Papers by Ye Wu

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference (2025.findings-acl)

Challenge:	Current work on understanding assembly code is oriented towards generating function names, which involve numerous abbreviations that make them confusing.
Approach:	They propose a control flow graph and pseudo code guided binary code summarization framework to learn the comprehensive binary function execution behavior and logic semantics.
Outcome:	The proposed framework improves the efficiency of reverse engineering on 3 different binary optimization levels for 3 different computer architectures.

Copied to clipboard

Ping Gong, Jiawei Yi, Shengnan Wang, Juncheng Zhang, Zewen Jin, Ouxiang Zhou, Ruibo Liu, Guanbin Xu, Youhui Bai, Bowen Ye, Kun Yuan, Tong Yang, Gong Zhang, Renhai Chen, Feng Wu, Cheng Li

Green & Sustainable NLP

Challenge:	Existing top-k attention methods struggle to strike a balance between efficiency and accuracy.
Approach:	They propose a top-k attention approach that integrates low-overhead techniques into the Top-k Attention process to achieve 7.2 speedup compared to vanilla full attention.
Outcome:	The proposed approach achieves 7.2 speedup compared to current top-k attention methods while maintaining model accuracy.

CoCA: Fusing Position Embedding with Collinear Constrained Attention in Transformers for Long Context Window Extending (2024.acl-long)

Copied to clipboard

Shiyi Zhu, Jing Ye, Wei Jiang, Siqiao Xue, Qi Zhang, Yifan Wu, Jianguo Li

Capturing Event Argument Interaction via A Bi-Directional Entity-Level Recurrent Decoder (2021.acl-long)

Challenge:	Existing models that use self-attention and position embedding have anomalous behavior that hinder long context window extrapolation.
Approach:	They propose a collinear constraint between Q and K to integrate RoPE and self-attention.
Outcome:	The proposed model integrates self-attention and position embedding into LLMs without fine-tuning.

Copied to clipboard

Xi Xiangyu, Wei Ye, Shikun Zhang, Quanxiu Wang, Huixing Jiang, Wei Wu

Llama SLayer 8B: Shallow Layers Hold the Key to Knowledge Injection (2024.findings-emnlp)

Challenge:	Existing efforts to capture event argument interactions are limited by the argument role type information of contextual entities.
Approach:	They propose to capture event argument interactions as a Seq2Seq-like learning problem where a sentence with a specific event trigger is mapped to a sequence of event argument roles.
Outcome:	The proposed neural architecture generates argument roles by incorporating contextual entities’ argument role predictions, like a word-by-word text generation process, thereby distinguishing implicit argument distribution patterns within an event more accurately.

Copied to clipboard

Tianxiang Chen, Zhentao Tan, Tao Gong, Yue Wu, Qi Chu, Bin Liu, Jieping Ye, Nenghai Yu

Challenge:	Existing methods to augment pre-trained large language models require extensive computational efforts and massive data volumes, challenging the widespread accessibility of LLM research.
Approach:	They propose a post-pretraining strategy of selectively enhancing shallow layers while pruning less effective deep ones to augment pretrained large language models.
Outcome:	The proposed approach improves performance on the corpus of code & math and a legal corpus and is widely applicable.

GMSA: Enhancing Context Compression via Group Merging and Layer Semantic Alignment (2026.acl-long)

Copied to clipboard

Jiwei Tang, Zhicheng Zhang, Shunlong Wu, Jingheng Ye, Lichen Bai, Zitai Wang, Tingwei Lu, Lin Hai, Yiming Zhao, Hai-Tao Zheng, Hong-Gee Kim

Leveraging Entity Information for Cross-Modality Correlation Learning: The Entity-Guided Multimodal Summarization (2024.findings-acl)

Challenge:	Large Language Models (LLMs) have achieved remarkable performance across NLP tasks . however, in long-context scenarios, they face high computational cost and information redundancy.
Approach:	They propose an encoder-decoder context compression framework that generates a compact sequence of soft tokens for downstream tasks.
Outcome:	Experiments show that GMSA outperforms baselines on multiple long-context question answering and summarization benchmarks while maintaining low end-to-end latency.

Copied to clipboard

Yanghai Zhang, Ye Liu, Shiwei Wu, Kai Zhang, Xukai Liu, Qi Liu, Enhong Chen

RepoAgent: An LLM-Powered Open-Source Framework for Repository-level Code Documentation Generation (2024.emnlp-demo)

Challenge:	Multimodal Summarization with Multimodal Output (MSMO) is a new approach to produce a multimodal summary that integrates both text and relevant images.
Approach:	They propose an Entity-Guided Multimodal Summarization model that integrates both text and relevant images to produce a multimodal summary.
Outcome:	The proposed model integrates text-image and entity-image information and refines image selection through knowledge distillation from a pre-trained vision-language model.

Copied to clipboard

Qinyu Luo, Yining Ye, Shihao Liang, Zhong Zhang, Yujia Qin, Yaxi Lu, Yesai Wu, Xin Cong, Yankai Lin, Yingli Zhang, Xiaoyin Che, Zhiyuan Liu, Maosong Sun

LoopCoder: Scaling Code Intelligence via Looped Language Models (2026.findings-acl)

Challenge:	Xia et al., 2018) demonstrate that a large language model can generate and maintain high-quality code documentation.
Approach:	They propose a large language model powered open-source framework for generating, maintaining, and updating code documentation.
Outcome:	The proposed framework generates high-quality documentation for the entire project.

Copied to clipboard

Jian Yang, Wei Zhang, Shuyue Guo, Yizhi LI, Linzheng Chai, Zhengmao Ye, Shukai Liu, Yuyang Song, Jiajun Wu, Che Liu, Tianyu Zheng, Siwei Wu, Leo L, Xudong Ma, Chuan Hao, Ran Tao, Yan Xing, Jianzhou Wang, Mingjie Tang, Aishan Liu, Zhoujun Li, Xianglong Liu, Weifeng Lv, Bryan Dai

On the Vulnerability of Safety Alignment in Open-Access LLMs (2024.findings-acl)

Challenge:	Large language models have mastered syntax-level code generation, but complex algorithmic reasoning remains a challenge.
Approach:	They propose a recurrent inductive bias that aligns with the recursive nature of programming logic.
Outcome:	The proposed model achieves comparable performance to standard dense models with more parameters.

