Papers by He Zhu
Enabling Self-Improving Agents to Learn at Test Time With Human-In-The-Loop Guidance (2025.emnlp-industry)
Copied to clipboard
Yufei He, Ruoyu Li, Alex Chen, Yue Liu, Yulin Chen, Yuan Sui, Cheng Chen, Yi Zhu, Luca Luo, Frank Yang, Bryan Hooi
| Challenge: | Existing large language model (LLM) agents are unable to adapt to changing domain knowledge and rules. |
| Approach: | They propose an LLM agent framework that continuously learns updated domain knowledge at test time. |
| Outcome: | The proposed agent improves on a customer due diligence name screening task on . the agent learns updated domain knowledge at test time. |
NarrativePlay: Interactive Narrative Understanding (2024.eacl-demo)
Copied to clipboard
| Challenge: | Existing systems for interactive agents focus on specific capabilities in predetermined scenarios. |
| Approach: | They propose a novel system that allows users to role-play a fictional character and interact with other characters in narratives in an immersive environment. |
| Outcome: | The proposed system generates human-like responses guided by personality traits extracted from narratives. |
Chinese SafetyQA: A Safety Short-form Factuality Benchmark for Large Language Models (2025.acl-long)
Copied to clipboard
Yingshui Tan, Boren Zheng, Baihui Zheng, Kerui Cao, Huiyun Jing, Jincheng Wei, Jiaheng Liu, Yancheng He, Wenbo Su, Xiaoyong Zhu, Bo Zheng, Kaifu Zhang
| Challenge: | Large language models have created significant safety concerns . factuality ability is crucial in determining whether they can be deployed and applied safely and compliantly within specific regions. |
| Approach: | They propose a benchmark to evaluate the factuality of large language models in China . they evaluate the models' ability to provide accurate and reliable information . |
| Outcome: | The proposed benchmark evaluates the factuality abilities of existing LLMs and compares them to LLM abilities. |
Tracing the Roots: A Multi-Agent Framework for Uncovering Data Lineage in Post-Training LLMs (2026.acl-long)
Copied to clipboard
Yu Li, Xiaoran Shang, Qizhi Pei, Yun Zhu, Xin Gao, Honglin Lin, Zhanping Zhong, Zhuoshi Pan, Zheng Liu, Xiaoyang Wang, Conghui He, Dahua Lin, Feng Zhao, Lijun Wu
| Challenge: | High-quality post-training data is the primary engine driving LLM capabilities . datasets are often treated as isolated artifacts, overlooking their true developmental context . |
| Approach: | They propose a framework to reconstruct the evolutionary graph of dataset development using data lineage. |
| Outcome: | The proposed framework characterizes domain-specific structural patterns in Math-oriented datasets and general-domain corpora. |
CORD: Bridging the Audio–Text Reasoning Gap via Weighted On-policy Cross-modal Distillation (2026.findings-acl)
Copied to clipboard
Hu Jing, Danxiang Zhu, Xianlong Luo, Dan Zhang, Shuwei He, Yishu Lei, Shikun Feng, Hai-Tao Zheng, Jingzhou HE, Yu Sun, Hua Wu, Haifeng Wang
| Challenge: | Large Audio Language Models (LALMs) exhibit a degradation in knowledge and reasoning capabilities . empirical results show that CORD significantly bridges the audio–text performance gap . |
| Approach: | They propose a framework that performs online cross-modal self-distillation to bridge the acoustic-semantic gap between LALMs and text-based models. |
| Outcome: | The proposed framework bridges the acoustic-semantic gap between LALMs and text-based models . it employs on-policy reverse KL divergence with importance-aware weighting . |
HiCoLoRA: Addressing Context-Prompt Misalignment via Hierarchical Collaborative LoRA for Zero-Shot DST (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to zero-shot Dialog State Tracking (zs-DST) are inadequate to generalize to new domains without extensive training. |
| Approach: | They propose a framework that enhances zero-shot slot inference through robust prompt alignment. |
| Outcome: | Experiments on multi-domain datasets show that HiCoLoRA outperforms baselines, achieving SOTA in zs-DST. |
EXPLAIN, EDIT, GENERATE: Rationale-Sensitive Counterfactual Data Augmentation for Multi-hop Fact Verification (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to augment training data with counterfactuals fail to handle multi-hop fact verification due to their incapability to preserve complex logical relationships. |
| Approach: | They propose to augment training data with counterfactuals that alter causal features of the original data by preserving logical relationships. |
| Outcome: | The proposed method outperforms the baselines and can generate linguistically diverse counterfactuals without disrupting their logical relationships. |
JointCL: A Joint Contrastive Learning Framework for Zero-Shot Stance Detection (2022.acl-long)
Copied to clipboard
| Challenge: | Existing methods achieve promising performance in in-target stance detection when trained and tested on the same datasets. |
| Approach: | They propose a joint contrastive learning framework to generalize stance features for unseen targets. |
| Outcome: | The proposed framework achieves state-of-the-art on three benchmark datasets. |
RWKV: Reinventing RNNs for the Transformer Era (2023.findings-emnlp)
Copied to clipboard
Bo Peng, Eric Alcaide, Quentin Anthony, Alon Albalak, Samuel Arcadinho, Stella Biderman, Huanqi Cao, Xin Cheng, Michael Chung, Leon Derczynski, Xingjian Du, Matteo Grella, Kranthi Gv, Xuzheng He, Haowen Hou, Przemyslaw Kazienko, Jan Kocon, Jiaming Kong, Bartłomiej Koptyra, Hayden Lau, Jiaju Lin, Krishna Sri Ipsit Mantri, Ferdinand Mom, Atsushi Saito, Guangyu Song, Xiangru Tang, Johan Wind, Stanisław Woźniak, Zhenyuan Zhang, Qinghua Zhou, Jian Zhu, Rui-Jie Zhu
| Challenge: | recurrent neural networks struggle to match the performance of Transformers due to limitations in parallelization and scalability. |
| Approach: | They propose a model architecture that combines the efficient parallelizable training of transformers with the efficient inference of RNNs. |
| Outcome: | The proposed model performs on par with similarly sized RNNs, suggesting future work can leverage this architecture to create more efficient models. |
Forest for the Trees: Overarching Prompting Evokes High-Level Reasoning in Large Language Models (2025.naacl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have greatly propelled the progress of natural language process (NLP). |
| Approach: | They propose a deductive paradigm that decomposes the reasoning process and a prompting method that elicits high-level thinking of large language models (LLMs). |
| Outcome: | The proposed method improves ChatGPT and CoT by 19.0% and 3.1% on MMLU’s College Physics, 8.8% and 2.3% on GSM8k, and 10.3% and 2.5% on StrategyQA, respectively. |
RepoDebug: Repository-Level Multi-Task and Multi-Language Debugging Evaluation of Large Language Models (2025.findings-emnlp)
Copied to clipboard
Jingjing Liu, Zeming Liu, Zihao Cheng, Mengliang He, Xiaoming Shi, Yuhang Guo, Xiangrong Zhu, Yuanfang Guo, Yunhong Wang, Haifeng Wang
| Challenge: | Large Language Models (LLMs) have exhibited significant proficiency in code debugging, especially in automatic program repair. |
| Approach: | They propose a repository-level code debugging dataset with 22 subtypes of errors that supports 8 commonly used programming languages and 3 debug tasks. |
| Outcome: | The proposed dataset supports 8 commonly used programming languages and 3 debugging tasks. |
Tag-Instruct: Controlled Instruction Complexity Enhancement through Structure-based Augmentation (2025.findings-acl)
Copied to clipboard
| Challenge: | High-quality instruction data is crucial for developing large language models (LLMs), yet existing approaches struggle to effectively control instruction complexity. |
| Approach: | They propose a framework that compresses instructions into a compact tag space and enhances complexity through RL-guided tag expansion. |
| Outcome: | The proposed framework outperforms existing methods in the evaluation of instruction complexity augmentation and semantic compression of text into a compact tag space. |
ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch (2026.acl-long)
Copied to clipboard
Zheng Liu, Honglin Lin, Xiaoyang Wang, Xin Gao, Yu Li, Mengzhang Cai, Yun Zhu, Zhanping Zhong, Qizhi Pei, Zhuoshi Pan, Xiaoran Shang, Conghui He, Bin Cui, Wentao Zhang, Lijun Wu
| Challenge: | Existing open-source vision language models lack high-quality training data for chart reasoning . current models are simplistic and repetitive, while associated QA pairs are prone to hallucinations . |
| Approach: | They propose a framework to synthesize complex charts and reliable reasoning data from scratch. |
| Outcome: | Experimental results show that ChartVerse-8B surpasses existing models in QA and difficulty . lack of high-quality training data hampers development of open-source models . |
AutoMedEval: Harnessing Language Models for Automatic Medical Capability Evaluation (2025.acl-long)
Copied to clipboard
Xiechi Zhang, Zetian Ouyang, Linlin Wang, Gerard De Melo, Zhu Cao, Xiaoling Wang, Ya Zhang, Yanfeng Wang, Liang He
| Challenge: | Existing evaluation methods based on large language models (LLMs) are expensive and lack expertise due to limitations in human expertise. |
| Approach: | They propose an open-source automatic evaluation model with 13B parameters specifically engineered to measure the question-answering proficiency of medical LLMs. |
| Outcome: | The proposed model surpasses baselines in terms of correlation with human judgments. |
MADial-Bench: Towards Real-world Evaluation of Memory-Augmented Dialogue Generation (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing evaluation metrics for memory-augmented dialogue systems lack practical value . current evaluation methods only consider passive memory retrieval while ignoring diverse memory recall with rich triggering factors. |
| Approach: | They propose to use long-term memory to create human-like dialogues using chatbots. |
| Outcome: | The proposed benchmark covers memory retrieval and memory recognition tasks with both passive and proactive memory recall data. |
LlmLink: Dual LLMs for Dynamic Entity Linking on Long Narratives with Collaborative Memorisation and Prompt Optimisation (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods focus on supervised fine-tuning or limited to one-off prediction, which poses a challenge where the context is long. |
| Approach: | They propose a dynamic approach to CoREFerence resolution in chunked long narratives by deploying dual Large Language Models. |
| Outcome: | The proposed model achieves performance gains over existing models and fine-tuning approaches on long narrative datasets, significantly reducing the resources required for inference and training. |
Progressive Re-ranking for Multimodal Retrieval-Augmented Generation via Curriculum Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to improve retrieval performance of large language models are limited by static knowledge. |
