communicative Agents for Code Review (2024.emnlp-main)
Copied to clipboard
Xunzhu Tang, Kisub Kim, Yewei Song, Cedric Lothritz, Bei Li, Saad Ezzini, Haoye Tian, Jacques Klein, Tegawendé Bissyandé
| Challenge: | Existing methods for code review rely on single input-output generative models and thus lack the collaborative nature of code review. |
| Approach: | They propose a multi-agent Large Language Model (LLM) system for code review automation that incorporates a supervisory agent to ensure that all the agents’ contributions address the initial review question. |
| Outcome: | The proposed system detects inconsistencies between code changes and commit messages, identify vulnerabilities, validates code style adherence, and suggests code revisions. |
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. |
Causality-aware Concept Extraction based on Knowledge-guided Prompting (2023.acl-long)
Copied to clipboard
| Challenge: | Concepts in knowledge graphs (KGs) are far from complete in existing knowledge graph models. |
| Approach: | They propose to equip a PLM-based extractor with a knowledge-guided prompt to alleviate concept bias by removing spurious co-occurrence correlations from existing knowledge. |
| Outcome: | The proposed prompt can alleviate concept bias and improve the performance of existing models. |
Domain-Specific Data Generation Framework for RAG Adaptation (2026.findings-acl)
Copied to clipboard
| Challenge: | Retrieval-Augmented Generation (RAG) combines the language understanding and reasoning capabilities of large language models (LLMs) with external retrieval to produce domain-grounded responses. |
| Approach: | They propose a scalable and modular data-centric framework for generating domain-grounded question–answer–context triples tailored to diverse RAG adaptation strategies. |
| Outcome: | The proposed framework generates domain-grounded question–answer–context triples for multiple RAG adaptation strategies. |
Re-examining the Role of Schema Linking in Text-to-SQL (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing text-to-SQL models treat schema linking as a minor component . Existing solutions treat schema as merely a string component based on string matching . |
| Approach: | They build a schema linking corpus based on a Spider text-to-SQL dataset . they find schema linking is the crux for the current text- to-Sql task . |
| Outcome: | The proposed model performs well on the Spider text-to-SQL dataset despite its simplicity. |
Paraphrase Generation as Unsupervised Machine Translation (2022.coling-1)
Copied to clipboard
| Challenge: | Existing methods for paraphrase generation rely on labeled datasets or are limited in narrow domains. |
| Approach: | They propose a paradigm for paraphrase generation by treating the task as unsupervised machine translation based on pairs of unlabeled monolingual sentences. |
| Outcome: | The proposed paradigm can generate paraphrases on a large unlabeled monolingual corpus without relying on bilingual sentence pairs. |
Improving Federated Learning for Aspect-based Sentiment Analysis via Topic Memories (2021.emnlp-main)
Copied to clipboard
| Challenge: | Aspect-based sentiment analysis (ABSA) predicts sentiment polarity for aspect term in sentences . labeled data stored at different locations and inaccessible due to privacy or legal concerns . |
| Approach: | They propose a model with federated learning to combine labeled data across different domains . they incorporate topic memory to take data from diverse domains into consideration . |
| Outcome: | The proposed model outperforms baselines on a simulated environment with three nodes. |
CAP: Controllable Alignment Prompting for Unlearning in LLMs (2026.acl-long)
Copied to clipboard
Zhaokun Wang, Jinyu Guo, Jingwen Pu, Hongli Pu, Meng Yang, Xunlei Chen, Jie Ou, Wenyi Li, Guangchun Luo, Wenhong Tian
| Challenge: | Existing methods for modifying parameters are unsystematic and rely on empirical experience. |
| Approach: | They propose a controllable alignment prompting for unlearning framework that decouples unlearning into a learnable prompt optimization process via reinforcement learning. |
| Outcome: | The proposed framework achieves precise, controllable unlearning without updating model parameters. |
Battling against Tough Resister: Strategy Planning with Adversarial Game for Non-collaborative Dialogues (2025.acl-long)
Copied to clipboard
| Challenge: | Non-collaborative dialogue involves two participants with conflicting interests engaging in multiround dialogue to achieve their own goals. |
| Approach: | They propose a Game-based Adversarial self-play InterActive training paradigm which constructs an adversarial two-player (a persuader and a resister) zero-sum game and guides the game to approximate Nash Equilibrium (NE) via reinforcement learning. |
| Outcome: | The proposed model achieves state-of-the-art performance on three datasets. |
Enable Fast Sampling for Seq2Seq Text Diffusion (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing text generation methods use autoregressive (AR) methods, which generate tokens one by one, but are time-consuming. |
| Approach: | They propose an efficient model FMSeq which utilizes flow matching to straighten the generation path, thereby enabling fast sampling for diffusion-based seq2seq text generation. |
| Outcome: | The proposed model generates comparable quality to the SOTA diffusion-based DiffuSeq in just 10 steps, achieving a 200-fold speedup. |
Re-embedding Difficult Samples via Mutual Information Constrained Semantically Oversampling for Imbalanced Text Classification (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing frameworks for imbalanced text classification can generate anchor instances for difficult samples . difficult samples are hard to classify as they are embedded into an overlapping semantic region with the majority class. |
| Approach: | They propose a Mutual Information constrained Semantically Oversampling framework that generates anchor instances for difficult samples to help the backbone network determine the re-embedding position of a non-overlapping representation. |
| Outcome: | The proposed framework can generate anchor instances to help classifiers achieve significant improvements over baselines on a variety of imbalanced text classification tasks. |
R-Judge: Benchmarking Safety Risk Awareness for LLM Agents (2024.findings-emnlp)
Copied to clipboard
Tongxin Yuan, Zhiwei He, Lingzhong Dong, Yiming Wang, Ruijie Zhao, Tian Xia, Lizhen Xu, Binglin Zhou, Fangqi Li, Zhuosheng Zhang, Rui Wang, Gongshen Liu
| Challenge: | Large language models (LLMs) have shown compelling abilities in reasoning, decision-making, and instruction following. |
| Approach: | They propose a benchmark to evaluate the proficiency of large language models (LLMs) in judging and identifying safety risks given agent interaction records. |
| Outcome: | The proposed model outperforms the best-performing model, GPT-4o, while no other models significantly exceed the random. |
PV-SQL: Synergizing Database Probing and Rule-based Verification for Text-to-SQL Agents (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing text-to-SQL systems struggle with deep contextual understanding . |
| Approach: | They propose a framework that provides a tool to help query databases with deeper contextual understanding . they propose two components that iteratively generate probing queries and verify queries . |
| Outcome: | Experiments show PV-SQL outperforms the best text-to-SqL baseline by 5% execution accuracy and 20.8% valid efficiency score while consuming fewer tokens. |
CEDAR: A Chinese Evaluation Dataset for Computational Argumentation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing debate datasets neglect important labels for argument mining, generation, and evaluation. |
| Approach: | They propose a Chinese Evaluation Dataset for Computational Argumentation that includes key arguments and key rhetorical figures, debater roles, modal words, debate results and transcripts. |
| Outcome: | The proposed dataset covers 600 debates about 318 topics from Chinese debate competitions. |
Improving Named Entity Recognition with Attentive Ensemble of Syntactic Information (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies have shown that named entity recognition (NER) is effective in encoding and aggregating syntactic information, but they lack the appropriate knowledge to model such properties. |
| Approach: | They propose to leverage syntactic information by leveraging attentive ensembles to model NER . they propose key-value memory networks, syntax attention and gate mechanism for encoding, weighting and aggregating syntaktic information. |
| Outcome: | The proposed model outperforms previous studies on six English and Chinese benchmark datasets. |
Enhancing Content Preservation in Text Style Transfer Using Reverse Attention and Conditional Layer Normalization (2021.acl-long)
Copied to clipboard
| Challenge: | Text style transfer aims to alter the style of a sentence while preserving its content. |
| Approach: | They propose to remove style information at token level and fuse it to style representations using conditional layer normalization. |
| Outcome: | The proposed model outperforms the state-of-the-art models in terms of content preservation and fluency. |
Joint Aspect Extraction and Sentiment Analysis with Directional Graph Convolutional Networks (2020.coling-main)
Copied to clipboard
| Challenge: | End-to-end aspect-based sentiment analysis uses two sub-tasks to extract aspect terms . experimental results demonstrate the effectiveness of our approach on all datasets . |
| Approach: | They propose to combine aspect extraction and sentiment analysis with encoding syntactic information to improve model's representation of input sentences. |
| Outcome: | The proposed approach achieves state-of-the-art on three benchmark datasets. |
RAPO: An Adaptive Ranking Paradigm for Bilingual Lexicon Induction (2022.emnlp-main)
Copied to clipboard
Zhoujin Tian, Chaozhuo Li, Shuo Ren, Zhiqiang Zuo, Zengxuan Wen, Xinyue Hu, Xiao Han, Haizhen Huang, Denvy Deng, Qi Zhang, Xing Xie
| Challenge: | Existing approaches focus on minimizing distances between words in aligned pairs, while suffering from low discriminative capability to distinguish the relative orders between positive and negative candidates. |
| Approach: | They propose a ranking-oriented induction model to learn personalized mapping function for each word. |
| Outcome: | The proposed model can learn personalized mapping function for each word on public datasets including rich-resource and low-resourced languages. |
StyleFlow: Disentangle Latent Representations via Normalizing Flow for Unsupervised Text Style Transfer (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods to separate content from style but some words contain both content and style information. |
| Approach: | They propose a method which uses a reversible encoder to improve content disentanglement. |
| Outcome: | The proposed method outperforms baselines on sentiment transfer and formality transfer tasks. |
SEOE: A Scalable and Reliable Semantic Evaluation Framework for Open Domain Event Detection (2025.acl-long)
Copied to clipboard
| Challenge: | Existing evaluation methods for Open Domain Event Detection (ODED) lack representative representations of the real world, making it difficult to accurately reflect performance of various ODED methods in real-world scenarios. |
| Approach: | They propose a scalable and reliable Semantic-level Evaluation framework for Open domain event detection by constructing a more representative evaluation benchmark and introducing a semantic evaluation metric. |
| Outcome: | The proposed framework first constructs a more representative evaluation benchmark that currently includes 564 event types covering 7 major domains, with a cost-effective supplementary annotation strategy to ensure the benchmark’s representativeness. |
A Unified Framework for Pun Generation with Humor Principles (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models for generating homophonic and homographic puns lack the linguistic attributes of successful puns to resolve the split-up in existing work. |