Copied to clipboard

Jingwei Yi, Rui Ye, Qisi Chen, Bin Zhu, Siheng Chen, Defu Lian, Guangzhong Sun, Xing Xie, Fangzhao Wu

Grafting Pre-trained Models for Multimodal Headline Generation (2022.emnlp-industry)

Challenge:	Large language models (LLMs) are susceptible to malicious exploitation, but are often rejected and limited harmfulness is limited.
Approach:	They propose two types of reverse alignment techniques: reverse supervised fine-tuning (RSFT) and reverse preference optimization (RPO).
Outcome:	The proposed methods can significantly enhance the success rate and harmfulness of jailbreak attacks, but they face high rejection rates and limited harmfulness.

Copied to clipboard

Lingfeng Qiao, Chen Wu, Ye Liu, Haoyuan Peng, Di Yin, Bo Ren

Optimizing User Profiles via Contextual Bandits for Retrieval-Augmented LLM Personalization (2026.acl-long)

Challenge:	Existing approaches to generate video headlines with pre-trained language models are labor intensive and impractical.
Approach:	They propose to graft the encoder from the pre-trained video-language model on the generative pre-trainer model and propose a consensus fusion mechanism for the integration of different components.
Outcome:	The proposed model achieves strong results on a brand-new dataset collected from real-world applications.

Copied to clipboard

Linfeng Du, Ye Yuan, Zichen Zhao, Fuyuan Lyu, Emiliano Penaloza, Xiuying Chen, Zipeng Sun, Jikun Kang, Laurent Charlin, Xue Liu, Haolun Wu

Rehearsal-free Continual Language Learning via Efficient Parameter Isolation (2023.acl-long)

Challenge:	Existing approaches for personalizing large language models require modifying parameters.
Approach:	They propose a lightweight approach to personalizing large language models via retrieval augmentation . relevance serves as an unreliable proxy for utility, they argue .
Outcome:	The proposed framework outperforms strong heuristic and retrieval-augmented baselines on nine personalization tasks.

Copied to clipboard

Zhicheng Wang, Yufang Liu, Tao Ji, Xiaoling Wang, Yuanbin Wu, Congcong Jiang, Ye Chao, Zhencong Han, Ling Wang, Xu Shao, Wenqiu Zeng

Green & Sustainable NLP

Challenge:	Existing methods for learning continual tasks do not cache history data, which makes the problem more challenging.
Approach:	They propose a method that allocates a small portion of private parameters and learns them with a shared pre-trained model.
Outcome:	The proposed method is comparable to existing methods and comparable to those using historical data.

Self-Adaptive In-Context Learning: An Information Compression Perspective for In-Context Example Selection and Ordering (2023.acl-long)

Copied to clipboard

Zhiyong Wu, Yaoxiang Wang, Jiacheng Ye, Lingpeng Kong

Low-Resource NLP

Challenge:	In-context learning is a common practice to randomly sample examples to serve as context.
Approach:	They propose a new principle for in-context learning that helps each sample find an in-constitut example organization that can derive the correct prediction.
Outcome:	The proposed method achieves 40% relative improvement over the common practice setting.

Reasoning or Knowledge: Stratified Evaluation of Biomedical LLMs (2026.eacl-long)

Copied to clipboard

Rahul Thapa, Qingyang Wu, Kevin Wu, Harrison G Zhang, Angela Zhang, Eric Wu, Haotian Ye, James Zou

TransferTOD: A Generalizable Chinese Multi-Domain Task-Oriented Dialogue System with Transfer Capabilities (2024.emnlp-main)

Challenge:	Medical reasoning in large language models is a complex cognitive process through which clinicians interpret patient data and make diagnostic and therapeutic decisions.
Approach:	They propose an evaluation framework that disentangles knowledge recall from reasoning by training a PubMedBERT-based classifier and applying it to 11 widely used biomedical QA benchmarks.
Outcome:	The proposed evaluation framework disentangles knowledge recall from reasoning by training a PubMedBERT-based classifier and applying it to 11 widely used biomedical QA benchmarks.

Copied to clipboard

Ming Zhang, Caishuang Huang, Yilong Wu, Shichun Liu, Huiyuan Zheng, Yurui Dong, Yujiong Shen, Shihan Dou, Jun Zhao, Junjie Ye, Qi Zhang, Tao Gui, Xuanjing Huang

kNN-ICL: Compositional Task-Oriented Parsing Generalization with Nearest Neighbor In-Context Learning (2024.naacl-long)

Challenge:	Current datasets cater to user-led systems and are limited to predefined specific scenarios and slots.
Approach:	They propose to use a Chinese dialogue dataset to train a model that authentically simulates human-computer dialogues in 30 popular life service scenarios.
Outcome:	The proposed model achieves a joint accuracy of 75.09% in out-of-domain evaluations . it also achieves notable abilities in slot filling and questioning .

Copied to clipboard

Wenting Zhao, Ye Liu, Yao Wan, Yibo Wang, Qingyang Wu, Zhongfen Deng, Jiangshu Du, Shuaiqi Liu, Yunlong Xu, Philip Yu

RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within Generation (2025.acl-long)

Challenge:	Recent advances in task-oriented parsing involve formulating the task as a sequence-to-sequence problem, relying on a wealth of labeled data.
Approach:	They propose a task-oriented parsing framework that integrates nearest-neighbor learning with a nearest-nearest approach.
Outcome:	The proposed model can be used to synthesize computer programs based on a natural-language prompt without additional data or specialized prompts.

Copied to clipboard

Xiaoxi Li, Jiajie Jin, Yujia Zhou, Yongkang Wu, Zhonghua Li, Ye Qi, Zhicheng Dou

KELE: Residual Knowledge Erasure for Enhanced Multi-hop Reasoning in Knowledge Editing (2025.findings-emnlp)

Challenge:	Existing methods rely on separate retrievers to fetch top-k text chunks for generating evidence, and they lack joint optimization.
Approach:	They propose a framework that integrates retrieval and generation into a single, auto-regressive process, enabling LLMs to directly generate fine-grained evidence from the corpus with constrained decoding.
Outcome:	Extensive experiments on five open-domain QA datasets demonstrate the proposed framework’s superior performance across both in-domain and out-of-domain tasks.