| Approach: | They propose a multimodal re-ranking framework that combines curriculum learning with fine-grained reranking and multimodal section reassessment to improve CLIP-based visual coarse-grain retrieval. |
| Outcome: | The proposed framework achieves state-of-the-art answer accuracy and competitive retrieval performance on InfoSeek and Enc-VQA. |
SILC-EFSA: Self-aware In-context Learning Correction for Entity-level Financial Sentiment Analysis (2025.coling-main)
Copied to clipboard
Senbin Zhu, ChenYuan He, Hongde Liu, Pengcheng Dong, Hanjie Zhao, Yuchen Yan, Yuxiang Jia, Hongying Zan, Min Peng
| Challenge: | Currently, most sentiment analysis corpora use sequence-level annotation. |
| Approach: | They propose a two-stage approach to financial entity-level sentiment analysis called Self-aware In-context Learning Correction. |
| Outcome: | The proposed approach achieves state-of-the-art on the largest English and Chinese financial entity-level sentiment analysis datasets to date. |
Cross-layer Attention Sharing for Pre-trained Large Language Models (2026.tacl-1)
Copied to clipboard
Yongyu Mu, Yuzhang Wu, Yuchun Fan, Chenglong Wang, Hengyu Li, Jiali Zeng, Qiaozhi He, Murun Yang, Fandong Meng, Jie Zhou, Tong Xiao, Jingbo Zhu
| Challenge: | Existing studies focus on compressing the Key-Value cache or grouping attention heads, while overlooking redundancy between layers. |
| Approach: | They propose a lightweight substitute for self-attention in well-trained LLMs that uses feed-forward networks to align attention heads between adjacent layers and low-rank matrices to approximate differences in layer-wise attention weights. |
| Outcome: | The proposed model reduces redundancy by sharing weights across layers while maintaining high response quality while reducing redundant calculations within 53% 84% of the total layers. |
UTBoost: Rigorous Evaluation of Coding Agents on SWE-Bench (2025.acl-long)
Copied to clipboard
| Challenge: | Large language models have enabled the development of coding agents for real-world code generation. |
| Approach: | They propose a novel LLM-driven test case generator that analyzes codebases and dependencies to generate test cases for real-world Python projects. |
| Outcome: | The proposed framework improves the performance of SWE-Bench by analyzing codebases and dependencies. |
Z-Code++: A Pre-trained Language Model Optimized for Abstractive Summarization (2023.acl-long)
Copied to clipboard
Pengcheng He, Baolin Peng, Song Wang, Yang Liu, Ruochen Xu, Hany Hassan, Yu Shi, Chenguang Zhu, Wayne Xiong, Michael Zeng, Jianfeng Gao, Xuedong Huang
| Challenge: | Z-Code++ is a pre-trained language model optimized for abstractive text summarization. |
| Approach: | They propose a pre-trained language model optimized for abstractive text summarization that uses a two-phase pre-training technique to improve model's performance. |
| Outcome: | The proposed model outperforms the competing models on low-resource summarization tasks in zero-shot and few-shot settings. |
Granular Entity Mapper: Advancing Fine-grained Multimodal Named Entity Recognition and Grounding (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for fine-grained content extraction are limited by long-tailed distribution of textual entity categories and performance of object detectors. |
| Approach: | They propose a multi-granularity entity recognition module and a reranking module to integrate hierarchical information of entity categories, visual cues, and external textual resources collectively. |
| Outcome: | The proposed framework achieves state-of-the-art on the fine-grained content extraction task. |
The Microsoft Toolkit of Multi-Task Deep Neural Networks for Natural Language Understanding (2020.acl-demos)
Copied to clipboard
Xiaodong Liu, Yu Wang, Jianshu Ji, Hao Cheng, Xueyun Zhu, Emmanuel Awa, Pengcheng He, Weizhu Chen, Hoifung Poon, Guihong Cao, Jianfeng Gao
| Challenge: | MT-DNN is an open-source natural language understanding toolkit . it allows researchers and developers to train customized deep learning models . |
| Approach: | They present MT-DNN, an open-source natural language understanding toolkit . it is designed to facilitate rapid customization for a broad spectrum of NLU tasks . MT supports multi-task knowledge distillation, which can substantially compress a deep neural model without significant performance drop. |
| Outcome: | The proposed model can significantly compress a large model without significant performance drop. |
Topic-Driven and Knowledge-Aware Transformer for Dialogue Emotion Detection (2021.acl-long)
Copied to clipboard
| Challenge: | Emotion detection in dialogues requires the identification of thematic topics underlying a conversation, commonsense knowledge, and the intricate transition patterns between affective states. |
| Approach: | They propose a Topic-Driven Knowledge-Aware Transformer model that integrates topic representation and commonsense knowledge from ATOMIC for dialogue emotion detection. |
| Outcome: | The proposed model outperforms state-of-the-art models on four dialogue datasets . it can detect topics which help distinguish emotion categories, the authors show . |
GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation (2025.findings-naacl)
Copied to clipboard
Runchuan Zhu, Xinke Jiang, Jiang Wu, Zhipeng Ma, Jiahe Song, Fengshuo Bai, Dahua Lin, Lijun Wu, Conghui He
| Challenge: | Experimental evaluations on open-ended and multiple-choice questions demonstrate GRAIT significantly outperforms existing RAIT methods in the overall performance. |
| Approach: | They propose a framework to reduce the risk of over-refusal and reduce hallucinations by rejecting unknown questions to minimize hallucinism and ensuring correct answers are not rejected. |
| Outcome: | The proposed framework outperforms existing methods on open-ended and multiple-choice questions. |
Texar: A Modularized, Versatile, and Extensible Toolkit for Text Generation (P19-3)
Copied to clipboard
Zhiting Hu, Haoran Shi, Bowen Tan, Wentao Wang, Zichao Yang, Tiancheng Zhao, Junxian He, Lianhui Qin, Di Wang, Xuezhe Ma, Zhengzhong Liu, Xiaodan Liang, Wanrong Zhu, Devendra Sachan, Eric Xing
| Challenge: | Texar is an open-source text generation toolkit that supports a broad set of text generation tasks. |
| Approach: | They introduce Texar, an open-source text generation toolkit that supports text generation tasks. |
| Outcome: | Texar supports machine translation, summarization, dialog, content manipulation, and more. |
BrailleLLM: Braille Instruction Tuning with Large Language Models for Braille Domain Tasks (2025.emnlp-main)
Copied to clipboard
Tianyuan Huang, Zepeng Zhu, Hangdi Xing, Zirui Shao, Zhi Yu, Chaoxiong Yang, Jiaxian He, Xiaozhong Liu, Jiajun Bu
| Challenge: | Existing Braille research focuses on isolated tasks while mixed-content Braille tasks face data scarcity and ambiguities. |
| Approach: | They propose a syntax tree-based augmentation method tailored for Braille data. |
| Outcome: | The proposed method improves Braille translation, formula-to-Braille conversion, and mixed-text translation. |
HILL: Hierarchy-aware Information Lossless Contrastive Learning for Hierarchical Text Classification (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing self-supervised methods in natural language processing rely on augmentation rules to generate contrastive samples. |
| Approach: | They propose a hierarchy-aware information lossless contrastive learning scheme that uses syntactic information reserved in the input sample and fused during the learning process. |
| Outcome: | The proposed learning scheme is superior to existing methods in hierarchical text classification . the proposed learning system is based on a structure encoder and a text encoder . |
Sparse Activation Editing for Reliable Instruction Following in Narratives (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing benchmarks fail to capture the challenges of instruction following in complex narrative contexts. |
| Approach: | They propose a training-free framework that identifies and edits instruction-relevant neurons using only natural language instructions without requiring labelled data. |
| Outcome: | The proposed framework improves instruction following by identifying and editing instruction-relevant neurons using only natural language instructions, without requiring labelled data. |
BPP-Search: Enhancing Tree of Thought Reasoning for Mathematical Modeling Problem Solving (2025.acl-long)
Copied to clipboard
Teng Wang, Wing Yin Yu, Zhenqi He, Zehua Liu, HaileiGong HaileiGong, Han Wu, Xiongwei Han, Wei Shi, Ruifeng She, Fangzhou Zhu, Tao Zhong
| Challenge: | Existing datasets in operations research domain lack detailed annotations of the modeling process, focusing only on objective values. |
| Approach: | They propose an annotation-based tree-of-thought tree-based reasoning algorithm that integrates reinforcement learning into a tree- of-though. |
| Outcome: | The proposed algorithm outperforms state-of-the-art methods on StructuredOR, NL4OPT, and MAMO-ComplexLP datasets. |
AgentV-RL: Scaling Reward Modeling with Agentic Verifier (2026.findings-acl)
Copied to clipboard
Jiazheng Zhang, Ziche Fu, Zhiheng Xi, Wenqing Jing, Mingxu Chai, Wei He, Guoqiang Zhang, Chenghao Fan, Chenxin An, Wenxiang Chen, Zhicheng Liu, Haojie Pan, Dingwei Zhu, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing approaches to improve LLM reasoning are limited in complex domains and lack external grounding makes verifiers unreliable on computation-intensive tasks. |
| Approach: | They propose a framework that transforms reward modeling into a multi-turn, tool-augmented deliberative process. |
| Outcome: | The proposed framework surpasses state-of-the-art ORMs by 25.2% under parallel and sequential TTS. |
Recurrent Alignment with Hard Attention for Hierarchical Text Rating (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models excel at understanding and generating plain text, but they are not tailored to handle hierarchical text structures or directly predict task-specific properties such as text rating. |
| Approach: | They propose a framework that integrates Recurrent Alignment with Hard Attention to analyze hierarchically structured text. |
| Outcome: | The proposed framework outperforms existing state-of-the-art methods on three hierarchical text rating datasets. |
LLM-based Conversational Recommendation Agents with Collaborative Verbalized Experience (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated impressive zero-shot capabilities in conversational recommender systems (CRS). |
| Approach: | They propose LLM-based CRS-based LLMs with Collaborative Verbalized Experience to enhance historical conversations by sampling trajectories of LLM agents on historical queries and establishing verbalized experience banks . |