| Approach: | They propose a framework to generate both homophonic and homographic puns to resolve the split-up in existing works by incorporating three linguistic attributes of puns into the language models: ambiguity, distinctiveness, and surprise. |
| Outcome: | The proposed model over strong baselines shows that it can generate both homophonic and homographic puns. |
MGPO: Thinking with Images via Multi-Turn Grounding-Based Reinforcement Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | State-of-the-art large multimodal models face challenges when processing high-resolution images, as these inputs are converted into enormous visual tokens, many of which are irrelevant to the downstream task. |
| Approach: | They propose a multi-turn grounding-based policy optimization framework that enables LMMs to iteratively focus on key visual regions by automatically cropping sub-images based on model-predicted grounding coordinates within a multiple-turn conversation framework. |
| Outcome: | The proposed framework improves on Qwen2.5-VL-7B with 21K samples and surpasses OpenAI’s o1 and GPT-4o models on the out-of-distribution (OOD) V* Bench. |
HSCodeComp: A Realistic and Expert-level Agent Benchmark for Hierarchical Rule Application (2026.acl-long)
Copied to clipboard
| Challenge: | Existing agent benchmarks neglect hierarchical rule application in real-world domains . a critical gap persists in numerous real-life professional domains where decision-making is governed by expert-written rules. |
| Approach: | They propose a benchmark requiring agents to assign a unique 10-digit Harmonized System (HS) Code to products by aligning their fuzzy attributes with strict tariff classification rules. |
| Outcome: | The proposed benchmarks lack hierarchical rule application capability in real-world domains . the proposed benchmark is based on e-commerce and is open-source . |
Interpret and Improve In-Context Learning via the Lens of Input-Label Mappings (2025.acl-long)
Copied to clipboard
| Challenge: | Large language models excel at downstream NLP tasks through in-context learning . however, the internal mechanisms behind ICL remain under-explored . |
| Approach: | They propose a PC patching approach to identify modules where input-label mappings function . they observe and verify that key heads utilize input-labeled mappings to generate target labels for new queries. |
| Outcome: | The proposed approach detects modules where input-label mappings function . it also detects that key heads use the mappings to generate labels for new queries . |
CFlowPsyD: An Analysis-Enhanced Dataset for Asynchronous Psychological Counseling through Self-Optimizing Multi-Agent Framework (2026.findings-acl)
Copied to clipboard
| Challenge: | Asynchronous psychological counseling (APC) is a crucial mental health service modality that transcends temporal and spatial constraints. |
| Approach: | They propose a self-optimizing multi-agent framework for counseling dialogue generation, CFlowPsy, which utilizes real anonymized counseling cases as seed data to synthesize diverse problem-solving-oriented APC conversations through large language models. |
| Outcome: | The proposed framework synthesizes diverse problem-solving-oriented APC conversations through large language models. |
PARA: Parameter-Efficient Fine-tuning with Prompt-Aware Representation Adjustment (2024.emnlp-industry)
Copied to clipboard
| Challenge: | Existing methods for parameter-efficient fine-tuning excel in the context of single-backbone multi-tenant applications. |
| Approach: | They propose to integrate a lightweight vector generator within each Transformer layer to improve prompt-aware representation adjustment. |
| Outcome: | The proposed method surpasses current benchmarks in terms of performance despite having a similar number of adjustable parameters. |
Rethinking Creativity Evaluation: A Critical Analysis of Existing Creativity Evaluations (2026.eacl-long)
Copied to clipboard
| Challenge: | Creativity measures that distinguish creativity in one domain fail in others, and different metrics disagree on the same data points. |
| Approach: | They examine, analyze, and compare four representative creativity measures across the diverse creative domains, including creative writing, unconventional problem-solving, and research ideation. |
| Outcome: | The measures of creativity across creative domains are compared using a set of human-aligned examples and lack consistency across domains and metrics. |
ROMA: Real-time Omni-Multimodal Assistant with Interactive Streaming Understanding (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing omni-multimodal large language models lack incomplete modality support or lack autonomous proactive monitoring. |
| Approach: | They propose a real-time omni-multimodal assistant for unified reactive and proactive interaction that decouples response initiation from generation to ensure precise triggering without task conflict. |
| Outcome: | The proposed model achieves state-of-the-art performance on proactive tasks while competing in reactive settings. |
Incremental Transformer: Efficient Encoder for Incremented Text Over MRC and Conversation Tasks (2025.coling-main)
Copied to clipboard
| Challenge: | Existing encoders that encode incremented inputs have to re-encode the whole text to obtain the encoding of the extended input. |
| Approach: | They propose an efficient encoder dedicated for faster encoding of incremented input . it takes only added input as input but attends to cached representations of original input a lower layer . |
| Outcome: | The proposed encoder achieves 6.2x speedup over current encoders . it takes only added input as input but attends to cached representations of original input . |
DL-QAT: Weight-Decomposed Low-Rank Quantization-Aware Training for Large Language Models (2024.emnlp-industry)
Copied to clipboard
| Challenge: | Quantization-aware Training (QAT) is a popular technique for reducing memory usage and improving computational efficiency in large language models. |
| Approach: | They propose a weight-decomposed low-rank quantization-aware training approach that integrates QAT with a group-specific quantization magnitude adjustment. |
| Outcome: | The proposed method outperforms the state-of-the-art method on LLaMA and LLama2 models. |
Unraveling the Mechanics of Learning-Based Demonstration Selection for In-Context Learning (2025.acl-long)
Copied to clipboard
| Challenge: | Recent learning-based demonstration selection methods have proven beneficial to in-context learning (ICL) by choosing more useful exemplars. |
| Approach: | They propose two methods to capture task-agnostic similarities between input and output of LLMs. |
| Outcome: | The proposed methods integrate task-agnostic similarities of different levels between input and output of exemplars and test cases to eliminate costly data collection. |
IAPT: Instance-Aware Prompt Tuning for Large Language Models (2024.acl-long)
Copied to clipboard
| Challenge: | Existing methods for prompt tuning require many soft tokens to guarantee performance . large language models still require a large amount of GPU memory and computations to fine-tune . |
| Approach: | They propose to use a parameter-efficient soft prompt generator to generate idiosyncratic soft prompts for each input instruction. |
| Outcome: | The proposed method outperforms the baselines with comparable tunable parameters and is more efficient than LoRA under the single-backbone multi-tenant setting. |
From Grounding to Manipulation: Case Studies of Foundation Model Integration in Embodied Robotic Systems (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a new study examines the operational characteristics of different integration strategies for robotics . end-to-end vision-language-action models implicitly unify perception and planning . |
| Approach: | They propose end-to-end vision-language-action models that implicitly unify perception and planning . they also propose modular pipelines using either vision-linguistic models or MLLMs . |
| Outcome: | The proposed frameworks implicitly unify perception and planning, and modular pipelines using either vision-language models or multimodal large language models. |
Topic Coverage-based Demonstration Retrieval for In-Context Learning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Prior methods to retrieve demonstrations based on embedding similarity or generation probability, resulting in irrelevant or redundant examples. |
| Approach: | They propose a topic coverage-based retrieval framework that selects demonstrations to comprehensively cover topic-level knowledge relevant to both the test input and the model. |
| Outcome: | The proposed framework covers all the necessary knowledge for the test input and the model. |
GRASS: Gradient-based Adaptive Layer-wise Importance Sampling for Memory-efficient Large Language Model Fine-tuning (2026.findings-acl)
Copied to clipboard
Kaiyuan Tian, Linbo Qiao, Yu Tang, Gongqingjian Jiang, Baihui Liu, Yifu Gao, Xialin Su, Dongsheng Li
| Challenge: | Low-rank adaptation methods for large language models limit expressiveness and performance . layer-wise fine-tuning methods overlook variations in layer importance across tasks and training stages, resulting in suboptimal performance on downstream tasks. |
| Approach: | They propose a gradient-based adaptive layer-wise importance sampling framework that updates only a subset of parameters to reduce memory usage. |
| Outcome: | The proposed framework outperforms state-of-the-art methods in accuracy and memory usage. |
CLIPErase: Efficient Unlearning of Visual-Textual Associations in CLIP (2025.acl-long)
Copied to clipboard
| Challenge: | MU has gained significant attention as a means to remove the influence of specific data from a trained model without requiring full retraining. |
| Approach: | They propose a novel approach that disentangles and selectively forgets both visual and textual associations, ensuring that unlearning does not compromise model performance. |
| Outcome: | Experiments on CIFAR-100, Flickr30K, and Conceptual 12M show that CLIPErase effectively removes designated associations from multimodal samples in downstream tasks while preserving model performance on retain set. |
Learning to Instruct: Fine-Tuning a Task-Aware Instruction Optimizer for Black-Box LLMs (2025.findings-emnlp)
Copied to clipboard
Yunzhe Qi, Jinjin Tian, Tianci Liu, Ruirui Li, Tianxin Wei, Hui Liu, Xianfeng Tang, Monica Xiao Cheng, Jingrui He
| Challenge: | Learning to Instruct is a new paradigm for black-box LLMs with inaccessible internal states. |
| Approach: | They propose a new paradigm that formulates instruction optimization as an LLM fine-tuning objective for a white-box “instruction engineer” LLM. |
| Outcome: | The proposed framework outperforms strong baselines in performance and efficiency. |
Learning Transition Patterns by Large Language Models for Sequential Recommendation (2025.coling-main)
Copied to clipboard
Jianyang Zhai, Zi-Feng Mai, Dongyi Zheng, Chang-Dong Wang, Xiawu Zheng, Hui Li, Feidiao Yang, Yonghong Tian
| Challenge: | Extensive experiments on six real-world datasets show our approach outperforms the best baselines by 7.33% in NDCG@10, 4.65% in Recall@10 and 8.42% in MRR. |
| Approach: | They propose a framework for mapping sequential item texts to sequential item IDs that incorporates multi-query input and item linear projection to model conditional probability distribution of items. |
| Outcome: | The proposed framework outperforms baseline models on six real-world datasets by 7.33% and 4.65% respectively. |
Data Drives Unstable Hierarchical Generalization in LMs (2025.emnlp-main)
Copied to clipboard
| Challenge: | Early in training, LMs can behave like n-gram models but eventually learn tree-based syntactic rules and generalize out of distribution (OOD). |
| Approach: | They study how complex data drives hierarchical rules, while less complex encourages shortcut learning . they find a model uses rules to generalize if its training data is *diverse* . |
| Outcome: | The proposed model learns to generalize hierarchically if its training data is complex . a model learn if it includes center-embedded clauses, a special syntactic structure . |
Semantic Role Labeling Guided Out-of-distribution Detection (2024.lrec-main)
Copied to clipboard
Jinan Zou, Maihao Guo, Yu Tian, Yuhao Lin, Haiyao Cao, Lingqiao Liu, Ehsan Abbasnejad, Javen Qinfeng Shi