Copied to clipboard

Mengqi Zhang, Bowen Fang, Qiang Liu, Xiaotian Ye, Shu Wu, Pengjie Ren, Zhumin Chen, Liang Wang

TrendSim: Simulating Trending Topics in Social Media Under Poisoning Attacks with LLM-based Multi-agent System (2025.findings-naacl)

Challenge:	Existing knowledge editing techniques show limitations when applied to multi-hop reasoning . residual single-hop knowledge causes edited models to revert to original answers .
Approach:	They propose a knowledge editing method that incorporates a Knowledge Erasure mechanism for Large language model Editing (KELE) they propose an erasure function for residual knowledge and an injection function for new knowledge .
Outcome:	The proposed method significantly improves multi-hop reasoning capability of edited models.

Copied to clipboard

Zeyu Zhang, Jianxun Lian, Chen Ma, Yaning Qu, Ye Luo, Lei Wang, Rui Li, Xu Chen, Yankai Lin, Le Wu, Xing Xie, Ji-Rong Wen

Act-Adaptive Margin: Dynamically Calibrating Reward Models for Subjective Ambiguity (2026.acl-long)

Challenge:	Trending topics bring in a new channel for poisoning attacks, resulting in negative impacts on society.
Approach:	They propose an LLM-based multi-agent system to simulate trending topics in social media . they propose a time-aware interaction mechanism, centralized message dissemination, and an interactive system .
Outcome:	The proposed system simulates trending topics under poisoning attacks on social media platforms.

Copied to clipboard

Feiteng Fang, Dingwei Chen, Xiang Huang, Ting-En Lin, Yuchuan Wu, Xiong Liu, Jing Ye, Ziqiang Liu, Haonan Zhang, Liang Zhu, Hamid Alinejad-Rokny, Min Yang, Yongbin Li

Challenge:	Existing approaches to reward modeling in reinforcement learning tasks are limited when dealing with ambiguous preferences.
Approach:	They propose to use AAM to dynamically calibrate preference margins using the Bradley-Terry model's internal parameter knowledge to improve reward modeling in subjective tasks.
Outcome:	The proposed approach improves reward modeling by dynamically calibrating preference margins using the model’s internal parameter knowledge.

Alleviating Hallucinations from Knowledge Misalignment in Large Language Models via Selective Abstention Learning (2025.acl-long)

Copied to clipboard

Lei Huang, Xiaocheng Feng, Weitao Ma, Yuchun Fan, Xiachong Feng, Yuxuan Gu, Yangfan Ye, Liang Zhao, Weihong Zhong, Baoxin Wang, Dayong Wu, Guoping Hu, Lingpeng Kong, Tong Xiao, Ting Liu, Bing Qin

Hierarchical Document Refinement for Long-context Retrieval-augmented Generation (2025.acl-long)

Challenge:	Large language models (LLMs) suffer from severe hallucination issues due to the knowledge misalignment between the pre-training stage and the supervised fine-tuning stage.
Approach:	They propose a training objective with an abstention mechanism that selectively rejects tokens that misalign with the desired knowledge distribution via a special [REJ] token.
Outcome:	The proposed model selectively rejects tokens that misalign with the desired knowledge distribution via a special [REJ] token.

Copied to clipboard

Jiajie Jin, Xiaoxi Li, Guanting Dong, Yuyao Zhang, Yutao Zhu, Yongkang Wu, Zhonghua Li, Ye Qi, Zhicheng Dou

Effective Sequence-to-Sequence Dialogue State Tracking (2021.emnlp-main)

Challenge:	Real-world RAG applications often encounter long-context input scenarios where redundant information and noise results in higher inference costs and reduced performance.
Approach:	They propose an efficient plug-and-play refiner that leverages the structural characteristics of long documents.
Outcome:	Experiments on seven QA datasets show that LongRefiner achieves competitive performance in various scenarios while using 10x fewer computational costs and latency compared to baseline.

Copied to clipboard

Jeffrey Zhao, Mahdis Mahdieh, Ye Zhang, Yuan Cao, Yonghui Wu

Beyond Text: Incorporating Metadata and Label Structure for Multi-Label Document Classification using Heterogeneous Graphs (2021.emnlp-main)

Challenge:	Using Sequence-to-Sequence models for dialogue state tracking remains an understudied topic.
Approach:	They propose to use a pre-training objective and a dialogue context representation to investigate this problem.
Outcome:	The proposed model is more effective than auto-regressive language modeling, the authors show . the proposed model may have a hard time recovering from earlier mistakes, they say .

Copied to clipboard

Chenchen Ye, Linhai Zhang, Yulan He, Deyu Zhou, Jie Wu

Information Extraction & Text Mining

Challenge:	Existing methods for multi-label document classification ignore the heterogeneous graphical structures of metadata and labels.
Approach:	They propose a neural network based approach to multi-label document classification that uses two heterogeneous graphs to model metadata and labels.
Outcome:	The proposed approach outperforms state-of-the-art models on two benchmark datasets.

ChatSOP: An SOP-Guided MCTS Planning Framework for Controllable LLM Dialogue Agents (2025.acl-long)

Copied to clipboard

Zhigen Li, Jianxiang Peng, Yanmeng Wang, Yong Cao, Tianhao Shen, Minghui Zhang, Linxi Su, Shang Wu, Yihang Wu, YuQian Wang, Ye Wang, Wei Hu, Jianfeng Li, Shaojun Wang, Jing Xiao, Deyi Xiong

Learning While Staying Curious: Entropy-Preserving Supervised Fine-Tuning via Adaptive Self-Distillation for Large Reasoning Models (2026.acl-long)

Challenge:	Existing models that use Large Language Models (LLMs) show superior performance in various tasks, but lack of controllability leads to unfocused conversations or task failure.
Approach:	They propose a standard operating procedure (SOP) framework to regulate dialogue flow by integrating Chain of Thought reasoning and supervised fine-tuning for SOP prediction.
Outcome:	The proposed method achieves a 27.95% improvement in action accuracy compared to baseline models based on GPT-3.5 and also shows notable gains for open-source models.