| Outcome: | The proposed system improves on existing approaches to enhancing historical conversations by leveraging trajectories and verbalized experiences from LLMs on historical queries and user feedback. |
Large Language Models Fall Short: Understanding Complex Relationships in Detective Narratives (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing datasets for narrative understanding fail to represent complexity and uncertainty of relationships in real-life social scenarios. |
| Approach: | They propose a benchmark for extracting and analysing intricate character relation graphs from detective narratives using large-scale large-language models. |
| Outcome: | The proposed dataset extracts and analyses character relation graphs from detective narratives using advanced Large Language Models like GPT-3.5, GPT-4, and Llama2 . |
RESF: Regularized-Entropy-Sensitive Fingerprinting for Black-Box Tamper Detection of Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for tamper detection rely on model stability, not inherently stochastic models. |
| Approach: | They propose a hypothesis-testing method for black-box tamper detection for LLMs . they propose regularized entropy-sensitive fingerprinting to enable efficient fingerprinting . |
| Outcome: | The proposed method achieves 98.80% detection accuracy under challenging conditions . it is based on a first-order surrogate for KL divergence to identify prompts most responsive to parameter perturbations. |
Let’s Rectify Step by Step: Improving Aspect-based Sentiment Analysis with Diffusion Models (2024.lrec-main)
Copied to clipboard
| Challenge: | Empirical evaluations conducted on eight benchmark datasets underscore the compelling advantages offered by DiffusionABSA when compared against robust baseline models. |
| Approach: | They propose a diffusion model which extracts aspects step by step and learns a denoising process that progressively restores them in a reverse manner. |
| Outcome: | Empirical evaluations on eight benchmark datasets underscore the compelling advantages offered by DiffusionABSA when compared against robust baseline models. |
CLEAN–EVAL: Clean Evaluation on Contaminated Large Language Models (2024.findings-naacl)
Copied to clipboard
Wenhong Zhu, Hongkun Hao, Zhiwei He, Yun-Ze Song, Jiao Yueyang, Yumeng Zhang, Hanxu Hu, Yiran Wei, Rui Wang, Hongyuan Lu
| Challenge: | Existing methods to evaluate large language models are prone to data contamination. |
| Approach: | They propose a method which parses contaminated data and back-translates it into a candidate set. |
| Outcome: | The proposed method reduces data contamination and evaluates the LLMs more cleanly. |
Enhancing Character-Level Understanding in LLMs through Token Internal Structure Learning (2025.acl-long)
Copied to clipboard
Zhu Xu, Zhiqiang Zhao, Zihan Zhang, Yuchi Liu, Quanwei Shen, Fei Liu, Yu Kuang, Jian He, Conglin Liu
| Challenge: | Large language models (LLMs) use tokenization methods but often obscure internal character structures within tokens. |
| Approach: | They propose a method that improves models’ ability to capture character positions within tokens by training them on reverse character prediction tasks using the tokenizer’s vocabulary. |
| Outcome: | Experiments show that the proposed method improves position prediction accuracy in large language models, enabling more precise identification of target characters in original text. |
UMRSpell: Unifying the Detection and Correction Parts of Pre-trained Models towards Chinese Missing, Redundant, and Spelling Correction (2023.acl-long)
Copied to clipboard
| Challenge: | Chinese Spelling Correction (CSC) is a task of detecting and correcting misspelled charac- ters in Chinese texts. |
| Approach: | They propose a model to learn detection and correction parts together from a multi-task learning perspective. |
| Outcome: | The proposed model can learn detection and correction parts together from a multi-task learning perspective. |
PlanGPT: Enhancing Urban Planning with a Tailored Agent Framework (2025.acl-industry)
Copied to clipboard
| Challenge: | Empirical tests demonstrate that PlanGPT framework has achieved advanced performance, providing comprehensive support that significantly enhances professional planning efficiency. |
| Approach: | They propose a specialized AI agent framework tailored for urban and spatial planning that integrates a customized local database retrieval system and domain-specific knowledge activation capabilities. |
| Outcome: | Empirical tests show that PlanGPT framework significantly improves planning efficiency . it integrates a customized database retrieval system, domain-specific knowledge activation capabilities, and advanced tool orchestration mechanisms. |
Infusing Disease Knowledge into BERT for Health Question Answering, Medical Inference and Disease Name Recognition (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to augment pre-trained language models with disease knowledge are lacking. |
| Approach: | They propose a method to augment BERT-like pre-trained language models with disease knowledge. |
| Outcome: | The proposed method improves on a suite of BERT models over three tasks. |
SERM: Self-Evolving Relevance Model with Agent-Driven Learning from Massive Query Streams (2026.findings-acl)
Copied to clipboard
Chenglong Wang, Canjia Li, Xingzhao Zhu, Yifu Huo, Huiyu Wang, Weixiong Lin, Yun Yang, Qiaozhi He, Tian Hua Zhou, null Changxiaojia, JingBo Zhu, Tong Xiao
| Challenge: | Existing approaches to generate relevance judgments are limited due to dynamic nature of query distributions. |
| Approach: | They propose a self-evolving relevance model approach to generalize queries to practical search scenarios . they use a multi-agent sample miner and a relevance annotator to generate reliable labels . |
| Outcome: | The proposed approach can achieve significant performance gains on a large-scale industrial platform, validated by offline multilingual evaluations and online testing. |
See the World, Discover Knowledge: A Chinese Factuality Evaluation for Large Vision Language Models (2025.findings-acl)
Copied to clipboard
Jihao Gu, Yingyao Wang, Pi Bu, Chen Wang, Ziming Wang, Tengtao Song, Donglai Wei, Jiale Yuan, Yingxiu Zhao, Yancheng He, Shilong Li, Jiaheng Liu, Meng Cao, Jun Song, Yingshui Tan, Xiang Li, Wenbo Su, Xiaoyong Zhu, Bo Zheng
| Challenge: | Existing models for large vision language models do not fully reflect their knowledge capacity and reliability, resulting in erroneous outputs that do not align with the image content or provide answers lacking knowledge evidence. |
| Approach: | They propose a Chinese-based benchmark for visual factuality across 8 major topics and 56 subtopics and a multi-hop question construction. |
| Outcome: | The proposed model decouples visual factuality into two parts: seeing the world and discovering knowledge. |
SEEKR: Selective Attention-Guided Knowledge Retention for Continual Learning of Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods fail to fully exploit the knowledge embedded in models from previous tasks . Existing techniques fail to exploit the information embedded in previous tasks, resulting in a large number of replay samples to achieve good results. |
| Approach: | They propose a method that uses attention weights to extract knowledge from previous tasks . they use a data replay strategy to extract the knowledge from the previous tasks. |
| Outcome: | The proposed method achieves comparable or even better performance with only 1/10 of replayed data used by other methods. |
Why LLMs Hallucinate on Structured Knowledge: A Mechanistic Analysis of Reasoning over Linearized Representations (2026.acl-long)
Copied to clipboard
Shanghao Li, Jinda Han, Yibo Wang, Yuanjie Zhu, Zihe Song, Langzhou He, Kenan Kamel A Alghythee, Philip S. Yu
| Challenge: | Existing literature primarily addresses this problem through external interventions such as retrieval augmentation and prompt engineering at the input or output level. |
| Approach: | They find that LLMs can still produce hallucinated outputs when using structured external knowledge. |
| Outcome: | The proposed models fail to ground the provided knowledge, causing the model to revert to parametric memory. |
INVESTORBENCH: A Benchmark for Financial Decision-Making Tasks with LLM-based Agent (2025.acl-long)
Copied to clipboard
Haohang Li, Yupeng Cao, Yangyang Yu, Shashidhar Reddy Javaji, Zhiyang Deng, Yueru He, Yuechen Jiang, Zining Zhu, K.p. Subbalakshmi, Jimin Huang, Lingfei Qian, Xueqing Peng, Jordan W. Suchow, Qianqian Xie
| Challenge: | Recent advances have underscored the potential of large language model (LLM)-based agents in financial decision-making. |
| Approach: | They propose to evaluate LLM agents using 13 different LLMs as backbone models across various market environments and tasks. |
| Outcome: | The proposed framework assesses the reasoning and decision-making capabilities of 13 different LLMs across various market environments and tasks. |
Stealthy Jailbreak Attacks on Large Language Models via Benign Data Mirroring (2025.naacl-long)
Copied to clipboard
Honglin Mu, Han He, Yuxin Zhou, Yunlong Feng, Yang Xu, Libo Qin, Xiaoming Shi, Zeming Liu, Xudong Han, Qi Shi, Qingfu Zhu, Wanxiang Che
| Challenge: | Existing black-box jailbreak methods often rely on model feedback . existing methods may be intercepted by content moderators during the search process . |
| Approach: | They propose a method that guides malicious prompt construction by local training a mirror model of the target black-box model through benign data distillation. |
| Outcome: | The proposed method achieves a 92% attack success rate and 80% stealth rate on a subset of AdvBench. |
RGAR: Recurrence Generation-augmented Retrieval for Factual-aware Medical Question Answering (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing retrieval approaches often overlook patient-specific factual knowledge embedded in EHRs . existing retrieval frameworks often overlook this factual information, limiting its effectiveness in clinical decision-making. |
| Approach: | They propose a recurrence generation-augmented retrieval framework that synergizes factual and conceptual knowledge from dual sources. |
| Outcome: | The proposed framework improves on factual-aware medical QA benchmarks. |
Attribution-Based Analysis and Optimization of Modular Agentic Workflows (2026.findings-acl)
Copied to clipboard
Yingxuan Yang, Bo Huang, Siyuan Qi, Chao Feng, Haoyi Hu, Yuxuan Zhu, Jinbo Hu, Haoran Zhao, Ziyi He, Xiao Liu, ZongYu Wang, Muning Wen, Lin Qiu, Xuezhi Cao, Xunliang Cai, Yong Yu, Weinan Zhang
| Challenge: | Large Language Models (LLMs) have driven the rise of agentic workflows . yet, how can we attribute performance gains to individual upgrades and their interactions? |
