Papers by Yan Chen
Hierarchy-aware Label Semantics Matching Network for Hierarchical Text Classification (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods ignore the semantic relationship between text and labels, so they cannot make full use of hierarchical information. |
| Approach: | They propose a hierarchy-aware label semantics matching network to model the semantic relationship between text and labels in a semantic matching problem. |
| Outcome: | The proposed model captures the text-label semantics matching relationship among coarse-grained labels and fine-grain labels in a hierarchy-aware manner. |
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. |
Towards Explainable Computerized Adaptive Testing with Large Language Model (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods focus on minimizing the number of questions required to assess ability, lacking clear and reliable explanations for the question selection process. |
| Approach: | They propose to use large language models to enhance computer adaptive testing (CAT) by providing human-like interpretability and explanations. |
| Outcome: | The proposed agent-based CAT performs comparably or superior to traditional CAT methods in accuracy and significantly improves student trust and satisfaction. |
Incentivizing In-depth Reasoning over Long Contexts with Process Advantage Shaping (2026.findings-acl)
Copied to clipboard
| Challenge: | Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective in enhancing LLMs’ short-context reasoning but falters in long-contemporal scenarios requiring precise grounding and multi-hop reasoning. |
| Approach: | They propose a framework that constructs high-difficulty, multi-hop long-context QA pairs with inherent reasoning chains to overcome this bottleneck. |
| Outcome: | The proposed framework outperforms RLVR baselines and matches frontier LLMs while using far fewer parameters. |
FLIQA-AD: a Fusion Model with Large Language Model for Better Diagnose and MMSE Prediction of Alzheimer’s Disease (2025.naacl-short)
Copied to clipboard
| Challenge: | Existing classification and regression models that only extract finer-grained information from magnetic resonance imaging (MRI) may not be effective for Alzheimer's disease (AD). |
| Approach: | They propose to use a 3D Adapter in a Vision Transformer to extract the patient's EHR information and questions related to the disease as text prompts. |
| Outcome: | The proposed model can discriminate and predict the corresponding MMSE score based on the extracted brain structural information and textual content . |
Word Graph Guided Summarization for Radiology Findings (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing studies focus on introducing salient word information to general text summarization framework to guide selection of key content in radiology findings. |
| Approach: | They propose a method for automatic impression generation using word graphs and a Word Graph guided Summarization model to capture critical words and their relations. |
| Outcome: | The proposed method is validated on two datasets, OPENI and MIMIC-CXR. |
Capability Salience Vector: Fine-grained Alignment of Loss and Capabilities for Downstream Task Scaling Law (2025.acl-long)
Copied to clipboard
Qiming Ge, Shuhao Xing, Songyang Gao, Yunhua Zhou, Yicheng Zou, Songyang Zhang, Zhi Chen, Hang Yan, Qi Zhang, Qipeng Guo, Kai Chen
| Challenge: | Large language models have demonstrated impressive performance across a wide range of tasks, but this achievement comes with the trade-off of significant computational demands. |
| Approach: | They propose a scaling law that decomposes the overall validation loss and assigns different importance weights to tokens to assess a specific meta-capability. |
| Outcome: | The proposed model can predict the loss trending of models across different levels of computation without a gap between validation loss and model's downstream capabilities. |
Safe: Enhancing Mathematical Reasoning in Large Language Models via Retrospective Step-aware Formal Verification (2025.acl-long)
Copied to clipboard
Chengwu Liu, Ye Yuan, Yichun Yin, Yan Xu, Xin Xu, Zaoyu Chen, Yasheng Wang, Lifeng Shang, Qun Liu, Ming Zhang
| Challenge: | Chain-of-Thought prompting is a de facto method to elicit reasoning capabilities from large language models (LLMs). |
| Approach: | They propose a step-aware formal verification framework Safe to address hallucinations in CoT prompting . they propose 'formal step' as a benchmark for step correctness theorem proving with 30,809 formal statements. |
| Outcome: | The proposed framework shows significant performance improvement while offering interpretable and verifiable evidence. |
Dolphin: Moving Towards Closed-loop Auto-research through Thinking, Practice, and Feedback (2025.acl-long)
Copied to clipboard
Jiakang Yuan, Xiangchao Yan, Bo Zhang, Tao Chen, Botian Shi, Wanli Ouyang, Yu Qiao, Lei Bai, Bowen Zhou
| Challenge: | Recent studies show that AI-assisted research methods can improve research efficiency . a closed-loop framework is used to enhance the automation level of scientific research . |
| Approach: | They propose a closed-loop LLM-driven framework to enhance the automation level of scientific research. |
| Outcome: | The proposed framework improves the efficiency of scientific research by improving data analysis, accelerating computation, and fostering novel idea generation. |
Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language Models (2024.acl-long)
Copied to clipboard
Changyu Chen, Xiting Wang, Ting-En Lin, Ang Lv, Yuchuan Wu, Xin Gao, Ji-Rong Wen, Rui Yan, Yongbin Li
| Challenge: | Despite the advances in large language models, they still face difficulties with multi-step reasoning tasks. |
| Approach: | They propose a method that randomly masks certain tokens within the chain of thought to improve model accuracy by 5% over standard supervised fine-tuning. |
| Outcome: | The proposed method improves accuracy and accuracy by 5% over standard fine-tuning with a few codes modified. |
A Deep Learning-Based System for PharmaCoNER (D19-57)
Copied to clipboard
Ying Xiong, Yedan Shen, Yuanhang Huang, Shuai Chen, Buzhou Tang, Xiaolong Wang, Qingcai Chen, Jun Yan, Yi Zhou
| Challenge: | Efficient access to mentions of clinical entities is very important for using clinical text. |
| Approach: | They developed a pipeline system based on deep learning methods for this shared task . it achieves a micro-average F1-score of 0.9105 on track 1 and a mini-average LSTM score of 0.8391 on track 2 . |
| Outcome: | The proposed system achieves a micro-average F1-score of 0.9105 on track 1 and a mini-average score of 0.8391 on track 2. |
Model Composition for Multimodal Large Language Models (2024.acl-long)
Copied to clipboard
Chi Chen, Yiyang Du, Zheng Fang, Ziyue Wang, Fuwen Luo, Peng Li, Ming Yan, Ji Zhang, Fei Huang, Maosong Sun, Yang Liu
| Challenge: | Existing methods for creating versatile MLLMs rely on joint training with paired instruction data, which is resource-intensive and challenging to extend to new modalities. |
| Approach: | They propose a new paradigm for multimodal large language models by reusing modality encoders and merging LLM parameters. |
| Outcome: | The proposed model retains the modal understanding capabilities of each original model. |
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. |
Test-time Backdoor Mitigation for Black-Box Large Language Models with Defensive Demonstrations (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing studies on backdoor defense have focused on training phase, overlooking critical aspect of testing time defense. |
| Approach: | They propose to use demonstrations as a defense mechanism against backdoor attacks in black-box LLMs. |
| Outcome: | The proposed method outperforms existing defense baselines across most evaluation scenarios. |
Decouple knowledge from paramters for plug-and-play language modeling (2023.findings-acl)
Copied to clipboard
| Challenge: | Pre-trained language models (PLMs) have made impressive results in a wide range of NLP tasks. |
| Approach: | They propose a pre-training model with editable and scalable key-value memory and leverage knowledge in an explainable manner by knowledge retrieval in the pasted macro ‘MEMORY’. |
| Outcome: | The proposed model decouples the knowledge storage from model parameters with an editable and scalable key-value memory and leverages knowledge in an explainable manner by knowledge retrieval in the pasted macro ‘MEMORY’. |
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. |
CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and Generation (2024.acl-long)
Copied to clipboard
Weixiang Yan, Haitian Liu, Yunkun Wang, Yunzhe Li, Qian Chen, Wen Wang, Tingyu Lin, Weishan Zhao, Li Zhu, Hari Sundaram, Shuiguang Deng
| Challenge: | Existing benchmarks for evaluating the code understanding and generation capacities of Large Language Models are insufficient . existing benchmarks focus on a narrow range of popular programming languages and specific tasks . |
| Approach: | They propose an execution-based, multilingual, multitask evaluation benchmark for LLMs . they evaluate coding performance from three dimensions: length, difficulty, efficiency . |
| Outcome: | The proposed benchmark covers 43 programming languages and eight coding tasks. |
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. |
DynaEval: Unifying Turn and Dialogue Level Evaluation (2021.acl-long)
Copied to clipboard
Chen Zhang, Yiming Chen, Luis Fernando D’Haro, Yan Zhang, Thomas Friedrichs, Grandee Lee, Haizhou Li
| Challenge: | Existing evaluation metrics focus on the turn-level quality of a dialogue . a unified framework that holistically considers the quality of the entire dialogue is needed . |
| Approach: | They propose a unified automatic evaluation framework which holistically considers the quality of the entire dialogue. |
| Outcome: | The proposed framework outperforms the state-of-the-art dialogue coherence model and correlates strongly with human judgements across multiple evaluation aspects at both turn and dialogue level. |
TrInk: Ink Generation with Transformer Network (2025.emnlp-main)
Copied to clipboard
Zezhong Jin, Shubhang Desai, Xu Chen, Biyi Fang, Zhuoyi Huang, Zhe Li, Chong-Xin Gan, Xiao Tu, Man-Wai Mak, Yan Lu, Shujie Liu
| Challenge: | Existing methods for handwriting generation capture global dependencies and can generate high-quality handwritten samples. |
| Approach: | They propose a Transformer-based model for ink generation, TrInk, which captures global dependencies. |
| Outcome: | The proposed model reduces character error rate and word error rate by 35.56% on the IAM-OnDB dataset compared to previous models. |
DynaThink: Fast or Slow? A Dynamic Decision-Making Framework for Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) have emerged as prominent foundation models for diverse applications due to their outstanding ability to understand and generate humanlike text. |
| Approach: | They propose a dynamic decision-making framework that categorizes tasks into two distinct pathways: 'Fast' and 'Slow' they propose 'self-consistency' strategy to replace the straight-forward decoding method used in COT prompting . |
| Outcome: | The proposed method achieves more than 3% increase in accuracy with lower cost on five popular reasoning benchmarks. |
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. |
SAC: Neural Speech Codec with Semantic-Acoustic Dual-Stream Quantization (2026.acl-long)
Copied to clipboard
Wenxi Chen, Ruiqi Yan, Yushen Chen, Zhikang Niu, Ziyang Ma, Xiquan Li, Yuzhe Liang, null Wenhanlin, Shunshun Yin, Ming Tao, Xinsheng Wang, Xie Chen
| Challenge: | Existing speech codecs struggle to balance high-quality reconstruction with semantically rich representations, limiting their effectiveness in both generative and understanding tasks. |
| Approach: | They propose a neural speech codec with semantic-acoustic dual-stream quantization that disentangles semantic and acousian modeling into two dedicated streams. |
| Outcome: | The proposed codec outperforms state-of-the-art speech tokenizers in auto-propagating text-to-speech models. |
Cool-Fusion: Fuse Large Language Models without Training (2025.acl-long)
Copied to clipboard
| Challenge: | Cool-Fusion is a simple yet effective approach to combine two or more heterogeneous large language models . |
| Approach: | They propose a method that fuses the knowledge of two or more heterogeneous large language models to leverage complementary strengths. |
| Outcome: | The proposed method increases accuracy from three strong source LLMs on GSM8K by 17.4%. |
Generate, Discriminate and Contrast: A Semi-Supervised Sentence Representation Learning Framework (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing supervised sentence embedding techniques rely on expensive human-annotated sentence pairs as the supervised signals. |
| Approach: | They propose a semi-supervised sentence embedding framework that leverages large-scale unlabeled data. |
| Outcome: | The proposed framework surpasses state-of-the-art methods on four domain adaptation tasks. |
From Synthesis to Clinical Assistance: A Strategy-Aware Agent Framework for Autism Intervention based on Real Clinical Dataset (2026.acl-long)
Copied to clipboard
| Challenge: | Applied Behavior Analysis (ABA) is the gold standard for clinical intervention, but large language models struggle to adhere to its standardized procedures. |
| Approach: | They propose a strategy-aware framework to unify high-fidelity intervention dialogue synthesis and clinical decision support. |
| Outcome: | Experiments show that ASDAgent achieves nearly 80% strategic consistency with human experts. |
Magnet: Multi-turn Tool-use Data Synthesis and Distillation via Graph Translation (2025.acl-long)
Copied to clipboard
Fan Yin, Zifeng Wang, I-Hung Hsu, Jun Yan, Ke Jiang, Yanfei Chen, Jindong Gu, Long Le, Kai-Wei Chang, Chen-Yu Lee, Hamid Palangi, Tomas Pfister
| Challenge: | Large language models have been shown to be effective in multi-turn interactions . however, their performance may be limited in complex, multi-turned interactions involving users and multiple tools. |
| Approach: | They propose a framework for synthesizing high-quality training trajectories to enhance the function calling capability of large language model agents in multi-turn conversations with humans. |
| Outcome: | The proposed model outperforms the teacher model by 68.01 on BFCL-v3 and 73.30 on ToolQuery. |
DRBO: Mitigating Short Board Effect via Dynamic Reward Balancing in Multi-reward LLM Optimization (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a new framework to optimize large language models (LLMs) for evaluation metrics is needed to balance weaker metrics. |
| Approach: | They propose a Dynamic Reward Balancing Optimization framework to mitigate the "short-board effect" they apply it to single-task and multi-type task scenarios . |
| Outcome: | The proposed framework improves performance and balances performance across multiple metrics. |
A Pre-training Strategy for Zero-Resource Response Selection in Knowledge-Grounded Conversations (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods to train retrieval-based dialogue systems rely on crowd-sourced data . however, it is difficult to collect large-scale dialogues that are grounded on background knowledge . |
| Approach: | They propose to decompose training of knowledge-grounded response selection into three tasks . they propose to combine query-passage matching task with query-dialogue history matching task . |
| Outcome: | Experimental results show that the proposed model can perform comparable to existing methods . the retrieval-based system can leverage background knowledge when conversing with humans . |
The Stepwise Deception: Simulating the Evolution from True News to Fake News with LLM Agents (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies assume fake news is inherently existing rather than exploring its gradual formation. |
| Approach: | They propose a Large Language Model-based simulation approach explicitly focusing on fake news evolution from real news. |
| Outcome: | The proposed framework captures fake news evolution patterns and accurately reproduces known fake news, aligning closely with human evaluations. |
Capturing Relations between Scientific Papers: An Abstractive Model for Related Work Section Generation (2021.acl-long)
Copied to clipboard
| Challenge: | Existing related work generation models are inflexible and extract sentences from multiple papers to form a related work discussion. |
| Approach: | They propose a Relation-aware Related work generator which generates an abstractive related work from the given multiple scientific papers in the same research area. |
| Outcome: | The proposed model improves over existing models and can be used to familiarize researchers with the state of the art in the field. |
SocialBench: Sociality Evaluation of Role-Playing Conversational Agents (2024.findings-acl)
Copied to clipboard
Hongzhan Chen, Hehong Chen, Ming Yan, Wenshen Xu, Gao Xing, Weizhou Shen, Xiaojun Quan, Chenliang Li, Ji Zhang, Fei Huang
| Challenge: | Existing studies on role-playing agents have focused on enhancing their conversational capability, role-specific knowledge and style, but there has been a gap in assessing their social intelligence. |
| Approach: | They propose a benchmark to evaluate the sociality of role-playing agents using LLMs. |
| Outcome: | The proposed benchmark is constructed from various sources and covers a wide range of 500 characters and over 6,000 question prompts and 30,800 multi-turn role-playing utterances. |
Ladder: A Model-Agnostic Framework Boosting LLM-based Machine Translation to the Next Level (2024.emnlp-main)
Copied to clipboard
| Challenge: | General-purpose Large Language Models (LLMs) like GPT-4 have exhibited strong translation abilities. |
| Approach: | They propose to use a model-agnostic model to refine the performance of general-purpose large-language models for machine translation (MT) by utilizing Gemma-2B/7B as the backbone. |
| Outcome: | The proposed model-agnostic and cost-effective tool improves the performance of general-purpose large-language models for machine translation (MT) by integrating it with any general-use LLM. |
Distract Large Language Models for Automatic Jailbreak Attack (2024.emnlp-main)
Copied to clipboard
| Challenge: | Commercial large language models (LLMs) have made great progress in various NLP tasks. |
| Approach: | They propose a black-box jailbreak framework for automated red teaming of Large language models using an iterative optimization algorithm to conceal malicious content and memory reframing. |
| Outcome: | The proposed framework outperforms existing jailbreak defense methods and highlights the need to develop more effective and practical defense strategies. |
Towards the Law of Capacity Gap in Distilling Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Language model (LM) distillation aims at distilling knowledge in a large teacher LM to a small student one. |
| Approach: | They propose to use the law of capacity gap to distill knowledge from a large teacher to a small student model. |
| Outcome: | The proposed model outperforms other language models on a larger scale by using the law of capacity gap inducted from a preliminary study on small-scale (3B) LMs. |
Iterative Document Representation Learning Towards Summarization with Polishing (D18-1)
Copied to clipboard
| Challenge: | Existing summarization methods read through document only once to generate a document representation, resulting in a sub-optimal representation. |
| Approach: | They propose an iterative model for supervised extractive text summarization which polishes the document representation on many passes through the document. |
| Outcome: | The proposed model outperforms state-of-the-art extractive systems on CNN/DailyMail and DUC2002 datasets. |
SPARD: Self-Paced Curriculum for RL Alignment via Integrating Reward Dynamics and Data Utility (2026.acl-long)
Copied to clipboard
Xuyang Zhi, Peilun Zhou, Chengqiang Lu, Hang Lv, Yiwei Liang, Rongyang Zhang, Yan Gao, null Yiwu, Yao Hu, Hongchao Gu, Defu Lian, Hao Wang, Enhong Chen
| Challenge: | Large Language Models (LLMs) are shifting the focus from single verifiable tasks toward complex, open-ended real-world scenarios. |
| Approach: | They propose a framework that automatically adjusts reward weights and data importance to synchronize learning intent with data utility for optimal performance. |
| Outcome: | The proposed framework improves model capabilities across all domains and scales. |
DialoGPS: Dialogue Path Sampling in Continuous Semantic Space for Data Augmentation in Multi-Turn Conversations (2023.acl-long)
Copied to clipboard
| Challenge: | a context leads to various responses, and a response answers multiple contexts. |
| Approach: | They propose a method that augments open-domain dialogue generation from a many-to-many perspective. |