| Challenge: | Existing methods for identifying domain-shifted instances are prone to OOD and adversarial inputs. |
| Approach: | They propose an unsupervised method that separates, extracts, and learns the semantic role labeling guided out-of-distribution Detection (SRLOOD) they propose a self-supervised approach to enhance global-local feature learning by predicting SRL extracted role. |
| Outcome: | The proposed method achieves SOTA performance on four OOD benchmarks. |
Empathetic and Emotionally Positive Conversation Systems with an Emotion-specific Query-Response Memory (2022.findings-emnlp)
Copied to clipboard
Zhiliang Tian, Yinliang Wang, Yiping Song, Chi Zhang, Dongkyu Lee, Yingxiu Zhao, Dongsheng Li, Nevin L. Zhang
| Challenge: | Existing emotional conversation systems output responses according to either a given emotion or the user’s emotion reflected in the input queries. |
| Approach: | They propose to generate empathetic responses catering to the user’s emotions while leading the conversation to be emotionally positive by abstracting the conversation corpus and extracting the different responding strategies for different users’ emotions and conversational topics into a memory. |
| Outcome: | The proposed model surpasses the baseline methods in appropriateness, diversity, and generating emotionally positive responses. |
Democratizing Large Language Models via Personalized Parameter-Efficient Fine-tuning (2024.emnlp-main)
Copied to clipboard
| Challenge: | Experimental results demonstrate that OPPU significantly outperforms existing prompt-based methods across seven diverse tasks in the LaMP benchmark. |
| Approach: | They propose to integrate parametric user knowledge into the personal PEFT parameters and non-parametric knowledge from retrieval and profiles, adapting LLMs to user behavior shifts. |
| Outcome: | The proposed method outperforms existing prompt-based methods across seven diverse tasks in the LaMP benchmark. |
From Short Video to Clickable Search: RLVR-Enabled Listwise Query Suggestion with Retrieval-Augmented Context (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing methods to generate short-video bottom-bar queries are largely retrieval-based. |
| Approach: | They propose to reformulate the task as one-shot list generation, producing multiple queries per video . they also build multi-query ground truth from exposure and CTR logs, and redesign offline evaluation . |
| Outcome: | The proposed system yields strong offline and online improvements . it is deployed on Kuaishou to serve hundreds of millions of users daily . |
Simple Neologism Based Domain Independent Models to Predict Year of Authorship (C18-1)
Copied to clipboard
| Challenge: | Using domain independent models, we date documents based only on neologism usage patterns . nasa models use only 200 input features, compared to state of the art models using 200K features. |
| Approach: | They propose domain independent models to date documents based only on neologism usage patterns. |
| Outcome: | The proposed models can generalize to various domains like News, Fiction, and Non-Fiction with competitive performance. |
Generalized Category Discovery with Large Language Models in the Loop (2024.findings-acl)
Copied to clipboard
Wenbin An, Wenkai Shi, Feng Tian, Haonan Lin, QianYing Wang, Yaqiang Wu, Mingxiang Cai, Luyan Wang, Yan Chen, Haiping Zhu, Ping Chen
| Challenge: | Generalized Category Discovery (GCD) is a crucial task that aims to recognize both known and novel categories from a set of unlabeled data. |
| Approach: | They propose a framework that introduces Large Language Models into the training loop to generate category names without human effort. |
| Outcome: | The proposed framework outperforms SOTA models on three benchmark datasets and generates accurate category names for the discovered clusters. |
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. |
GRV-KBQA: A Three-Stage Framework for Knowledge Base Question Answering with Decoupled Logical Structure, Semantic Grounding and Structure-Aware Validation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for Knowledge Base Question Answering generate non-executable queries and inefficiencies in query execution. |
| Approach: | a framework that decouples logical structure generation from semantic grounding is proposed . the framework explicitly enforces KB constraints to improve alignment between generated logical forms and KB structures. |
| Outcome: | GRV-KBQA decouples logical structure generation from semantic grounding and incorporates structure-aware validation to enhance accuracy. |
MathAgent: Adversarial Evolution of Constraint Graphs for Mathematical Reasoning Data Synthesis (2026.findings-acl)
Copied to clipboard
| Challenge: | Current approaches to synthesising high-quality mathematical reasoning data without human priors suffer from mode collapse and limited logical complexity. |
| Approach: | They propose a hierarchical synthesis framework that formulates data synthesis as an unsupervised optimization problem over a constraint graph followed by semantic instantiation rather than a direct text generation task. |
| Outcome: | The proposed framework outperforms widely-used datasets on eight mathematical benchmarks. |
Your Reasoning Model Knows What Counts: Self-Guided Chain-of-Thought Pruning for Efficient Reasoning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to Chain-of-Thought reasoning are often degraded because they disregard the model’s intrinsic reasoning dependency. |
| Approach: | They propose a self-guided pruning framework that leverages the model’s intrinsic likelihood landscape to identify segments that are extraneous to its specific reasoning pattern. |
| Outcome: | The proposed framework reduces output length while maintaining or improving accuracy on multiple benchmarks. |
DPGA-TextSyn: Differentially Private Genetic Algorithm for Synthetic Text Generation (2025.findings-acl)
Copied to clipboard
Zhonghao Sun, Zhiliang Tian, Yiping Song, Yuyi Si, Juhua Zhang, Minlie Huang, Kai Lu, Zeyu Xiong, Xinwang Liu, Dongsheng Li
| Challenge: | Existing methods to fine-tune large language models pose privacy risks . researchers have synthesized data with strong generation capabilities closed-source LLMs to alleviate this problem . |
| Approach: | They propose to combine general LLMs with genetic algorithm to produce relevant and diverse synthetic text under differential privacy constraints. |
| Outcome: | The proposed method significantly improves the performance of the model in downstream tasks while ensuring privacy. |
BioProAgent: Neuro-Symbolic Grounding for Constrained Scientific Planning (2026.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated significant reasoning capabilities in scientific discovery but struggle to bridge the gap to physical execution in wet-labs. |
| Approach: | They propose a framework that anchors probabilistic planning in a deterministic Finite State Machine (FSM) they propose reducing token consumption by 6 through symbolic abstraction to address context bottlenecks . |
| Outcome: | The proposed framework achieves 95.6% physical compliance, compared to 21.0% for ReAct, in the extended BioProBench benchmark. |
Aspect-based Sentiment Analysis with Context Denoising (2024.findings-naacl)
Copied to clipboard
| Challenge: | Existing approaches to ABSA use text encoders to locate important context features or remove them from input. |
| Approach: | They propose to improve ABSA with context denoising to remove noise from text . they use diffusion networks to perform denoizing process to gradually eliminate noise . paper shows that aspect-based sentiment analysis is effective for fine-grained analysis . |
| Outcome: | The proposed approach improves ABSA on five widely used ABSA datasets. |
Untie the Knots: An Efficient Data Augmentation Strategy for Long-Context Pre-Training in Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have prioritized expanding the context window from which they can incorporate more information. |
| Approach: | They propose a data augmentation strategy to enable large language models to gain long-context capabilities without the need to modify existing data mixture. |
| Outcome: | The proposed model outperforms existing models on 20 billion tokens and achieves 75% and 84.5% accuracy on RULER at 128K context length. |
Neural Sparse Topical Coding (P18-1)
Copied to clipboard
| Challenge: | Topic models with sparsity enhancement are effective at learning discriminative and coherent latent topics of short texts. |
| Approach: | They propose a novel sparsity-enhanced topic model with back propagation that replaces the inference process with the back propagations, making it easy to explore extensions. |
| Outcome: | The proposed model outperforms existing methods on Web Snippet and 20Newsgroups datasets. |
A Diffusion Weighted Graph Framework for New Intent Discovery (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to learn from unlabeled data generate noisy supervisory signals . current methods only rely on semantic similarities to generate supervisory signal . |
| Approach: | They propose a weighted DWGF framework to capture semantic similarities and structure relationships in data. |
| Outcome: | The proposed method outperforms state-of-the-art models on evaluation metrics across multiple benchmark datasets. |
Alloc-MoE: Budget-Aware Expert Activation Allocation for Efficient Mixture-of-Experts Inference (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches that reduce expert activations lead to severe model performance degradation. |
| Approach: | They propose a framework that optimizes budget allocation coordinately at layer and token levels to minimize model performance degradation. |
| Outcome: | The proposed framework achieves 1.15 prefill and 1.34 decode speedups on DeepSeek-V2-Lite at half of the original budget. |
DebugBench: Evaluating Debugging Capability of Large Language Models (2024.findings-acl)
Copied to clipboard
Runchu Tian, Yining Ye, Yujia Qin, Xin Cong, Yankai Lin, Yinxu Pan, Yesai Wu, Hui Haotian, Liu Weichuan, Zhiyuan Liu, Maosong Sun
| Challenge: | Large language models (LLMs) have demonstrated exceptional coding capabilities, but their debugging capabilities remain relatively unexplored. |
| Approach: | They propose a debugging benchmark consisting of 4,253 LLMs with four major bug categories and 18 minor types in C++, Java, and Python. |
| Outcome: | The proposed benchmark covers four major bug categories and 18 minor types in C++, Java, and Python. |
Service-oriented Text-to-SQL Parsing (2020.findings-emnlp)
Copied to clipboard
| Challenge: | TEXT2SQL models focus on generating complex SQL query in a precise and complete fashion . current models focus only on executing complex queries in production environment . TExT2sql models are limited by human labor and limited by predefined template . |
| Approach: | They propose a text-to-sql parser that translates natural language utterance to SQL query . the framework enables flexibly access database than rigid API in the application . |
| Outcome: | The proposed model outperforms baseline models in the WikiSQL task by 13% error reduction. |
mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections (2022.emnlp-main)
Copied to clipboard
Chenliang Li, Haiyang Xu, Junfeng Tian, Wei Wang, Ming Yan, Bin Bi, Jiabo Ye, He Chen, Guohai Xu, Zheng Cao, Ji Zhang, Songfang Huang, Fei Huang, Jingren Zhou, Luo Si
| Challenge: | Existing pre-trained vision-language models suffer from inefficiency and linguistic signal overwhelmed by long visual sequences in cross-modal alignment. |
| Approach: | They propose a vision-language foundation model with cross-modal skip-connections that can be pre-trained end-to-end on large-scale image-text pairs with both discriminative and generative objectives. |
| Outcome: | The proposed model achieves state-of-the-art results on a wide range of vision-language downstream tasks, including image captioning, image-text retrieval, visual grounding and visual question answering. |
MirrorCAPTCHA: Wild CAPTCHA, Wild Distribution, Wild Web-based Platform Meet Multimodal LLM Agents (2026.acl-long)
Copied to clipboard
Xiangyu Wu, Yuwei Hu, Tianyu Cui, Yueying Tian, Qing-Guo Chen, Zhao Xu, Weihua Luo, Kaifu Zhang, Yang Yang, Jianfeng Lu