| Approach: | They propose a game-theoretic framework that models component upgrades as players and evaluates component coalitions to compute Shapley values. |
| Outcome: | The proposed framework provides interaction-aware attribution and recommendation for model allocation under a fixed workflow structure. |
Mem-Gallery: Benchmarking Multimodal Long-Term Conversational Memory for MLLM Agents (2026.acl-long)
Copied to clipboard
Yuanchen Bei, Tianxin Wei, Xuying Ning, Yanjun Zhao, Zhining Liu, Xiao Lin, Yada Zhu, Hendrik Hamann, Jingrui He, Hanghang Tong
| Challenge: | Existing benchmarks evaluate multi-session memory in text-only conversations or assess multimodal understanding within localized contexts. |
| Approach: | They propose a benchmark for evaluating multimodal long-term conversational memory in MLLM agents. |
| Outcome: | The proposed framework assesses key memory capabilities along three functional dimensions: memory extraction and test-time adaptation, memory reasoning, and memory knowledge management. |
Second Language (Arabic) Acquisition of LLMs via Progressive Vocabulary Expansion (2025.acl-long)
Copied to clipboard
Jianqing Zhu, Huang Huang, Zhihang Lin, Juhao Liang, Zhengyang Tang, Khalid Almubarak, Mosen Alharthi, Bang An, Juncai He, Xiangbo Wu, Fei Yu, Junying Chen, Ma Zhuoheng, Yuhao Du, He Zhang, Saied Alshahrani, Emad A. Alghamdi, Lian Zhang, Ruoyu Sun, Haizhou Li, Benyou Wang, Jinchao Xu
| Challenge: | In the evolving landscape of large language models, the predominant focus has been on English and Chinese. |
| Approach: | They propose to utilize Arabic-specific vocabulary in the tokenizer to accelerate decoding. |
| Outcome: | The proposed model achieves decent performance comparable to the best Arabic LLMs across various Arabic benchmarks. |
PersLEARN: Research Training through the Lens of Perspective Cultivation (2023.acl-demo)
Copied to clipboard
Yu-Zhe Shi, Shiqian Li, Xinyi Niu, Qiao Xu, Jiawen Liu, Yifan Xu, Shiyu Gu, Bingru He, Xinyang Li, Xinyu Zhao, Zijian Zhao, Yidong Lyu, Zhen Li, Sijia Liu, Lin Qiu, Jinhao Ji, Lecheng Ruan, Yuxi Ma, Wenjuan Han, Yixin Zhu
| Challenge: | PersLEARN is a tool designed to facilitate the cultivation of scientific perspectives . junior researchers struggle to identify the perspectives reflected in the literature and struggle to develop their own viewpoints. |
| Approach: | They propose a tool to facilitate the cultivation of scientific perspectives by interacting with a prompt-based model and allowing students to develop their own perspectives explicitly. |
| Outcome: | The proposed tool outperforms baseline approaches across multiple domains of literature from different perspectives. |
RealHiTBench: A Comprehensive Realistic Hierarchical Table Benchmark for Evaluating LLM-Based Table Analysis (2025.findings-acl)
Copied to clipboard
Pengzuo Wu, Yuhang Yang, Guangcheng Zhu, Chao Ye, Hong Gu, Xu Lu, Ruixuan Xiao, Bowen Bao, Yijing He, Liangyu Zha, Wentao Ye, Junbo Zhao, Haobo Wang
| Challenge: | Existing benchmarks for large language models focus on simple, flat table structures. |
| Approach: | They propose a benchmark to evaluate the performance of both Large Language Models and Multimodal LLMs across a variety of input formats for complex tabular data, including LaTeX, HTML, and PNG. |
| Outcome: | The proposed benchmark evaluates the performance of LLMs and Multimodal LLM models across a variety of input formats for complex tabular data, including LaTeX, HTML, and PNG. |
Conformalized Answer Set Prediction for Knowledge Graph Embedding (2025.naacl-long)
Copied to clipboard
| Challenge: | Knowledge graph embeddings (KGE) map entities and predicates into numerical vectors, providing non-classical reasoning capabilities based on similarities and analogies between entities and relations. |
| Approach: | They propose to use knowledge graph embeddings to provide non-classical reasoning capabilities by exploiting similarities and analogies between entities and relations. |
| Outcome: | The proposed model can generate answer sets with probabilistic guarantees on four benchmark datasets and is scaled well with respect to the difficulty of the query. |
WinoLogic: A Zero-Shot Logic-based Diagnostic Dataset for Winograd Schema Challenge (2021.emnlp-main)
Copied to clipboard
| Challenge: | Recent success of neural language models on the Winograd Schema Challenge has called for further investigation of commonsense reasoning ability of these models. |
| Approach: | They propose a logic-based framework that focuses on high-quality commonsense knowledge. |
| Outcome: | The proposed framework focuses on high-quality commonsense knowledge. |
PychoAgent: Psychology-driven LLM Agents for Explainable Panic Prediction on Social Media during Sudden Disaster Events (2025.emnlp-main)
Copied to clipboard
Mengzhu Liu, Zhengqiu Zhu, Chuan Ai, Chen Gao, Xinghong Li, Lingnan He, Kaisheng Lai, Yingfeng Chen, Xin Lu, Yong Li, Quanjun Yin
| Challenge: | Social media's rich information content and spatiotemporal granularity provide unique opportunities for emotion prediction and management. |
| Approach: | They propose a Psychology-driven generative Agent framework for explainable panic prediction based on emotion arousal theory. |
| Outcome: | The proposed framework improves panic emotion prediction performance by 13% to 21% compared to baseline models. |
Leveraging Explicit Lexico-logical Alignments in Text-to-SQL Parsing (2022.acl-short)
Copied to clipboard
| Challenge: | Text-to-SQL parsing aims to parse natural language questions into SQL queries . current attention-based approaches can only model alignments at the token level . |
| Approach: | They propose a method to leverage explicit lexico-logical alignments by identifying possible phrase-level alignments and injecting them as additional contexts into the parsing procedure. |
| Outcome: | The proposed approach improves performance by 3.4% on Squall. |
Comprehensive Benchmarking of Long-Form Speech Generation in Diverse Scenarios (2026.findings-acl)
Copied to clipboard
Changhao Pan, Rui Yang, Han Wang, Zhuan Zhou, Xuming He, Wenxiang Guo, Ziyue Jiang, Ruiqi Li, Yu Zhang, Chenyuhao Wen, Ke Lei, Xiang Yin, Jingyu Lu, Zhiyuan Zhu, Zhou Zhao
| Challenge: | Existing evaluation benchmarks for long-form speech are limited to limited domains, creating a significant gap with the diverse downstream applications. |
| Approach: | They propose a benchmark that decomposes "long-form speech quality" into specific, disentangled dimensions. |
| Outcome: | The proposed benchmark decomposes “long-form speech quality” into specific, disentangled dimensions. |
Beyond Prompting: An Efficient Embedding Framework for Open-Domain Question Answering (2025.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have recently pushed open-domain question answering (ODQA) to new heights. |
| Approach: | They propose an embedding-level framework that enhances both the retriever and the reader by reordering query representations via lightweight linear layers under an unsupervised contrastive learning objective. |
| Outcome: | The proposed framework outperforms baselines in accuracy and efficiency across three open-source LLMs, three retrieval methods, and four ODQA benchmarks. |
MuSC: Improving Complex Instruction Following with Multi-granularity Self-Contrastive Training (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for complex instruction-following with elaborate constraints rely on a weaker model, especially GPT-4, limiting their application. |
| Approach: | They propose a Multi-granularity Self-Contrastive Training framework to improve instruction alignment without relying on a stronger model. |
| Outcome: | The proposed framework improves instruction-following with elaborate constraints without external supervision on coarse and fine granularity. |
MdEval: Massively Multilingual Code Debugging (2026.findings-acl)
Copied to clipboard
Shukai Liu, Linzheng Chai, Jian Yang, Jiajun Shi, He Zhu, Liran Wang, Jin Ke, Wei Zhang, Hualei Zhu, Shuyue Guo, Tao Sun, Jiaheng Liu, Yunlong Duan, Yu Hao, Liqun Yang, Guanglin Niu, Ge Zhang, Zhoujun Li
| Challenge: | Existing benchmarks primarily focus on Python and are limited in terms of language diversity. |
| Approach: | They propose a multilingual debugging benchmark that includes 3.9K test samples of 20 programming languages and introduces the debug instruction corpora MdEval-Instruct by injecting bugs into the correct multilingual queries and solutions. |
| Outcome: | The proposed benchmark includes 3.9K test samples of 20 programming languages and covers the automated program repair task, bug localization task, and bug identification task. |
OpenToM: A Comprehensive Benchmark for Evaluating Theory-of-Mind Reasoning Capabilities of Large Language Models (2024.acl-long)
Copied to clipboard
| Challenge: | Existing N-ToM benchmarks lack ambiguous and artificial narratives, lack of personality traits and preferences, and limited diversity in the questions posed. |
| Approach: | They propose a benchmark to assess Neural Theory-of-Mind (N-ToM) with longer and clearer narrative stories, characters with explicit personality traits, actions triggered by character intentions, and questions designed to challenge LLMs’ abilities of modeling characters’ mental states. |
| Outcome: | The proposed test aims to assess the performance of LLMs in the physical and psychological worlds. |
CNNSum: Exploring Long-Context Summarization with Large Language Models in Chinese Novels (2025.findings-acl)
Copied to clipboard
| Challenge: | Currently, long-context summarization mainly relies on memory ability. |
| Approach: | They propose a multi-scale long-context summarization benchmark based on Chinese novels . they use human-driven annotations to analyze long-constituency models . |
| Outcome: | The proposed benchmark features human-driven annotations across four subsets with lengths ranging from 16k to 128k. |
A Simple Hash-Based Early Exiting Approach For Language Understanding and Generation (2022.findings-acl)
Copied to clipboard
Tianxiang Sun, Xiangyang Liu, Wei Zhu, Zhichao Geng, Lingling Wu, Yilong He, Yuan Ni, Guotong Xie, Xuanjing Huang, Xipeng Qiu
| Challenge: | Existing methods to measure instance difficulty use generalization and threshold-tuning . a new approach to learn to exit is based on hash functions to assign tokens to a fixed exiting layer. |
| Approach: | They propose a Hash-based Early Exiting approach that replaces learn-to-exit modules with hash functions to assign each token to a fixed exiting layer. |
| Outcome: | The proposed approach improves on learning to exit and predicting instance difficulty. |
PromptAttack: Probing Dialogue State Trackers with Adversarial Prompts (2023.findings-acl)
Copied to clipboard
| Challenge: | Toward building more robust and reliable conversational systems, we introduce a prompt-based learning approach to automatically generate effective adversarial examples to probe DST models. |