| Outcome: | The proposed method can augment open-domain dialogue generation tasks with automatic and human evaluation. |
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. |
DeepPresenter: Environment-Grounded Reflection for Agentic Presentation Generation (2026.findings-acl)
Copied to clipboard
Hao Zheng, Guozhao Mo, Xinru Yan, Qianhao Yuan, Wenkai Zhang, Xuanang Chen, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun
| Challenge: | Existing presentation agents rely on predefined workflows and fixed templates to generate presentations. |
| Approach: | They propose an agentic framework that adapts to diverse user intents and iterative refinement based on observation. |
| Outcome: | The proposed framework can be used to generate presentations with environmental observations. |
SAGE: Steerable Agentic Data Generation for Deep Search with Execution Feedback (2026.findings-eacl)
Copied to clipboard
Fangyuan Xu, Rujun Han, Yanfei Chen, Zifeng Wang, I-Hung Hsu, Jun Yan, Vishy Tirumalashetty, Eunsol Choi, Tomas Pfister, Chen-Yu Lee
| Challenge: | High-quality, complex question-answer pairs are pivotal for training and evaluating capable deep search agents. |
| Approach: | They propose a pipeline that generates high-quality, difficulty-controlled deep search question-answer pairs for a given corpus and a target difficulty level. |
| Outcome: | The proposed pipeline generates high-quality, difficulty-controlled deep search question-answer pairs for a given corpus and a target difficulty level. |
Beyond Noise: Characterizing Creative Potential in Unverifiable LLM Hallucinations (2026.acl-long)
Copied to clipboard
Yu Yan, Chunhong Zhang, Haiyu Zhao, Ziyang Zeng, Zihao Liu, Yongkang Wu, Jianzhou Diao, YiJie Chen, Shujie Wang, Zheng Hu
| Challenge: | Large Language Models generate outputs that extend beyond established knowledge . prior work does not characterize the unverifiable space as a whole . |
| Approach: | They propose a novelty-verifiability characterization that distinguishes Creative Synthesis from Groundless Fabrication by a conceptual creation task. |
| Outcome: | The proposed model distinguishes Creative Synthesis (Region A) from Groundless Fabrication (Regium B) it shows that Region A is non-negligible and robust, persisting across generation strategies, models, domains, and embedding choices. |
Flaming-hot Initiation with Regular Execution Sampling for Large Language Models (2025.findings-naacl)
Copied to clipboard
Weizhe Chen, Zhicheng Zhang, Guanlin Liu, Renjie Zheng, Wenlei Shi, Chen Dun, Zheng Wu, Xing Jin, Lin Yan
| Challenge: | Large language models (LLMs) have demonstrated remarkable capabilities across various domains since the release of ChatGPT . a key challenge in developing these general capabilities is efficiently sourcing diverse, high-quality data. |
| Approach: | They introduce Flaming-hot Initiation with Regular Execution (FIRE) sampling to efficiently find good responses by promoting diversity. |
| Outcome: | The proposed method enhances inference-time generation quality and benefits training in the alignment stage. |
Incomplete In-context Learning (2026.acl-long)
Copied to clipboard
Wenqiang Wang, Wen Yujia, Yan Xiao, Zhifeng Chen, Yangshijie Zhang, Peng Chen, Mingbo Yang, Xiaochun Cao
| Challenge: | Existing in-context learning assumes the retrieval dataset contains demonstrations for all output label spaces. |
| Approach: | They propose a framework with train-free and train-based variants to address IICL . they propose to integrate a dataset with labeled demonstrations for each output space . |
| Outcome: | The proposed framework outperforms existing methods under incomplete retrieval datasets and even outperformed ICL with complete labels. |
Group-wise Contrastive Learning for Neural Dialogue Generation (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to training dialogue models have low diversity in open-domain contexts . prior art suggests that naive MLE objective is not effective enough . |
| Approach: | They propose to incorporate contrastive learning into dialogue generation by using a pretrained baseline model as a reference. |
| Outcome: | The proposed framework is suited for training a wide range of dialogue generation models with favorable performance over baseline training approaches. |
ImPart: Importance-Aware Delta-Sparsification for Improved Model Compression and Merging in LLMs (2025.acl-long)
Copied to clipboard
| Challenge: | Recent approaches to reduce resource requirements for task-specific large language models have been developed. |
| Approach: | They propose a delta compression approach that optimizes for importance of a model . they use SVD to dynamically adjust the sparsity ratios of different vectors based on their importance . |
| Outcome: | The proposed approach achieves state-of-the-art in retaining task-specific knowledge even at high sparsity ratios. |
An Effective Pronunciation Assessment Approach Leveraging Hierarchical Transformers and Pre-training Strategies (2024.acl-long)
Copied to clipboard
Bi-Cheng Yan, Jiun-Ting Li, Yi-Cheng Wang, Hsin Wei Wang, Tien-Hong Lo, Yung-Chang Hsu, Wei-Cheng Chao, Berlin Chen
| Challenge: | Existing attempts to quantify a second language learner’s pronunciation proficiency in a target language often sideline the hierarchy of linguistic units and relatedness among the pronunciation aspects. |
| Approach: | They propose a hierarchical automatic pronunciation assessment method that models the intrinsic structures of an utterance while considering the relatedness among the pronunciation aspects. |
| Outcome: | The proposed method can be used to quantify a second language learner’s pronunciation proficiency in a target language by providing fine-grained feedback with multiple pronunciation aspect scores at various linguistic levels. |
Quantifying and Mitigating Unimodal Biases in Multimodal Large Language Models: A Causal Perspective (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models have facilitated the development of Multimodal LLMs. |
| Approach: | They propose a causal framework to interpret unimodal biases in visual question answering problems and a framework to integrate information from different modalities and mitigate biase. |
| Outcome: | The proposed framework analyzes visual question answering (VQA) problems to assess their impact on predictions. |
Battle of the Large Language Models: Dolly vs LLaMA vs Vicuna vs Guanaco vs Bard vs ChatGPT - A Text-to-SQL Parsing Comparison (2023.findings-emnlp)
Copied to clipboard
| Challenge: | a number of open-source large language models claim to be performing better than commercial ones . however, these models fall short of the performance achieved by closed-source models like GPT-3.5 . |
| Approach: | They evaluate six popular large language models against each other to evaluate their performance . authors say open-source models are not as effective as those built by commercial models . |
| Outcome: | a new set of models claim to match or surpass the language understanding abilities of commercial models . the results show that the models performed far below the performance of closed-source models compared to open-source ones . |
Text Style Transfer with Contrastive Transfer Pattern Mining (2023.acl-long)
Copied to clipboard
| Challenge: | Existing methods for text style transfer only focus on the transformation between styles, yet they do not take into account that this transformation can be achieved via different hidden transfer patterns. |
| Approach: | They propose a novel approach which automatically mines hidden transfer patterns to improve TST . they use a clustering module to automatically discover hidden transfer pattern from the data . |
| Outcome: | The proposed method can be applied in a plug-and-play manner to enhance other methods to further improve their performance. |
DecoupleSearch: Decouple Planning and Search via Hierarchical Reward Modeling (2025.emnlp-main)
Copied to clipboard
Hao Sun, Zile Qiao, Bo Wang, Guoxin Chen, Yingyan Hou, Yong Jiang, Pengjun Xie, Fei Huang, Yan Zhang
| Challenge: | Retrieval-Augmented Generation (RAG) systems have emerged as a pivotal methodology for enhancing Large Language Models (LLMs). |
| Approach: | They propose a framework that decouples planning and search processes using dual value models, enabling independent optimization of plan reasoning and search grounding. |
| Outcome: | The proposed framework decouples planning and search processes using dual value models, enabling independent optimization of plan reasoning and search grounding. |
A Systematic Survey of Automatic Prompt Optimization Techniques (2025.emnlp-main)
Copied to clipboard
Kiran Ramnath, Kang Zhou, Sheng Guan, Soumya Smruti Mishra, Xuan Qi, Zhengyuan Shen, Shuai Wang, Sangmin Woo, Sullam Jeoung, Yawei Wang, Haozhu Wang, Han Ding, Yuzhe Lu, Zhichao Xu, Yun Zhou, Balasubramaniam Srinivasan, Qiaojing Yan, Yueyan Chen, Haibo Ding, Panpan Xu, Lin Lee Cheong
| Challenge: | Recent advances in prompt engineering have created impediments for end users to adopt . however, prompt engineering remains an impedance due to rapid advances in models, tasks, and associated best practices. |
| Approach: | They propose to define APO as a 5-part unifying framework and categorize all relevant works based on their salient features. |
| Outcome: | The proposed framework aims to improve the performance of large language models on various tasks. |
CELLO: Causal Evaluation of Large Vision-Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in large vision-language models have improved causal reasoning abilities . however, current models struggle with tasks like causal reasoning . |
| Approach: | They propose a fine-grained and unified definition of causality involving interactions between humans and objects. |
| Outcome: | The proposed model surpasses traditional commonsense causality by including explicit causal graphs . it also shows that current LVLMs can benefit from a causally inspired prompting strategy . |
Enhancing Foundation Models in Transaction Understanding with LLM-based Sentence Embeddings (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Existing foundation models for tabular transactional data rely on index-based representations for categorical merchant fields. |
| Approach: | They propose a framework that uses LLM-generated embeddings as semantic initializations for lightweight transaction models. |
| Outcome: | The proposed framework improves performance on large transaction datasets. |
Federated LoRA Fine-Tuning with Pipelined Error-Mitigated Aggregation and Matrix-Wise Freezing (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for fine-tuning large language models often suffer from biased model aggregation and are hindered by significant communication and computation burden. |
| Approach: | They propose a Federated low-rank adaptation system for large language models that leverages pipelined error-mitigated model aggregation and adaptive matrix-wise parameter freezing to mitigate aggregations. |
| Outcome: | The proposed system improves time-to-target by 2.17-8.48 on real-world datasets. |
Browse and Concentrate: Comprehending Multimodal Content via Prior-LLM Context Fusion (2024.acl-long)
Copied to clipboard
Ziyue Wang, Chi Chen, Yiqi Zhu, Fuwen Luo, Peng Li, Ming Yan, Ji Zhang, Fei Huang, Maosong Sun, Yang Liu
| Challenge: | Multimodal Large Language Models (MLLMs) lack understanding of multi-image and interleaved inputs due to the visual features encoded by frozen encoders before being fed into the LLM backbone. |
| Approach: | They propose a two phase paradigm to enable in-depth multimodal context fusion prior to feeding the features into LLMs. |
| Outcome: | The proposed paradigm boosts the performance on 7 multi-image scenarios, contributing to increments on average accuracy by 2.13% and 7.60% against strong MLLMs baselines with 3B and 11B LLMs, respectively. |
Selection and Generation: Learning towards Multi-Product Advertisement Post Generation (2020.emnlp-main)
Copied to clipboard
| Challenge: | E-commerce websites have billions of products, so it is impossible to write all copywriting manually. |
| Approach: | They propose a model to generate an AD post using a select network and a MGenNet network to generate a post including selected products. |
| Outcome: | The proposed model achieves impressive performance on a large-scale real-world AD post dataset. |
Retrieving, Rethinking and Revising: The Chain-of-Verification Can Improve Retrieval Augmented Generation (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Recent Retrieval Augmented Generation (RAG) aims to enhance Large Language Models . however, such approach can generate inconsistent answer with external references . |
| Approach: | They propose to integrate the verification module into the RAG to improve external retrieval correctness and internal generation consistency. |
| Outcome: | The proposed model can significantly surpass the state-of-the-art baselines using different LLM backbones. |
PersLLM: A Personified Training Approach for Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models exhibit human-like intelligence, enabling them to simulate human behavior and support various applications that require both humanized communication and extensive knowledge reserves. |
| Approach: | They propose a framework for better data construction and model tuning to unlock the potential of LLM personification by using Chain-of-Thought prompting and anti-induction. |
| Outcome: | The proposed framework improves data construction and model tuning for insufficient data usage and rigid behavior patterns. |
Scientific Paper Extractive Summarization Enhanced by Citation Graphs (2022.emnlp-main)
Copied to clipboard
| Challenge: | citation graphs can be used to extract scientific papers under different conditions. |
| Approach: | They propose a multi-granularity unsupervised summarization model that fine tunes a pre-trained encoder model on the citation graph by link prediction tasks. |
| Outcome: | The proposed model outperforms baseline models on a public benchmark dataset. |
PALM: Pre-training an Autoencoding&Autoregressive Language Model for Context-conditioned Generation (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing techniques for natural language understanding and generation use autoencoding and/or autoregressive objectives to train models. |
| Approach: | They propose a self-supervised pre-training scheme that pre-trains an autoencoding and autoregressive language model on a large unlabeled corpus for generating new text conditioned on context. |
| Outcome: | The proposed scheme achieves state-of-the-art results on a variety of language generation benchmarks covering generative question answering, abstractive summarization and conversational response generation. |
Learning to Use Tools via Cooperative and Interactive Agents (2024.findings-emnlp)
Copied to clipboard
Zhengliang Shi, Shen Gao, Xiuyi Chen, Yue Feng, Lingyong Yan, Haibo Shi, Dawei Yin, Pengjie Ren, Suzan Verberne, Zhaochun Ren
| Challenge: | Existing methods for large language models (LLMs) use one agent to iterate and execute tools, but they suffer from performance degradation when addressing practical tasks. |
| Approach: | They propose a tool learning framework that coordinates three specialized agents for tool selection, tool execution, and action calibration separately. |
| Outcome: | The proposed framework outperforms baseline models on three datasets with 14% higher success rate. |
“What Do You Mean by That?” A Parser-Independent Interactive Approach for Enhancing Text-to-SQL (2020.emnlp-main)
Copied to clipboard
| Challenge: | In Natural Language Interfaces to Databases systems, text-to-SQL parsers allow users to query databases by using natural language questions. |
| Approach: | They propose a parser-independent interactive approach that interacts with users using multi-choice questions and can easily work with arbitrary parsers. |
| Outcome: | The proposed approach improves performance with limited interaction turns by using simulation and human evaluation on two cross-domain datasets with five state-of-the-art parsers. |
FedCoT: Federated Chain-of-Thought Distillation for Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have emerged as a transformative force in artificial intelligence, demonstrating exceptional proficiency across various tasks. |
| Approach: | They propose a federated framework for the Chain-of-Thought distillation of knowledge from LLMs to SLMs, while adhering to privacy requirements. |
| Outcome: | The proposed framework ensures secure knowledge transfer from an LLM on a high-powered server to an SLM on resource-constrained client while adhering to privacy requirements. |
RLKGF: Reinforcement Learning from Knowledge Graph Feedback Without Human Annotations (2025.findings-acl)
Copied to clipboard
| Challenge: | Lack of human preference labels remains a significant bottleneck when applying RLHF to a downstream domain. |
| Approach: | They propose a method that leverages human priors encoded in Knowledge Graphs (KGs) to derive RL rewards in the absence of manual annotations. |
| Outcome: | Experiments on three public and one private medical dialogue datasets show that the proposed method outperforms the competitive RLAIF in improving LLM diagnostic accuracy. |
Reasoning Like Program Executors (2022.emnlp-main)
Copied to clipboard
Xinyu Pi, Qian Liu, Bei Chen, Morteza Ziyadi, Zeqi Lin, Qiang Fu, Yan Gao, Jian-Guang Lou, Weizhu Chen
| Challenge: | Existing language models are inadequate in reasoning, according to studies . a new reasoning pre-training paradigm is based on pretraining language models with programs . |
| Approach: | They propose a reasoning pre-training paradigm that empowers language models to harvest reasoning knowledge possessed by program executors. |
| Outcome: | The proposed reasoning pre-training paradigm can boost models' reasoning skills . it can be instantiated by different kinds of program executors and run on a single database . |
Bridging Language and Items for Retrieval and Recommendation: Benchmarking LLMs as Semantic Encoders (2026.acl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models have enabled their use as semantic encoders for recommendation, but their roles and behaviors in this setting are still not well understood. |
| Approach: | They propose a benchmark to evaluate large language models as semantic encoders in recommendation scenarios. |
| Outcome: | The proposed benchmark shows that ranking of 11 leading LLMs is low compared to MTEB, highlighting the unique challenges of semantic encoding in recommendation. |
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. |
Incorporating External Knowledge into Machine Reading for Generative Question Answering (D19-1)
Copied to clipboard
| Challenge: | Existing knowledge-aware QA models do not have commonsense and background knowledge to answer nontrivial questions. |
| Approach: | They propose a new neural model which exploits external knowledge to generate answers in natural language for a given question with context. |
| Outcome: | The proposed model improves answer quality over existing models without knowledge and knowledge-aware models, a study shows . state officials in Hawaii confirmed that president Barack Obama was born in the U.S. |
KBAlign: Efficient Self Adaptation on Specific Textual Knowledge Bases (2025.findings-emnlp)
Copied to clipboard
Zheni Zeng, Yuxuan Chen, Shi Yu, Ruobing Wang, Yukun Yan, Zhenghao Liu, Shuo Wang, Xu Han, Zhiyuan Liu, Maosong Sun
| Challenge: | Existing methods for retrieval-augmented generation (RAG) are limited and fine-tuning incurs prohibitive costs of external signals. |
| Approach: | They propose a self-supervised framework that enhances RAG systems through efficient model adaptation. |
| Outcome: | The proposed framework achieves 90% of the performance gain obtained through GPT-4-supervised adaptation while relying entirely on self-annotation of much smaller models. |
Listening Like Humans: Semantics-Guided Noise-Robust Multimodal Speech Recognition (2026.acl-long)
Copied to clipboard
| Challenge: | Severe acoustic degradation results in unreliable ASR outputs . et al., 2024b): critical concerns regarding reliability and fairness of ASR . |
| Approach: | They propose a multimodal framework that reframes ASR as semantics-guided speech reconstruction. |
| Outcome: | The proposed framework achieves an average reduction in WER while also attaining 98.71% BERTScore and 96.7% USE over advanced baselines. |
Large Language Models as Zero-shot Dialogue State Tracker through Function Calling (2024.acl-long)
Copied to clipboard
Zekun Li, Zhiyu Chen, Mike Ross, Patrick Huber, Seungwhan Moon, Zhaojiang Lin, Xin Dong, Adithya Sagar, Xifeng Yan, Paul Crook
| Challenge: | Large language models (LLMs) are increasingly prevalent in conversational systems due to their advanced understanding and generative capabilities in general contexts. |
| Approach: | They propose a method for solving dialogue state tracking (DST) with large language models through function calling. |