| Challenge: | Existing agent benchmarks fail to evaluate an agent's real-world capacity to handle CAPTCHA . Existing benchmarks ignore this practical challenge, failing to evaluate agents' ability to handle complex visual CAPTchas. |
| Approach: | They propose a benchmark annotated with Weighted Pass Rate and a new metric to measure agent's ability to handle CAPTCHA. |
| Outcome: | The proposed benchmark outperforms current state-of-the-art closed-source models on mirrorCAPTCHA and achieves 9.4% higher average weighted pass rate and 2.13% higher average Completion degree. |
Improving Pre-trained Language Models with Knowledge Enhancement and Filtering Framework (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing knowledge enhancement techniques for pre-trained language models (PLMs) introduce noisy entity representations. |
| Approach: | They propose a knowledge enhancement filter that integrates external knowledge bases to enhance PLMs' ability to capture entity knowledge. |
| Outcome: | The proposed method achieves the highest F1-score and accuracy while reducing the computational cost by 1.7-2.5x. |
From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms (2026.findings-acl)
Copied to clipboard
Jinghao Luo, Yuchen Tian, Chuxue Cao, Ziyang Luo, Hongzhan Lin, Kaixin Li, Chuyi Kong, Ruichao Yang, Jing Ma
| Challenge: | Large Language Models (LLMs)-based agents have fundamentally reshaped artificial intelligence . however, the inherent statelessness of LLMs hinders their ability to maintain logical consistency across complex, multi-step tasks . |
| Approach: | They propose a framework for LLM agent memory mechanisms that formalizes the development process into three stages: storage, reflection, and experience. |
| Outcome: | The proposed framework breaks the development process into three stages . it analyzes the need for long-range consistency, challenges in dynamic environments, and the ultimate goal of continual learning. |
InfoPO: On Mutual Information Maximization for Large Language Model Alignment (2025.naacl-long)
Copied to clipboard
Teng Xiao, Zhen Ge, Sujay Sanghavi, Tian Wang, Julian Katz-Samuels, Marc Versage, Qingjun Cui, Trishul Chilimbi
| Challenge: | Recent studies have shown that direct preference optimization and its variants can be useful for fine-tuning large language models with human preferences data. |
| Approach: | They propose a preference fine-tuning algorithm that effectively and efficiently aligns large language models using preference data. |
| Outcome: | Extensive experiments show that the proposed algorithm outperforms established baselines on reasoning tasks. |
Beyond End-to-End: Dynamic Chain Optimization for Private LLM Adaptation on the Edge (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are revolutionizing mobile intelligence, but their implementation on mobile devices is severely bottlenecked by the prohibitive resource demands of LLMs. |
| Approach: | They propose a paradigm that forgoes end-to-end updates in favor of a sequential, layer-by-layer manner. |
| Outcome: | Extensive experiments on multiple benchmarks demonstrate the superiority of ChainFed over existing methods, boosting average accuracy by up to 46.46%. |
Decoding Scientific Experimental Images: The SPUR Benchmark for Perception, Understanding, and Reasoning (2026.acl-long)
Copied to clipboard
Junpeng Ding, Zichen Tang, Haihong E, Mengyuan Ji, Yang Liu, Haolin Tian, Haiyang Sun, Pengqi Sun, Yang Xu, Yichen Liu, Haocheng Gao, Zijie Xi, Ruomeng Jiang, Peizhi Zhao, Rongjin Li, Yuanze Li, Jiacheng Liu, Zhongjun Yang, Jintong Chen, Siying Lin
| Challenge: | Xu and Peng, 2025) . . SPUR is a comprehensive benchmark for scientific experimental image perception, understanding, and reasoning, comprising 4,264 question-answering (QA) pairs derived from 1,084 expert-curated images. |
| Approach: | They propose to use 4,264 question-answering (QA) pairs derived from 1,084 expert-curated images to evaluate the visual perception of multimodal large language models (MLLMs) . they also propose to utilize cross-panel relation understanding to evaluate MLLM’s ability to decipher intricate cross-panel relations. |
| Outcome: | The proposed model is based on 4,264 question-answering pairs derived from 1,084 expert-curated images. |
Enhancing Multiple-choice Machine Reading Comprehension by Punishing Illogical Interpretations (2021.emnlp-main)
Copied to clipboard
| Challenge: | Multiple-choice MRC is one of the most studied tasks in MRC due to the convenience of evaluation and the flexibility of answer format. |
| Approach: | They propose to use multiple-choice MRC to explain a trained model and reveal how it arrives at the prediction by punishing illogical attributions. |
| Outcome: | The proposed method improves model performance without external information and model structure change without any external information. |
Towards Better Entity Linking with Multi-View Enhanced Distillation (2023.acl-long)
Copied to clipboard
Yi Liu, Yuan Tian, Jianxun Lian, Xinlong Wang, Yanan Cao, Fang Fang, Wen Zhang, Haizhen Huang, Weiwei Deng, Qi Zhang
| Challenge: | Entity linking is a fundamental task in Natural Language Processing (NLP), connecting mentions within unstructured contexts to their corresponding entities in a Knowledge Base (KB). |
| Approach: | They propose a dual-encoder framework that can efficiently match mentions to two-encoding frameworks by a global-view. |
| Outcome: | The proposed framework achieves state-of-the-art on several entity linking benchmarks. |
GROVE: A Retrieval-augmented Complex Story Generation Framework with A Forest of Evidence (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for generating stories with complex plots rely on detailed prompts, which inadvertently limit the creative potential of the generated stories. |
| Approach: | They propose a retrieval-auGmented stoRy generation framework with a fOrest of eVidEnce to enhance stories’ complexity. |
| Outcome: | The proposed framework enables generating more diverse plotlines from human-written stories. |
Re3: Generating Longer Stories With Recursive Reprompting and Revision (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent work has generated short stories of several pages in length, but they are much shorter than typical short stories meant for human consumption. |
| Approach: | They propose a framework to generate long-range plot coherence and relevance by prompting a general-purpose language model and a language model. |
| Outcome: | The proposed framework generates stories of 2000-2500 words, compared to similar-length stories generated directly from the same model. |
mABC: Multi-Agent Blockchain-inspired Collaboration for Root Cause Analysis in Micro-Services Architecture (2024.findings-emnlp)
Copied to clipboard
Wei Zhang, Hongcheng Guo, Jian Yang, Zhoujin Tian, Yi Zhang, Yan Chaoran, Zhoujun Li, Tongliang Li, Xu Shi, Liangfan Zheng, Bo Zhang
| Challenge: | Root cause analysis (RCA) in Micro-services architectures with escalating complexity is challenging due to fault propagation and circular dependencies among nodes. |
| Approach: | They propose a framework where multiple agents follow Agent Workflow and collaborate in blockchain-inspired voting to ensure the reliability of root cause analysis. |
| Outcome: | The proposed framework reduces the number of steps and standardizes task processing through Agent Workflow. |
LeafNATS: An Open-Source Toolkit and Live Demo System for Neural Abstractive Text Summarization (N19-4)
Copied to clipboard
| Challenge: | Neural abstractive text summarization (NATS) has gained a lot of attention in the past few years from both industry and academia. |
| Approach: | They propose an open-source toolkit for training and evaluation of different sequence-to-sequence based models for the NATS task and for deploying the pre-trained models to real-world applications. |
| Outcome: | The proposed model can be used to generate high-quality summaries that are verbally innovative and can easily incorporate external knowledge. |
ERNIE-Code: Beyond English-Centric Cross-lingual Pretraining for Programming Languages (2023.findings-acl)
Copied to clipboard
| Challenge: | ERNIE-Code is a unified pre-trained language model for 116 NLs and 6 PLs. |
| Approach: | They propose a unified pre-trained language model for 116 NLs and 6 PLs . they employ span-corruption language modeling that learns patterns from monolingual NL or PL . |
| Outcome: | The proposed model outperforms previous multilingual models for NL or NL across end tasks. |
How to Fine-Tune Safely on a Budget: Model Adaptation Using Minimal Resources (2025.emnlp-industry)
Copied to clipboard
Anh C. Pham, Mihir Thalanki, Michael Sun, Aditya Chaloo, Ankita Gupta, Tian Xia, Aditya Mate, Ehi Nosakhare, Soundararajan Srinivasan
| Challenge: | Existing methods for fine-tuning safety examples are underdeveloped. |
| Approach: | They hypothesize that the effectiveness of a safety example is governed by its instruction-response behavior and its semantic diversity across harm categories. |
| Outcome: | The proposed method reduces harmfulness by up to 41% while adding only 0.05% more data to the fine-tuning set. |
Target-Oriented Relation Alignment for Cross-Lingual Stance Detection (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing work on cross-lingual stance detection has ignored the inconsistency in the occurrences and distributions of targets between languages, which consequently degrades the performance of stance detector in low-resource languages. |
| Approach: | They propose a fine-grained method which considers both target-level associations and language-level alignments to learn the in-language and cross-language associations. |
| Outcome: | The proposed method is compared with competing methods under variant settings and shows that it performs better in low-resource languages. |
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. |
PRISM-MCTS: Learning from Reasoning Trajectories with Metacognitive Reflection (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing reasoning models are limited by inefficiency and computational redundancy . PRISM-MCTS integrates a process reward model with a dynamic shared memory . |
| Approach: | They propose a reasoning framework that integrates a process reward model with a dynamic shared memory. |
| Outcome: | PRISM-MCTS integrates a process reward model with a dynamic shared memory . it halves trajectory requirements on GPQA while surpassing MCTS-RAG and Search-o1 . |
Bridging Word-Pair and Token-Level Metaphor Detection with Explainable Domain Mining (2024.acl-long)
Copied to clipboard
| Challenge: | Existing methods for word-pair metaphor detection provide intermediate explainable clues for detection results. |
| Approach: | They propose a method to bridge word-pair and token-level metaphor detection by modeling word pairs as explainable intermediate information. |
| Outcome: | The proposed method bridges word-pair and token-level metaphor detection by using word pairs . it provides intermediate explainable clues for the detection results, but this is a challenge . |
Born Pragmatic, Trained to Hallucinate? Quantifying the Origins of Contextual Bias in LLMs via the PaCE Benchmark (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models excel at capturing communicative intent, but they have a side effect: pragmatic hallucination. |
| Approach: | They propose a benchmark to quantify the impact of pragmatic hallucination on large language models . they propose RLHF and SFT to induce a strong tendency for pragmatic over-attribution . |
| Outcome: | The proposed model outperforms existing models in predicting pragmatic hallucinations . the evaluations show that current alignment paradigms lack precise control over pragmatic boundaries . |
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. |
ALoRA: Allocating Low-Rank Adaptation for Fine-tuning Large Language Models (2024.naacl-long)
Copied to clipboard
| Challenge: | Low-rank adaptation (LoRA) has demonstrated commendable performance as a popular method . however, it is implemented with a fixed intrinsic rank that might not be ideal for downstream tasks. |
| Approach: | They propose a method that estimates the importance score of each LoRA rank and prunes abundant LoRA ranks to improve performance. |