| Approach: | They propose a prompt-based learning approach to automatically generate effective adversarial examples to probe DST models. |
| Outcome: | The proposed framework leads to the greatest reduction in accuracy and the best attack success rate while maintaining good fluency and a low perturbation ratio. |
Few-Shot Table Understanding: A Benchmark Dataset and Pre-Training Baseline (2022.coling-1)
Copied to clipboard
| Challenge: | Pre-trained language models have demonstrated their effectiveness for few-shot table understanding, but few-shoot table understanding is rarely explored due to the deficiency of public table pre-training corpus and well-defined downstream benchmark tasks. |
| Approach: | They establish a benchmark dataset and use it to explore few-shot table understanding in Chinese. |
| Outcome: | The proposed model improves the few-shot table understanding in Chinese. |
Generative Pre-trained Speech Language Model with Efficient Hierarchical Transformer (2024.acl-long)
Copied to clipboard
| Challenge: | Experimental results indicate that GPST significantly outperforms the existing speech language models in terms of word error rate, speech quality, and speaker similarity. |
| Approach: | They propose a hierarchical transformer that quantizes audio waveforms into two distinct types of discrete speech representations and integrates them within a transformer architecture. |
| Outcome: | The proposed model outperforms existing speech language models in word error rate, speech quality, and speaker similarity. |
TENP: Trapezoidal Expert Neuron Pruning For Mixture-of-Experts (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing compression approaches remove entire experts, disrupting routing topology and harming performance, or rely on unstructured weight pruning with limited practical efficiency. |
| Approach: | They propose a structured **T**rapezoidal **E**xpert **N**euron **P**running framework that uses a trapezoidal pattern to identify and retain important experts while applying expert neuron pruning (ENP) to less important experts. |
| Outcome: | The proposed framework outperforms the full-parameter model by 10% on code generation tasks under a sparse activation of experts and a 40% routing sparsity. |
QueryLink: Leveraging Query-Memory Alignment for Long-Term Reasoning in LLM Agents (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to integrating external memory prioritize memory organization while overlooking a critical semantic gap between implicit, intent-driven queries and explicit, narrative-based memories. |
| Approach: | They propose a framework that leverages Query-Memory Alignment to project both queries and memories into a shared semantic space. |
| Outcome: | The proposed framework significantly outperforms SOTA methods on the LoCoMo and LongMemEval benchmarks and can be integrated as a plug-and-play component to boost existing vector-based systems like A-MEM. |
Disentangled Learning of Stance and Aspect Topics for Vaccine Attitude Detection in Social Media (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing approaches to detect vaccine attitudes on social media require abundant annotations and pre-defined aspect categories. |
| Approach: | They propose a semi-supervised approach to detect vaccine attitudes on social media . they use an autoencoding architecture to learn from unlabelled data the topical information of the domain . |
| Outcome: | The proposed model outperforms existing aspect-based models on stance detection and tweet clustering. |
Better Literary Translation: A Multi-Aspect Data Generation and LLM Training Approach (2026.acl-industry)
Copied to clipboard
| Challenge: | Literary translation requires balancing expression fluency with literary effect due to the scarcity of high-quality training data and the difficulty of capturing nuanced quality trade-offs. |
| Approach: | They propose a multi-aspect iterative refinement framework that generates high-quality translation references and preference data through specialized LLM translators. |
| Outcome: | The proposed models outperform the ground truth for SFT by 8.65 CEA100 points while leveraging an explicit reward model for GRPO yields an additional 1.51 point improvement. |
TwinVoice: A Multi-dimensional Benchmark Towards Digital Twins via LLM Persona Simulation (2026.findings-acl)
Copied to clipboard
Bangde Du, Minghao Guo, Songming He, Ziyi Ye, Xi Zhu, Weihang Su, Shuqi Zhu, Yujia Zhou, Yongfeng Zhang, Qingyao Ai, Yiqun Liu
| Challenge: | Existing studies show that advanced LLMs produce text indistinguishable from human writing. |
| Approach: | They propose a benchmark to assess persona simulation across diverse contexts by decomposing the evaluation into six fundamental capabilities including opinion consistency, memory recall, logical reasoning, persona tone, and syntactic style. |
| Outcome: | The proposed model achieves moderate accuracy but falls short of the basic capabilities needed to simulate personas in real-world contexts. |
Hierarchical Information Matters: Text Classification via Tree Based Graph Neural Network (2022.coling-1)
Copied to clipboard
| Challenge: | Text classification is a primary task in natural language processing (NLP). |
| Approach: | They propose a graph neural network (HINT) that makes full use of hierarchical information contained in the text for the task of text classification. |
| Outcome: | The proposed method outperforms the state-of-the-art methods on popular benchmarks while having a simple structure and few parameters. |
What Breaks Knowledge Graph based RAG? Benchmarking and Empirical Insights into Reasoning under Incomplete Knowledge (2026.eacl-long)
Copied to clipboard
Dongzhuoran Zhou, Yuqicheng Zhu, Xiaxia Wang, Hongkuan Zhou, Yuan He, Jiaoyan Chen, Steffen Staab, Evgeny Kharlamov
| Challenge: | Existing evaluation metrics and lenient answer matching criteria obscure meaningful comparisons. |
| Approach: | They propose a general method for constructing benchmarks and a method to assess KG-RAG methods under incomplete knowledge. |
| Outcome: | The proposed method systematically assesses KG-RAG methods under incomplete knowledge. |
XMC-Agent : Dynamic Navigation over Scalable Hierarchical Index for Incremental Extreme Multi-label Classification (2024.findings-acl)
Copied to clipboard
Yanjiang Liu, Tianyun Zhong, Yaojie Lu, Hongyu Lin, Ben He, Shuheng Zhou, Huijia Zhu, Weiqiang Wang, Zhongyi Liu, Xianpei Han, Le Sun
| Challenge: | Existing methods for XMC struggle with the growing set of labels due to their static label assumptions, and embedding-based methods struggle with complex mapping relationships due to late interaction paradigm. |
| Approach: | They propose a large language model (LLM) powered agent framework for extreme multi-label classification, XMC-Agent, which can effectively learn, manage and predict the extremely large and dynamically increasing set of labels. |
| Outcome: | The proposed framework can learn, manage and predict the extremely large and dynamically growing set of labels and achieves state-of-the-art performance on three standard datasets. |
MoE Adapter for Large Audio Language Models: Sparsity, Disentanglement, and Gradient-Conflict-Free (2026.findings-acl)
Copied to clipboard
Yishu Lei, Shuwei He, Hu Jing, Dan Zhang, Xianlong Luo, Danxiang Zhu, Shikun Feng, Rui Liu, Jingzhou HE, Yu Sun, Hua Wu, Haifeng Wang
| Challenge: | Existing research on Large Language Models (LLMs) limited to textual input modality . acoustic information is intrinsically heterogeneous, entangling attributes such as speech, music, and environmental context. |
| Approach: | They propose a sparse Mixture-of-Experts architecture to decouple acoustic information by routing audio tokens to specialized experts. |
| Outcome: | The proposed architecture outperforms existing models on audio semantic and paralinguistic tasks while retaining shared experts for global context. |
A Neural Generative Model for Joint Learning Topics and Topic-Specific Word Embeddings (2020.tacl-1)
Copied to clipboard
| Challenge: | Experimental results show that the proposed model outperforms word-level embedding methods in word similarity evaluation and word sense disambiguation. |
| Approach: | They propose a generative model that explores local and global context for joint learning topics and topic-specific word embeddings. |
| Outcome: | The proposed model outperforms word-level embedding methods in word similarity evaluation and word sense disambiguation. |
MTR-DuplexBench: Towards a Comprehensive Evaluation of Multi-Round Conversations for Full-Duplex Speech Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing benchmarks focus on evaluating single-round interactions, neglecting other critical aspects. |
| Approach: | They propose a benchmark to evaluate full-duplex speech language models in multi-round settings . they segment continuous full-dual dialogues into discrete turns for evaluation . |
| Outcome: | The proposed benchmark compared full-duplex speech language models with full-dual speech models . the results show that the models perform better in multi-round settings than standard models compared to benchmarks . |
Bridging SFT and RL: Dynamic Policy Optimization for Robust Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing unified optimization strategies overlook the statistical conflict between these distinct gradient signals. |
| Approach: | They propose a framework to reduce bias-variance trade-offs in Large Language Models . they propose DYPO, which leverages intrinsic group dynamics to significantly reduce RL gradient variance . |
| Outcome: | The proposed framework outperforms traditional pipelines on reasoning benchmarks and out-of-distribution tasks. |
Machine Translation With Weakly Paired Documents (D19-1)
Copied to clipboard
| Challenge: | Recent studies explore the possibility of unsupervised machine translation with monolingual data only. |
| Approach: | They propose a method to mine bilingual sentences from weakly paired documents . they use word distribution-level alignments to constrain word distributions of two weakly-paired documents. |
| Outcome: | The proposed method outperforms previous results on six translation tasks using weakly paired bilingual documents and a large number of bilingual sentences. |
Towards Graph-hop Retrieval and Reasoning in Complex Question Answering over Textual Database (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing benchmarks for textual question answering only focus on single-chain or single-hop retrieval . Existing approaches to answer complex questions have limitations . |
| Approach: | They propose to conduct Graph-Hop, a novel multi-chains and multi-hops retrieval paradigm in complex question answering. |