| Outcome: | The proposed approach improves zero-shot DST, allowing adaptation to diverse domains without extensive data collection or model tuning. |
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. |
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. |
EmotionQueen: A Benchmark for Evaluating Empathy of Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing evaluations of emotional intelligence in large language models (LLMs) focus on basic sentiment analysis tasks, such as emotion recognition, which is not enough to evaluate LLMs’ overall emotional intelligence. |
| Approach: | They propose a framework for evaluating the emotional intelligence of large language models (LLMs) that includes four distinct tasks: Key Event Recognition, Mixed Event Recognition and Implicit Emotional Recognition. |
| Outcome: | The proposed framework includes four distinct tasks: Key Event Recognition, Mixed Event Recognition and Implicit Emotional Recognition. |
KGPT: Knowledge-Grounded Pre-Training for Data-to-Text Generation (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for data-to-text generation rely on labeled data, which is costly to acquire and limits their application to new tasks and domains. |
| Approach: | They propose to leverage pre-training and transfer learning to address this problem by leveraging a general knowledge-grounded generation model and a knowledge-based model. |
| Outcome: | The proposed model can generate knowledge-enriched text on a knowledge-grounded text corpus crawled from the web in three settings. |
In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents (2025.acl-long)
Copied to clipboard
Zhen Tan, Jun Yan, I-Hung Hsu, Rujun Han, Zifeng Wang, Long Le, Yiwen Song, Yanfei Chen, Hamid Palangi, George Lee, Anand Rajan Iyer, Tianlong Chen, Huan Liu, Chen-Yu Lee, Tomas Pfister
| Challenge: | Existing approaches to long-term dialogue memory management fail to capture the natural semantic structure of conversations, leading to fragmented and incomplete representations. |
| Approach: | They propose a mechanism that integrates forward- and backward-looking reflections into a personalized memory bank for effective future retrieval. |
| Outcome: | The proposed mechanism outperforms state-of-the-art benchmarks on a long-term dialogue memory model. |
ProphetNet: Predicting Future N-gram for Sequence-to-SequencePre-training (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing sequence-to-sequence models are optimized for future n-gram prediction and n stream self-attention mechanism. |
| Approach: | They propose a self-supervised objective called future n-gram prediction and the proposed n stream self-attention mechanism to optimize the model for sequence-to-sequence learning. |
| Outcome: | The proposed model achieves state-of-the-art on CNN/DailyMail, Gigaword, and SQuAD 1.1 benchmarks compared to the models using the same scale pre-training corpus. |
ShopSimulator: Evaluating and Exploring RL-Driven LLM Agent for Shopping Assistants (2026.acl-long)
Copied to clipboard
Pei Wang, Yanan Wu, Xiaoshuai Song, Weixun Wang, Gengru Chen, Zhongwen Li, Kezhong Yan, Qi Liu, Ken Deng, Shuaibing Zhao, Shaopan Xiong, Xuepeng Liu, Xuefeng Chen, Wanxi Deng, Wenbo Su, Bo Zheng
| Challenge: | Existing studies on large language model-based agents focus on evaluation benchmarks without training support. |
| Approach: | They propose a large-scale Chinese shopping simulation environment that uses large language models to train agents. |
| Outcome: | The proposed model performs poorly in a large-scale and challenging shopping environment in China. |
Injecting Domain-Specific Knowledge into Large Language Models: A Comprehensive Survey (2025.findings-emnlp)
Copied to clipboard
| Challenge: | specialized LLMs are often limited in domain-specific applications that require specialized knowledge. |
| Approach: | They provide a comprehensive overview of four key methods to enhance large language models by integrating domain-specific knowledge. |
| Outcome: | The proposed methods are categorized into four key approaches: dynamic knowledge injection, static knowledge embedding, modular adapters, and prompt optimization. |
S2O: Early Stopping for Sparse Attention via Online Permutation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing block-granularity sparsification can reduce latency, but coarse blocks impose an intrinsic sparsity ceiling. |
| Approach: | They propose a method that performs early stopping for sparse attention via online permutation. |
| Outcome: | The proposed approach reduces the complexity of the model and its performance. |
BioGen: Generating Biography Summary under Table Guidance on Wikipedia (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for summarizing text have not captured the salient information from an article. |
| Approach: | They propose a table-guided abstractive biography summarization that utilizes factual tables to capture important information and generate a summary of a biography. |
| Outcome: | The proposed method is the first large-scale biography summarization dataset with tables. |
SalaMAnder: Shapley-based Mathematical Expression Attribution and Metric for Chain-of-Thought Reasoning (2025.findings-emnlp)
Copied to clipboard
Yue Xin, Chen Shen, Shaotian Yan, Xiaosong Yuan, Yaoming Wang, Xiaofeng Zhang, Chenxi Huang, Jieping Ye
| Challenge: | Chain-of-Thought prompting improves the math reasoning capability of large language models. |
| Approach: | They propose a method for attribution of component-level contributions in CoT reasoning using Shapley value and a stratified sampling algorithm that significantly reduces computational complexity. |
| Outcome: | The proposed method reduces computational complexity and provides robust correlations with model performance. |
RHGN: Relation-gated Heterogeneous Graph Network for Entity Alignment in Knowledge Graphs (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for entity alignment fail to account for heterogeneity among KGs and distinction between KG entities and relations. |
| Approach: | They propose a Relation-gated Heterogeneous Graph Network (RHGN) that uses a relation-gate based convolutional layer to distinguish relations and entities in the KG. |
| Outcome: | Extensive experiments on four datasets show that the proposed method is superior to state-of-the-art methods. |
SPD-Faith Bench: Diagnosing and Improving Faithfulness in Chain-of-Thought for Multimodal Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing studies on multimodal faithfulness have focused on perceptual hallucinations, raising concerns about the validity of reasoning traces. |
| Approach: | They propose a diagnostic benchmark that enforces explicit visual comparison to assess faithfulness of reasoning traces. |
| Outcome: | The proposed framework improves visual routing and aligns reasoning with perception. |
Semantically Conditioned Dialog Response Generation via Hierarchical Disentangled Self-Attention (P19-1)
Copied to clipboard
| Challenge: | Existing models for limited-domain RNNs are difficult to scale due to the complexity of the inputs. |
| Approach: | They propose to use dialog acts to build a multi-layer hierarchical graph with a disentangled self-attention network. |
| Outcome: | The proposed model improves on the baselines on automatic and human evaluation metrics. |
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. |
Cross-modal Memory Networks for Radiology Report Generation (2021.acl-long)
Copied to clipboard
| Challenge: | Medical imaging reports are essential in clinical practice, and generating the reports is beneficial to reduce the burden of radiologists. |
| Approach: | They propose to use a shared memory to enhance the encoder-decoder framework for radiology report generation. |
| Outcome: | The proposed model can generate more accurate reports on two widely used datasets. |
Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection (2024.naacl-long)
Copied to clipboard
Jun Yan, Vikas Yadav, Shiyang Li, Lichang Chen, Zheng Tang, Hai Wang, Vijay Srinivasan, Xiang Ren, Hongxia Jin
| Challenge: | Instruction-tuned Large Language Models (LLMs) can modulate responses based on human instructions, but they can be maliciously steered to impact society in subtle but persistent ways. |
| Approach: | They propose a backdoor attack setting that allows an attacker to inject a virtual prompt into an LLM to steer it without any explicit injection at its input. |
| Outcome: | The proposed method is able to poison the model's instruction tuning data and show that it is highly effective in steering the model. |
Task-adaptive Pre-training and Self-training are Complementary for Natural Language Understanding (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Task-adaptive pre-training (TAPT) and Self-training can be complementary with simple TFS protocol. |
| Approach: | They propose to use task-adaptive pre-training and self-training to combine TAPT and ST with a simple TFS protocol to achieve strong combined gains across six datasets. |
| Outcome: | The proposed method can achieve strong combined gains across six datasets covering sentiment classification, paraphrase identification, natural language inference, named entity recognition and dialogue slot classification. |
Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing work on augmenting question answering models with external knowledge (e.g., knowledge graphs) lacks transparency into the model’s prediction rationale. |
| Approach: | They propose a knowledge-aware approach that equips pre-trained language models with a multi-hop relational reasoning module that performs multi-relational reasoning over subgraphs extracted from external knowledge graphs. |
| Outcome: | The proposed model performs multi-hop, multi-relational reasoning over subgraphs extracted from external knowledge graphs. |
Small LLMs Are Weak Tool Learners: A Multi-LLM Agent (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have revolutionized natural language processing with impressive capabilities, but they lack domain specificity, real-time information and face challenges in solving specialized problems. |
| Approach: | They propose a multi-LLM approach that decomposes the aforementioned capabilities into a planner, caller, and summarizer. |
| Outcome: | The proposed model outperforms existing models by demonstrating its effectiveness and advantages in tool learning. |
RSA-Bench: Benchmarking Audio Large Models in Real-World Acoustic Scenarios (2026.findings-acl)
Copied to clipboard
Yibo Zhang, Kaiwen Luo, Liang Lin, Shilinlu Yan, Jin Wang, Yaoqi Guo, Yitian Chen, Yalan Qin, Zhenhong Zhou, Kun Wang, Li Sun
| Challenge: | Existing evaluations rely on synthetic Gaussian noise or simplistic single-source interference, failing to capture the intricate, multi-layered acoustic dynamics that characterize authentic physical environments. |
| Approach: | They propose a robustness benchmark to stress-test Audio Large Models (ALLMs) using high-fidelity auditory scene simulations. |
| Outcome: | The proposed model performs well on a wide range of tasks, including automatic speech recognition, speech translation, and audio-based reasoning. |
Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language Models (2025.findings-acl)
Copied to clipboard
Yingqian Cui, Pengfei He, Jingying Zeng, Hui Liu, Xianfeng Tang, Zhenwei Dai, Yan Han, Chen Luo, Jing Huang, Zhen Li, Suhang Wang, Yue Xing, Jiliang Tang, Qi He
| Challenge: | Chain-of-Thought (CoT) reasoning has improved the performance of large language models (LLMs) however, the detailed reasoning process in CoT often incurs long generation times and high computational costs due to the inclusion of unnecessary steps. |
| Approach: | They propose a method to identify critical reasoning steps using perplexity as a measure of their importance. |
| Outcome: | The proposed method achieves a better balance between reasoning accuracy and efficiency of CoT. |
Multi-level Association Refinement Network for Dialogue Aspect-based Sentiment Quadruple Analysis (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for identifying quadruples rely on predefined dialogue structure and word semantics to achieve accurate and comprehensive sentiment associations between utterances and words. |
| Approach: | They propose a multi-level association refinement network to achieve more accurate sentiment associations between utterances and words. |
| Outcome: | The proposed framework achieves state-of-the-art performance under low-resource conditions. |
SLAM-Omni: Timbre-Controllable Voice Interaction System with Single-Stage Training (2025.findings-acl)
Copied to clipboard
Wenxi Chen, Ziyang Ma, Ruiqi Yan, Yuzhe Liang, Xiquan Li, Ruiyang Xu, Zhikang Niu, Yanqiao Zhu, Yifan Yang, Zhanxun Liu, Kai Yu, Yuxuan Hu, Jinyu Li, Yan Lu, Shujie Liu, Xie Chen
| Challenge: | a new spoken dialogue system with single-stage training is demonstrating its low latency and high quality . SLAM-Omni achieves zero-shot timbre control by modeling spoken language with semantic tokens . |
| Approach: | They propose a timbre-controllable, end-to-end voice interaction system with single-stage training. |
| Outcome: | The proposed system outperforms previous models on 4 GPUs with limited data. |
Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents (2023.emnlp-main)
Copied to clipboard
Weiwei Sun, Lingyong Yan, Xinyu Ma, Shuaiqiang Wang, Pengjie Ren, Zhumin Chen, Dawei Yin, Zhaochun Ren
| Challenge: | Existing work utilizes generative LLMs for Information Retrieval (IR) rather than direct passage ranking. |
| Approach: | They investigate generative LLMs such as ChatGPT and GPT-4 for relevance ranking in IR and use a test set to verify the model’s ability to rank unknown knowledge. |
| Outcome: | The proposed model outperforms a 3B supervised model on the BEIR benchmark. |
LiveFact: A Dynamic, Time-Aware Benchmark for LLM-Driven Fake News Detection (2026.acl-long)
Copied to clipboard
| Challenge: | Current evaluation frameworks are static and vulnerable to benchmark data contamination . current models are ineffective at assessing reasoning under temporal uncertainty . |
| Approach: | They propose a live-based benchmark that simulates the real-world "fog of war" they propose evaluating models on their ability to reason with evolving, incomplete information . |
| Outcome: | The proposed model outperforms proprietary state-of-the-art models in classification and evidence mode . it also provides a component to monitor BDC explicitly . |
CrossTune: Black-Box Few-Shot Classification with Label Enhancement (2024.lrec-main)
Copied to clipboard
| Challenge: | Training large-scale language models requires substantial computation resources . current research focuses on adapting black-box models to downstream tasks using prompt optimization . |
| Approach: | They propose a label-enhanced cross-attention network called CrossTune to improve the generalization of the model. |
| Outcome: | The proposed approach outperforms the state-of-the-art black-box tuning method by 5.7% on average. |
Same Claim, Different Judgment: Benchmarking Scenario-Induced Bias in Multilingual Financial Misinformation Detection (2026.findings-acl)
Copied to clipboard
Zhiwei Liu, Yupeng Cao, Yuechen Jiang, Mohsinul Kabir, Polydoros Giannouris, Chen Xu, Ziyang Xu, Tianlei Zhu, Md. Tariquzzaman, Triantafillos Papadopoulos, Yan Wang, Lingfei Qian, Xueqing Peng, Zhuohan Xie, Ye Yuan, Saeed Almheiri, Abdulrazzaq Alnajjar, Ming-Bin Chen, Harry Stuart, Paul Thompson, Prayag Tiwari, Alejandro Lopez-Lira, Xue Liu, Jimin Huang, Sophia Ananiadou
| Challenge: | Existing research on LLM biases has focused on direct questioning or general-purpose settings . pronounced behavioral biase despite their growing deployment in financial analysis, forecasting, and decision support. |
| Approach: | They propose a benchmark to evaluate behavioral biases of large language models in MFMD . they use a multilingual financial misinformation dataset to integrate these with misinformation claims . |
| Outcome: | The proposed benchmark evaluates behavioral biases of large language models across economic scenarios. |
ProBench: Judging Multimodal Foundation Models on Open-ended Multi-domain Expert Tasks (2025.findings-acl)
Copied to clipboard
| Challenge: | Solving expert-level multimodal tasks requires strong user query understanding, domain-specific knowledge, and advanced reasoning abilities. |
| Approach: | They propose a benchmark of open-ended user queries encapsulating professional expertise and advanced reasoning. |
| Outcome: | The proposed benchmark is publicly accessible at TBC. |
MultiCodeAttack: Iterative Jailbreak Attacking on LLMs with Multi-Code Prompt Injection (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to jailbreak rely on fixed template design and a single programming language . however, existing approaches do not consider language diversity or adaptive template evolution . |
| Approach: | They propose a structured jailbreak framework that explores and optimizes multi-language code templates. |
| Outcome: | The proposed framework outperforms existing jailbreak baselines and produces higher harmful outputs than baseline methods. |
Anti-Length Shift: Dynamic Outlier Truncation for Training Efficient Reasoning Models (2026.acl-long)
Copied to clipboard
Wei Wu, Liyi Chen, Congxi Xiao, Tianfu Wang, Qimeng Wang, Chengqiang Lu, Yan Gao, null Yiwu, Yao Hu, Hui Xiong
| Challenge: | Existing efficient reasoning methods rely on explicit length penalties for excessive verbosity on simple queries. |
| Approach: | They propose a training-time intervention that selectively suppresses redundant tokens . they find length shift occurs when models generate unnecessary reasoning on trivial inputs - a phenomenon that is often unexplored . |
| Outcome: | The proposed method reduces inference token usage by 78% while increasing accuracy compared to the initial policy and surpasses state-of-the-art efficient reasoning methods. |
System Prompt Hijacking via Permutation Triggers in LLM Supply Chains (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) are rapidly transforming the landscape of artificial intelligence due to the substantial resources required for training. |
| Approach: | They propose a post-deployment attack that bypasses system prompts to compromise models . they introduce Precise Activation Guarding and Unit Deviation Sampling to protect against attack . |
| Outcome: | The proposed attack bypasses system prompts, enabling unrestricted model outputs and safety violations. |
Multilingual Generation in Abstractive Summarization: A Comparative Study (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing models for multilingual generation lack thorough analysis due to extensive linguistic diversity. |
| Approach: | They propose to classify multilingual generation methodologies into three categories based on their underlying modeling principles . they introduce an automatic metric to mitigate spurious correlations associated with language mixing . |
| Outcome: | The proposed model improves in high-resource, low-resourced, and zero-shot scenarios. |
Summarizing Procedural Text: Data and Approach (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Procedural text summarization task is a popular task in the NLP field because of its long length and complexity. |
| Approach: | They propose a procedural text summarization task with two granularity . they propose an Entity-State Graph-based Summarizer (ESGS) which aggregates contextual information for each procedure. |
| Outcome: | The proposed model can summarize the entire procedural text or give an overview for each step or both . Experiments on two datasets confirm the proposed model's effectiveness. |
Task Knowledge Injection via Interpolations and Reinstatement for Large Language Model Generalization (2025.findings-acl)
Copied to clipboard
| Challenge: | Pre-trained large language models have been widely adopted to elicit their superior performance on downstream tasks, but instruction tuning may overfit them to specific task formats, compromising their generalization on unseen tasks. |
| Approach: | They propose to inject latent task adaptation and knowledge reinstatement into large language models to mitigate spurious correlations between inputs and targets. |
| Outcome: | The proposed method improves generalization on in-domain and out-of-domain unseen tasks. |
From Redundancy to Relevance: Information Flow in LVLMs Across Reasoning Tasks (2025.naacl-long)
Copied to clipboard
Xiaofeng Zhang, Yihao Quan, Chen Shen, Xiaosong Yuan, Shaotian Yan, Liang Xie, Wenxiao Wang, Chaochen Gu, Hao Tang, Jieping Ye
| Challenge: | Large visionlanguage models (LVLMs) are a powerful visual-language reasoning tool. |
| Approach: | They propose to integrate attention analysis with LLaVA-CAM to determine interactions between visual representations. |
| Outcome: | The proposed approach can be used to determine interactions between visual representations. |
SocialEval: Evaluating Social Intelligence of Large Language Models (2025.acl-long)