Copied to clipboard

Hao Wang, Hao Gu, Hongming Piao, Kaixiong Gong, Yuxiao Ye, Xiangyu Yue, Sirui Han, Yike Guo, Dapeng Wu

UNComp: Can Matrix Entropy Uncover Sparsity? — A Compressor Design from an Uncertainty-Aware Perspective (2025.emnlp-main)

Challenge:	Recent advances establish "SFT-then-RL" as the defacto paradigm for enhancing large reasoning mod- els on automatically verifiable tasks.
Approach:	They propose an entropy-preserving SFT method to enhance exploration capabilities through intrinsic curiosity.
Outcome:	The proposed method outperforms the vanilla method on reasoning tasks by 2.5 points . it also outperformed the vanilla SFT by 2.9 points on out-of-distribution tasks .

Copied to clipboard

Jing Xiong, Jianghan Shen, Fanghua Ye, Chaofan Tao, Zhongwei Wan, Jianqiao Lu, Xun Wu, Chuanyang Zheng, Zhijiang Guo, Min Yang, Lingpeng Kong, Ngai Wong

Reasoning

Challenge:	Deploying large language models (LLMs) for long-context inference remains challenging due to their substantial memory and computational demands.
Approach:	They propose an uncertainty-aware framework that leverages truncated matrix entropy to identify areas of low information content.
Outcome:	The proposed framework reduces the KV cache size to 4.74% of the original and achieves a 6% speedup.

A Bounding Box is Worth One Token - Interleaving Layout and Text in a Large Language Model for Document Understanding (2025.findings-acl)

Copied to clipboard

Jinghui Lu, Haiyang Yu, Yanjie Wang, Yongjie Ye, Jingqun Tang, Ziwei Yang, Binghong Wu, Qi Liu, Hao Feng, Han Wang, Hao Liu, Can Huang

MulDimIF: A Multi-Dimensional Constraint Framework for Evaluating and Improving Instruction Following in Large Language Models (2026.findings-acl)

Challenge:	Existing methods for integrating spatial layouts with text have limitations . existing methods produce overly long text sequences or lack autoregressive traits of LLMs .
Approach:	They introduce Interleaving Layout and Text in a Large Language Model (LayTextLLM) they use OCR-derived text and spatial layouts to integrate with LLMs for document understanding .
Outcome:	The proposed model shows an increase in performance in KIE and VQA tasks.

Copied to clipboard

Junjie Ye, Caishuang Huang, Zhuohan Chen, Wenjie Fu, Chenyuan Yang, Leyi Yang, Yilong Wu, Peng Wang, Meng Zhou, Xiaolong Yang, Tao Gui, Qi Zhang, Zhongchao Shi, Jianping Fan, Xuanjing Huang

STELLA: A Multimodal LLM for Protein Functional Annotation via Unified Sequence-Structure Encoding (2026.findings-acl)

Challenge:	Existing research has focused on constraint categories, offering little guidance for improving instruction following abilities.
Approach:	They propose a multi-dimensional constraint framework that allows for instruction following . they construct 9,106 code-verifiable samples and evaluate 18 LLMs .
Outcome:	The proposed framework improves instruction following performance without compromising general performance.

Copied to clipboard

Hongwang Xiao, Wenjun Lin, Xi Chen, Hui Wang, Kai Chen, Jiashan Li, Yuancheng Sun, Sicheng Dai, Boya Wu, Qiwei Ye

Context-Fidelity Boosting: Enhancing Faithful Generation through Watermark-Inspired Decoding (2026.findings-acl)

Challenge:	a multimodal protein language model (LLM) integrates sequence, structure, and function into functional annotation.
Approach:	They propose a multimodal protein language model that synergistically aligns bimodal representations with the textual modality to advance protein functional annotation.
Outcome:	The proposed model synergizes bimodal representations with the textual modality to advance protein functional annotation.

Copied to clipboard

Weixu Zhang, Fanghua Ye, Qiang Gao, Jian Li, Haolun Wu, Yuxing Tian, Sijing Duan, Nan Du, Xiaolong Li

Reasoning

Challenge:	Large language models produce content that contradicts or overlooks information provided in the input context, a phenomenon known as faithfulness hallucination.
Approach:	They propose a lightweight framework that boosts the generation probability of context-relevant tokens by boosting the generation of tokens.
Outcome:	The proposed framework improves faithfulness metrics with minimal generation overhead.

SimVBG: Simulating Individual Values by Backstory Generation (2025.emnlp-main)

Copied to clipboard

Bangde Du, Ziyi Ye, Zhijing Wu, Monika A. Jankowska, Shuqi Zhu, Qingyao Ai, Yujia Zhou, Yiqun Liu

Challenge:	Large language models (LLMs) have strong human-like capabilities, but rarely simulating individualized human values.
Approach:	They propose a framework that simulates individual values based on individual backstories . they use structured data on an individual to transform their backstoried information to a backstory .
Outcome:	The proposed framework improves top-1 accuracy by more than 10% over retrieval-augmented generation methods.

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

MolErr2Fix: Benchmarking LLM Trustworthiness in Chemistry via Modular Error Detection, Localization, Explanation, and Correction (2025.emnlp-main)

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.

Copied to clipboard

Yuyang Wu, Jinhui Ye, Shuhao Zhang, Lu Dai, Yonatan Bisk, Olexandr Isayev

ObfusLM: Privacy-preserving Language Model Service against Embedding Inversion Attacks (2025.acl-long)

Challenge:	Large Language Models (LLMs) have shown growing potential in molecular sciences, but they often produce chemically inaccurate descriptions and struggle to recognize or justify potential errors.
Approach:	They propose a benchmark to assess LLMs on error detection and correction in molecular descriptions.
Outcome:	The proposed benchmark targets LLMs on error detection and correction in molecular descriptions.

Copied to clipboard

Yu Lin, Ruining Yang, Yunlong Mao, Qizhi Zhang, Jue Hong, Quanwei Cai, Ye Wu, Huiqi Liu, Zhiyu Chen, Bing Duan, Sheng Zhong

Learning to Extract Structured Entities Using Language Models (2024.emnlp-main)

Challenge:	Recent studies show that obfuscation techniques for MLaaS are susceptible to embedding inversion attacks (EIAs).
Approach:	They propose a model obfuscation framework that protects client inputs from embedding inversion attacks by obliviously obbing models.
Outcome:	The proposed framework outperforms existing works in utility by 10% with a nearly 80% resistance rate against embedding inversion attacks.