| Outcome: | The proposed model provides explicit and fine-grained evidence graphs for complex question to support comprehensive and detailed reasoning. |
InstructDiff: Domain-Adaptive Data Selection via Contrastive Entropy for Efficient LLM Fine-Tuning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing data selection methods suffer from severe domain specificity . existing methods for general instruction-following fail on reasoning tasks . |
| Approach: | They propose a framework that operationalizes contrastive entropy as a domain-adaptive selection criterion through warmup calibration, bi-directional NLL filtering, and entropic-based ranking. |
| Outcome: | Experiments show that InstructDiff outperforms baseline training on reasoning tasks while using only 10% of the data. |
Task-aware Contrastive Mixture of Experts for Quadruple Extraction in Conversations with Code-like Replies and Non-opinion Detection (2025.emnlp-main)
Copied to clipboard
| Challenge: | Applying Large Language Models (LLMs) for this specific task presents two primary challenges: the accurate extraction of multiple elements and the understanding of complex dialogue reply structure. |
| Approach: | They propose a novel LLM-based multi-task approach to extract sentiment quadruples from conversations by integrating expert-level contrastive loss within task-oriented mixture of experts layer. |
| Outcome: | The proposed method outperforms existing fine-tuning techniques in terms of accuracy and computational efficiency. |
PlanGPT-VL: Enhancing Urban Planning with Domain-Specific Vision-Language Models (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Existing Vision-Language Models (VLMs) fail to analyze planning maps . specialized visual representations of land use zones, transportation networks, and development policies are needed to interpret complex planning maps. |
| Approach: | They propose a domain-specific VLM tailored for urban planning maps that employs three innovations: PlanAnno-V framework for high-quality VQA data synthesis, Critical Point Thinking (CPT) and PlanBench-V benchmark for systematic evaluation. |
| Outcome: | The new model outperforms general-purpose VLMs on planning map interpretation tasks. |
Learning to Imagine: Integrating Counterfactual Thinking in Neural Discrete Reasoning (2022.acl-long)
Copied to clipboard
| Challenge: | Existing NDR models suffer from large performance drop on hypothetical questions, e.g., “what the annualized rate of return would be if the revenue in 2020 was doubled”. |
| Approach: | They propose a learning to imagine module which can be seamlessly incorporated into NDR models to perform the imagination of unseen counterfactual. |
| Outcome: | The proposed model can perform the imagination of unseen counterfactuals on hypothetical questions. |
Predictive Multiplicity of Knowledge Graph Embeddings in Link Prediction (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Knowledge graph embeddings (KGE) models are often used to predict missing links for knowledge graphs (KGs) however, multiple KG embedds can give conflicting predictions for unseen queries. |
| Approach: | They define predictive multiplicity in link prediction and introduce evaluation metrics to measure it using commonly used benchmark datasets. |
| Outcome: | The proposed methods significantly mitigat conflicts by 66% to 78% in link prediction. |
FANNO: Augmenting High-Quality Instruction Data with Open-Sourced LLMs Only (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent studies explore approaches to synthesize instruction data with open-sourced LLMs but require high-quality human-crafted seed data. |
| Approach: | They propose an end-to-end framework to synthesize high-quality instruction data with open-sourced LLMs and sampled unlabeled documents, eliminating the need for seed data. |
| Outcome: | The proposed framework synthesizes high-quality instruction data with open-sourced LLMs and sampled unlabeled documents, eliminating the need for seed data. |
Disentangling Aspect and Stance via a Siamese Autoencoder for Aspect Clustering of Vaccination Opinions (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to mining public opinions about vaccines from social media make direct usage of supervision information constraining the models to predefined aspect classes while still not distinguishing those aspects from users’ stances. |
| Approach: | They propose a model for vaccination opinion mining from social media that disentangles users’ stances from opinions via a disentangling attention mechanism and a Swapping-Autoencoder. |
| Outcome: | The proposed model outperforms existing methods on aspect-based opinion mining. |
SearchGym: Bootstrapping Real-World Search Agents via Cost-Effective and High-Fidelity Environment Simulation (2026.acl-long)
Copied to clipboard
Xichen Zhang, Ziyi He, Yinghao Zhu, Sitong Wu, Shaozuo Yu, Meng Chu, Wenhu Zhang, Haoru Tan, Jiaya Jia
| Challenge: | Search agents are a pivotal paradigm for solving open-ended, knowledge-intensive reasoning tasks. |
| Approach: | They propose a search agent simulation environment that bootstraps robust search agents using Reinforcement Learning. |
| Outcome: | The proposed model outperforms the web-enhanced ASearcher model by 10.6%. |
SCAIR: Schema-Conditioned Agentic Iterative Reasoning for Enterprise Knowledge Graphs (2026.acl-industry)
Copied to clipboard
Prateek Chaturvedi, Yuqicheng Zhu, Hongkuan Zhou, Dongzhuoran Zhou, Yunjie He, Steffen Staab, Fei Du, Jie Tang, Evgeny Kharlamov
| Challenge: | Existing agentic approaches for Knowledge Graph-based Retrieval-Augmented Generation fail to generalize to real-world enterprise Knowledge graphs (KGs) dense, schema-driven, and operationally constrained, requiring a training-free framework. |
| Approach: | They propose a training-free framework that integrates structured planning with controlled iterative reasoning by injecting schema-conditioned structural priors and enforcing schemas during multi-hop reasoning. |
| Outcome: | The proposed framework significantly improves on a real-world enterprise-oriented benchmark constructed from a Configuration Management DataBase (CMDB). |
Explaining Graph Neural Networks with Large Language Models: A Counterfactual Perspective on Molecule Graphs (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Graph Neural Networks (GNNs) are successful in molecular property prediction tasks, but their outputs are often black-box and not easily understandable by humans. |
| Approach: | They propose a method to unleash the power of large language models (LLMs) to explain GNNs for molecular property prediction. |
| Outcome: | The proposed method uses autoencoder to generate the counterfactual graph topology from a set of counterfact text pairs based on an input graph. |
Beat LLMs at Their Own Game: Zero-Shot LLM-Generated Text Detection via Querying ChatGPT (2023.emnlp-main)
Copied to clipboard
Biru Zhu, Lifan Yuan, Ganqu Cui, Yangyi Chen, Chong Fu, Bingxiang He, Yangdong Deng, Zhiyuan Liu, Maosong Sun, Ming Gu
| Challenge: | Large language models (LLMs) are capable of performing tasks but are likely to be misused. |
| Approach: | They propose a zero-shot black-box method to detect LLM-generated texts . they revise the text to be detected using the ChatGPT model . |
| Outcome: | The proposed method can detect LLM-generated texts with a zero-shot black-box model . it is based on intuition that the model will make fewer revisions to LLMs than to human-written texts . |
SPS: Steering Probability Squeezing for Better Exploration in Reinforcement Learning for Large Language Models (2026.findings-acl)
Copied to clipboard
Yifu Huo, Chenglong Wang, Ziming Zhu, Shunjie Xing, Peinan Feng, Tongran Liu, Qiaozhi He, Tian Hua Zhou, null Changxiaojia, JingBo Zhu, Zhengtao Yu, Tong Xiao
| Challenge: | Reinforcement learning (RL) training typically improves single-sample success rates but limited exploration of diverse reasoning trajectories. |
| Approach: | They propose a training paradigm that interleaves conventional RL with inverse reinforcement learning (IRL) they propose 'Steering Probability Squeezing' to enhance exploration without external supervision . |
| Outcome: | The proposed training paradigm improves Pass@k and improves exploration of diverse reasoning trajectories without external supervision. |
RAG over Tables: Hierarchical Memory Index, Multi-Stage Retrieval, and Benchmarking (2026.findings-acl)
Copied to clipboard
| Challenge: | Retrieval-Augmented Generation (RAG) integrates knowledge from tables with an external knowledge base to improve the answer relevance and accuracy. |
| Approach: | They propose a table-corpora-aware RAG framework called T-RAG to integrate external knowledge into Large Language Models (LLMs) they then develop a multi-table question answering benchmark called MultiTableQA which spans 3 different task types, 57,193 tables, and 23,758 questions in total. |
| Outcome: | The proposed framework achieves state-of-the-art accuracy, recall, and runtime performance, with improvements of up to 9.4%. |
Mitigating Hallucinations in Large Vision-Language Models without Performance Degradation (2026.acl-long)
Copied to clipboard
| Challenge: | Recent advances in large vision-language models produce hallucinations that compromise output reliability. |
| Approach: | They propose a dual-stage framework for mitigating hallucinations without performance degradation . they propose semantic-aware component disentanglement and interpretable parameter updates . |
| Outcome: | The proposed model reduces hallucinations by 23.4% while maintaining 97.4% of general generative capability. |
FocalOrder: Focal Preference Optimization for Reading Order Detection (2026.acl-long)
Copied to clipboard
Fuyuan Liu, Dianyu Yu, He Ren, Nayu Liu, Xiaomian Kang, Delai Qiu, Fa Zhang, Genpeng Zhen, Shengping Liu, Liang Jiaen, null Weihuang, Yining Wang, Junnan Zhu
| Challenge: | Existing methods for document comprehension rely on uniform supervision, resulting in a performance degradation in the intermediate sections. |
| Approach: | They propose a framework driven by Focal Preference Optimization to detect reading order in document layouts. |
| Outcome: | The proposed framework outperforms competing baselines and surpasses large-scale general VLMs. |
Mirror: Multiple-perspective Self-Reflection Method for Knowledge-rich Reasoning (2024.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) struggle with knowledge-rich problems without external resources. |
| Approach: | They propose a Multiple-perspective self-reflection method that allows LLMs to reflect from multiple-perceptive clues, achieved through a heuristic interaction between a Navigator and a Reasoner. |
| Outcome: | The proposed method is superior to other self-reflection methods on five reasoning datasets. |
UniRAG: Unified Query Understanding Method for Retrieval Augmented Generation (2025.acl-long)
Copied to clipboard