Copied to clipboard
Jinfeng Zhou, Yuxuan Chen, Yihan Shi, Xuanming Zhang, Leqi Lei, Yi Feng, Zexuan Xiong, Miao Yan, Xunzhi Wang, Yaru Cao, Jianing Yin, Shuai Wang, Quanyu Dai, Zhenhua Dong, Hongning Wang, Minlie Huang
| Challenge: | Existing work on LLMs does not address their social intelligence (SI) and their discrepancy with humans. |
| Approach: | They propose a script-based bilingual SI benchmark that integrates outcome-oriented goal achievement evaluation and process-oriented interpersonal ability evaluation by manually crafting narrative scripts. |
| Outcome: | The proposed model is based on a script-based bilingual evaluation paradigm that integrates outcome- and process-oriented evaluation by manually crafting narrative scripts. |
FlexiQA: Leveraging LLM’s Evaluation Capabilities for Flexible Knowledge Selection in Open-domain Question Answering (2024.findings-eacl)
Copied to clipboard
| Challenge: | Current methods for open-domain question answering lacks the hallucination and relevance of acquired knowledge to the given question. |
| Approach: | They propose a new pipeline that utilizes the diverse evaluation capabilities of large language models to select knowledge effectively and flexibly. |
| Outcome: | The proposed pipeline combines the strengths of both paradigms and overcomes their shortcomings. |
Tandem: Riding Together with Large and Small Language Models for Efficient Reasoning (2026.findings-acl)
Copied to clipboard
Zichuan Fu, Xian Wu, Guojing Li, Yejing Wang, Yijun Chen, Zhao Zihao, Luo Yixuan, Hanyu Yan, Yefeng Zheng, Xiangyu Zhao
| Challenge: | Recent advances in large language models (LLMs) have catalyzed the rise of reasoningintensive inference paradigms, where models perform explicit step-by-step reasoning before generating final answers. |
| Approach: | They propose a large-small LLM collaboration framework that synergizes large and small language models to achieve high-quality reasoning with significantly reduced computational cost. |
| Outcome: | The proposed framework outperforms the mentor LLM while preserving the benefits of the thinking paradigm of LLMs. |
TestAgent: An Adaptive and Intelligent Expert for Human Assessment (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing adaptive testing methods face several challenges due to mechanized nature of most algorithms and noisy response data. |
| Approach: | They propose to use large language models to enhance adaptive testing through interactive engagement to capture test-takers’ responses and anomalies. |
| Outcome: | The proposed agent achieves more accurate results with 20% fewer questions than state-of-the-art baselines and testers preferred it in speed, smoothness, and other dimensions. |
Advancing Precise Outline-Conditioned Text Generation with Task Duality and Explicit Outline Control (2024.eacl-long)
Copied to clipboard
| Challenge: | Existing studies on outline-conditioned text generation focus on generating text using provided outlines as rough sketches, but lack of clarity and rationality of the rough outlines hampers quality of the generated text. |
| Approach: | They propose a novel task that requires generating stories based on specific, sentence-level outlines. |
| Outcome: | The proposed framework improves the quality of precise outline-conditioned text generation. |
RAM-SD: Retrieval-Augmented Multi-agent framework for Sarcasm Detection (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to sarcastic detection use a uniform reasoning strategy . existing approaches lack a framework to deal with the diverse analytical demands of sarcasm . |
| Approach: | They propose a Retrieval-Augmented Multi-Agent framework for Sarcasm Detection . the framework provides transparent and interpretable reasoning traces . |
| Outcome: | The proposed framework outperforms existing methods on four benchmarks and outperformed the strong GPT-4o+CoC baseline. |
SelfAug: Mitigating Catastrophic Forgetting in Retrieval-Augmented Generation via Distribution Self-Alignment (2025.findings-emnlp)
Copied to clipboard
Yuqing Huang, Rongyang Zhang, Qimeng Wang, Chengqiang Lu, Yan Gao, null Yiwu, Yao Hu, Xuyang Zhi, Guiquan Liu, Xin Li, Hao Wang, Enhong Chen
| Challenge: | Existing solutions for supervised fine-tuning often lead to catastrophic forgetting, where models lose their previously acquired knowledge and general capabilities. |
| Approach: | They propose a self-distribution alignment method that aligns input sequence logits to preserve the model’s semantic distribution, thereby mitigating catastrophic forgetting and improving downstream performance. |
| Outcome: | The proposed method achieves a superior balance between downstream learning and general capability retention. |
Text2Tree: Aligning Text Representation to the Label Tree Hierarchy for Imbalanced Medical Classification (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to medical text classification are struggling with imbalanced data distribution and rare labels. |
| Approach: | They propose a framework-agnostic algorithm that only utilizes internal label hierarchy in training deep learning models. |
| Outcome: | The proposed approach performs better on public datasets and real-world medical records than existing methods. |
Finding the Dominant Winning Ticket in Pre-Trained Language Models (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing studies on pre-trained language models show that they can fine-tune parameters but achieve good downstream performance. |
| Approach: | They find that a dominant winning ticket takes up 0.05% of the parameters and is transferable across different tasks. |
| Outcome: | The proposed model can achieve comparable performance with the full-parameter model, the authors show . the dominant winning ticket takes up 0.05% of the parameters, and the model is transferable across tasks, they show - the authors conclude . |
DANCER: Entity Description Augmented Named Entity Corrector for Automatic Speech Recognition (2024.lrec-main)
Copied to clipboard
| Challenge: | End-to-end automatic speech recognition systems suffer from mistranscription of domain-specific phrases, such as named entities. |
| Approach: | They propose a named entity correction model that leverages phonetic con-fusion to mitigate phonetic confusion. |
| Outcome: | The proposed model outperforms the existing model on AISHELL-1 and Homophone datasets. |
EcoLANG: Efficient and Effective Agent Communication Language Induction for Social Simulation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated impressive ability to role-play humans and replicate complex social dynamics. |
| Approach: | They propose an efficient agent communication language induction for social simulations that reduces token consumption by over 20%. |
| Outcome: | The proposed model reduces token consumption by over 20% while preserving human language. |
DetectBench: Can Large Language Model Detect and Piece Together Implicit Evidence? (2024.findings-emnlp)
Copied to clipboard
Zhouhong Gu, Lin Zhang, Xiaoxuan Zhu, Jiangjie Chen, Wenhao Huang, Yikai Zhang, Shusen Wang, Zheyu Ye, Yan Gao, Hongwei Feng, Yanghua Xiao
| Challenge: | Existing LLMs' abilities to detect evidence in long contexts are far inferior to humans. |
| Approach: | They propose a benchmark to assess LLMs' abilities in evidence and multi-step commonsense reasoning within a long context. |
| Outcome: | The proposed method improves the performance of LLMs in evidence detection and commonsense reasoning. |
Thinking Economically: A Hierarchical Framework for Adaptive-Complexity Reasoning in LLMs (2026.findings-acl)
Copied to clipboard
Yubo Gao, Haotian Wu, Hong Chen, Junquan Huang, Yibo Yan, Jungang Li, Zihao Dongfang, Sicheng Tao, PS Tan, Jie Zhang, Xuming Hu
| Challenge: | Existing efficiency methods for Chain-of-Thought (CoT) generate excessively long rationales without commensurate accuracy gains. |
| Approach: | They propose a training framework that operationalizes this principle through coarse-to-fine budgeting. |
| Outcome: | Experiments on GSM8K and MATH500 show that HAB surpasses standard CoT in accuracy and reduces token usage, achieving stronger performance-efficiency trade-off than baselines. |
DeepNote: Note-Centric Deep Retrieval-Augmented Generation (2025.findings-emnlp)
Copied to clipboard
Ruobing Wang, Qingfei Zhao, Yukun Yan, Daren Zha, Yuxuan Chen, Shi Yu, Zhenghao Liu, Yixuan Wang, Shuo Wang, Xu Han, Zhiyuan Liu, Maosong Sun
| Challenge: | . - (EN) |
| Approach: | . - (EN) |
| Outcome: | . - (EN) |
Conditional Augmentation for Aspect Term Extraction via Masked Sequence-to-Sequence Generation (2020.acl-main)
Copied to clipboard
| Challenge: | Aspect term extraction is a task to extract aspect terms from review texts as opinion targets for sentiment analysis. |
| Approach: | They propose a conditional generation task for augmentation of aspect term extraction . they use a sequence-to-sequence method that generates a new sentence . results confirm that their method alleviates the data scarcity problem significantly . |
| Outcome: | The proposed method reduces the data scarcity problem significantly and boosts current models. |
MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large-scale reinforcement learning (RL) methods have proven effective in enhancing the reasoning abilities of large language models. |
| Approach: | They propose an open-source adaptation of the R1-Zero RL framework for machine translation (MT) their code is available at https://github.com/fzp0424/MT-R1-zero. |
| Outcome: | The proposed framework surpasses towerinstruct-7B-v0.2 on the english-chinese benchmark by 1.26 points. |
Dialogue Summarization with Static-Dynamic Structure Fusion Graph (2023.acl-long)
Copied to clipboard
| Challenge: | Dialogue summarization is a challenging task since it has dynamic interaction nature and inconsistent information flow among various speakers. |
| Approach: | They propose a Static-Dynamic graph-based Dialogue Summarization model which fuses prior knowledge from human expertise and adaptively learns the graph structure in an end-to-end learning fashion. |
| Outcome: | The proposed model can help people capture the highlights of a semi-structured and multi-participant dialogue without reviewing the complex dialogue context. |
CATE: A Contrastive Pre-trained Model for Metaphor Detection with Semi-supervised Learning (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing models for metaphor detection require a large amount of labeled data and are not linguistically-based. |
| Approach: | They propose a ContrAstive pre-Trained modEl (CATE) for metaphor detection with semi-supervised learning using a pre-trained model to obtain a contextual representation of target words. |
| Outcome: | The proposed model outperforms existing models on several benchmark datasets and achieves better performance against state-of-the-art models. |
Representation Interventions Enable Lifelong Knowledge Memory Control in LLMs (2026.acl-long)
Copied to clipboard
Xuyuan Liu, Shengyu Chen, Xinshuai Dong, Yanchi Liu, Xujiang Zhao, Haoyu Wang, Yujun Yan, Haifeng Chen, Zhengzhang Chen
| Challenge: | Large language models (LLMs) produce outdated or inaccurate content. Updating their knowledge efficiently and accurately without costly retraining is a major challenge. |
| Approach: | They propose a robust and scalable method that treats knowledge control as interventions within the model’s representation space. |
| Outcome: | The proposed method achieves fine-grained control over complex, unstructured knowledge while maintaining general utility with frozen base weights. |
Specialization through Collaboration: Understanding Expert Interaction in Mixture-of-Expert Large Language Models (2026.eacl-long)
Copied to clipboard
| Challenge: | Mixture-of-Experts (MoE) based large language models are popular for multitasking . however, whether each expert can specialize to a task remains unclear . |
| Approach: | They propose to use a dictionary learning approach to analyze expert collaboration mechanisms in MoE LLMs. |
| Outcome: | The proposed model outperforms existing methods by 2.5% while enabling 50% expert reduction. |
How Susceptible are Large Language Models to Ideological Manipulation? (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have the potential to exert substantial influence on public perceptions and interactions with information. |
| Approach: | They examine how LLMs can learn and generalize ideological biases from their instruction-tuning data. |
| Outcome: | The LLMs show a startling ability to absorb ideology from one topic and generalize it to even unrelated ones. |
DRAGON: Domain-specific Robust Automatic Data Generation for RAG Optimization (2026.findings-eacl)
Copied to clipboard
Haiyang Shen, Hang Yan, Zhongshi Xing, Mugeng Liu, Yue Li, Zhiyang Chen, Yuxiang Wang, Jiuzheng Wang, Yun Ma
| Challenge: | Existing retrieval-augmented generation paradigms rely heavily on public knowledge . Existing RAGs reliant on public information and often falter when faced with domain-specific queries. |
| Approach: | They propose a framework that combines a data-construction modeling approach with a scalable synthetic data-generation pipeline to optimize domain-specific retrieval performance. |
| Outcome: | The proposed framework optimizes domain-specific retrieval performance and bolsters retriever robustness. |
Stylized Dialogue Generation with Feature-Guided Knowledge Augmentation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods synthesize pseudo data through back translation but lack guidance on target style features. |
| Approach: | They propose a knowledge-augmented stylized dialogue generation model with a feature-guided style knowledge selection module that utilizes context and response features. |
| Outcome: | The proposed model produces a satisfactory performance on two public benchmarks on both semantic and stylized levels. |
ClueAnchor: Clue-Anchored Knowledge Reasoning Exploration and Optimization for Retrieval-Augmented Generation (2025.findings-emnlp)
Copied to clipboard
Hao Chen, Yukun Yan, Sen Mei, Wanxiang Che, Zhenghao Liu, Qi Shi, Xinze Li, Yuchun Fan, Pengcheng Huang, Qiushi Xiong, Zhiyuan Liu, Maosong Sun
| Challenge: | Existing RAG systems often underutilize the retrieved documents, authors say . they fail to extract and integrate key clues needed to support faithful and interpretable reasoning . |
| Approach: | a new framework extracts key clues from retrieved content and generates multiple reasoning paths . the framework optimizes the model by selecting the most appropriate reasoning path . |
| Outcome: | Experiments show that ClueAnchor outperforms baseline RAG frameworks in completeness and robustness. |
Mitigating Judgment Preference Bias in Large Language Models through Group-Based Polling (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are used as automatic evaluators to provide accurate and reliable assessments. |
| Approach: | They propose a framework that integrates LLM-based judgment models into a multi-agent system and simulates the interactive client-server polling mechanism. |
| Outcome: | The proposed framework outperforms supervised models trained on annotated judgment data while requiring no human-labeled annotations. |
Fortify the Shortest Stave in Attention: Enhancing Context Awareness of Large Language Models for Effective Tool Use (2024.acl-long)
Copied to clipboard
| Challenge: | In this paper, we demonstrate that an inherent waveform pattern in the attention allocation of large language models significantly affects their performance in tasks demanding a high degree of context awareness. |
| Approach: | They propose a method that compensates an attention trough with an attention peak by a process to enhance the model's awareness to various contextual positions. |
| Outcome: | The proposed method improves the performance of a 7B model on the largest tool-use benchmark, comparable to that of GPT-4. |
How Large a Vocabulary Does Text Classification Need? A Variational Approach to Vocabulary Selection (N19-1)
Copied to clipboard
| Challenge: | Using a pre-defined vocabulary is a common approach to selecting text inputs . however, using a large vocabulary is not economical, as it limits the model's applicability on computation-or memoryconstrained scenarios. |
| Approach: | They propose a more sophisticated variational vocabulary dropout to perform vocabulary selection . they propose two new metrics to measure area under accuracy-vocab curve and Vocab Size under X% accuracy drop . |
| Outcome: | The proposed framework outperforms the baselines on the vocabulary selection problem on multiple NLP classification tasks. |
KCS: Diversify Multi-hop Question Generation with Knowledge Composition Sampling (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to multi-hop question answering focus on generating simple questions and neglecting the integration of essential knowledge, such as relevant sentences within documents. |
| Approach: | They propose a framework to expand the diversity of generated multi-hop questions by sampling varied knowledge compositions within a given context. |
| Outcome: | The proposed framework improves the overall accuracy of knowledge composition selection by 3.9% on hotpotQA and 2WikiMultihopQA datasets. |
A Span-based Dynamic Local Attention Model for Sequential Sentence Classification (2021.acl-short)
Copied to clipboard
| Challenge: | Existing methods for sentence classification ignore latent segment structure of document, in which contiguous sentences have coherent semantics. |
| Approach: | They propose a span-based dynamic local attention model that captures structural information by supervised dynamic local focus. |
| Outcome: | The proposed model outperforms state-of-the-art models on two benchmark datasets. |
Distinguish Before Answer: Generating Contrastive Explanation as Knowledge for Commonsense Question Answering (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing knowledge-enhanced methods have trouble obtaining knowledge from different knowledge bases . a concept-centric model can be used to generate a contrastive explanation for QA tasks . |
| Approach: | They propose a Concept-centric Prompt-bAsed Contrastive Explanation Generation model which converts obtained symbolic knowledge into the contrastive explanation for better distinguishing the differences among given candidates. |
| Outcome: | The proposed model achieves new SOTA on CSQA, QASC, and OBQA. |
HOTVCOM: Generating Buzzworthy Comments for Videos (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing research focuses on generating descriptive comments in English . hot-comments are important for video marketing and branding, authors say . |
| Approach: | They propose a framework to generate hot-comments on a Chinese video dataset . they use a combination of visual, auditory, and textual data to generate them . |
| Outcome: | The proposed framework shows that it generates hot-comments on both the new and existing datasets. |
SEER: Self-Aligned Evidence Extraction for Retrieval-Augmented Generation (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for enhancing RAG performance rely on heuristic-based augmentation . Existing approaches rely heavily on a heuriistic-driven approach, resulting in poor generalization and skews in the evidence length. |
| Approach: | They propose a model-based evidence extraction learning framework that optimizes a vanilla model as an evidence extractor with desired properties through self-aligned learning. |
| Outcome: | The proposed method reduces the evidence length by 9.25 times and improves reliability and reliability. |
FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing prompt-based debiasing methods exhibit instability due to sensitivity to prompt changes . fine-tuning-based techniques incur substantial computational overhead and catastrophic forgetting . |
| Approach: | They propose a debiasing framework that encodes fairness-related features into separable directions in the hidden activation space. |
| Outcome: | The proposed framework performs inference-time debiasing without requiring retraining or prompt design . it detects bias signatures in activations and then computes debiased steering vectors . the proposed framework is available to download in the u.s. |
Generating Classical Chinese Poems via Conditional Variational Autoencoder and Adversarial Training (D18-1)
Copied to clipboard
| Challenge: | Existing models for automatic poetry generation lack term novelty and thematic consistency. |
| Approach: | They propose a conditional variational autoencoder with adversarial training for classical Chinese poem generation. |
| Outcome: | The proposed model outperforms existing models on a large poetry corpus on 'classical Chinese' . it generates poems with novel terms and learns their thematic consistency with their titles. |
ProphetNet-X: Large-Scale Pre-training Models for English, Chinese, Multi-lingual, Dialog, and Code Generation (2021.acl-demo)
Copied to clipboard