Copied to clipboard

Haolun Wu, Ye Yuan, Liana Mikaelyan, Alexander Meulemans, Xue Liu, James Hensman, Bhaskar Mitra

Guardian-as-an-Advisor: Advancing Next-Generation Guardian Models for Trustworthy LLMs (2026.findings-acl)

Challenge:	Language Models (LMs) play a pivotal role in extracting structured information from unstructured text.
Approach:	They propose to reformulate the task to be entity-centric, enabling the use of diverse metrics that can provide more insights from various perspectives.
Outcome:	The proposed model outperforms baselines and human evaluations on the extracted entities.

Copied to clipboard

Yue Huang, Haomin Zhuang, Jiayi Ye, Han Bao, Yanbo Wang, Hang Hua, Siyuan Wu, Pin-Yu Chen, Xiangliang Zhang

Fundamental Capabilities of Large Language Models and their Applications in Domain Scenarios: A Survey (2024.acl-long)

Challenge:	prevailing taxonomies neglect robustness and honesty, yielding safer-on-paper but less useful systems.
Approach:	They propose a soft-gating pipeline where a guardian predicts a binary risk label plus a concise explanation and prepends this advice to the original query for re-inference.
Outcome:	The proposed model maintains safety while reducing over-refusal.

Copied to clipboard

Jiawei Li, Yizhe Yang, Yu Bai, Xiaofeng Zhou, Yinghao Li, Huashan Sun, Yuhang Liu, Xingpeng Si, Yuhao Ye, Yixiao Wu, 林一冠林一冠, Bin Xu, Ren Bowen, Chong Feng, Yang Gao, Heyan Huang

Landmark-Guided Cross-Speaker Lip Reading with Mutual Information Regularization (2024.lrec-main)

Challenge:	Existing benchmark-based evaluations cannot accurately reflect the performance of real-world applications.
Approach:	They propose a reliable strategy for domains to choose more robust LLMs for real-world applications.
Outcome:	The proposed strategy addresses the challenges faced by domains to choose more robust LLMs for real-world applications.

Copied to clipboard

Linzhi Wu, Xingyu Zhang, Yakun Zhang, Changyan Zheng, Tiejun Liu, Liang Xie, Ye Yan, Erwei Yin

Training-free LLM Merging for Multi-task Learning (2025.acl-long)

Challenge:	Lip reading is a process of interpreting silent speech from visual lip movements . but lip reading in cross-speaker scenarios poses a challenging problem due to inter-speech variability .
Approach:	They propose to exploit lip landmark-guided visual clues instead of mouth-cropped images as input features.
Outcome:	Experimental results show that the proposed approach reduces speaker-specific appearance characteristics in cross-speaker scenarios.

Copied to clipboard

Zichuan Fu, Xian Wu, Yejing Wang, Wanyu Wang, Shanshan Ye, Hongzhi Yin, Yi Chang, Yefeng Zheng, Xiangyu Zhao

Structure-aware Domain Knowledge Injection for Large Language Models (2025.acl-long)

Challenge:	Large Language Models (LLMs) have demonstrated exceptional capabilities across diverse natural language processing tasks.
Approach:	They propose a training-free method for unifying different specialized LLMs into a single model using model-wise and layer-wise pruning and scaling.
Outcome:	The proposed method outperforms existing merging techniques and surpasses models fine-tuned on combined datasets in most scenarios.

Copied to clipboard

Kai Liu, Ze Chen, Zhihang Fu, Wei Zhang, Rongxin Jiang, Fan Zhou, Yaowu Chen, Yue Wu, Jieping Ye

Tram: A Token-level Retrieval-augmented Mechanism for Source Code Summarization (2024.findings-naacl)

Challenge:	Structure-aware Continual Pre-Training (SCPT) and Structure-Aware Supervised Fine-Tuning (SSFT) are two-stage strategies for knowledge injection and alignment that reduces the training corpus needs to 5% while achieving 100% of traditional knowledge injection performance.
Approach:	They propose a method to efficiently transform foundation Large Language Models into domain specialists by using two-stage strategies: Structure-aware Continual Pre-Training and Structure-Aware Supervised Fine-Tuning.
Outcome:	The proposed method significantly reduces the training corpus needs to a mere 5% while achieving 100% of traditional knowledge injection performance.

Copied to clipboard

Tong Ye, Lingfei Wu, Tengfei Ma, Xuhong Zhang, Yangkai Du, Peiyu Liu, Shouling Ji, Wenhai Wang

Memory as Action: Autonomous Context Curation for Long-Horizon Agentic Tasks (2026.findings-acl)

Challenge:	Existing methods to generate source code summaries are coarse-grained and noise-filled . however, they do not capture contextual code semantics and are often outdated in continuous software iteration.
Approach:	They propose a fine-grained Token-level retrieval-augmented mechanism on the decoder side to enhance performance of neural models.
Outcome:	The proposed method produces more low-frequency tokens and is interpretable.

Copied to clipboard

Yuxiang Zhang, Jiangming Shu, Ye Ma, Xueyuan Lin, Shangxi Wu, Jitao Sang

Reasoning

Challenge:	Existing approaches to managing working memory are based on external mechanisms that lack awareness of the agent’s reasoning state, leading to suboptimal decisions.
Approach:	They propose a framework that treats working memory management as learnable policy actions and enables joint optimization of information retention and task performance through end-to-end reinforcement learning.
Outcome:	The proposed framework matches models 16 larger while reducing average context length by 51%, with learned strategies that adapt to model capabilities and generalize across task complexities.

SciCustom: A Framework for Custom Evaluation of Scientific Capabilities in Large Language Models (2026.acl-long)

Copied to clipboard

Yiyang Gu, Junwei Yang, Junyu Luo, Ye Yuan, Bin Feng, Yingce Xia, Shufang Xie, Kaili Liu, Bohan Wu, Qi Shi, Haoran Li, Beier Xiao, Zhiping Xiao, Xiao Luo, Weizhi Zhang, Philip S. Yu, Zequn Liu, Ming Zhang

ToolSword: Unveiling Safety Issues of Large Language Models in Tool Learning Across Three Stages (2024.acl-long)

Challenge:	Existing evaluations of large language models fail to reflect fine-grained capabilities . existing benchmarks are manually curated or domain-generic, limiting scalability and alignment with real use cases.
Approach:	They propose a framework that allows custom construction of benchmarks from large-scale scientific data to evaluate application-specific scientific capabilities in LLMs.
Outcome:	The proposed framework reveals fine-grained differences in scientific capabilities that standard benchmarks overlook . it allows custom construction of benchmarks from large-scale scientific data to evaluate application-specific capabilities in LLMs.