| Outcome: | The proposed method outperforms baselines on a variety of tasks with comparable parameters. |
Multi-Domain Dialogue Acts and Response Co-Generation (2020.acl-main)
Copied to clipboard
| Challenge: | Existing pipeline approaches for task-oriented dialogue systems tend to predict multiple dialogue acts first and use them to assist response generation. |
| Approach: | They propose a neural co-generation model that generates dialogue acts and responses concurrently and preserves semantic structures of multi-domain dialogue acts. |
| Outcome: | The proposed model improves over state-of-the-art models in automatic and human evaluations on a large-scale dataset. |
UrbanGeoEval: A City-Scale Benchmark for Evaluating Large Language Models in Geospatial Reasoning (2026.acl-long)
Copied to clipboard
| Challenge: | Extensive experiments on 18 widely used LLMs uncover critical insights: (1) models exhibit severe geographic biases and resolution gaps; (2) failures in complex multi-hop tasks stem from brittle foundational spatial skills rather than high-level logic deficits. |
| Approach: | They propose a dual-module framework that disentangles factual recall and spatial logic from the model's real capabilities in urban environments. |
| Outcome: | Extensive tests on 18 widely used LLMs reveal that models exhibit severe geographic biases and resolution gaps, and failures in complex multi-hop tasks often stem from brittle foundational spatial skills rather than high-level logic deficits. |
BOOKWORLD: From Novels to Interactive Agent Societies for Story Creation (2025.acl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have enabled social simulation through multi-agent systems. |
| Approach: | They propose a system for constructing and simulating book-based multi-agent societies that simulates established fictional worlds and characters. |
| Outcome: | The proposed system generates high-quality stories while maintaining fidelity to the source books, surpassing previous methods with a win rate of 75.36%. |
POINTS-Reader: Distillation-Free Adaptation of Vision-Language Models for Document Conversion (2025.emnlp-main)
Copied to clipboard
Yuan Liu, Zhongyin Zhao, Le Tian, Haicheng Wang, Xubing Ye, Yangxiu You, Zilin Yu, Chuhan Wu, Zhou Xiao, Yang Yu, Jie Zhou
| Challenge: | Existing approaches to training document conversion models with manual annotation are costly and time-consuming, and training student models by distilling outputs from teacher models can significantly limit their performance in real-world applications. |
| Approach: | They propose a fully automated framework for constructing high-quality document extraction datasets and models capable of handling diverse document formats and layouts. |
| Outcome: | The proposed model outperforms existing models and improves on annotated documents. |
ChiMST: A Chinese Medical Corpus for Word Segmentation and Medical Term Recognition (2022.lrec-1)
Copied to clipboard
| Challenge: | Chinese word segmentation and named entity recognition are important tasks in natural language processing. |
| Approach: | They develop a Chinese medical corpus annotated with Chinese word boundary and medical term information to address this problem. |
| Outcome: | The proposed corpus will be a valuable resource for Chinese word segmentation and named entity recognition research on the medical domain. |
DiffER: Diffusion Entity-Relation Modeling for Reversal Curse in Diffusion Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing large language models exhibit unidirectional behavior when processing bidirectional relationships . authors propose a solution to alleviate the reversal curse in Diffusion LLMs . |
| Approach: | They propose a model that addresses the "reversal curse" of bidirectional behavior in large language models . they propose 'entity-aware training' and balanced data construction to alleviate asymmetry and missing relations . |
| Outcome: | The proposed model alleviates the "reversal curse" in Diffusion LLMs . the proposed model employs whole-entity masking to mitigate entity fragmentation . |
Federated Chinese Word Segmentation with Global Character Associations (2021.findings-acl)
Copied to clipboard
| Challenge: | Chinese word segmentation (CWS) is a fundamental task for natural language processing. |
| Approach: | They propose a neural model for Chinese word segmentation with federated learning to help CWS deal with data isolation. |
| Outcome: | The proposed model outperforms baselines on a simulated environment with five nodes. |
CodeTransOcean: A Comprehensive Multilingual Benchmark for Code Translation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing code translation datasets focus on a single pair of programming languages . early software systems are developed using programming languages such as Fortran and COBOL . |
| Approach: | They propose a large-scale comprehensive benchmark that supports the largest variety of programming languages for code translation. |
| Outcome: | The proposed framework supports translations between multiple programming languages and a cross-framework dataset for deep learning code across different frameworks. |
Unsupervised Melody-to-Lyrics Generation (2023.acl-long)
Copied to clipboard
Yufei Tian, Anjali Narayan-Chen, Shereen Oraby, Alessandra Cervone, Gunnar Sigurdsson, Chenyang Tao, Wenbo Zhao, Tagyoung Chung, Jing Huang, Nanyun Peng
| Challenge: | Existing methods for automatic melody-to-lyric generation are limited due to the limited amount of melody-lyrical aligned data. |
| Approach: | They propose a method for automatic melody-to-lyric generation without training on any aligned melody-lyr data. |
| Outcome: | The proposed model generates high-quality lyrics that are singable, intelligible, and coherent than baseline models. |
From Informal to Formal – Incorporating and Evaluating LLMs on Natural Language Requirements to Verifiable Formal Proofs (2025.acl-long)
Copied to clipboard
Jialun Cao, Yaojie Lu, Meiziniu Li, Haoyang Ma, Haokun Li, Mengda He, Cheng Wen, Le Sun, Hongyu Zhang, Shengchao Qin, Shing-Chi Cheung, Cong Tian
| Challenge: | Recent studies in formal mathematical reasoning have shown an unstoppable growth trend. |
| Approach: | They constructed 18k high-quality instruction-response pairs across five mainstream formal specification languages and evaluated them against ten open-sourced LLMs. |
| Outcome: | The proposed model compared instruction-response pairs across five formal specification languages and found that the LLMs were good at writing proof segments when given either the code, or the detailed description of proof steps. |
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%. |
Learning Continuous Temporal Dynamics on Symplectic Manifolds for Temporal Knowledge Graph Embedding (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for temporal knowledge graph embedding lack explicit structural constraints for continuous-time dynamics. |
| Approach: | They propose a Temporal Knowledge Graph Embedding framework that embeds temporal dynamics into a symplectic phase space. |
| Outcome: | The proposed framework achieves competitive performance with lower embedding dimensions. |
SaSR-Net: Source-Aware Semantic Representation Network for Enhancing Audio-Visual Question Answering (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing AVQA methods often fail to link sound-producing objects in the video with the audio-visual information. |
| Approach: | They introduce a source-aware semantic representation network for AVQA . they use source-wise learnable tokens to capture and align audio-visual elements with the question . |
| Outcome: | The proposed model outperforms state-of-the-art models on the Music-AVQA and AVQA-Yang datasets. |
HypoGen: Hyperbole Generation with Commonsense and Counterfactual Knowledge (2021.findings-emnlp)
Copied to clipboard
| Challenge: | despite its abundance, the computational explorations of hyperboles remain under-explored. |
| Approach: | They propose a sentence-level hyperbole generation method that leverages commonsense and counterfactual inference to generate hyperbolic candidates based on the results. |
| Outcome: | The proposed method generates hyperboles with high success rate, intensity, funniness, and creativity. |
Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate (2024.emnlp-main)
Copied to clipboard
Tian Liang, Zhiwei He, Wenxiang Jiao, Xing Wang, Yan Wang, Rui Wang, Yujiu Yang, Shuming Shi, Zhaopeng Tu
| Challenge: | Modern large language models (LLMs) have shown remarkable performance on general language tasks but struggle on complex reasoning tasks. |
| Approach: | They propose a multi-agent debate framework that encourages divergent thinking in LLMs . they propose to break debate and use a judge to obtain a final solution . |
| Outcome: | The proposed framework encourages divergent thinking in large language models . it is able to generate novel thoughts even if initial stance is incorrect . |
Lightweight Haar Wavelet Subband Pruning for LLMs (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have impressive performance but require computational and memory resources. |
| Approach: | They propose a post-training framework that uses a Haar wavelet transform to prune weights. |
| Outcome: | The proposed pruning framework reduces pruning time and computational costs by removing less important weights while preserving model architecture. |
Preference Heads in Large Language Models: A Mechanistic Framework for Interpretable Personalization (2026.acl-long)
Copied to clipboard
Weixu Zhang, Ye Yuan, Changjiang Han, Yuxing Tian, Zipeng Sun, Linfeng Du, Jikun Kang, Hong Kang, Xue Liu, Haolun Wu
| Challenge: | Large Language Models exhibit strong implicit personalization ability, but most approaches treat this behavior as a black box. |
| Approach: | They propose a mechanistic interpretation perspective and propose 'sparse' set of Preference Heads . they compute a Preference Contribution Score for each attention head and compare their predictions . |
| Outcome: | The proposed framework computes a Preference Contribution Score (PCS) for each attention head and measures its causal impact on user aligned outputs. |
xLAM: A Family of Large Action Models to Empower AI Agent Systems (2025.naacl-long)
Copied to clipboard
Jianguo Zhang, Tian Lan, Ming Zhu, Zuxin Liu, Thai Quoc Hoang, Shirley Kokane, Weiran Yao, Juntao Tan, Akshara Prabhakar, Haolin Chen, Zhiwei Liu, Yihao Feng, Tulika Manoj Awalgaonkar, Rithesh R N, Zeyuan Chen, Ran Xu, Juan Carlos Niebles, Shelby Heinecke, Huan Wang, Silvio Savarese, Caiming Xiong
| Challenge: | Autonomous agents powered by large language models (LLMs) have attracted significant research interest, but there are few standards for developing specialized models for agent tasks. |
| Approach: | They propose a series of large action models with dense and mixture-of-expert architectures that unifies, augments, and synthesizes diverse datasets to enhance agent generalizability and performance. |
| Outcome: | The proposed models outperform GPT-4, Claude-3, and many other models in terms of tool use and outperformed GPT-based models on multiple agent ability benchmarks. |
A Neural Transition-based Joint Model for Disease Named Entity Recognition and Normalization (2021.acl-long)
Copied to clipboard
| Challenge: | Existing models for disease recognition and normalization ignore text surface form of each candidate concept, causing boundary inconsistency. |
| Approach: | They propose a neural transition-based joint model to normalize disease entities from biomedical text. |
| Outcome: | The proposed model improves on two publicly available datasets. |
BNLP: A Text Annotation Platform for Quality Control of LLM-Generated Annotations (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing annotation tools lack support for Large Language Models (LLMs) or use LLMs as one-off preannotation engines, compromising data reliability. |
| Approach: | They propose a text annotation platform that embeds LLM-assisted labeling into a quality-aware collaborative workflow. |
| Outcome: | Experiments show that BNLP reduces annotation time by 74.3% and improves annotation quality by 11.6% over purely manual annotation in LLM-assisted settings. |
Rethinking Expert Trajectory Utilization in LLM Post-training for Mathematical Reasoning (2026.acl-long)