Weizhen Qi, Yeyun Gong, Yu Yan, Can Xu, Bolun Yao, Bartuer Zhou, Biao Cheng, Daxin Jiang, Jiusheng Chen, Ruofei Zhang, Houqiang Li, Nan Duan
| Challenge: | Existing models for pre-training are not convenient for users to find and set them up. |
| Approach: | They propose to extend ProphetNet into other domains and languages by pre-training models . they pre-train a cross-lingual generation model ProphetNet-Multi and a Chinese generation model . |
| Outcome: | The proposed models achieve new state-of-the-art on 10 benchmarks. |
From Evasion to Concealment: Stealthy Knowledge Unlearning for LLMs (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to unlearning often treat nonsensical responses or template-based refusals as the unlearning target, making the process even more vulnerable to attacks and jailbreaks. |
| Approach: | They propose a method that uses inverted facts to remove the need for auxiliary models or retaining data while avoiding leakage. |
| Outcome: | Evaluated on the ToFU Knowledge Unlearning dataset using Llama2-7B-Chat and Phi-1.5, MEOW outperforms baselines in forgetting quality while preserving model utility. |
ERGO: Event Relational Graph Transformer for Document-level Event Causality Identification (2022.coling-1)
Copied to clipboard
| Challenge: | Existing methods to identify event-event causal relations in a document are noisy and require heuristic rules or external tools. |
| Approach: | They propose a document-level event-event causality identification framework that uses heuristic rules to design edges between events. |
| Outcome: | The proposed framework outperforms existing state-of-the-art methods on two benchmark datasets. |
EduMARS: Can Vision-Language Models Grade Like Teachers? Benchmarking Multimodal, Rubric-Based Assessment on Chinese K-12 Answers (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing benchmarks for automated grading of student work fail to evaluate real student responses . existing models fail to assess real student work, especially on cognitively demanding tasks . |
| Approach: | They propose a multimodal benchmark for rubric-aligned evaluation of real Chinese K-12 student answers. |
| Outcome: | The proposed model improves performance and interpretability of existing models on EduMARS . existing models fail to perform on real-world, cognitively demanding tasks, authors say . |
AgentOCR: Reimagining Agent History via Optical Self-Compression (2026.acl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have enabled agentic systems trained with reinforcement learning over multi-turn interaction, but practical deployment is bottlenecked by rapidly growing textual histories that inflate token and memory costs. |
| Approach: | They propose a framework that represents the accumulated observation-action history as a compact rendered image. |
| Outcome: | The proposed framework preserves over 95% of text-based agent performance while significantly reducing token consumption (>50%), yielding consistent token and memory efficiency. |
Reward Modeling Requires Automatic Adjustment Based on Data Quality (2024.findings-emnlp)
Copied to clipboard
Binghai Wang, Rui Zheng, Lu Chen, Zhiheng Xi, Wei Shen, Yuhao Zhou, Dong Yan, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Reinforcement Learning from Human Feedback (RLHF) is a method for aligning language models with human values. |
| Approach: | They propose a method that automatically adjusts reward modeling based on data quality . they use preference data to train a reward model that is more aligned with human values . |
| Outcome: | The proposed method stabilizes reward model training and significantly improves alignment performance on human preference datasets. |
CapArena: Benchmarking and Analyzing Detailed Image Captioning in the LLM Era (2025.findings-acl)
Copied to clipboard
Kanzhi Cheng, Wenpo Song, Jiaxin Fan, Zheng Ma, Qiushi Sun, Fangzhi Xu, Chenyang Yan, Nuo Chen, Jianbing Zhang, Jiajun Chen
| Challenge: | Image captioning has been a challenge for vision-language researchers for decades . current VLMs focus on tasks like visual question answering (YA) but image captioning is not as advanced as expected. |
| Approach: | They evaluate VLMs' performance on image captioning using human annotations . they find that some metrics show high caption-level agreement with humans . |
| Outcome: | The proposed model outperforms open-source models on image captioning . it achieves 93.4% correlation with human rankings at $4 per test . |
Dr.Academy: A Benchmark for Evaluating Questioning Capability in Education for Large Language Models (2024.acl-long)
Copied to clipboard
| Challenge: | Recognizing LLMs’ capability to generate educational content can lead to advances in automated and personalized learning. |
| Approach: | They propose to evaluate the questioning capability in education as a teacher of large language models by evaluating their generated educational questions. |
| Outcome: | The proposed model can generate educational content that aligns with human perspectives and is more apt as an interdisciplinary teacher. |
ModelScope-Agent: Building Your Customizable Agent System with Open-source Large Language Models (2023.emnlp-demo)
Copied to clipboard
Chenliang Li, He Chen, Ming Yan, Weizhou Shen, Haiyang Xu, Zhikai Wu, Zhicheng Zhang, Wenmeng Zhou, Yingda Chen, Chen Cheng, Hongzhu Shi, Ji Zhang, Fei Huang, Jingren Zhou
| Challenge: | Large language models (LLMs) have demonstrated remarkable capabilities to comprehend human intentions, engage in reasoning, and design planning-like behavior. |
| Approach: | They propose a framework that equips large language models with tool-use capabilities . they propose LLaMA and Chat-GLM as controllers, and a model-based agent framework . |
| Outcome: | The proposed framework equips open-source LLMs with tool-use capabilities . it provides a user-friendly system library with a customizable engine design . |
Monotonic Paraphrasing Improves Generalization of Language Model Prompting (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated remarkable proficiency in zero-shot decision making and instruction following. |
| Approach: | They propose an end-to-end decoding strategy that paraphrases given prompts or instructions into their lower perplexity counterparts based on an ensemble of a paraphrase LM for prompt rewriting, and a target LM that constrains the generation for lower perxity. |
| Outcome: | The proposed method can efficiently paraphrase the original prompt without altering its semantic meaning while decreasing the perplexity of each generation as calculated by the target LM. |
What are the Essential Factors in Crafting Effective Long Context Multi-Hop Instruction Datasets? Insights and Best Practices (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods to generate long-context instruction-tuning data are limited by poor quality and fewer than 35% of samples are multi-hop . |
| Approach: | They propose a framework that integrates a quality verification agent, a single-hop question generation agent, and a multi-hop questions merger agent to enhance model performance. |
| Outcome: | The proposed framework significantly improves data quality with high-quality, multi-hop, and diverse data. |
PhiloGPT: A Philology-Oriented Large Language Model for Ancient Chinese Manuscripts with Dunhuang as Case Study (2024.emnlp-main)
Copied to clipboard
Yuqing Zhang, Baoyi He, Yihan Chen, Hangqi Li, Han Yue, Shengyu Zhang, Huaiyong Dou, Junchi Yan, Zemin Liu, Yongquan Zhang, Fei Wu
| Challenge: | philology requires years of professional training in extensive knowledge memorization and manual textual retrieval. |
| Approach: | They curated the PhiloCorpus-ZH, a rich collec-tion of ancient Chinese texts spanning a millennium with 30 diverse topics, including firsthand folk copies. |
| Outcome: | The PhiloCorpus-ZH corpus facilitated the development of the first LLM tailored for discovering ancient Chinese manuscripts. |
Keywords and Instances: A Hierarchical Contrastive Learning Framework Unifying Hybrid Granularities for Text Generation (2022.acl-long)
Copied to clipboard
Mingzhe Li, XieXiong Lin, Xiuying Chen, Jinxiong Chang, Qishen Zhang, Feng Wang, Taifeng Wang, Zhongyi Liu, Wei Chu, Dongyan Zhao, Rui Yan
| Challenge: | Existing studies focus on contrastive learning on the instance level without discriminating the contribution of each word. |
| Approach: | They propose a hierarchical contrastive learning mechanism which can unify semantic meaning in the input text. |
| Outcome: | The proposed model outperforms baselines on storytelling, paraphrasing, dialogue generation, and storytelling tasks. |
Prompting Few-shot Multi-hop Question Generation via Comprehending Type-aware Semantics (2024.findings-naacl)
Copied to clipboard
| Challenge: | Existing approaches for multi-hop question generation rely on large annotated data . supervised approaches rely only on large labeled data, making it hard to perform tasks. |
| Approach: | They propose a type-aware semantics extraction-based chain-of-thought method for multi-hop question generation for documents . they first extract question types and essential semantic phrases from the given documents and the answer . |
| Outcome: | The proposed approach extracts question types and essential semantic phrases from documents and the answer. |
MLLM-Bench: Evaluating Multimodal LLMs with Per-sample Criteria (2025.naacl-long)
Copied to clipboard
Wentao Ge, Shunian Chen, Hardy Chen, Nuo Chen, Junying Chen, Zhihong Chen, Wenya Xie, Shuo Yan, ChenghaoZhu ChenghaoZhu, Ziyue Lin, Dingjie Song, Xidong Wang, Anningzhe Gao, Zhang Zhiyi, Jianquan Li, Xiang Wan, Benyou Wang
| Challenge: | Existing evaluation methodologies for multimodal large language models are limited in evaluating objective queries without considering real-world user experiences. |
| Approach: | They propose to evaluate multimodal large language models with per-sample criteria using potent MLLM as the judge. |
| Outcome: | The proposed evaluation paradigm shows that it can be used to evaluate multimodal large language models with per-sample criteria. |
MoDification: Mixture of Depths Made Easy (2025.naacl-long)
Copied to clipboard
Chen Zhang, Meizhi Zhong, Qimeng Wang, Xuantao Lu, Zheyu Ye, Chengqiang Lu, Yan Gao, Yao Hu, Kehai Chen, Min Zhang, Dawei Song
| Challenge: | Long-context efficiency is a trending topic in large language model (LLM) serving. |
| Approach: | They propose a method to combine long-context efficiency and mixture of depths to bring down both latency and memory. |
| Outcome: | The proposed method achieves 1.2 speedup in latency and 1.8 reduction in memory compared to original LLMs especially in long-context applications. |
Scaling is Not All You Need: Clinical-Oriented Reinforcement Learning Makes Parameter-Efficient Clinical Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models are increasingly used in medicine, but expert-level clinical reasoning remains a high-complexity, high-stakes frontier. |
| Approach: | They propose to train clinical reasoning models using a Reasoning-Oriented Data Strategy based on topological synthesis and CoT cold-start. |
| Outcome: | The proposed pipeline outperforms existing models and outperformed the strongest open-source alternatives up to 671B in MedXpertQA. |
Extracting and Understanding the Superficial Knowledge in Alignment (2025.naacl-long)
Copied to clipboard
Runjin Chen, Gabriel Jacob Perin, Xuxi Chen, Xilun Chen, Yan Han, Nina S. T. Hirata, Junyuan Hong, Bhavya Kailkhura
| Challenge: | Recent studies have shown that alignment of large language models with human values and preferences requires substantial data and computation resources. |
| Approach: | They propose a method to extract and isolate superficial knowledge from aligned models by focusing on the shallow modifications to the final token selection process. |
| Outcome: | The proposed method extracts and isolates superficial knowledge from aligned models, focusing on the shallow modifications to the final token selection process. |
AgentRM: Enhancing Agent Generalization with Reward Modeling (2025.acl-long)
Copied to clipboard
Yu Xia, Jingru Fan, Weize Chen, Siyu Yan, Xin Cong, Zhong Zhang, Yaxi Lu, Yankai Lin, Zhiyuan Liu, Maosong Sun
| Challenge: | Existing LLM-based agents have strong performance on held-in tasks, but their generalizability to unseen tasks remains poor. |
| Approach: | They propose a reward-based generalizable reward model to guide the policy model for effective test-time search. |
| Outcome: | The proposed agentRM outperforms existing agents on held-in tasks by 8.8 points on average. |
KERS: A Knowledge-Enhanced Framework for Recommendation Dialog Systems with Multiple Subgoals (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing frameworks for multi-subgoal dialogs require a system to build a social bond with users to gain trust and develop affinity. |
| Approach: | They propose a framework for common knowledge-based multi-subgoal dialogs that divides up conversations with multiple subgoals and propose mechanisms to filter noisy knowledge and to include cleaned knowledge in the dialog response generation process. |
| Outcome: | The proposed framework obtains state-of-the-art results on a DuRecDial dataset in both automatic and human evaluation. |
Global Textual Relation Embedding for Relational Understanding (P19-1)
Copied to clipboard
| Challenge: | Existing methods to learn textual relation embeddings are lacking in large open-domain corpora. |
| Approach: | They propose to learn a general-purpose embedding of textual relations using a large dataset from Freebase. |
| Outcome: | The proposed embedding can facilitate downstream tasks requiring relational understanding of the text. |
Encourage or Inhibit Monosemanticity? Revisit Monosemanticity from a Feature Decorrelation Perspective (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies focus on monosemanticity on its basic units. |
| Approach: | They propose to revisit monosemanticity from the feature decorrelation perspective and advocate for its encouragement. |
| Outcome: | The proposed method improves representation diversity and activation sparsity and improves preference alignment performance. |
CODIS: Benchmarking Context-dependent Visual Comprehension for Multimodal Large Language Models (2024.acl-long)
Copied to clipboard
Fuwen Luo, Chi Chen, Zihao Wan, Zhaolu Kang, Qidong Yan, Yingjie Li, Xiaolong Wang, Siyu Wang, Ziyue Wang, Xiaoyue Mi, Peng Li, Ning Ma, Maosong Sun, Yang Liu
| Challenge: | Multimodal large language models have demonstrated promising results in a variety of tasks that combine vision and language. |
| Approach: | They propose a benchmark to assess the ability of models to use contextual information in free-form text to enhance visual comprehension. |
| Outcome: | The proposed model fails to extract and utilize contextual information to improve understanding of images. |
Understanding the RoPE Extensions of Long-Context LLMs: An Attention Perspective (2025.coling-main)
Copied to clipboard
| Challenge: | Enabling LLMs to handle lengthy context is currently a research hotspot . a notable challenge limiting further customization is the inability of LLM to utilize context beyond pretrained length due to the inherent flaw of rotary position embedding (RoPE). |
| Approach: | They propose to extend the RoPE from an attention perspective and on two benchmarking tasks. |
| Outcome: | The proposed extension of the RoPE improves extrapolation and retrieval errors. |
CycleAlign: Iterative Distillation from Black-box LLM to White-box Models for Better Human Alignment (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing language models that generate harmful responses are constrained by their inherent capability. |
| Approach: | They propose to align large language models with human preferences from AI feedback. |
| Outcome: | The proposed framework improves the alignment of large language models with human preferences from AI feedback. |
SeqAR: Jailbreak LLMs with Sequential Auto-Generated Characters (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing studies have focused on the potential misuse of large language models (LLMs) however, the ability to align LLMs with human values is still vulnerable to malicious attacks. |
| Approach: | They propose a red-teaming strategy to enhance LLM safety by using a framework to design jailbreak prompts automatically. |
| Outcome: | The proposed framework achieves attack success rates of 88% and 60% in cold-start scenarios. |
BAPO: Boundary-Aware Policy Optimization for Reliable Agentic Search (2026.findings-acl)
Copied to clipboard
Shiyu Liu, Yongjing Yin, Jianhao Yan, Yunbo Tang, Qinggang Zhang, Bei Li, Xin Chen, Jingang Wang, Xunliang Cai, Jinsong Su
| Challenge: | Existing RL-based agentic search models fail to recognize reasoning boundaries and rarely admit "I DON'T KNOW" lack of reliability leads to plausible but unreliable answers, introducing significant risks . |
| Approach: | They propose a framework to cultivate reliable boundary awareness without compromising accuracy. |
| Outcome: | Experiments show that the proposed framework improves the reliability of agentic search models. |
Multi-Granularity Hierarchical Attention Fusion Networks for Reading Comprehension and Question Answering (P18-1)
Copied to clipboard
| Challenge: | Existing approaches to read comprehension style question answering are limited by the volume of annotated datasets. |
| Approach: | They propose a hierarchical attention network for reading comprehension style question answering . they first encode the question and paragraph with fine-grained language embeddings . then propose fusion approach to fuse information from both global and attended representations based on the hierarchic attention network . |
| Outcome: | The proposed method achieves state-of-the-art on the SQuAD and TriviaQA Wiki leaderboards and two adversarial SQu AD datasets. |
FastSeq: Make Sequence Generation Faster (2021.acl-demo)
Copied to clipboard
Yu Yan, Fei Hu, Jiusheng Chen, Nikhil Bhendawade, Ting Ye, Yeyun Gong, Nan Duan, Desheng Cui, Bingyu Chi, Ruofei Zhang
| Challenge: | Transformer-based models have made tremendous impact in natural language generation, but inference speed is still a bottleneck due to large model size and intensive computing involved in auto-regressive decoding process. |
| Approach: | They propose an attention cache optimization, an efficient algorithm for detecting repeated n-grams, and an asynchronous generation pipeline with parallel I/O to accelerate sequence generation without loss of accuracy. |
| Outcome: | The proposed framework can accelerate the sequence generation by 4x to 9x with a simple one-line code change for a set of widely used and diverse models. |
MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Application (2026.acl-long)
Copied to clipboard
Xueqing Peng, Lingfei Qian, Yan Wang, Ruoyu Xiang, Yueru He, Yang Ren, Mingyang Jiang, Vincent Jim Zhang, Yuqing Guo, Jeff Zhao, Huan He, Yi Han, Yun Feng, Yuechen Jiang, Yupeng Cao, Haohang Li, Yangyang Yu, Xiaoyu Wang, Penglei Gao, Shengyuan Lin, Keyi Wang, Shanshan Yang, Yilun Zhao, Zhiwei Liu, Peng Lu, Jerry Huang, Suyuchen Wang, Triantafillos Papadopoulos, Polydoros Giannouris, Efstathia Soufleri, Nuo Chen, Zhiyang Deng, Heming Fu, Yijia Zhao, Mingquan Lin, Meikang Qiu, Kaleb E Smith, Arman Cohan, Xiao-Yang Liu, Jimin Huang, Guojun Xiong, Alejandro Lopez-Lira, Xi Chen, Junichi Tsujii, Jian-Yun Nie, Sophia Ananiadou, Qianqian Xie
| Challenge: | Existing evaluations of LLMs in finance are text-only, monolingual, and largely saturated by current models. |
| Approach: | They propose a multilingual and multimodal benchmark for evaluating LLMs in real financial contexts. |
| Outcome: | The first expert-annotated multilingual and multimodal benchmark is released . it evaluates 21 leading LLMs and shows they perform better in multilingual settings . |
On the Step Length Confounding in LLM Reasoning Data Selection (2026.findings-acl)
Copied to clipboard
Bing Wang, Rui Miao, Chen Shen, Shaotian Yan, Kaiyuan Liu, Ximing Li, Xiaosong Yuan, Sinan Fan, Jun Zhang, Jieping Ye
| Challenge: | Existing pipelines generate long reasoning data from more capable Large Language Models (LLMs) and apply manually heuristic or naturalness-based selection methods to filter high-quality samples. |
| Approach: | They propose to use supervised fine-tuning to generate long reasoning data from more capable Large Language Models and apply manually heuristic or naturalness-based selection methods to filter high-quality samples. |
| Outcome: | Experiments on four LLMs and five evaluation benchmarks show that the proposed approach is effective in mitigating step length confounding problem. |
GLGE: A New General Language Generation Evaluation Benchmark (2021.findings-acl)
Copied to clipboard
Dayiheng Liu, Yu Yan, Yeyun Gong, Weizhen Qi, Hang Zhang, Jian Jiao, Weizhu Chen, Jie Fu, Linjun Shou, Ming Gong, Pengcheng Wang, Jiusheng Chen, Daxin Jiang, Jiancheng Lv, Ruofei Zhang, Winnie Wu, Ming Zhou, Nan Duan