| Challenge: | Existing query augmentation methods face knowledge update lag and hallucinations in large language models (LLMs) Existing methods face two key challenges: (1) separation of query augmented and encoding tasks, which hinders information sharing and introduces cumulative errors; (2) difficulty of selecting optimal augmentation strategy for different scenarios. |
| Approach: | They propose a unified framework for query understanding in RAG that integrates internal and external knowledge to enhance query augmentation and encoding tasks. |
| Outcome: | The proposed framework outperforms traditional query augmentation methods in five knowledge-intensive benchmark tasks in both closed and open domain question answering. |
RISE: Reasoning Enhancement via Iterative Self-Exploration in Multi-hop Question Answering (2025.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) excel in many areas but face challenges with complex reasoning tasks, such as Multi-Hop Question Answering (MHQA). |
| Approach: | They propose a framework to enhance models’ reasoning capability through iterative self-exploration that addresses key errors in MHQA tasks such as Evidence Aggregation and Reasoning Decomposition. |
| Outcome: | Extensive experiments on multiple MHQA benchmarks show that the proposed framework significantly improves reasoning accuracy and task performance. |
ACE-M3: Automatic Capability Evaluator for Multimodal Medical Models (2025.coling-main)
Copied to clipboard
| Challenge: | Existing metrics for multimodal large language models only focus on token overlap and may not align with human judgment. |
| Approach: | They propose an open-source model that assesses the question answering abilities of multimodal large language models. |
| Outcome: | Experiments show that the ACE-M3 model performs better than existing models and is more reliable than existing metrics. |
DREAM: Disentangling Risks to Enhance Safety Alignment in Multimodal Large Language Models (2025.naacl-long)
Copied to clipboard
Jianyu Liu, Hangyu Guo, Ranjie Duan, Xingyuan Bu, Yancheng He, Shilong Li, Hui Huang, Jiaheng Liu, Yucheng Wang, Chenchen Jing, Xingwei Qu, Xiao Zhang, Pei Wang, Yanan Wu, Jihao Gu, Yangguang Li, Jianke Zhu
| Challenge: | Multimodal Large Language Models (MLLMs) pose unique safety challenges due to their integration of visual and textual data. |
| Approach: | They propose a method to disentangle risks through step-by-step reasoning within multimodal inputs. |
| Outcome: | The proposed approach improves safety alignment in MLLMs by fine-tuning and iterative Reinforcement Learning from AI feedback. |
CoRAG: Enhancing Hybrid Retrieval-Augmented Generation through a Cooperative Retriever Architecture (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods only retrieve related documents from local neighbors or subgraphs in the knowledge base, which often miss relevant information located further away from a global view. |
| Approach: | Hybrid-RAG combines textual documents and graph-structured relational information for RAG . existing methods only retrieve related documents from local neighbors or subgraphs in the knowledge base . |
| Outcome: | Hybrid-RAG combines textual documents and graph-structured relational information . existing methods only retrieve related documents from local neighbors or subgraphs in the knowledge base . |
ToolExpNet: Optimizing Multi-Tool Selection in LLMs with Similarity and Dependency-Aware Experience Networks (2025.findings-acl)
Copied to clipboard
| Challenge: | Current empirical methods that focus on isolated tools learning struggle with accurate multi-tool selection due to issues like confusing similar tools and neglecting dependencies. |
| Approach: | They propose a tool-learning paradigm which integrates tools and trial-and-error experiences into a network characterized by semantic similarity and dependency relationships. |
| Outcome: | The proposed model outperforms existing methods on multiple real-world API datasets and significantly outperformed baselines. |
Noise Learning for Text Classification: A Benchmark (2022.coling-1)
Copied to clipboard
| Challenge: | Existing noise learning methods for text classification are underdeveloped . authors propose a noise learning benchmark for text classification . |
| Approach: | They propose to use four state-of-the-art methods of noise learning from the image domain to classify text. |
| Outcome: | The proposed benchmark of noise learning for text classification is based on four methods and five noise modes. |
Copyright Detective: A Forensic System to Evidence LLMs Flickering Copyright Leakage Risks (2026.acl-demo)
Copied to clipboard
Guangwei Zhang, Jianing Zhu, Cheng Qian, Neil Zhenqiang Gong, Rada Mihalcea, Zhaozhuo Xu, Jingrui He, Jiaqi W. Ma, Chaowei Xiao, Bo Li, Ahmed Abbasi, Dongwon Lee, Heng Ji, Denghui Zhang
| Challenge: | **Copyright Detective** is the first interactive forensic system for detecting, analyzing, and visualizing potential copyright risks in LLM outputs. |
| Approach: | They propose a system that detects copyright infringements and visualizes them . they use content recall testing, paraphrase-level similarity analysis and persuasive jailbreak probing . |
| Outcome: | The proposed system detects, analyzes, and visualizes potential copyright risks in LLM outputs. |
Multimodal Joint Attribute Prediction and Value Extraction for E-commerce Product (2020.emnlp-main)
Copied to clipboard
| Challenge: | In the real world, product attribute values are incomplete and vary over time, which hinders practical applications. |
| Approach: | They propose a multimodal method to jointly predict product attributes and extract values from product images using multimodal product information. |
| Outcome: | The proposed method can predict product attributes and extract values from product images with the help of product images. |
DialogueMMT: Dialogue Scenes Understanding Enhanced Multi-modal Multi-task Tuning for Emotion Recognition in Conversations (2025.coling-main)
Copied to clipboard
| Challenge: | Existing ERC methods fail to handle emotional cues from both visual sources and discourse structures due to the complexity of visual scenes and contextual dependencies in conversations. |
| Approach: | They propose a framework for Emotion Recognition in conversations that utilizes multi-task instruction tuning to enhance the model's understanding of multi-modal dialogue scenes. |
| Outcome: | The proposed framework outperforms existing state-of-the-art models on three benchmark ERC datasets and is based on a video-language connector and a chain-of thought strategy. |
DivScore: Zero-Shot Detection of LLM-Generated Text in Specialized Domains (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing zero-shot detectors fail when applied to specialized content due to domain shift . DivScore outperforms state-of-the-art detectors in specialized domains . |
| Approach: | They propose a zero-shot detection framework that uses normalized entropy-based scoring and domain knowledge distillation to identify LLM-generated text in specialized domains. |
| Outcome: | The proposed framework outperforms state-of-the-art detectors on medical and legal datasets with 14.4% higher AUROC and 64.0% higher recall. |
AceGPT, Localizing Large Language Models in Arabic (2024.naacl-long)
Copied to clipboard
Huang Huang, Fei Yu, Jianqing Zhu, Xuening Sun, Hao Cheng, Song Dingjie, Zhihong Chen, Mosen Alharthi, Bang An, Juncai He, Ziche Liu, Junying Chen, Jianquan Li, Benyou Wang, Lian Zhang, Ruoyu Sun, Xiang Wan, Haizhou Li, Jinchao Xu
| Challenge: | Significant concerns emerge when addressing cultural sensitivity and local values. |
| Approach: | They propose a localized Large Language Model (LLM) specifically for Arabic, a language imbued with unique cultural characteristics inadequately addressed by current mainstream models. |
| Outcome: | The proposed model sets the state-of-the-art standard for open Arabic LLMs across various benchmarks. |
Multitask Pre-training of Modular Prompt for Chinese Few-Shot Learning (2023.acl-long)
Copied to clipboard
| Challenge: | Prompt tuning is a parameter-efficient approach to adapting pre-trained language models to downstream tasks. |
| Approach: | They propose to combine pre-trained modules with pre-trains to boost prompt tuning for few-shot learning. |
| Outcome: | The proposed model outperforms prompt tuning, full model tuning, and prior prompt pre-training methods in few-shot learning settings. |
How Can Synthetic Data Improve Multilingual Language Model Pretraining? A Data Quality Perspective (2026.acl-long)
Copied to clipboard
| Challenge: | Low-resource languages are a long-tail problem for multilingual LLMs due to limited high-quality training data. |
| Approach: | They propose a method that translates high-quality, knowledge-rich English data into low-resource languages . they propose SynRank, which leverages synthetic data as positive samples to train a classifier . |
| Outcome: | The proposed method matches handcrafted rule-based filtering by human experts and significantly improves knowledge-intensive tasks with less data. |
Multimodal Sentence Summarization via Multimodal Selective Encoding (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods for generating summary from text and image ignore that the image can improve the ability of the encoder to identify highlights of a news event or document. |
| Approach: | They propose a multimodal selective gate network that takes reciprocal relationships between textual and multi-level visual features into account to select highlights of the event. |
| Outcome: | The proposed model can generate summary for a given sentence-image pair using visual signals . it can also capture highlights embedded in the image more accurately, the authors show . |
Cracking the Code of Hallucination in LVLMs with Vision-aware Head Divergence (2025.acl-long)
Copied to clipboard
Jinghan He, Kuan Zhu, Haiyun Guo, Junfeng Fang, Zhenglin Hua, Yuheng Jia, Ming Tang, Tat-Seng Chua, Jinqiao Wang
| Challenge: | Existing methods focus on alignment training or decoding refinements but address symptoms at the generation stage without probing the underlying causes. |
| Approach: | They propose a training-free approach to mitigate hallucination by enhancing the role of vision-aware attention heads. |
| Outcome: | The proposed method achieves superior performance compared to state-of-the-art approaches in mitigating hallucinations while maintaining high efficiency with negligible additional time overhead. |
SymbolicThought: Integrating Language Models and Symbolic Reasoning for Consistent and Interpretable Human Relationship Understanding (2026.acl-demo)
Copied to clipboard
| Challenge: | Existing methods for constructing character relationships from plain text are time-consuming and low in coverage. |