Copied to clipboard
Bowen Ding, Yuhan Chen, Jiayang Lyu, Jiyao Yuan, Qi Zhu, Shuangshuang Tian, Dantong Zhu, Futing Wang, Heyuan Deng, Fei Mi, Lifeng Shang, Tao Lin
| Challenge: | evolving generic Large Language Models into specialized Large Reasoning Models requires effective post-training. |
| Approach: | They propose a plasticity-ceiling framework to harness expert trajectories . they establish the Sequential SFT-then-RL pipeline as the superior standard . |
| Outcome: | The proposed framework overcomes stability and premature convergence deficits in synchronized approaches. |
MMCode: Benchmarking Multimodal Large Language Models for Code Generation with Visually Rich Programming Problems (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Programming often involves translating detailed and complex specifications into code . current state-of-the-art models struggle to solve these problems, a new study shows . |
| Approach: | They propose a multi-modal coding dataset to evaluate algorithmic problem-solving skills in visually rich contexts. |
| Outcome: | The proposed model lacks powerful vision-code models due to the extreme demand for reasoning abilities. |
Large Language Models Are No Longer Shallow Parsers (2024.acl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have reshaped the field of natural language processing (NLP) however, fundamental NLP tasks that involve linguistic analysis still play essential roles in the field. |
| Approach: | They propose to use constituency parsing to improve performance of LLMs on deep syntactic parse trees to prompt LLM chunking, filter out low-quality chunks and add remaining chunks to prompts to instruct LLM for parser. |
| Outcome: | The proposed approach improves LLMs' performance on constituency parsing on English and Chinese benchmark datasets. |
Metagent-P: A Neuro-Symbolic Planning Agent with Metacognition for Open Worlds (2025.findings-acl)
Copied to clipboard
YanfangZhou YanfangZhou, Yuntao Liu, Xiaodong Li, Yongqiang Zhao, Xintong Wang, Jinlong Tian, Zhenyu Li, Xinhai Xu
| Challenge: | Recent advances in large language models (LLMs) show promising potential through their world knowledge and language processing capabilities in open-world planning. |
| Approach: | They propose a framework that integrates the world knowledge of large language models, symbolic reasoning capabilities of cognitive architectures, and metacognition to improve experience utilization. |
| Outcome: | The proposed framework outperforms current state-of-the-art methods in Minecraft and reduces the average replanning counts by 34% and exceeds the human success rate by 18.96%. |
ERNIE-Gram: Pre-Training with Explicitly N-Gram Masked Language Modeling for Natural Language Understanding (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing methods to model coarse-grained linguistic information do not integrate coarse-gram information into pre-training. |
| Approach: | They propose an explicitly n-gram masking method to enhance integration of coarse-grained linguistic information into pre-training. |
| Outcome: | The proposed method outperforms existing models on English and Chinese text corpora and fine-tunes on 19 downstream tasks. |
Learning to Abstract for Memory-augmented Conversational Response Generation (P19-1)
Copied to clipboard
| Challenge: | Existing generative models for open-domain chit-chat conversations lack informativeness and diversity. |
| Approach: | They propose a retrieval-augmented generative model that learns to abstract from the training corpus and saves useful information to the memory to assist the response generation. |
| Outcome: | The proposed model outperforms other baselines in query-response clustering and learning to utilize these characteristics for response generation. |
QualiSpeech: A Speech Quality Assessment Dataset with Natural Language Reasoning and Descriptions (2025.acl-long)
Copied to clipboard
Siyin Wang, Wenyi Yu, Xianzhao Chen, Xiaohai Tian, Jun Zhang, Lu Lu, Yu Tsao, Junichi Yamagishi, Yuxuan Wang, Chao Zhang
| Challenge: | Existing datasets lack comprehensive annotations for speech quality assessment . existing methods lack detailed annotations, resulting in inaccurate evaluations. |
| Approach: | They propose a low-level speech quality assessment dataset incorporating natural language descriptions and a Benchmark to evaluate low- level speech understanding capabilities of auditory large language models. |
| Outcome: | The proposed model can be used to evaluate the low-level speech understanding capabilities of auditory large language models. |
Root Defense Strategies: Ensuring Safety of LLM at the Decoding Level (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods to detect harmful outputs from prefill-level lacks utilization of the model’s decoding outputs, leading to relatively lower effectiveness and robustness. |
| Approach: | They propose a robust decoding mechanism that corrects harmful queries directly rather than rejecting them outright. |
| Outcome: | The proposed model improves model security without compromising reasoning speed. |
An LLM-Enabled Knowledge Elicitation and Retrieval Framework for Zero-Shot Cross-Lingual Stance Identification (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing research is conducted in monolingual setting on English datasets, whereas in other low-resource languages, it lacks sufficient data for training quality stance detection models. |
| Approach: | They propose a knowledge elicitation and retrieval framework that leverages the capability of large language models for stance knowledge acquisition and matches the target language input to the most relevant stance information. |
| Outcome: | The proposed framework improves on multilingual datasets and competitive baselines. |
Complementary Learning of Aspect Terms for Aspect-based Sentiment Analysis (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing ABSA models do not pay attention to aspect terms and their contexts . a discriminator is introduced to improve ABSA, allowing for better understanding of aspect terms . |
| Approach: | They propose to improve ABSA by complementary learning of aspect terms . they explicitly recover aspect terms from each input sentence to better understand aspects . |
| Outcome: | The proposed approach improves ABSA on five widely used English benchmark datasets. |
ToMELP: A Theory-of-Mind Benchmark for Route-Controlled Persuasion under the Elaboration Likelihood Model (2026.findings-acl)
Copied to clipboard
| Challenge: | Theory of Mind (ToM) is widely regarded as central to effective persuasion, yet existing evaluations fail to capture the infer–apply loop that arises in real-world dialogue. |
| Approach: | They propose a benchmark that conditions on the audience persona p and the Elaboration Likelihood Model (ELM) route r within persuasive conversations. |
| Outcome: | The proposed model can model the interlocutor's mental states over multiple turns and adapt strategy and tone accordingly. |
STAPO: Selective Trajectory-Aware Policy Optimization for LLM Agent Training (2026.acl-long)
Copied to clipboard
Qiuyi Qi, Tian Liang, Mutian Bao, Jinjian Zhang, Dongnan Liu, Wei Zhou, Linjian Mo, Ming Kong, Jie Liu, Feng Zhang, Qiang Zhu
| Challenge: | Prior work has explored step-level supervision using Shannon-entropy-based uncertainty signals, which conflate inherent state complexity with agent confidence. |
| Approach: | They propose a hierarchical group-based RL framework that leverages normalized entropy to locate outlier steps associated with trajectory neglect and optimizes them via a mechanism of trajectory-aware reward and trajectory-independent penalty. |
| Outcome: | Experiments on ALFWorld, WebShop, and Search-Augmented QA show that STAPO achieves state-of-the-art performance while substantially alleviating trajectory neglect. |
Router-Tuning: A Simple and Effective Approach for Dynamic Depth (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to improve computational efficiency are under-explored and face several critical challenges. |
| Approach: | They propose a method that selectively activates only a subset of the model's layers, skipping those deemed less important. |
| Outcome: | The proposed method significantly improves performance on Attention layers and MoE layers while reducing redundant computation and memory usage. |
Enhancing One-Shot Pruned Pre-trained Language Models through Sparse-Dense-Sparse Mechanism (2025.coling-main)
Copied to clipboard
Guanchen Li, Xiandong Zhao, Lian Liu, Zeping Li, Yixing Xu, Dong Li, Lu Tian, Jie He, Ashish Sirasao, Emad Barsoum
| Challenge: | Pre-trained language models (PLMs) are robust in contextual understanding but their considerable size incurs significant computational and storage costs. |
| Approach: | They propose a Sparse-Dense-Sparse pruning framework to prune PLMs . they prune less critical connections using conventional pruning methods . |
| Outcome: | The proposed pruning framework outperforms SparseGPT and Wanda under identical sparsity. |
LongTableBench: Benchmarking Long-Context Table Reasoning across Real-World Formats and Domains (2025.findings-emnlp)
Copied to clipboard
Liyao Li, Jiaming Tian, Hao Chen, Wentao Ye, Chao Ye, Haobo Wang, Ningtao Wang, Xing Fu, Gang Chen, Junbo Zhao
| Challenge: | Evaluating 52 LLMs reveals that only the strongest models maintain robust performance under increasing context lengths and format diversity. |
| Approach: | They propose a benchmark for evaluating long-context reasoning over semi-structured tables across diverse formats, tasks, and domains. |
| Outcome: | The proposed model outperforms compression-based approaches on tasks requiring semantic integration. |
Safe-FedLLM: Delving into the Safety of Federated Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Existing work on federated learning for large language models (FL) addresses privacy and data-silo issues in the training of large language model training. |
| Approach: | They propose a probe-based defense framework for FedLLM that constructs defenses across three levels: Step-Level, Client-Level and Shadow-Level. |
| Outcome: | The proposed framework improves FedLLM's robustness against malicious clients while maintaining competitive performance on benign data. |
A Novel Cascade Binary Tagging Framework for Relational Triple Extraction (2020.acl-main)
Copied to clipboard
| Challenge: | Existing approaches to extract relational triples from unstructured text are inadequate to solve the overlapping triple problem. |
| Approach: | They propose a cascade binary tagging framework that models relations as functions that map subjects to objects in a sentence. |
| Outcome: | The proposed framework outperforms state-of-the-art methods on two datasets . it outperformed baseline methods by 17.5 and 30.2 absolute gains . |
MingOfficial: A Ming Official Career Dataset and a Historical Context-Aware Representation Learning Framework (2023.emnlp-main)
Copied to clipboard
You-Jun Chen, Hsin-Yi Hsieh, Yu Lin, Yingtao Tian, Bert Chan, Yu-Sin Liu, Yi-Hsuan Lin, Richard Tsai
| Challenge: | In Chinese studies, understanding the nuanced traits of historical figures can be challenging due to the need for domain expertise, specialist knowledge, and context-specific insights. |
| Approach: | They propose a large-scale multi-modal dataset for Chinese officials from the Ming Dynasty that integrates structured and text data to enable investigation of social structures. |
| Outcome: | The proposed dataset could enable exploratory analysis of official identities and significantly boost performance in tasks such as identifying nuance identities from 24.6% to 98.2% F1 score in hold-out test set. |
DOC: Improving Long Story Coherence With Detailed Outline Control (2023.acl-long)
Copied to clipboard
| Challenge: | Detailed Outline Control (DOC) framework improves long-range plot coherence . human evaluations of DOC show it outperforms strong Re3 on plot cohesion, outline relevance and interestingness . |
| Approach: | They propose a Detailed Outline Control framework to improve long-range plot coherence . the detailed outliner creates a more detailed, hierarchically structured outline . they propose doc with a detailed controller to ensure the more detailed outline is respected . |
| Outcome: | The proposed framework outperforms Re3 on plot coherence, outline relevance and interestingness. |