| Challenge: | Multi-task benchmarks focus on a range of Natural Language Understanding (NLU) tasks without considering the Natural Language Generation (NLG) models. |
| Approach: | They propose a multi-task benchmark for evaluating the generalization capabilities of NLG models across eight language generation tasks. |
| Outcome: | The proposed benchmarks are based on GLUE and Su-perGLUE for English and several other languages. |
Act as you think: Reinforcing Consistent Reasoning in Medical Visual Question Answering (2026.acl-long)
Copied to clipboard
Songtao Jiang, Yuan Wang, Ruizhe Chen, Yan Zhang, Ruilin Luo, Bohan Lei, Yeying Jin, Sibo Song, ZhiBo Yang, Jimeng Sun, Jian Wu, Zuozhu Liu
| Challenge: | Recent advances have improved the accuracy of medical visual question answering (Med-VQA) however, the high stakes nature of the medical domain has precipitated a shift towards interpretability and transparency of reasoning processes. |
| Approach: | They propose a reinforcement learning from verifiable rewards framework that rewards internal consistency and logical coherence. |
| Outcome: | The proposed framework rewards internal consistency and logical coherence, and is highly versatile, the authors show. |
Modeling Personalization in Continuous Space for Response Generation via Augmented Wasserstein Autoencoders (D19-1)
Copied to clipboard
| Challenge: | Existing work on variableal autoencoders and waterstein autoencoding models has shown significant progress in open-domain response generation. |
| Approach: | They propose to embed user-level and utterance-level information into two multimodal distributions and combine them into a mixed distribution. |
| Outcome: | The proposed model outperforms state-of-the-art models on a large-scale real-world dataset. |
Towards Effective and Efficient Continual Pre-training of Large Language Models (2025.acl-long)
Copied to clipboard
Jie Chen, Zhipeng Chen, Jiapeng Wang, Kun Zhou, Yutao Zhu, Jinhao Jiang, Yingqian Min, Xin Zhao, Zhicheng Dou, Jiaxin Mao, Yankai Lin, Ruihua Song, Jun Xu, Xu Chen, Rui Yan, Zhewei Wei, Di Hu, Wenbing Huang, Ji-Rong Wen
| Challenge: | Continual pre-training (CPT) has been an important approach for adapting language models to specific domains or tasks. |
| Approach: | They propose a Continual pre-training method that can greatly improve Chinese language ability and scientific reasoning ability of LLMs. |
| Outcome: | The proposed method can greatly improve Chinese language ability and scientific reasoning ability of LLMs. |
Reasoning While Asking: Transforming Reasoning Large Language Models from Passive Solvers to Proactive Inquirers (2026.acl-long)
Copied to clipboard
| Challenge: | Existing reasoning-oriented LLMs lack a blind self-thinking paradigm . current models fail to recognize when their reasoning is underinformed or based on ambiguous user instructions . |
| Approach: | They propose a new reasoning paradigm that transforms LLMs into proactive inquirers that interleave reasoning with clarification. |
| Outcome: | The proposed model outperforms baseline models on mathematical reasoning, code generation, and document editing. |
RikiNet: Reading Wikipedia Pages for Natural Question Answering (2020.acl-main)
Copied to clipboard
| Challenge: | Using Wikipedia pages to answer open-domain questions remains challenging in natural language understanding. |
| Approach: | They propose a model which reads Wikipedia pages for natural question answering . it uses a dynamic paragraph dual-attention reader and a cascaded answer predictor . |
| Outcome: | The proposed model outperforms the human model on the Natural Questions dataset . it achieves 74.3 F1 and 57.9 F1 on long-answer and short-answer tasks . |
Task-Related In-Context Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Standard in-context learning assumes identical output spaces between test and retrieval datasets . however, in practice, these datasets can be fully aligned, partially alignes, or fully disjoint in label space . |
| Approach: | They propose a framework for in-context learning under output-space mismatch . they identify demonstrations relevant to the test label space via a Bayesian probabilistic criterion . |
| Outcome: | The proposed framework achieves state-of-the-art results across three LLMs, three task types, and four datasets. |
Seamlessly Integrating Factual Information and Social Content with Persuasive Dialogue (2022.aacl-main)
Copied to clipboard
| Challenge: | Persuasive dialogue systems are designed for chatbots to communicate with and influence users with specific goals. |
| Approach: | They propose a modular dialogue system framework that integrates factual information and social content into persuasive dialogues. |
| Outcome: | The proposed framework is generalizable to any dialogue tasks that have mixed social and task contents. |
An Analysis and Mitigation of the Reversal Curse (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent research observes a phenomenon in large language models called the "reversal curse" when dealing with two entities, LLMs excel in handling sequences in the form of "aRb" but when asked "who is Mary Lee Pfeiffer's son?" the LLM exhibits considerable confusion and fails to provide a as the answer . |
| Approach: | They conduct the first-ever study of how the reversal curse happens in large language models . they find that LLMs excel in handling sequences in the form of "aRb" but struggle to provide a satisfactory answer when asked "who is Mary Lee Pfeiffer's son?" |
| Outcome: | The proposed study shows that the reversal curse can stem from specific training objectives . the study also shows that a reverse query can be difficult to understand . |
Controllable Dialogue Simulation with In-context Learning (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to generate annotated dialogues require crowdsourcing, which is expensive and time-consuming. |
| Approach: | They propose a dialogue simulation method based on large language model in-context learning that generates new dialogues and annotations in a controllable way. |
| Outcome: | The proposed method can expand a small set of dialogue data with minimum or zero human involvement and parameter update. |
CHEER: Centrality-aware High-order Event Reasoning Network for Document-level Event Causality Identification (2023.acl-long)
Copied to clipboard
| Challenge: | Recent studies focus on building a document-level graph for cross-sentence reasoning, but ignore important causal structures. |
| Approach: | They propose a document-level event causality identification model which annotates central events and incorporates event centrality information into the reasoning network. |
| Outcome: | The proposed model performs high-order reasoning while considering event centrality. |
FedMKT: Federated Mutual Knowledge Transfer for Large and Small Language Models (2025.coling-main)
Copied to clipboard
| Challenge: | Recent research in large language models (LLMs) has focused on enabling clients to fine-tune their locally deployed homogeneous LLMs collaboratively or on transferring knowledge from server-based LLM to small language models at downstream clients. |
| Approach: | They propose a parameter-efficient federated mutual knowledge transfer framework for large and small language models that allows for token alignment and selective knowledge transfer between client-side LLMs and a server-side SLM. |
| Outcome: | The proposed framework enhances the performance of both LLMs and SLMs with clients' unique domain insights while preserving the server's LLM and client's unique domain insight. |
MUSEG: Reinforcing Video Temporal Understanding via Timestamp-Aware Multi-Segment Grounding (2026.acl-long)
Copied to clipboard
Fuwen Luo, Shengfeng Lou, Chi Chen, Ziyue Wang, Chenliang Li, Weizhou Shen, Jiyue Guo, Peng Li, Ming Yan, Ji Zhang, Fei Huang, Yang Liu
| Challenge: | Existing methods for MLLMs struggle with fine-grained temporal reasoning . despite advances in video understanding, current methods struggle with time-sensitive tasks . |
| Approach: | They propose a time-stamp-aware multi-segment grounding method that enhances temporal understanding by introducing timestamps. |
| Outcome: | The proposed method outperforms existing methods on time-sensitive tasks and generalizes well across diverse temporal understanding scenarios. |
RankCSE: Unsupervised Sentence Representations Learning via Learning to Rank (2023.acl-long)
Copied to clipboard
Jiduan Liu, Jiahao Liu, Qifan Wang, Jingang Wang, Wei Wu, Yunsen Xian, Dongyan Zhao, Kai Chen, Rui Yan
| Challenge: | Unsupervised sentence representation learning is one of the fundamental problems in natural language processing . contrastive learning methods fail to capture fine-grained ranking information among the sentences . |
| Approach: | They propose a novel approach for unsupervised sentence representation learning that integrates ranking consistency and ranking distillation with contrastive learning into a unified framework. |
| Outcome: | The proposed approach performs better over state-of-the-art models on STS and TR tasks. |
Keyphrase Generation with Correlation Constraints (D18-1)
Copied to clipboard
| Challenge: | Existing methods for keyphrase generation ignore correlation among keyphrases, resulting in duplication and coverage issues. |
| Approach: | They propose a new sequence-to-sequence architecture for keyphrase generation that captures correlation among keyphrases by preceding phrases to eliminate duplicate phrases and improve result coherence. |
| Outcome: | The proposed model outperforms the state-of-the-art method on benchmark datasets in terms of accuracy and diversity. |
FrontCoder: Scaling Visual Fidelity in Front-End Code Generation (2026.findings-acl)
Copied to clipboard
Jun Feng, Jian Yang, Wei Zhang, Jing Wang, Keyi Chen, Xiaokun Yang, Weicheng Gu, Yihang Lou, Yan Bai, Xianglong Liu
| Challenge: | Existing work on front-end code generation fails to provide visual fidelity and rendering quality for front- end developers. |
| Approach: | They propose a three-stage pipeline to enhance front-end code generation capabilities in LLMs . they use synthetic data, quality-controlled supervised fine-tuning, and reinforcement learning . |
| Outcome: | The proposed model achieves competitive performance with frontier models while maintaining generation efficiency. |
ASCEND: A Spontaneous Chinese-English Dataset for Code-switching in Multi-turn Conversation (2022.lrec-1)
Copied to clipboard
Holy Lovenia, Samuel Cahyawijaya, Genta Winata, Peng Xu, Yan Xu, Zihan Liu, Rita Frieske, Tiezheng Yu, Wenliang Dai, Elham J. Barezi, Qifeng Chen, Xiaojuan Ma, Bertram Shi, Pascale Fung
| Challenge: | Code-switching is a speech phenomenon occurring when a speaker switches language during a conversation. |
| Approach: | They propose to collect Mandarin Chinese-English code-switching corpus from read speech rather than spontaneous speech to address this phenomenon. |
| Outcome: | ASCEND consists of 10.62 hours of clean speech, collected from 23 bilingual speakers of Chinese and English. |
Clinical-Coder: Assigning Interpretable ICD-10 Codes to Chinese Clinical Notes (2020.acl-demos)
Copied to clipboard
| Challenge: | Existing methods of automatic coding prediction have been successful, but the interpretability of predicted codes is a challenge. |
| Approach: | They propose an online system that can predict ICD codes for Chinese clinical notes by using a Dilated Convolutional Attention network with N-gram Matching mechanism. |
| Outcome: | The proposed system is able to provide supporting information in clinical decision making. |
From Long to Lean: Performance-aware and Adaptive Chain-of-Thought Compression via Multi-round Refinement (2025.emnlp-main)
Copied to clipboard
| Challenge: | Chain-of-Thought reasoning introduces significant inference latency due to its verbosity. |
| Approach: | They propose a framework that leverages token elasticity phenomenon to progressively compress CoTs via multiround refinement. |
| Outcome: | The proposed method achieves an average accuracy improvement of 5.6% over state-of-the-art baselines while reducing CoT length by an average of 47 tokens and significantly lowering latency. |
Contrastive Instruction Tuning (2024.findings-acl)
Copied to clipboard
| Challenge: | Current LLMs exhibit limited robustness to unseen instructions, generating inconsistent outputs when the same instruction is phrased with slightly varied forms or language styles. |
| Approach: | They propose a method which maximizes the similarity between the hidden representations of semantically equivalent instruction-instance pairs while minimizing the similarities between semantically different ones. |
| Outcome: | Experiments on the PromptBench benchmark show that Contrastive Instruction Tuning improves LLMs’ robustness to unseen instructions with variations across character, word, sentence, and semantic levels by +2.5% in accuracy. |
CFBench: A Comprehensive Constraints-Following Benchmark for LLMs (2025.acl-long)
Copied to clipboard
Tao Zhang, ChengLIn Zhu, Yanjun Shen, Wenjing Luo, Yan Zhang, Hao Liang, Tao Zhang, Fan Yang, Mingan Lin, Yujing Qiao, Weipeng Chen, Bin Cui, Wentao Zhang, Zenan Zhou
| Challenge: | Existing evaluations of Large Language Models (LLMs) focus on fragmented constraints or narrow scenarios, but they overlook the comprehensiveness and authenticity of constraints from the user’s perspective. |
| Approach: | They propose a Chinese Comprehensive Constraints Following Benchmark for LLMs that compiles constraints from real-world instructions and constructs a systematic framework for constraint types. |
| Outcome: | The proposed framework integrates multi-dimensional assessment criteria with requirement prioritization, covering various perspectives of constraints, instructions, and requirement fulfillment. |
Towards Efficient CoT Distillation: Self-Guided Rationale Selector for Better Performance with Fewer Rationales (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing work on rationale quality underestimates the importance of CoT distillation, focusing primarily on data quantity, which may result in transferring noisy or incorrect information to the student model. |
| Approach: | They propose a method which can discern and select high quality rationales for distillation and a Rationale Difficulty metric to measure the ability of the student model to generate the correct answer under a given rationale. |
| Outcome: | The proposed method achieves 4.6% accuracy improvement over baseline data on seven datasets over three tasks, controlling accuracy, diversity, and difficulty. |
Uncovering and Categorizing Social Biases in Text-to-SQL (2023.acl-long)
Copied to clipboard
| Challenge: | Existing Text-to-SQL models are trained on clean, neutral datasets, such as Spider and WikiSQl, but these models contain social bias at different rates. |
| Approach: | They propose to use data to map natural language utterances to SQL queries. |
| Outcome: | The proposed model can contain social bias at different rates in the downstream Text-to-SQL task. |
MPII: Multi-Level Mutual Promotion for Inference and Interpretation (2022.acl-long)
Copied to clipboard
| Challenge: | Existing methods for providing interpretations provide human-unfriendly interpretations, resulting in sub-optimal performance. |
| Approach: | They propose a multi-level Mutual Promotion mechanism for self-evolved inference and sentence-level interpretation that integrates inference with interpretation in an autoregressive manner. |
| Outcome: | The proposed approach outperforms baseline models on NLI and CQA tasks for both inference performance and interpretation quality. |
AMPO: Automatic Multi-Branched Prompt Optimization (2024.emnlp-main)
Copied to clipboard
Sheng Yang, Yurong Wu, Yan Gao, Zineng Zhou, Bin Zhu, Xiaodi Sun, Jian-Guang Lou, Zhiming Ding, Anbang Hu, Yuan Fang, Yunsong Li, Junyan Chen, Linjun Yang
| Challenge: | Existing prompt engineering techniques are limited to producing single flow instructions, struggling with handling diverse patterns. |
| Approach: | They propose an automatic prompt optimization method that iteratively develops a multi-branched prompt using failure cases as feedback. |
| Outcome: | The proposed method achieves the best results across five tasks and demonstrates significant optimization efficiency due to adoption of a minimal search strategy. |
XL-NBT: A Cross-lingual Neural Belief Tracking Framework (D18-1)
Copied to clipboard
| Challenge: | a multi-lingual approach to training dialog systems is expensive and tedious, but it can be useful for cross-lingual support. |
| Approach: | They propose to annotate data for multiple languages and train a multi-lingual dialog system for each language. |
| Outcome: | The proposed framework bypasses the expensive human annotation and achieves promising results. |
ESC-Eval: Evaluating Emotion Support Conversations in Large Language Models (2024.emnlp-main)
Copied to clipboard
Haiquan Zhao, Lingyu Li, Shisong Chen, Shuqi Kong, Jiaan Wang, Kexin Huang, Tianle Gu, Yixu Wang, Jian Wang, Liang Dandan, Zhixu Li, Yan Teng, Yanghua Xiao, Yingchun Wang
| Challenge: | Emotion Support Conversation (ESC) is a crucial application for reducing stress and providing emotional guidance. |
| Approach: | They re-organize 2,801 role-playing cards to define roles of role-players . they train a specific role- playing model called ESC-Role which behaves more like a confused person than GPT-4 . |
| Outcome: | The proposed model behaves more like a confused person than GPT-4, and the model performs better than GPLs. |
Generating Radiology Reports via Memory-driven Transformer (2020.emnlp-main)
Copied to clipboard
| Challenge: | Medical imaging reports are time-consuming and can be error-prone for inexperienced radiologists. |
| Approach: | They propose to generate radiology reports with memory-driven Transformer using relational memory and memory-based conditional layer normalization. |
| Outcome: | The proposed method outperforms existing models on IU X-Ray and MIMIC-CXR . it generates long reports with medical terms and meaningful image-text attention mappings . |
GRPO-Guided Modality Selection Enhanced LoRA-Tuned LLMs for Multimodal Emotion Recognition (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Multimodal emotion recognition in conversation (MERC) aims to identify speakers’ emotional states by utilizing text, audio, and visual modalities. |
| Approach: | They propose an adaptive modality selection framework for multimodal emotion recognition in conversation that integrates all available modalities into one . |
| Outcome: | The proposed framework outperforms existing methods on multimodal dialogue datasets and is available at https://github.com/youflyaway/Modality-Selection-Enhanced-LoRA-Tuned-LLMs. |
Thinking Before Running! Efficient Code Generation with Thorough Exploration and Optimal Refinement (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent research indicates that large language models (LLMs) have demonstrated remark-able capabilities in various programming-related domains, such as code generation and code refinement. |
| Approach: | They propose a framework that combines exploration with refinement to reduce test-time computation overhead. |
| Outcome: | The proposed framework outperforms SOTA and AgentCoder on humanEval and MBPP benchmarks while reducing test-time computation overhead and scalability. |
Fin-STAR: Structure-as-Semantics to Resolve Implicitness in Financial Retrieval (2026.findings-acl)
Copied to clipboard
Yu Zou, Yan Chen, Lida He, Qi Zhou, Xiaorui Zhou, Aixi Zhong, Yi Wang, Wei Li, Qingyu Wang, Jiatao Li, Wei Gong, Jialei Zeng, Jingmei Zhao, Ke Jiang, Qing Li
| Challenge: | Existing Retrieval-Augmented Generation systems treat structure as a physical navigational skeleton rather than intrinsic semantic knowledge. |
| Approach: | They propose a framework that redefining hierarchy as intrinsic semantics and uses snippets to enrich hierarchical lineage. |
| Outcome: | The proposed framework outperforms state-of-the-art hierarchical and graph-based benchmarks on FinTierQA Gold. |
When Personalization Tricks Detectors: The Feature-Inversion Trap in Machine-Generated Text Detection (2026.acl-long)
Copied to clipboard
Lang Gao, Xuhui Li, Chenxi Wang, Mingzhe Li, Wei Liu, Zirui Song, Jinghui Zhang, Rui Yan, Preslav Nakov, Xiuying Chen
| Challenge: | Personalized MGT detection remains largely underexplored due to personalization challenges . large language models (LLMs) can imitate personal writing styles, but they can generate fake news and misinformation. |
| Approach: | They propose a benchmark to evaluate detector robustness under personalization . they attribute this limitation to a feature-inversion trap that flips the effect in personalized contexts . |
| Outcome: | The proposed framework predicts detector robustness under personalization with an 85% correlation to actual results. |
Demystify the Role of Memory in Machine Learning Engineering Agents (2026.findings-acl)
Copied to clipboard