Copied to clipboard

Junjie Ye, Sixian Li, Guanyu Li, Caishuang Huang, Songyang Gao, Yilong Wu, Qi Zhang, Tao Gui, Xuanjing Huang

Can LLMs Simulate L2-English Dialogue? An Information-Theoretic Analysis of L1-Dependent Biases (2025.acl-long)

Challenge:	Existing research focuses on enhancing LLMs capabilities through tool utilization.
Approach:	They propose a framework to investigate safety issues in large language models in tool learning . they propose malicious queries and jailbreak attacks in the input stage .
Outcome:	The proposed framework investigates six safety scenarios for LLMs in tool learning . the data will be released upon acceptance of the proposed framework .

Copied to clipboard

Rena Wei Gao, Xuetong Wu, Tatsuki Kuribayashi, Mingrui Ye, Siya Qi, Carsten Roever, Yuanxing Liu, Zheng Yuan, Jey Han Lau

CPO: Addressing Reward Ambiguity in Role-playing Dialogue via Comparative Policy Optimization (2025.findings-emnlp)

Challenge:	Large Language Models (LLMs) can simulate non-native-like English use observed in human second language (L2) learners interfered with by their native first language (N1) knowledge.
Approach:	They use large language models to simulate non-native-like English use observed in human second language (L2) learners, and then compare their outputs to real L2 learner data.
Outcome:	The proposed models replicate L1-dependent patterns observed in human second language (L2) learners, with distinct influences from various languages.

Copied to clipboard

Jing Ye, Rui Wang, Yuchuan Wu, Victor Ma, Feiteng Fang, Fei Huang, Yongbin Li

Large Language Model Agents in Finance: A Survey Bridging Research, Practice, and Real-World Deployment (2025.findings-emnlp)

Challenge:	Comparative Policy Optimization (CPO) redefines the reward evaluation paradigm by shifting from sample-wise scoring to comparative group-wise score.
Approach:	They propose a method to optimize subjective tasks by shifting from sample-wise to comparative group-wise scoring.
Outcome:	The proposed framework shifts from sample-wise scoring to comparative group-wise score . it minimizes contextual bias and enables more robust and fair performance evaluation.

Copied to clipboard

Yifei Dong, Fengyi Wu, Kunlin Zhang, Yilong Dai, Sanjian Zhang, Wanghao Ye, Sihan Chen, Zhi-Qi Cheng

LLaMA Pro: Progressive LLaMA with Block Expansion (2024.acl-long)

Challenge:	a systematic review of large language models (LLMs) is conducted to better align their capabilities with real-world demands.
Approach:	They propose a functional taxonomy mapping financial domains to tasks, datasets, and institutional constraints. they catalog over 30 financial benchmarks and 20 representative models.
Outcome:	The proposed model frameworks are bridging financial practice and LLM research.

Copied to clipboard

Chengyue Wu, Yukang Gan, Yixiao Ge, Zeyu Lu, Jiahao Wang, Ye Feng, Ying Shan, Ping Luo

Knowledge Graph Enhanced Large Language Model Editing (2024.emnlp-main)

Challenge:	Existing studies have demonstrated that pre-trained LLMs are limited in certain domains, such as programming, mathematics, biomedical, or finance.
Approach:	They propose a new post-pretraining method with an expansion of Transformer blocks to tune the expanded blocks using only new corpus, efficiently and effectively improving the model’s knowledge while mitigating forgetting.
Outcome:	The proposed model outperforms existing models in programming and math and its instruction-following counterpart LLaMA Pro-8.3B in general tasks, programming, and mathematics.

Copied to clipboard

Mengqi Zhang, Xiaotian Ye, Qiang Liu, Pengjie Ren, Shu Wu, Zhumin Chen

Truth or Sophistry? LoFa: A Benchmark for LLM Robustness Against Logical Fallacies (2026.acl-long)

Challenge:	Existing methods for editing large language models struggle to track and incorporate changes in knowledge associated with edits, which limits the generalization ability of post-edit LLMs in processing edited knowledge.
Approach:	They propose a model editing method that leverages knowledge graphs to enhance LLM editing by capturing changes in associated knowledge by constructing an external graph.
Outcome:	The proposed method improves the generalization ability of LLMs in processing edited knowledge.

Copied to clipboard

Xudong Shen, li Yuan, Ye Chen, Xin Wu, Yi Cai, Zhiyong Wu

A Multitask Active Learning Framework for Natural Language Understanding (2020.coling-main)

Challenge:	Prior work has focused on the ability of Large Language Models to identify or classify fallacies, but their robustness against these fallacias in persuasive contexts remains largely unexplored.
Approach:	They propose a new metric to assess LLM robustness against fallacies by pairing factual questions with fallacious arguments and developing a multi-round debate framework to assess model resilience.
Outcome:	The proposed metric disentangles robustness from a model’s knowledge limitations and demonstrates unique vulnerability profiles across models.

Copied to clipboard

Hua Zhu, Wu Ye, Sihan Luo, Xidong Zhang

LLM Safety From Within: Detecting Harmful Content with Internal Representations (2026.acl-long)

Challenge:	Existing studies have shown that relation information between intents and slots can improve the efficiency of active learning algorithms.
Approach:	They propose a multitask active learning framework that exploits relation information between sub-tasks provided by a joint model.
Outcome:	The proposed framework achieves competitive performance with less training data than baseline methods on all datasets.

Copied to clipboard

Difan Jiao, Yilun Liu, Ye Yuan, Zhenwei Tang, Linfeng Du, Haolun Wu, Ashton Anderson

Representation Learning

Challenge:	State-of-the-art guard models rely on terminal-layer representations and overlook safety-relevant features encoded across internal layers.
Approach:	They propose a lightweight guard model that harnesses safety neurons from LLM internals without modifying the underlying model.
Outcome:	The proposed model outperforms open-source guard models across multiple benchmarks while using 250 fewer trainable parameters.