| Approach: | They propose a human-in-the-loop framework that combines LLM-based extraction with symbolic reasoning. |
| Outcome: | The proposed framework improves annotation accuracy and consistency while significantly reducing time cost. |
LMGQS: A Large-scale Dataset for Query-focused Summarization (2023.findings-emnlp)
Copied to clipboard
Ruochen Xu, Song Wang, Yang Liu, Shuohang Wang, Yichong Xu, Dan Iter, Pengcheng He, Chenguang Zhu, Michael Zeng
| Challenge: | Lack of large-scale datasets for query-focused summarization hinders model development . lack of data limits the ability of QFS models to train robust neural models . |
| Approach: | They propose to generate a query for each summary sentence in a generic summarization annotation using a pretrained language model. |
| Outcome: | The proposed model achieves state-of-the-art zero-shot and supervised performance on multiple existing QFS benchmarks. |
MRT: Multi-modal Short- and Long-range Temporal Convolutional Network for Time-sync Comment Video Behavior Prediction (2024.lrec-main)
Copied to clipboard
| Challenge: | Using time-sync comments, it is difficult to understand user behavior due to complexity of interactions between users, videos, and comments. |
| Approach: | They propose a novel time-sync comment behavior prediction model that takes historical behavior into account and optimizes it on the basis of user preferences. |
| Outcome: | The proposed model improves the performance of time-sync comments on visual frames and textual comments on two cats playing simultaneously. |
HeteroSpec: Leveraging Contextual Heterogeneity for Efficient Speculative Decoding (2026.acl-long)
Copied to clipboard
| Challenge: | Autoregressive decoding limits the inference throughput of Large Language Models due to its sequential dependency. |
| Approach: | They propose a framework that allocates verification effort in proportion to candidate uncertainty. |
| Outcome: | Speculative decoding achieves an average speedup over state-of-the-art methods . a small subset of high-confidence predictions accounts for most successful verifications . |
Neural Temporal Opinion Modelling for Opinion Prediction on Twitter (2020.acl-main)
Copied to clipboard
| Challenge: | Existing studies have used a manual segmentation of a tweet sequence into equallyspaced intervals based on either tweet counts or time duration. |
| Approach: | They propose to model users’ tweet posting behaviour as a temporal point process to jointly predict the posting time and the stance label of the next tweet given a user’s historical tweet sequence and tweets posted by their neighbours. |
| Outcome: | The proposed model predicts the posting time and the stance labels of future tweets more accurately compared to baselines. |
OAgents: An Empirical Study of Building Effective Agents (2025.findings-emnlp)
Copied to clipboard
He Zhu, Tianrui Qin, King Zhu, Heyuan Huang, Yeyi Guan, Jinxiang Xia, Hanhao Li, Yi Yao, Ningning Wang, Pai Liu, Tianhao Peng, Xin Gui, Li Xiaowan, Yuhui Liu, Xiangru Tang, Jian Yang, Ge Zhang, Xitong Gao, Yuchen Eleanor Jiang, Changwang Zhang, Jun Wang, Jiaheng Liu, Wangchunshu Zhou
| Challenge: | a recent study shows that agent research practices are far from standard, rigorous . lack of a standard evaluation protocol makes previous works not reproducible, authors say . |
| Approach: | They conduct an empirical study on the GAIA benchmark to investigate agent design choices . they find that lack of a standard evaluation protocol makes previous works not reproducible . |
| Outcome: | The proposed framework achieves state-of-the-art performance among open-source projects. |
LIFBench: Evaluating the Instruction Following Performance and Stability of Large Language Models in Long-Context Scenarios (2025.acl-long)
Copied to clipboard
| Challenge: | Existing benchmarks rarely focus on instruction-following in long-context scenarios or stability on different inputs. |
| Approach: | They propose a scalable dataset to evaluate LLMs’ instruction-following capabilities and stability across long contexts. |
| Outcome: | The proposed method evaluates LLMs’ instruction-following capabilities and stability across long contexts. |
LayAlign: Enhancing Multilingual Reasoning in Large Language Models via Layer-Wise Adaptive Fusion and Alignment Strategy (2025.findings-naacl)
Copied to clipboard
| Challenge: | Large language models (LLMs) are pretrained on multilingual corpora but exhibit suboptimal performance on low-resource languages. |
| Approach: | They propose a framework that integrates representations from all encoder layers and an adaptive fusion-enhanced attention mechanism to enable layer-wise interaction between the LLM and the multilingual encoder. |
| Outcome: | Experiments on multilingual reasoning tasks show that the proposed framework outperforms baselines. |
LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-Training (2024.emnlp-main)
Copied to clipboard
| Challenge: | Mixture-of-Experts (MoE) has gained increasing popularity as a framework for scaling up large language models. |
| Approach: | They investigate how to build Mixture-of-Experts (MoE) models from existing large language models . they use expert construction, Continual pre-training and data sampling strategies . |
| Outcome: | The proposed model outperforms existing models with similar parameters on a wide range of tasks. |
BenchMAX: A Comprehensive Multilingual Evaluation Suite for Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing multilingual benchmarks focus primarily on language understanding tasks. |
| Approach: | They develop a multi-way multilingual benchmark that measures critical capabilities of large language models across languages. |
| Outcome: | Extensive experiments on BenchMAX reveal uneven utilization of core capabilities across languages, emphasizing the performance gaps that scaling model size alone does not resolve. |
Predicate-Conditional Conformalized Answer Sets for Knowledge Graph Embeddings (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods provide probabilistic guarantees over a reference set of queries and answers, but they fail to identify when the answers to a query are uncertain. |
| Approach: | They propose a method that approximates predicate-conditional coverage guarantees while maintaining compact prediction sets. |
| Outcome: | The proposed method provides predicate-conditional coverage guarantees while maintaining compact prediction sets. |
M2RC-EVAL: Massively Multilingual Repository-level Code Completion Evaluation (2025.acl-long)
Copied to clipboard
Jiaheng Liu, Ken Deng, Congnan Liu, Jian Yang, Shukai Liu, He Zhu, Peng Zhao, Linzheng Chai, Yanan Wu, JinKe JinKe, Ge Zhang, Zekun Moore Wang, Guoan Zhang, Yingshui Tan, Bangyu Xiang, Zhaoxiang Zhang, Wenbo Su, Bo Zheng
| Challenge: | Existing repository-level code completion benchmarks focus on a limited number of languages . existing benchmarks report overall average scores of different languages ignoring fine-grained abilities . |
| Approach: | They propose to use repository-level code completion benchmarks to evaluate general code intelligence abilities across languages for existing code Large Language Models. |
| Outcome: | The proposed benchmarks improve the code completion abilities of existing LLMs by using two types of annotations on the parsed syntax tree. |
An Empirical Study on Parameter-Efficient Fine-Tuning for MultiModal Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Multimodal Large Language Models fine-tuned with multimodal instruction-following data have demonstrated formidable capabilities in multimodal tasks. |
| Approach: | They propose to employ four PEFT methods to fine-tune the LLM component of open-source MLLMs. |
| Outcome: | The proposed method is the best performing on seven datasets, while fine-tuning the connector layers leads to improved performance in most MLLMs. |
Are NLP Models Good at Tracing Thoughts: An Overview of Narrative Understanding (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models (LLMs) excel in generating coherent texts, but their ability to comprehend the author’s thoughts remains uncertain. |
| Approach: | They conduct a comprehensive survey of narrative understanding tasks, examining their key features, definitions, taxonomy, associated datasets, evaluation metrics, and limitations. |
| Outcome: | The proposed framework could be extended to address novel narrative understanding tasks. |
PANACEA: An Automated Misinformation Detection System on COVID-19 (2023.eacl-demo)
Copied to clipboard
Runcong Zhao, Miguel Arana-catania, Lixing Zhu, Elena Kochkina, Lin Gui, Arkaitz Zubiaga, Rob Procter, Maria Liakata, Yulan He
| Challenge: | Using social media and fact-checking to detect misinformation is not enough to prevent the spread of false information. |
| Approach: | They propose a web-based misinformation detection system PANACEA which has two modules, fact-checking and rumour detection. |
| Outcome: | The system outperforms state-of-the-art methods and adapts graph convolutional networks model to detect rumours based on tweets rather than knowledge bases. |
Large Language Models are Better Reasoners with Self-Verification (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to solve complex natural language processing tasks require multiple steps to verify the answers. |
| Approach: | They propose to use chain of thought prompting to solve reasoning tasks with large language models. |
| Outcome: | The proposed method can improve reasoning performance on arithmetic, commonsense, and logical reasoning datasets. |
HiTIN: Hierarchy-aware Tree Isomorphism Network for Hierarchical Text Classification (2023.acl-long)
Copied to clipboard
| Challenge: | Existing dual-encoder methods in HTC achieve weak performance gains with huge memory overheads and their structure encoders heavily rely on domain knowledge. |
| Approach: | They propose a hierarchy-aware tree isomorphism network to enhance the text representations with only syntactic information of the label hierarchy. |
| Outcome: | The proposed model could boost the performance of hierarchical text classification without prior statistics or label semantics without prior data. |
E3-TIR: Enhanced Experience Exploitation for Tool-Integrated Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing training paradigms for Large Language Models (LLMs) suffer from inefficient exploration and mode degradation due to a lack of prior guidance, while SFT-then-RL is limited by high data costs and capability plateaus caused by low-entropy collapse. |
| Approach: | They propose an Enhanced Experience Exploitation paradigm that integrates expert prefixes, expert guided, and self-exploration to improve agent training. |
| Outcome: | The proposed model achieves a 6% performance improvement over traditional paradigms on tool-use tasks while requiring less than 10% of the synthetic data. |