Xinyu Zhao, Junpeng Wang, Yuzhong Chen, Menghai Pan, Chin-Chia Michael Yeh, Jiarui Sun, Yan Zheng, Mahashweta Das, Tianlong Chen
| Challenge: | Unlike short, reactive exchanges, MLE agents solve tasks through cycles of experimentation and improvement where past errors can inform future success. |
| Approach: | They propose a dynamic coding memory that captures and reuses debugging experiences and integrates it into two representative agent paradigms. |
| Outcome: | The proposed agent model captures and reuses debugging experiences and integrates it into two agent paradigms. |
Do Large Language Models have Problem-Solving Capability under Incomplete Information Scenarios? (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing games such as "Who is undercover" are subjective and difficult to evaluate . |
| Approach: | They propose a game called BrainKing that evaluates LLMs' problem-solving capability under incomplete information scenarios. |
| Outcome: | The proposed game requires LLMs to identify target entities with limited yes-or-no questions and potential misleading answers. |
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. |
MIND: Towards Immersive Psychological Healing with Multi-Agent Inner Dialogue (2025.findings-emnlp)
Copied to clipboard
Yujia Chen, Changsong Li, Yiming Wang, Tianjie Ju, Qingqing Xiao, Nan Zhang, Zifan Kong, Peng Wang, Binyu Yan
| Challenge: | Mental health issues are worsening in today’s competitive society, such as depression and anxiety. |
| Approach: | They propose a multi-agent inner dialogue paradigm that provides more immersive psychological healing environments. |
| Outcome: | The proposed paradigm provides more immersive psychological healing environments. |
Perovskite-LLM: Knowledge-Enhanced Large Language Models for Perovskite Solar Cell Research (2025.findings-emnlp)
Copied to clipboard
Xiang Liu, Penglei Sun, Shuyan Chen, Longhan Zhang, Peijie Dong, Huajie You, Yongqi Zhang, Chang Yan, Xiaowen Chu, Tong-yi Zhang
| Challenge: | a rapid advancement of perovskite solar cells has led to an exponential growth in research publications. |
| Approach: | They propose a knowledge-enhanced system for perovskite solar cells that integrates three key components. |
| Outcome: | The proposed system outperforms existing models in domain-specific knowledge retrieval and scientific reasoning tasks. |
Vector Calligrapher: Generating Scalable Vector Graphics via Structured Linguistic Supervision (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to generate SVG-based fonts struggle with semantic ambiguity and inefficiency . edward mcginley: generic text tokenizers fragment coordinate-dense SVG XML into excessively long sequences . |
| Approach: | They propose a system that treats SVG generation as a conditional language modeling task . they propose linguistic supervision framework that decomposes typographic style into interpretable linguistic dimensions . |
| Outcome: | The proposed system improves CLIP score by +23% while reducing geometric error by 48% and boosts generation efficiency by 18% Command-per-Token (C/T) ratio. |
VMSMO: Learning to Generate Multimodal Summary for Video-based News Articles (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies show that multimodal news can significantly improve users' sense of satisfaction for informativeness. |
| Approach: | They propose a task of Video-based Multimodal Summarization with Multimodal Output to solve this problem. |
| Outcome: | The proposed method can generate multimodal summaries with a single input . it can model the temporal dependency of video with semantic meaning of article . |
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. |
MirrorQA: Benchmarking Multimodal LLMs on Mirror-Orientation Reasoning (2026.acl-long)
Copied to clipboard
| Challenge: | Multimodal large language models (MLLMs) have achieved remarkable progress in recent years, yet their ability to perform left–right reasoning in mirror contexts remains underexplored. |
| Approach: | They propose a benchmark to evaluate MLLMs' ability to distinguish left from right from a subject-centered perspective. |
| Outcome: | The proposed benchmarks show that even the best performing models achieve only 65.40% accuracy, far below the 99.28% accuracy of humans. |
Enhancing Chain-of-Thought Reasoning with Critical Representation Fine-tuning (2025.acl-long)
Copied to clipboard
Chenxi Huang, Shaotian Yan, Liang Xie, Binbin Lin, Sinan Fan, Yue Xin, Deng Cai, Chen Shen, Jieping Ye
| Challenge: | Representation Fine-tuning (ReFT) is a proposed method for improving parameter efficiency . however, it yields suboptimal performance, as fixed-position representations have uncertain impact on outputs . |
| Approach: | They propose a method that fine-tunes critical representations in a low-rank linear subspace while freezing the base model. |
| Outcome: | The proposed method improves accuracy of LLaMA-2-7B and ReFT by 18.2 and 3.8 on GSM8K. |
A Survey of Reinforcement Learning for Large Language Models under Data Scarcity: Challenges and Solutions (2026.acl-long)
Copied to clipboard
Zhiyin Yu, Yuchen Mou, Juncheng Yan, Junyu Luo, Chunchun Chen, Xing Wei, Yunhui Liu, Hongru Sun, Yuxing Zhang, Jun Xu, Yatao Bian, Ming Zhang, Wei Ye, Tieke He, Jie Yang, Guanjie Zheng, Zhonghai Wu, Bo Zhang, Lei Bai, Xiao Luo
| Challenge: | Existing research on reinforcement learning for LLMs under data scarcity has not been unified. |
| Approach: | They propose a top-up hierarchical framework built around three complementary perspectives: data-centric, training-centric and framework-centric. |
| Outcome: | The proposed framework provides a clear conceptual foundation for understanding the design space of data-efficient RL for large language models and to guide researchers working in this emerging area. |
Empirical Analysis of Decoding Biases in Masked Diffusion Models (2026.acl-long)
Copied to clipboard
Pengcheng Huang, Tianming Liu, Zhenghao Liu, Yukun Yan, Shuo Wang, Tong Xiao, Zulong Chen, Maosong Sun
| Challenge: | Existing MDMs employ uncertainty-based decoding strategies that limit their reasoning ability and ultimately degrade generation quality. |
| Approach: | They propose a framework that regularizes uncertainty-based decoding by incorporating two complementary priors to shape global decoding trajectories and promote content informativeness. |
| Outcome: | The proposed framework outperforms existing decoding strategies by more than 7% while achieving comparable performance to autoregressive models of similar parameter scales. |
Analyzing and Evaluating Faithfulness in Dialogue Summarization (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies on faithfulness of text summarization have not been conducted on abstractive summarizing. |
| Approach: | They propose a method to evaluate faithfulness of dialogue summarization models by multi-choice questions. |
| Outcome: | The proposed method can facilitate the development of dialogue summarization systems. |
How to Write Summaries with Patterns? Learning towards Abstractive Summarization through Prototype Editing (D19-1)
Copied to clipboard
| Challenge: | Extensive experiments on a large-scale real-world text summarization dataset show that PESG achieves the state-of-the-art performance in terms of both automatic metrics and human evaluations. |
| Approach: | They propose a model that learns summary patterns and prototype facts from a prototype document . they use a fact checker to estimate mutual information between the input document and generated summary . |
| Outcome: | Experiments on a large-scale real-world text summarization dataset show that PESG achieves state-of-the-art performance. |
CERD: A Comprehensive Chinese Rhetoric Dataset for Rhetorical Understanding and Generation in Essays (2024.findings-emnlp)
Copied to clipboard
Nuowei Liu, Xinhao Chen, Hongyi Wu, Changzhi Sun, Man Lan, Yuanbin Wu, Xiaopeng Bai, Shaoguang Mao, Yan Xia
| Challenge: | Existing rhetorical understanding and generation datasets focus on single coarse-grained categories or fine-grain categories, neglecting the intrinsic connections between different rhetorical devices. |
| Approach: | They propose a Chinese Essay Rhetoric Dataset with four coarse-grained categories . they propose to treat these categories as separate sub-tasks, thereby improving writing skills . |
| Outcome: | The proposed dataset improves the author's writing proficiency and language usage skills by recognizing and generating rhetorical sentences under given conditions. |
Long-Chain Reasoning Distillation via Adaptive Prefix Alignment (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable reasoning capabilities, especially in solving complex mathematical problems. |
| Approach: | They propose a framework that exploits teacher CoTs for distillation through adaptive prefix alignment. |
| Outcome: | The proposed framework outperforms baseline models on multiple mathematical reasoning benchmarks by over 3%. |
MODE-LSTM: A Parameter-efficient Recurrent Network with Multi-Scale for Sentence Classification (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing models for sentence classification use linear convolution, which may not be sufficient to model the non-consecutive dependency of the phrase and may overfit the sequential information. |
| Approach: | They propose a model that extracts multi-scale n-gram features for understanding the semantic meaning of sentences by some key-phrases located at different positions. |
| Outcome: | The proposed model outperforms existing models on eight benchmark datasets and is competitive against state-of-the-art models. |
Lost in the Context: Insufficient and Distracted Attention to Contexts in Preference Modeling (2025.acl-long)
Copied to clipboard
Shihan Dou, Jiayi Chen, Chenhao Huang, Feng Chen, Wei Chengzhi, Huiyuan Zheng, Shichun Liu, Yan Liu, Chenxiao Liu, Chao Xin, Lin Yan, Zongzhang Zhang, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing reward models concatenate contexts and responses, but they often ignore crucial segments of the context that are important for evaluating the response quality. |
| Approach: | They propose a reward model that evaluates the response quality based on a given context and assigns a rewards reward. |
| Outcome: | The proposed framework significantly improves preference modeling by increasing attention to relevant information within the context and achieves better generalizability. |
Lang2Act: Fine-Grained Visual Reasoning through Self-Emergent Linguistic Toolchains (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing frameworks depend on rigid, pre-defined external tools to extend perceptual capabilities of VLMs. |
| Approach: | They propose a framework that leverages self-emergent linguistic toolchains to enhance visual perception and reasoning. |
| Outcome: | The proposed framework improves the visual perception capabilities of large language models by incorporating external visual documents to address a given query. |
SafeEraser: Enhancing Safety in Multimodal Large Language Models through Multimodal Machine Unlearning (2025.findings-acl)
Copied to clipboard
Junkai Chen, Zhijie Deng, Kening Zheng, Yibo Yan, Shuliang Liu, PeiJun Wu, Peijie Jiang, Jia Liu, Xuming Hu
| Challenge: | Existing methods for MU forget quality and model utility are not fully explored for safety in MLLMs. |
| Approach: | They propose a safety unlearning benchmark for MLLMs to measure over-forgetting . they propose MU methods to forget quality and model utility . |
| Outcome: | The proposed method reduces over-forgetting by 79.5% while maintaining forget quality and model utility. |
SCALE: Synergized Collaboration of Asymmetric Language Translation Engines (2024.findings-acl)
Copied to clipboard
| Challenge: | In this paper, we introduce SCALE, a collaborative framework that connects a compact Specialized Translation Model (STM) and a general-purpose Large Language Model (LLM) as one unified translation engine. |
| Approach: | They propose a collaborative framework that connects a Specialized Translation Model (STM) and a general-purpose Large Language Model (LLM) as one unified translation engine. |
| Outcome: | The proposed framework outperforms both LLMs and supervised models in high-resource or challenging low-resourced settings. |
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. |
Robust Natural Language Understanding with Residual Attention Debiasing (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing ensemble-based debiasing methods do not address unintended dataset biases . attention plays a crucial role in providing robust prediction in NLU models . |
| Approach: | They propose an end-to-end debiasing method that mitigates unintended biases from attention. |
| Outcome: | The proposed method improves the OOD performance of BERT-based models on three benchmarks. |
LMR-BENCH: Evaluating LLM Agent’s Ability on Reproducing Language Modeling Research (2025.emnlp-main)
Copied to clipboard
Shuo Yan, Ruochen Li, Ziming Luo, Zimu Wang, Daoyang Li, Liqiang Jing, Kaiyu He, Peilin Wu, Juntong Ni, George Michalopoulos, Yue Zhang, Ziyang Zhang, Mian Zhang, Zhiyu Chen, Xinya Du
| Challenge: | Large language model (LLM) agents have demonstrated remarkable potential in advancing scientific discovery, but their capability in reproducing code from research papers remains underexplored. |
| Approach: | They propose to evaluate LLM agents' ability to reproduce scientific research papers by analyzing code reproduction tasks from 23 research papers published in top-tier NLP venues. |
| Outcome: | The proposed benchmark systematically evaluates the capability of large language model (LLM) agents on code reproduction from Language Modeling Research. |
CoLLiE: Collaborative Training of Large Language Models in an Efficient Way (2023.emnlp-demo)
Copied to clipboard
Kai Lv, Shuo Zhang, Tianle Gu, Shuhao Xing, Jiawei Hong, Keyu Chen, Xiaoran Liu, Yuqing Yang, Honglin Guo, Tengxiao Liu, Yu Sun, Qipeng Guo, Hang Yan, Xipeng Qiu
| Challenge: | Large language models (LLMs) are increasingly pivotal in a wide range of tasks . however, the resources required for training these models necessitate efficient solutions . |
| Approach: | They propose a library that facilitates collaborative training of large language models . they use 3D parallelism, parameter-efficient fine-tuning methods and optimizers . |
| Outcome: | The proposed library has proven superior training efficiency in comparison with prevalent solutions in pre-training and fine-tuning scenarios. |
DuQM: A Chinese Dataset of Linguistically Perturbed Natural Questions for Evaluating the Robustness of Question Matching Models (2022.emnlp-main)
Copied to clipboard
| Challenge: | a comprehensive evaluation of QM models should be conducted on natural texts, not on artificial adversarial examples . ral models are often not robust to adversarials, which means they predict unexpected outputs . |
| Approach: | They use a Chinese dataset to evaluate the robustness of QM models . they show that the effect of artificial adversarial examples does not work on natural texts . |
| Outcome: | The proposed model is more robust than other models on natural questions with 32 linguistic perturbations. |
SportQA: A Benchmark for Sports Understanding in Large Language Models (2024.naacl-long)
Copied to clipboard
Haotian Xia, Zhengbang Yang, Yuqing Wang, Rhys Tracy, Yun Zhao, Dongdong Huang, Zezhi Chen, Yan Zhu, Yuan-fang Wang, Weining Shen
| Challenge: | SportQA is a benchmark specifically designed for evaluating Large Language Models (LLMs) sports knowledge is characterized by its fast pace, variety of types, abundance of strategies, and rich player narratives . |
| Approach: | They propose a benchmark specifically designed for evaluating Large Language Models in the context of sports understanding. |
| Outcome: | The proposed benchmark aims to bridge the gap between existing and specialized benchmarks in sports understanding. |
Bridging the Gap between Pre-Training and Fine-Tuning for Commonsense Generation (2023.findings-eacl)
Copied to clipboard
| Challenge: | Existing methods focusing on this task usually concatenate the concatened concepts words as the inputs of a pre-trained language model (PLM) however, in pre-training, the input is often corrupted sentences with correct word order. |
| Approach: | They propose a two-stage framework to improve the ability of pre-trained language models to deal with masked sentences with incorrect word order and a special token to make the input distribution more similar to the one used in pre-training. |
| Outcome: | The proposed method is able to generate a sentence containing all given concepts and correctly describe the relations between concepts. |
A Survey of Inductive Reasoning for Large Language Models (2026.acl-long)
Copied to clipboard
Kedi Chen, Dezhao Ruan, Yuhao Dan, Yaoting Wang, Siyu Yan, Xuecheng Wu, Yinqi Zhang, Qin Chen, Jie Zhou, Liang He, Biqing Qi, Linyang Li, Qipeng Guo, Xiaoming Shi, Wei Zhang
| Challenge: | Inductive reasoning is an important task for large language models (LLMs). |
| Approach: | They propose a survey of inductive reasoning for large language models . they categorize methods into three main areas: post-training enhancement, test-time exploration, and data augmentation. |
| Outcome: | The proposed method improves inductive reasoning in large language models. |
ProTOD: Proactive Task-oriented Dialogue System Based on Large Language Model (2025.coling-main)
Copied to clipboard
| Challenge: | Existing task-oriented dialogue systems engage with users in a reactive manner, relying on a basic single-query mechanism and employing passive policy planning. |
| Approach: | They propose a novel LLM-based proactive TOD framework to improve system proactivity and goal completion. |
| Outcome: | The proposed framework improves system proactivity and goal completion rates by 10% while enhancing proactive engagement. |
Revisiting Cross-Lingual Summarization: A Corpus-based Study and A New Benchmark with Improved Annotation (2023.acl-long)
Copied to clipboard
Yulong Chen, Huajian Zhang, Yijie Zhou, Xuefeng Bai, Yueguan Wang, Ming Zhong, Jianhao Yan, Yafu Li, Judy Li, Xianchao Zhu, Yue Zhang
| Challenge: | Existing work on cross-lingual summarization (CLS) does not consider crosslingual sources for summarizing. |
| Approach: | They propose a cross-lingual conversation summarization benchmark that explicitly considers source context. |
| Outcome: | The proposed method surpasses baselines on ConvSumX and 3 widely-used manual annotations. |
Reefknot: A Comprehensive Benchmark for Relation Hallucination Evaluation, Analysis and Mitigation in Multimodal Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing research focuses on object-level or attribute-level hallucinations, neglecting the more complex relation hallucinosities. |
| Approach: | They propose a comprehensive benchmark targeting relation hallucinations comprising over 20,000 real-world samples and a confidence-based mitigation strategy which reduces the halluciation rate by an average of 9.75% across three datasets. |
| Outcome: | The proposed approach reduces the hallucination rate by an average of 9.75% across three datasets, including Reefknot. |
Deep-Reporter: Deep Research for Grounded Multimodal Long-Form Generation (2026.acl-long)
Copied to clipboard
Fangda Ye, Kuicai Dong, Xie Zhifei, Yuxin Hu, Yihang Yin, Shurui Huang, Shikai Dong, Chen Zhang, Jianzhu Bao, Shuicheng Yan
| Challenge: | Recent agentic search frameworks are text-centric, overlooking multimodal evidence . a pressing task is multimodal long-form generation, a new paper argues . |
| Approach: | They propose a unified agentic framework for grounded multimodal long-form generation. |
| Outcome: | The proposed framework is based on a unified agentic framework for grounded multimodal long-form generation. |
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. |
ZigZagKV: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods to accelerate inference of Large Language models (LLMs) are limited in their ability to retain key tokens as input length increases. |
| Approach: | They propose a method that leverages layer uncertainty to allocate budget size for each layer to reduce memory usage. |
| Outcome: | The proposed method reduces memory usage of the KV caches to only 20% when compared to full KV inference while achieving nearly lossless performance. |
MCP-Flow: Facilitating LLM Agents to Master Real-World, Diverse and Scaling MCP Tools (2026.acl-long)
Copied to clipboard
WenHao Wang, Peizhi Niu, Zhao Xu, Zhaoyu Chen, Jian Du, Yaxin Du, Xianghe Pang, Keduan Huang, Yanfeng Wang, Qiang Yan, Siheng Chen
| Challenge: | Existing research on Large Language Models (LLMs) relies on few servers and lacks training support. |
| Approach: | They propose a web-agent-driven pipeline for large-scale server discovery, data synthesis, and model training that collects and filters data from 1166 servers and 11536 tools. |
| Outcome: | Empirical evidence shows that MCP-Flow generates higher quality instruction-function call pairs and higher agentic task performance than previous work. |