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use (2025.findings-emnlp)

Copied to clipboard

Junjie Ye, Yilong Wu, Sixian Li, Yuming Yang, Zhiheng Xi, Tao Gui, Qi Zhang, Xuanjing Huang, Peng Wang, Zhongchao Shi, Jianping Fan, Zhengyin Du

Prompt Optimization for Relation Extraction using Reinforcement Learning (2026.findings-acl)

Challenge:	a new approach to training large language models (LLMs) overlooks task-specific characteristics in tool use, leading to performance bottlenecks.
Approach:	They propose a task-feature-based framework that mitigates the effects of suboptimal training data . they use a dataset to train large-scale LLMs and a reward mechanism tailored to error categories .
Outcome:	The proposed framework matches or surpasses open- and closed-source LLMs in tool-use performance using only 1,217 training data points.

Copied to clipboard

Ying Liu, Dong Shuai, Cui Zibo, TengQi Ye, Gang Wu

ToolEyes: Fine-Grained Evaluation for Tool Learning Capabilities of Large Language Models in Real-world Scenarios (2025.coling-main)

Challenge:	Existing prompt-based methods rely heavily on large-scale annotated datasets limiting their applicability in domain-specific and low-resource scenarios.
Approach:	They propose a reinforcement learning-based automated prompt optimization framework for domain relation extraction that optimizes prompt quality through interaction with a black-box LLM.
Outcome:	The proposed framework outperforms existing prompt-based methods and supervised baselines on multiple extraction datasets across medical, financial, legal, and news domains.

Copied to clipboard

Junjie Ye, Guanyu Li, SongYang Gao, Caishuang Huang, Yilong Wu, Sixian Li, Xiaoran Fan, Shihan Dou, Tao Ji, Qi Zhang, Tao Gui, Xuanjing Huang

RAGLAB: A Modular and Research-Oriented Unified Framework for Retrieval-Augmented Generation (2024.emnlp-demo)

Challenge:	Existing evaluations of tool learning focus on validation of tools for large language models with expected outcomes, but this focus ignores the complex capabilities required for LLMs to effectively use tools.
Approach:	They propose a fine-grained system for evaluation of large language models’ tool learning capabilities in authentic scenarios.
Outcome:	The proposed system examines seven real-world scenarios, analyzing five dimensions crucial to LLMs in tool learning: format alignment, intent comprehension, behavior planning, tool selection, and answer organization.

Copied to clipboard

Xuanwang Zhang, Yun-Ze Song, Yidong Wang, Shuyun Tang, Xinfeng Li, Zhengran Zeng, Zhen Wu, Wei Ye, Wenyuan Xu, Yue Zhang, Xinyu Dai, Shikun Zhang, Qingsong Wen

PCBERT: Parent and Child BERT for Chinese Few-shot NER (2022.coling-1)

Challenge:	Existing research on Retrieval Augmented Generation (RAG) does not address the problem of hallucinations and real-time updating of knowledge.
Approach:	They propose a modular open-source library to equip LLMs with external knowledge.
Outcome:	The proposed approach reduces the need for expensive open-source tools and lacks fair comparisons between novel RAG algorithms.

Copied to clipboard

Peichao Lai, Feiyang Ye, Lin Zhang, Zhiwei Chen, Yanggeng Fu, Yingjie Wu, Yilei Wang

ZeroGen: Efficient Zero-shot Learning via Dataset Generation (2022.emnlp-main)

Challenge:	Existing approaches to improve model performance on few-shot or zero-shot datasets are not effective for Chinese few- shot NER.
Approach:	They propose a prompt-based Parent and Child BERT for Chinese few-shot NER to train an annotating model on high-resource datasets and then discover more implicit labels on low-resourced datasets.
Outcome:	The proposed model can be used on Weibo and other Chinese NER datasets and it is shown to be effective in few-shot learning.

Copied to clipboard

Jiacheng Ye, Jiahui Gao, Qintong Li, Hang Xu, Jiangtao Feng, Zhiyong Wu, Tao Yu, Lingpeng Kong

A Survey of Reinforcement Learning for Large Language Models under Data Scarcity: Challenges and Solutions (2026.acl-long)

Challenge:	Existing approaches to generate training data with pre-trained language models have been found effective in various scenarios.
Approach:	They propose an unsupervised zero-shot learning method that generates a dataset from scratch and trains a tiny task model under supervision of the synthesized dataset.
Outcome:	The proposed method is annotated-free and efficient, but can provide useful insights from the perspective of data-free model-agnostic knowledge distillation and unreferenced text generation evaluation.

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

RoTBench: A Multi-Level Benchmark for Evaluating the Robustness of Large Language Models in Tool Learning (2024.emnlp-main)

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.

Copied to clipboard

Junjie Ye, Yilong Wu, Songyang Gao, Caishuang Huang, Sixian Li, Guanyu Li, Xiaoran Fan, Qi Zhang, Tao Gui, Xuanjing Huang

DiMo-GUI: Advancing Test-time Scaling in GUI Grounding via Modality-Aware Visual Reasoning (2025.emnlp-main)

Challenge:	Current research emphasizes LLMs’ capacity to utilize tools in well-structured environments while overlooking their stability when confronted with the inevitable noise of the real world.
Approach:	They propose a multi-level benchmark to evaluate the robustness of large language models in tool learning by establishing five external environments with varying levels of noise.
Outcome:	The proposed model outperforms the GPT-4 model in tool learning in three critical phases: tool selection, parameter identification, and content filling.

Copied to clipboard

Hang Wu, Hongkai Chen, Yujun Cai, Chang Liu, Qingwen Ye, Ming-Hsuan Yang, Yiwei Wang

Neuro-Symbolic Query Compiler (2025.findings-acl)

Challenge:	DiMo-GUI is a training-free framework for GUI grounding that splits input into textual elements and iconic elements, allowing the model to reason over each modality independently using general-purpose vision-language models.
Approach:	They propose a training-free framework for GUI grounding that leverages two core strategies: dynamic visual grounding and modality-aware optimization.
Outcome:	The proposed framework splits the input into textual elements and iconic elements, allowing the model to reason over each modality independently using general-purpose vision-language models.