Response-Anticipated Memory for On-Demand Knowledge Integration in Response Generation (2020.acl-main)
Copied to clipboard
| Challenge: | Neural conversation models generate appropriate but non-informative responses in general. |
| Approach: | They propose to construct a document memory with anticipated responses in mind using a teacher-student framework and a student's input. |
| Outcome: | The proposed model outperforms the state-of-the-art for the Conversing by Reading task. |
Multi-level Adaptive Contrastive Learning for Knowledge Internalization in Dialogue Generation (2023.emnlp-main)
Copied to clipboard
Chenxu Yang, Zheng Lin, Lanrui Wang, Chong Tian, Liang Pang, Jiangnan Li, Qirong Ho, Yanan Cao, Weiping Wang
| Challenge: | Existing knowledge-grounded dialogue generation models struggle with dull and repetitive outputs, a problem commonly termed as text degeneration. |
| Approach: | They propose a framework that allows the model to "cheat" the objective by duplicating knowledge segments in a superficial pattern matching based on overlap. |
| Outcome: | The proposed framework can be applied to a WoW dataset and shows that it works across models and decoding strategies. |
Anti-Overestimation Dialogue Policy Learning for Task-Completion Dialogue System (2022.findings-naacl)
Copied to clipboard
| Challenge: | Recent research has focused on reinforcement learning (RL)-based dialogue policy. |
| Approach: | They propose a dynamic partial average estimator (DPAV) of the ground truth maximum action value to solve the overestimation problem. |
| Outcome: | The proposed method achieves better results on three dialogue datasets with a lower computational load compared to baselines on three different domains with lower bias. |
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. |
A Generic Method for Fine-grained Category Discovery in Natural Language Texts (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for fine-grained category discovery neglect semantic similarities of fine-grain categories. |
| Approach: | They propose a method that detects fine-grained clusters of semantically similar texts guided by a novel objective function. |
| Outcome: | The proposed method surpasses state-of-the-art methods on three benchmark tasks. |
Vision-aided Unsupervised Constituency Parsing with Multi-MLLM Debating (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches require explicit cross-modal alignment, but new approaches address these challenges. |
| Approach: | They propose a framework for vision-aided unsupervised constituency parsing . they leverage multimodal large language models pre-trained on diverse image-text or video-text data . |
| Outcome: | The proposed framework achieves state-of-the-art performance on image-text and video-text datasets, improving robustness and accuracy. |
Addressing Entity Translation Problem via Translation Difficulty and Context Diversity (2024.findings-acl)
Copied to clipboard
| Challenge: | Neural machine translation systems often produce inadequate translations for named entities. |
| Approach: | They propose a data augmentation strategy to enhance the accuracy of named entity translation by retraining the target named entity pair. |
| Outcome: | The proposed method improves translation accuracy across test sets and terminology tests. |
Interactive Text-to-SQL Generation via Editable Step-by-Step Explanations (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to generate SQL from natural language are still making many mistakes . a new interaction mechanism allows users to edit a step-by-step explanation of a query to fix errors. |
| Approach: | They propose a mechanism that allows users to edit a step-by-step explanation of a query to fix errors. |
| Outcome: | The proposed approach can achieve better performance than multiple SOTA approaches on multiple datasets and 24 participants. |
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. |
R3-NL2GQL: A Model Coordination and Knowledge Graph Alignment Approach for NL2GQL (2024.findings-emnlp)
Copied to clipboard
Yuhang Zhou, Yu He, Siyu Tian, Yuchen Ni, Zhangyue Yin, Xiang Liu, Chuanjun Ji, Sen Liu, Xipeng Qiu, Guangnan Ye, Hongfeng Chai
| Challenge: | Adapting existing approaches for converting natural language to SQL encounters hurdles due to distinct nature of GQL compared to SQL. |
| Approach: | They propose a method that integrates both small and large Foundation Models for ranking, rewriting, and refining tasks. |
| Outcome: | The proposed approach integrates both small and large Foundation Models for ranking, rewriting, and refining tasks while capitalizing on the superior generalization and query generation prowess of larger models for the final transformation of natural language queries into GQL formats. |
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. |
Bridging Kernel Drivers and Virtual Device Models with LLM-Powered Automation (2026.acl-demo)
Copied to clipboard
| Challenge: | Linux kernel device drivers are tightly coupled with hardware, making them difficult to execute and test without physical devices. |
| Approach: | They present a tool that generates QEMU-based virtual devices directly from Linux driver source code. |
| Outcome: | The proposed tool generates QEMU-based virtual devices directly from Linux driver source code. |
Adapters Selector: Cross-domains and Multi-tasks LoRA Modules Integration Usage Method (2025.coling-main)
Copied to clipboard
| Challenge: | Parameter-Efficient fine-tuning (PEFT) adapts large language models to specific domains by updating only a small portion of the parameters. |
| Approach: | They propose a framework for better integrating usage of multiple adapters by training a middleman adapter to select the appropriate adapter for inference. |
| Outcome: | The proposed framework can perform cross-domain multi-tasks effectively through the utilization of a compact model in combination with multiple LoRA modules. |
On-Policy Self-Distillation for Efficient Diffusion Language Models with Early-Stage Calibration (2026.findings-acl)
Copied to clipboard
Huaisheng Zhu, MingYu Liu, Junze Liu, Zhen Ge, Tian Wang, Jiri Gesi, Dakuo Wang, Weiqi Zhang, Houyu Zhang, Yufan Guo, Xian Li, Bing Yin, Sujay Sanghavi
| Challenge: | Recent studies have demonstrated that masked diffusion models (MDMs) can surpass autoregressive models (ARMs) in various tasks. |
| Approach: | They propose a method to calibrate early token predictions without demonstration data by distilling an unnormalized target distribution into the original model. |
| Outcome: | Experiments on math, planning, and RLHF tasks show that COPSD improves both effectiveness and efficiency, and further enhances performance when combined with supervised fine-tuning. |
Salespeople vs SalesBot: Exploring the Role of Educational Value in Conversational Recommender Systems (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing conversational recommender systems focus on a single-shot approach to understand user preferences and provide recommendations. |
| Approach: | They propose a problem space for conversational agents that aim to provide both product recommendations and educational value through mixed-type mixed-initiative dialog. |
| Outcome: | The proposed framework can simulate salesbot and shopperbot agents and provide both product recommendations and educational value through mixed-type mixed-initiative dialog. |
FaGANet: An Evidence-Based Fact-Checking Model with Integrated Encoder Leveraging Contextual Information (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing evidence-based fact-checking efforts are time-consuming and challenging . however, relying on surface patterns of claims makes it difficult to identify subtle connections between claims and evidence. |
| Approach: | They propose a model that leverages sentence-level attention and graph attention network to enhance accuracy and fusing claims and evidence information for accurate identification of even well-disguised data. |
| Outcome: | The proposed model improves accuracy and state-of-the-art in the evidence-based fact-checking task. |
Cache-of-Thought: Master-Apprentice Framework for Cost-Effective Vision Language Model Reasoning (2025.emnlp-main)
Copied to clipboard
Mingyuan Wu, Jize Jiang, Haozhen Zheng, Meitang Li, Zhaoheng Li, Beitong Tian, Bo Chen, Yongjoo Park, Minjia Zhang, ChengXiang Zhai, Klara Nahrstedt
| Challenge: | Recent Vision Language Models (VLMs) have shown tremendous promise in a wide range of realworld applications, but their size has made at-scale deployment and operation challenging due to high consumption of cloud computing resource, high latency, and expensive API calls. |
| Approach: | They propose a master–apprentice framework for collaborative inference between large and small vision language models. |
| Outcome: | The proposed framework improves reasoning performance on widely-recognized and challenging general reasoning benchmarks and specifically boosts reasoning of apprentice VLMs by 36.6%. |
EvoMemKG: An Evolvable Memory Agent for Multi-hop Knowledge Graph Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for integrating knowledge graphs with large language models lack continuous learning capabilities. |
| Approach: | They propose an agent framework with a dynamic, evolvable memory mechanism specifically designed for KG reasoning. |
| Outcome: | EvoMemKG achieves state-of-the-art performance without training or tools . it achieves improvements of up to 20% over baseline on multi-hop queries . |
360∘REA: Towards A Reusable Experience Accumulation with 360∘ Assessment for Multi-Agent System (2024.findings-acl)
Copied to clipboard
| Challenge: | Recent studies focus on optimizing the agent team or employing self-reflection to iteratively solve complex tasks. |
| Approach: | They propose a hierarchical multi-agent framework that uses 360 assessment to accumulate experience through fine-grained assessment. |
| Outcome: | The proposed framework is based on corporate organizational practices and employs a dual-level experience pool for agents to accumulate experience through fine-grained assessment. |
ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding (2022.findings-emnlp)
Copied to clipboard
Qiming Peng, Yinxu Pan, Wenjin Wang, Bin Luo, Zhenyu Zhang, Zhengjie Huang, Yuhui Cao, Weichong Yin, Yongfeng Chen, Yin Zhang, Shikun Feng, Yu Sun, Hao Tian, Hua Wu, Haifeng Wang
| Challenge: | Existing methods for visually rich document understanding lack layout-centered knowledge . experimental results show that ERNIE-Layout improves layout awareness . |
| Approach: | They propose a document pre-training solution with layout knowledge enhancement in the whole workflow to learn better representations that combine the features from text, layout, and image. |
| Outcome: | The proposed model outperforms existing models on key downstream tasks. |
Dependency-driven Relation Extraction with Attentive Graph Convolutional Networks (2021.acl-long)
Copied to clipboard
| Challenge: | Existing studies suffer from noise in dependency trees, which can cause confusions in relation extraction. |
| Approach: | They propose a dependency-driven approach for relation extraction with attentive graph convolutional networks . they apply an attention mechanism upon graph convolutional networks to different word dependencies . |
| Outcome: | The proposed approach outperforms previous studies on two English datasets and achieves state-of-the-art performance. |
Accelerating Adaptive Retrieval Augmented Generation via Instruction-Driven Representation Reduction of Retrieval Overlaps (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to augmented generation ignore the overlap in retrieval results . overlapping content is redundantly represented, affecting the overall efficiency. |
| Approach: | They propose a model-agnostic approach to re-augmented generation that speeds up prefilling and decoding . they propose an instruction-driven module to guide the model to more suitable ways for LLMs . |
| Outcome: | The proposed approach achieves 2.79 and 2.33 times significant acceleration on average for prefilling and decoding respectively while maintaining equal generation quality. |
Query Enhanced Knowledge-Intensive Conversation via Unsupervised Joint Modeling (2023.acl-long)
Copied to clipboard