Unlocking the Effectiveness of LoRA-FP for Seamless Transfer Implantation of Fingerprints in Downstream Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | lightweight plug-and-play framework that encodes backdoor fingerprints into LoRA adapters . |
| Approach: | proposed framework encodes backdoor fingerprints into LoRA adapters via constrained fine-tuning . enables seamless fingerprint transplantation through parameter fusion, eliminating full-parameter updates while maintaining integrity. |
| Outcome: | The proposed framework achieves superior robustness against various scenarios while reducing computational overhead compared to traditional approaches. |
Prune as You Generate: Online Rollout Pruning for Faster and Better RLVR (2026.acl-long)
Copied to clipboard
Haobo Xu, Sirui Chen, Ruizhong Qiu, Yuchen Yan, Chen Luo, Monica Xiao Cheng, Jingrui He, Hanghang Tong
| Challenge: | Reinforcement Learning with Verifiable Rewards (RLVR) has improved reasoning capabilities of Large Language Models (LLMs). |
| Approach: | They propose an online pruning method that prunes rollouts while steering correct ones to enhance learning signals. |
| Outcome: | The proposed method improves average accuracy by +2.30 to +2.99 across GRPO and DAPO on Qwen-3 and LLaMA-3.2 models. |
SAS: Dialogue State Tracking via Slot Attention and Slot Information Sharing (2020.acl-main)
Copied to clipboard
| Challenge: | Existing models with excessive information are inefficient and costly . |
| Approach: | They propose to integrate a Dialogue State Tracker with Slot Attention and Slot Information Sharing to reduce redundant information’s interference and improve long dialogue context tracking. |
| Outcome: | The proposed model significantly outperforms existing models on the MultiWOZ dataset. |
Improving Large Language Models in Event Relation Logical Prediction (2024.acl-long)
Copied to clipboard
| Challenge: | Event relation extraction tasks require rigorous logical reasoning and semantic comprehension, a challenge for narrative understanding and reasoning. |
| Approach: | They propose three approaches to endow LLMs with event relation logic to generate more coherent answers across different scenarios. |
| Outcome: | The proposed approach improves on a set of ERE tasks and provides insights for future work. |
From Style to Story: A Curriculum Learning Approach for Imitative Novel Generation (2026.findings-acl)
Copied to clipboard
| Challenge: | Novels create rich, immersive worlds with intricate plots and distinct styles, captivating readers through complex storytelling. |
| Approach: | They propose a novel generation system that imitates novel elements by predicting plot developments and writing concrete details using vivid, expressive language. |
| Outcome: | The novel imitative novel generation system is trained through a curriculum learning paradigm, progressing from low-level stylistic mastery to high-level narrative coherence. |
PsyAdvisor: A Plug-and-Play Strategy Advice Planner with Proactive Questioning in Psychological Conversations (2025.acl-long)
Copied to clipboard
| Challenge: | Current psychological LLMs are constrained by passive response mechanisms, limiting their capacity to deploy proactive strategies for psychological counseling. |
| Approach: | They propose a dataset that provides a multi-turn conversation dataset with interpretive labels including strategy decision logic and reaction attribution. |
| Outcome: | The proposed model significantly improves proactive questioning capacity, conversation depth, and response quality. |
URO-Bench: Towards Comprehensive Evaluation for End-to-End Spoken Dialogue Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a lack of comprehensive evaluations for SDMs in speech-to-speech (S2S) scenarios is a major challenge for end-to end spoken dialogue models. |
| Approach: | They propose to provide an extensive evaluation framework for end-to-end spoken dialogue models (SDMs) that includes both cognitive dimensions and paralinguistic cues . |
| Outcome: | The proposed benchmark is divided into two difficulty levels: basic track and pro track, each comprising 20 test sets, evaluating the spoken dialogue model’s abilities in U**nderstanding, **R**easoning, and **O**ral conversation. |
Stick to the Facts: Learning towards a Fidelity-oriented E-Commerce Product Description Generation (D19-1)
Copied to clipboard
Zhangming Chan, Xiuying Chen, Yongliang Wang, Juntao Li, Zhiqiang Zhang, Kun Gai, Dongyan Zhao, Rui Yan
| Challenge: | Existing models for product description generation do not take the product attribute information into account. |
| Approach: | They propose a model that takes the embedding and the entity label of each word into account . they establish a keyword memory that stores the entity labels as keys and keywords as values . |
| Outcome: | The proposed model increases the fidelity of the generated descriptions by 25%. |
Learning Representation Mapping for Relation Detection in Knowledge Base Question Answering (P19-1)
Copied to clipboard
| Challenge: | Existing approaches to detect relation detection only get high accuracy for questions whose relations have been seen in training data. |
| Approach: | They propose a method to learn representation mapping for both seen and unseen relations based on previously learned relation embedding. |
| Outcome: | The proposed method improves the performance of unseen relations while keeping the performance comparable to the state-of-the-art. |
IAD: In-Context Learning Ability Decoupler of Large Language Models in Meta-Training (2024.lrec-main)
Copied to clipboard
| Challenge: | In-context Learning (ICL) is a paradigm in which LLMs acquire task-specific knowledge by processing input-output pairs provided as prompts. |
| Approach: | They propose an In-context learning Ability Decoupler to separate ICL ability from general ability of LLMs in meta-training phase . they first identify parameters suitable for ICL by transference-driven gradient importance and propose a new max-margin loss to emphasize the separation of the two abilities. |
| Outcome: | The proposed model separates the ICL ability from the general ability of LLMs in the meta-training phase, where the I-related parameters are tuned to adapt for ICL tasks. |
War of Thoughts: Competition Stimulates Stronger Reasoning in Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models (LLMs) have reshaped the landscape of reasoning tasks. |
| Approach: | They propose a method that enhances LLM reasoning without finetuning by using test-time scaling. |
| Outcome: | The proposed method outperforms baseline models in both budget and model size. |
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. |
Relaxing the Constraints: A Dual-Importance Projection Mechanism for Lifelong Model Editing (2026.findings-acl)
Copied to clipboard
Zhenghai Chen, Senbin Xu, Jiaxi Tan, Xinhua Wu, Yan Zhang, Xiawu Zheng, Shengchuan Zhang, Ke Li, Sicheng Zhao, Liujuan Cao, Rongrong Ji
| Challenge: | Existing knowledge editing methods rely on strict orthogonal projection to preserve previously edited knowledge, but this constraint limits gradient expressiveness, resulting in degradation of model generalization and overall performance as the number of edits increases. |
| Approach: | They propose a method that leverages Singular Value Decomposition to identify critical gradient subspaces and introduces a dual mechanism comprising "accumulated importance" and "projection importance" |
| Outcome: | Extensive experiments on five mainstream LLMs show that the proposed method achieves an average comprehensive performance improvement of 10.36% and effectively maintains the model’s general capabilities on downstream tasks. |
KnowTuning: Knowledge-aware Fine-tuning for Large Language Models (2024.emnlp-main)
Copied to clipboard
Yougang Lyu, Lingyong Yan, Shuaiqiang Wang, Haibo Shi, Dawei Yin, Pengjie Ren, Zhumin Chen, Maarten Rijke, Zhaochun Ren
| Challenge: | Large language models (LLMs) are a default solution for many natural language processing tasks. |
| Approach: | They propose a knowledge-aware fine-tuning method to improve LLMs' knowledge awareness . they propose augmentation and comparison stages to improve accuracy and reliability . |
| Outcome: | The proposed method generates more facts with less factual error rate under fine-grained facts evaluation. |
Discovering Language Model Behaviors with Model-Written Evaluations (2023.findings-acl)
Copied to clipboard
Ethan Perez, Sam Ringer, Kamile Lukosiute, Karina Nguyen, Edwin Chen, Scott Heiner, Craig Pettit, Catherine Olsson, Sandipan Kundu, Saurav Kadavath, Andy Jones, Anna Chen, Benjamin Mann, Brian Israel, Bryan Seethor, Cameron McKinnon, Christopher Olah, Da Yan, Daniela Amodei, Dario Amodei, Dawn Drain, Dustin Li, Eli Tran-Johnson, Guro Khundadze, Jackson Kernion, James Landis, Jamie Kerr, Jared Mueller, Jeeyoon Hyun, Joshua Landau, Kamal Ndousse, Landon Goldberg, Liane Lovitt, Martin Lucas, Michael Sellitto, Miranda Zhang, Neerav Kingsland, Nelson Elhage, Nicholas Joseph, Noemi Mercado, Nova DasSarma, Oliver Rausch, Robin Larson, Sam McCandlish, Scott Johnston, Shauna Kravec, Sheer El Showk, Tamera Lanham, Timothy Telleen-Lawton, Tom Brown, Tom Henighan, Tristan Hume, Yuntao Bai, Zac Hatfield-Dodds, Jack Clark, Samuel R. Bowman, Amanda Askell, Roger Grosse, Danny Hernandez, Deep Ganguli, Evan Hubinger, Nicholas Schiefer, Jared Kaplan
| Challenge: | Prior work creates evaluations with crowdwork or existing data sources, which are not always available. |
| Approach: | They generate evaluations automatically with language models (LMs) using crowdwork or existing data sources to find out how they behave . |
| Outcome: | The results show that large LMs repeat back a dialog user’s preferred answer and express greater desire to pursue concerning goals like resource acquisition and goal preservation. |
IDEA: Enhancing the Rule Learning Ability of Large Language Model Agent through Induction, Deduction, and Abduction (2025.findings-acl)
Copied to clipboard
| Challenge: | RULEARN is a benchmark to assess the rule-learning abilities of large language models (LLMs) in interactive environments. |
| Approach: | They propose a framework that integrates the process of **I**nduction, **De**duction, and **A**bduction. |
| Outcome: | The proposed framework improves on the baseline and human-like rule learning in real-world scenarios. |
Shallow Focus, Deep Fixes: Enhancing Shallow Layers Vision Attention Sinks to Alleviate Hallucination in LVLMs (2025.emnlp-main)
Copied to clipboard
Xiaofeng Zhang, Yihao Quan, Chen Shen, Chaochen Gu, Xiaosong Yuan, Shaotian Yan, Jiawei Cao, Hao Cheng, Kaijie Wu, Jieping Ye
| Challenge: | Multimodal large language models (MLLMs) demonstrate excellent abilities for understanding visual information, but the hallucination remains a challenging problem. |
| Approach: | They propose a training-free approach to enhance vision attention sinks to facilitate convergence of the image token attention sink within shallow layers. |
| Outcome: | The proposed approach improves the convergence of the image token attention sink within shallow layers and strengthens the layer’s focus on the image itself. |
More is not always better? Enhancing Many-Shot In-Context Learning with Differentiated and Reweighting Objectives (2025.acl-long)
Copied to clipboard
Xiaoqing Zhang, Ang Lv, Yuhan Liu, Flood Sung, Wei Liu, Jian Luan, Shuo Shang, Xiuying Chen, Rui Yan
| Challenge: | Large language models excel at few-shot in-context learning but performance plateaus as ICL demonstrations increase from a few to many. |
| Approach: | They propose a novel optimization method that optimizes the negative log-likelihood objective and reweights the model to achieve many-shot performance. |
| Outcome: | The proposed method achieves significant performance improvements across a large-scale dataset. |
CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark (2022.acl-long)
Copied to clipboard
Ningyu Zhang, Mosha Chen, Zhen Bi, Xiaozhuan Liang, Lei Li, Xin Shang, Kangping Yin, Chuanqi Tan, Jian Xu, Fei Huang, Luo Si, Yuan Ni, Guotong Xie, Zhifang Sui, Baobao Chang, Hui Zong, Zheng Yuan, Linfeng Li, Jun Yan, Hongying Zan, Kunli Zhang, Buzhou Tang, Qingcai Chen
| Challenge: | a new benchmark for biomedical language understanding is being developed in Chinese . most benchmarks are limited to English, which makes it difficult to replicate success in other languages. |
| Approach: | They propose to use Chinese biomedical language understanding evaluation benchmarks to evaluate Chinese models. |
| Outcome: | The proposed benchmarks show that the current models perform worse than the human ceiling. |
Revisiting Self-training for Few-shot Learning of Language Model (2021.emnlp-main)
Copied to clipboard
| Challenge: | Unlabeled data are useful for few-shot learning of language models. |
| Approach: | They propose a prompt-based few-shot learner that uses unlabeled data to fine-tune language models. |
| Outcome: | The proposed approach outperforms state-of-the-art models on six sentence classification and six sentence-pair classification benchmarking tasks. |
Variational Knowledge Graph Reasoning (N18-1)
Copied to clipboard
| Challenge: | Existing knowledge graphs have large amount of missing links, which limits their application . a recent study has proposed to design an automated inference model to complete the missing links in large knowledge graph. |
| Approach: | They propose to use variation inference to solve missing links in knowledge graphs . they use a posterior approximator, prior (path finder) and likelihood (path reasoner) |
| Outcome: | The proposed model achieves state-of-the-art on multiple datasets and is highly accurate. |
LAGCL4Rec: When LLMs Activate Interactions Potential in Graph Contrastive Learning for Recommendation (2025.findings-emnlp)
Copied to clipboard
Leqi Zheng, Chaokun Wang, Canzhi Chen, Jiajun Zhang, Cheng Wu, Zixin Song, Shannan Yan, Ziyang Liu, Hongwei Li
| Challenge: | Traditional contrastive learning methods treat negative feedback as equally hard or easy, ignoring informative semantic difficulty during training. |
| Approach: | They propose a framework leveraging Large Language Models to Activate interactions in Graph Contrastive Learning for Recommendation. |
| Outcome: | The proposed framework outperforms state-of-the-art benchmarks on multiple benchmarks. |
BLEURT Has Universal Translations: An Analysis of Automatic Metrics by Minimum Risk Training (2023.acl-long)
Copied to clipboard
| Challenge: | Automated metrics are used for machine translation, but they are often considered to be black boxes with potential biases that are difficult to detect. |
| Approach: | They analyze automatic metrics from the perspective of their guidance for machine translation training. |
| Outcome: | The proposed measures improve the performance of machine translation models. |
Pi-SQL: Enhancing Text-to-SQL with Fine-Grained Guidance from Pivot Programming Languages (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing prompt-based methods craft meticulous text guidelines and examples to facilitate SQL generation, but their accuracy is hindered by the large semantic gap between the texts and the low-resource SQL programs. |
| Approach: | They propose to use Python as a pivot to bridge between natural language query and SQL program. |
| Outcome: | The proposed method improves the execution accuracy of the best-performing baseline by up to 3.20. |
Batch-ICL: Effective, Efficient, and Order-Agnostic In-Context Learning (2024.findings-acl)
Copied to clipboard
| Challenge: | In-context learning (ICL) is a meta-optimization process that affects performance . we develop a batch-based inference algorithm that is order-agnostic to ICL examples . |
| Approach: | They develop an order-agnostic inference algorithm that aggregates ICL examples in batches . they find it outperforms most permutations of ICL, and it even exceeds the best order . |
| Outcome: | The proposed method outperforms standard ICL examples while reducing computational resources. |
MCC-KD: Multi-CoT Consistent Knowledge Distillation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated remarkable abilities in complex reasoning through chain of thought (CoT) prompting. |
| Approach: | They propose to generate multiple rationales for each question and enforce consistency among their predictions by minimizing the bidirectional KL-divergence between the answer distributions. |
| Outcome: | The proposed model achieves superior performance on in-distribution and commonsense reasoning benchmarks. |
Concise and Organized Perception Facilitates Reasoning in Large Language Models (2025.findings-naacl)
Copied to clipboard
| Challenge: | Extensive experimental results on several popular logical benchmarks (ProofWriter, PrOntoQA, PrONtoQA-OOD, and FOLIO) and mathematical benchmark (DI-GSM) show that COP significantly outperforms previous state-of-the-art methods. |
| Approach: | They propose a reasoning approach called Concise and Organized Perception (COP) that carefully analyzes the given statements to identify the most pertinent information while eliminating redundancy efficiently. |
| Outcome: | The proposed approach outperforms state-of-the-art methods on several popular logical benchmarks and mathematical benchmarks. |
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. |
Enhancing Open-Domain Task-Solving Capability of LLMs via Autonomous Tool Integration from GitHub (2025.acl-long)
Copied to clipboard
Bohan Lyu, Xin Cong, Heyang Yu, Pan Yang, Cheng Qian, Zihe Wang, Yujia Qin, Yining Ye, Yaxi Lu, Chen Qian, Zhong Zhang, Yukun Yan, Yankai Lin, Zhiyuan Liu, Maosong Sun
| Challenge: | Existing approaches lack flexibility to address diverse and ever-evolving user queries in open domains. |
| Approach: | They propose to evaluate LLMs on open-domain knowledge that requires tools to solve diverse and ever-evolving user queries. |
| Outcome: | The proposed system outperforms baselines in the open domain task-solving benchmark. |
Large Language Models Meet Harry Potter: A Dataset for Aligning Dialogue Agents with Characters (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models that can create open-domain dialogue agents lack character representation and annotations. |
| Approach: | They propose a dataset to study character alignment and character representation . it includes all dialogue sessions from the Harry Potter series and includes annotations . |
| Outcome: | The proposed dataset can be used as a universal benchmark for character-driven LLMs. |
SpeechLLM-as-Judges: Towards General and Interpretable Speech Quality Evaluation (2026.acl-long)
Copied to clipboard
Hui Wang, Jinghua Zhao, Yifan Yang, Shujie Liu, Junyang Chen, Yanzhe Zhang, Shiwan Zhao, Jinyu Li, Jiaming Zhou, Haoqin Sun, Yan Lu, Yong Qin
| Challenge: | Existing methods for evaluating the perceptual quality of synthetic speech are limited due to the complexity of perceptual quality factors and the diversity of speech generation tasks. |
| Approach: | They propose a new paradigm for enabling large language models to conduct structured speech quality evaluation using a large-scale dataset. |
| Outcome: | The proposed model performs well across tasks and languages. |
Taking a Deep Breath: Enhancing Language Modeling of Large Language Models with Sentinel Tokens (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies have explored compression and accumulation methods to compress contexts, but these methods lose useful context information during the compression process, leading to performance degradation. |
| Approach: | They propose a method that allows LLMs to take a deep breath and insert a special token at the end of each chunk. |
| Outcome: | Experiments on language modeling and out-of-domain tasks validate the superiority of the proposed method. |
ASTRA: An Automated Framework for Strategy Discovery, Retrieval, and Evolution for Jailbreaking LLMs (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods lack the capability for continuous learning and self-evolution from interactions, limiting the diversity and adaptability of attack strategies. |
| Approach: | They propose an automated framework capable of discovering, retrieving, and evolving attack strategies. |
| Outcome: | The proposed framework outperforms existing baselines in a black-box setting. |
Tell Me How to Ask Again: Question Data Augmentation with Controllable Rewriting in Continuous Space (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing data augmentation techniques for natural language processing tasks are difficult to design. |
| Approach: | They propose a controllable rewriting based question data augmentation method for machine reading comprehension, question generation and question-answering natural language inference tasks. |
| Outcome: | The proposed method generates high-quality, high-quality question data samples on machine reading comprehension, question generation, and question-answering natural language inference tasks. |