| Challenge: | Existing methods to retrieve knowledge-intensive conversations are based on external resources such as Wikipedia databases or search engine results. |
| Approach: | They propose an unsupervised query enhanced approach for knowledge-intensive conversations . they conduct experiments on three knowledge- intensive conversation datasets . |
| Outcome: | The proposed approach performs better than all unsupervised methods across three datasets and achieves competitive performance compared to supervised methods. |
LAiW: A Chinese Legal Large Language Models Benchmark (2025.coling-main)
Copied to clipboard
Yongfu Dai, Duanyu Feng, Jimin Huang, Haochen Jia, Qianqian Xie, Yifang Zhang, Weiguang Han, Wei Tian, Hao Wang
| Challenge: | Xie et al., 2023) show that large language models (LLMs) can generate legal text, but lack the legal syllogism . legal experts are cautious about their practical application due to the opaque nature of the LLMs. |
| Approach: | They propose a Chinese legal LLM benchmark structured around the legal syllogism . they evaluate LLMs across three levels of capability, each reflecting a more complex stage of legal . |
| Outcome: | The proposed benchmark identifies that LLMs lack the legal syllogism, which hinders trust and understanding from legal experts. |
HoLLMwood: Unleashing the Creativity of Large Language Models in Screenwriting via Role Playing (2024.findings-emnlp)
Copied to clipboard
Jing Chen, Xinyu Zhu, Cheng Yang, Chufan Shi, Yadong Xi, Yuxiang Zhang, Junjie Wang, Jiashu Pu, Tian Feng, Yujiu Yang, Rongsheng Zhang
| Challenge: | Generative AI has demonstrated unprecedented creativity in the field of computer vision, yet such phenomena have not been observed in the realm of literary creation. |
| Approach: | They propose a framework for unleashing the creativity of large language models (LLMs) they assign LLMs to different roles involved in real-world scenario, they write . |
| Outcome: | The proposed framework outperforms baselines in terms of coherence, relevance, interestingness and overall quality on automatically generated screenplays. |
Less Languages, Less Tokens: An Efficient Unified Logic Cross-lingual Chain-of-Thought Reasoning Framework (2026.acl-long)
Copied to clipboard
Chenyuan Zhang, Qiguang Chen, Xie Chen, Zhuotao Tian, Bowen Xing, Meishan Zhang, Libo Qin, Baotian Hu, Min Zhang
| Challenge: | Existing methods for cross-lingual chain-of-thought (XCoT) with self-consistency are costly due to extensive sampling of full trajectories across languages. |
| Approach: | They propose a cross-lingual chain-of-thought framework that minimizes redundancy in token usage and latency. |
| Outcome: | Experiments on polymath show that UL-XCoT reduces decoding token costs and latency by 50% . UL XCot also aggregates remaining high-quality reasoning paths via voting . |
Towards Unified Representations of Knowledge Graph and Expert Rules for Machine Learning and Reasoning (2022.aacl-main)
Copied to clipboard
| Challenge: | Empirical study shows superiority of proposed method over time-tested knowledge-driven and data-driven methods. |
| Approach: | They propose a cognitive knowledge graph that unifies expert rules and relational facts as the substrate of machine learning and reasoning models. |
| Outcome: | Empirical results show the proposed method superior to time-tested methods . the proposed model can perform both learning and reasoning with labeled data . |
CompKBQA: Component-wise Task Decomposition for Knowledge Base Question Answering (2025.emnlp-main)
Copied to clipboard
Yuhang Tian, Dandan Song, Zhijing Wu, Pan Yang, Changzhi Zhou, Jun Yang, Hao Wang, Huipeng Ma, Chenhao Li, Luan Zhang
| Challenge: | Existing knowledge base question answering methods struggle with complex queries. |
| Approach: | They propose a framework that optimizes the process of fine-tuning a LLM for generating logical forms by enabling it to learn relevant sub-tasks like skeleton generation, topic entity generation, and relevant relations generation. |
| Outcome: | The proposed framework achieves state-of-the-art on two benchmark KBQA datasets, WebQSP and CWQ. |
Joint Chinese Word Segmentation and Part-of-speech Tagging via Two-way Attentions of Auto-analyzed Knowledge (2020.acl-main)
Copied to clipboard
| Challenge: | Chinese word segmentation and part-of-speech tagging are important fundamental tasks in natural language processing. |
| Approach: | They propose a neural model for Chinese word segmentation and part-of-speech tagging . they incorporate context features and syntactic knowledge for each input character . |
| Outcome: | The proposed model can learn and benefit from existing tools, but its quality may be poor. |
Misleading Relation Classifiers by Substituting Words in Texts (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to generate adversarial examples for relation classification are vulnerable to adversarials. |
| Approach: | They propose a method that uses most important parts of speech to substitute words with synonyms or hyponyms to generate adversarial texts of high quality. |
| Outcome: | The proposed method can generate adversarial texts of high quality and most relationships can be correctly identified in the process of human evaluation. |
SecureVibeBench: Benchmarking Secure Vibe Coding of AI Agents via Reconstructing Vulnerability-Introducing Scenarios (2026.acl-long)
Copied to clipboard
Junkai Chen, Huihui Huang, Yunbo Lyu, Junwen An, Jieke Shi, Chengran Yang, Ting Zhang, Haoye Tian, Yikun Li, Zhenhao Li, Xin Zhou, Xing Hu, David Lo
| Challenge: | Existing benchmarks fail to capture scenarios in which vulnerabilities are introduced by humans . we evaluate 5 popular code agents supported by 5 LLMs on SecureVibeBench . |
| Approach: | They propose a benchmarking tool that compares 105 C/C++ secure coding tasks . they use real-world open-source vulnerabilities and a comprehensive evaluation tool . |
| Outcome: | The proposed benchmarks show that code agents struggle to produce correct and secure code . the best performing agent produces merely 23.8% correct and secured solutions . |
Knowledge Injection Exists in MoE? Exploring Expert-Aware Contrast Decoding in MoE for Mitigating LLMs’ Hallucinations (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods to mitigate hallucinations include prompt engineering and model optimization, but lack domain generalization and potential errors in fine-tuning data may exacerbate the hallucism. |
| Approach: | They propose an expert-aware adaptive contrast decoding that uses expert differences in MoE’s higher layers to mitigate hallucinations on QA tasks. |
| Outcome: | The proposed method outperforms baseline models on four datasets Large language models (LLMs) show strong performance but suffer from hallucinations, limiting their application. |
CMA-R: Causal Mediation Analysis for Explaining Rumour Detection (2024.findings-eacl)
Copied to clipboard
| Challenge: | Existing studies on explainable fake news or rumour detection by and large use attention weights as explanation, but the use of attention weighted explanations is problematic. |
| Approach: | They propose a causal mediation analysis approach to explain the decision-making process of neural models for rumour detection on Twitter by identifying salient tweets that explain model predictions and highlighting causally impactful words in the tweets. |
| Outcome: | The proposed approach shows strong agreement with human judgements for critical tweets determining the truthfulness of stories. |
Is Parameter Collision Hindering Continual Learning in LLMs? (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods to learn multiple tasks in parallel often lead to catastrophic forgetting, resulting in overwriting knowledge. |
| Approach: | They propose a non-collision low-rank Adaptation approach that leverages low collision rates to enhance continual learning (CL) in large language models. |
| Outcome: | The proposed approach achieves better task orthogonality and higher task orthognality than existing SOTA methods. |
SEARA: An Automated Approach for Obtaining Optimal Retrievers (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Existing evaluation methods suffer from prohibitive costs or disconnection from domain-specific scenarios. |
| Approach: | They propose a method which uses subset sampling techniques to obtain robust automated retrieval evaluation at low cost. |
| Outcome: | The proposed method achieves robust retrieval evaluation by minimal retrieval facts extraction and comprehensive retrieval metrics. |
An Effective Deployment of Diffusion LM for Data Augmentation in Low-Resource Sentiment Classification (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing models for textual data augmentation (DA) are highly data-hungry and struggle to perform satisfactorily under noisy conditions. |
| Approach: | They propose to leverage a diffusion language model to capture in-domain knowledge and generate pseudo samples by reconstructing strong label-related tokens. |
| Outcome: | The proposed method captures in-domain knowledge and generates pseudo samples by reconstructing strong label-related tokens. |
Who Wrote This Line? Evaluating the Detection of LLM-Generated Classical Chinese Poetry (2026.acl-long)
Copied to clipboard
Jiang Li, Tian Lan, Shanshan Wang, Dongxing Zhang, Dianqing Lin, Guanglai Gao, Derek F. Wong, Xiangdong Su
| Challenge: | a recent study shows that large language models can generate text, but they can also fabricate large amounts of false or misleading content. |
| Approach: | They propose a benchmark to detect LLM-generated classical Chinese poetry . they compare 12 different AI detectors to find out whether a poem is authored by AI . |
| Outcome: | The proposed benchmark compared 12 AI detectors with a dataset of 30,664 Chinese poems . the results highlight the limitations of current Chinese text detectors . |
Controllable Memory Usage: Balancing Anchoring and Innovation in Long-Term Human–Agent Interaction (2026.acl-long)
Copied to clipboard
Zisu Huang, Muzhao Tian, Xiaohua Wang, Jingwen Xu, Zhengkang Guo, Qi Qian, Kaitao Song, Jiakang Yuan, Changze Lv, Xiaoqing Zheng
| Challenge: | Existing systems that use memory as an "all-or-nothing" approach to memory usage are often static and rely on experience-following tendencies. |
| Approach: | They propose a framework that allows users to dynamically regulate memory reliance by adding context into the model's prompt. |
| Outcome: | The proposed model outperforms prompting and memory masking strategies in multiple scenarios. |
JumpCoder: Go Beyond Autoregressive Coder via Online Modification (2024.acl-long)
Copied to clipboard
| Challenge: | Existing code large language models lack reversibility and autoregressive sequential generation is incapable of correcting previous missing statements as humans do. |
| Approach: | They propose a model-agnostic framework that enables human-like online modification and non-sequential generation to augment code large language models. |
| Outcome: | The proposed framework enables human-like modification and non-sequential generation to augment code large language models. |
TANet: Thread-Aware Pretraining for Abstractive Conversational Summarization (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing pre-trained language models are difficult to apply to abstractive conversational summarization tasks. |
| Approach: | They propose a thread-aware Transformer-based network that incorporates contextual dependency into the conversational summarization model. |
| Outcome: | The proposed model can be applied to real conversations using a large-scale pretraining dataset. |
UOUO: Uncontextualized Uncommon Objects for Measuring Knowledge Horizons of Vision Language Models (2024.emnlp-main)
Copied to clipboard
Xinyu Pi, Mingyuan Wu, Jize Jiang, Haozhen Zheng, Beitong Tian, ChengXiang Zhai, Klara Nahrstedt, Zhiting Hu
| Challenge: | Vision-Language Models (VLMs) perform on par with larger models in general domain visual grounding and question-answering benchmarks. |
| Approach: | They propose a "Uncontextualized Uncommon Objects" benchmark to evaluate their performance on common datasets. |
| Outcome: | The proposed benchmark focuses on systematically testing VLMs with both large and small parameter counts on rare and specialized objects. |