Copied to clipboard

Yuyao Zhang, Zhicheng Dou, Xiaoxi Li, Jiajie Jin, Yongkang Wu, Zhonghua Li, Ye Qi, Ji-Rong Wen

PSST: A Benchmark for Evaluation-driven Text Public-Speaking Style Transfer (2024.findings-emnlp)

Challenge:	Retrieval-Augmented Generation (RAG) systems are limited in their ability to process information in open-source environments.
Approach:	They propose a neuro-symbolic framework inspired by linguistic grammar rules and compiler design to formalize complex queries using a minimal yet sufficient Backus-Naur Form grammar.
Outcome:	The proposed framework is based on a backus-naur form grammar and compiler design that maintains completeness while minimizing redundancy.

Copied to clipboard

Huashan Sun, Yixiao Wu, Yizhe Yang, Yinghao Li, Jiawei Li, Yuhao Ye, Yang Gao

Text Generation

Challenge:	Existing methods to transfer text style focus on sentence-level data, limiting performance . current LLMs struggle to generate public speaking texts that align with human preferences .
Approach:	They propose a task to transform official texts into public-speaking styles by analyzing real-world data.
Outcome:	The proposed task aims to transform public speaking texts into public-speaking styles . the proposed framework analyzes characteristics and identifies problems of stylized texts .

DebugBench: Evaluating Debugging Capability of Large Language Models (2024.findings-acl)

Copied to clipboard

Runchu Tian, Yining Ye, Yujia Qin, Xin Cong, Yankai Lin, Yinxu Pan, Yesai Wu, Hui Haotian, Liu Weichuan, Zhiyuan Liu, Maosong Sun

An Inversion Attack Against Obfuscated Embedding Matrix in Language Model Inference (2024.emnlp-main)

Challenge:	Large language models (LLMs) have demonstrated exceptional coding capabilities, but their debugging capabilities remain relatively unexplored.
Approach:	They propose a debugging benchmark consisting of 4,253 LLMs with four major bug categories and 18 minor types in C++, Java, and Python.
Outcome:	The proposed benchmark covers four major bug categories and 18 minor types in C++, Java, and Python.

Copied to clipboard

Yu Lin, Qizhi Zhang, Quanwei Cai, Jue Hong, Wu Ye, Huiqi Liu, Bing Duan

BrowseConf: Confidence-Guided Test-Time Scaling for Web Agents (2026.findings-acl)

Challenge:	Recent studies have explored transforming user inputs to obfuscated embedded vectors, so that the data will not be eavesdropped by service providers.
Approach:	They propose to transform user inputs to obfuscated embedded vectors so that the data will not be eavesdropped by service providers.
Outcome:	The proposed inversion attack can recover user input 100% from the obfuscated vectors without a solid and deliberate security design and analysis .

Copied to clipboard

Litu Ou, Kuan Li, Huifeng Yin, Liwen Zhang, Zhongwang Zhang, Xixi Wu, Rui Ye, Zile Qiao, Yong Jiang, Pengjun Xie, Fei Huang, Jingren Zhou

Challenge:	Existing work on confidence in LLMs is limited.
Approach:	They propose to use confidence scores to determine model answer quality and encourage model to try again until it reaches satisfactory confidence level.
Outcome:	The proposed methods significantly reduce token consumption while demonstrating competitive performance compared to baseline fixed budget methods.

POINTS-Reader: Distillation-Free Adaptation of Vision-Language Models for Document Conversion (2025.emnlp-main)

Copied to clipboard

Yuan Liu, Zhongyin Zhao, Le Tian, Haicheng Wang, Xubing Ye, Yangxiu You, Zilin Yu, Chuhan Wu, Zhou Xiao, Yang Yu, Jie Zhou

OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use (2025.acl-long)

Challenge:	Existing approaches to training document conversion models with manual annotation are costly and time-consuming, and training student models by distilling outputs from teacher models can significantly limit their performance in real-world applications.
Approach:	They propose a fully automated framework for constructing high-quality document extraction datasets and models capable of handling diverse document formats and layouts.
Outcome:	The proposed model outperforms existing models and improves on annotated documents.

Copied to clipboard

Xueyu Hu, Tao Xiong, Biao Yi, Zishu Wei, Ruixuan Xiao, Yurun Chen, Jiasheng Ye, Meiling Tao, Xiangxin Zhou, Ziyu Zhao, Yuhuai Li, Shengze Xu, Shenzhi Wang, Xinchen Xu, Shuofei Qiao, Zhaokai Wang, Kun Kuang, Tieyong Zeng, Liang Wang, Jiwei Li, Yuchen Eleanor Jiang, Wangchunshu Zhou, Guoyin Wang, Keting Yin, Zhou Zhao, Hongxia Yang, Fan Wu, Shengyu Zhang, Fei Wu

Preference Heads in Large Language Models: A Mechanistic Framework for Interpretable Personalization (2026.acl-long)

Challenge:	a new generation of (M)LLMs is enabling the creation of superintelligent AI assistants . OS Agents can complete tasks autonomously and have the potential to significantly enhance the lives of billions of users worldwide.
Approach:	They propose to build OS Agents that operate within operating systems' GUIs and GUIs . they examine evaluation metrics and benchmarks to identify promising directions .
Outcome:	The proposed agents are based on operating systems (OS) and operating systems frameworks.

Copied to clipboard

Weixu Zhang, Ye Yuan, Changjiang Han, Yuxing Tian, Zipeng Sun, Linfeng Du, Jikun Kang, Hong Kang, Xue Liu, Haolun Wu

Shallow Focus, Deep Fixes: Enhancing Shallow Layers Vision Attention Sinks to Alleviate Hallucination in LVLMs (2025.emnlp-main)

Challenge:	Large Language Models exhibit strong implicit personalization ability, but most approaches treat this behavior as a black box.
Approach:	They propose a mechanistic interpretation perspective and propose 'sparse' set of Preference Heads . they compute a Preference Contribution Score for each attention head and compare their predictions .
Outcome:	The proposed framework computes a Preference Contribution Score (PCS) for each attention head and measures its causal impact on user aligned outputs.

Copied to clipboard

Xiaofeng Zhang, Yihao Quan, Chen Shen, Chaochen Gu, Xiaosong Yuan, Shaotian Yan, Jiawei Cao, Hao Cheng, Kaijie Wu, Jieping Ye

Beyond Surface Features: Advancing Medical Vision-Language Alignment via Dynamic Evidence-Guided Preference Optimization (2026.acl-long)

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.

Copied to clipboard

Zixuan Huang, Zhihong Zhu, Xiaolong Liu, Yanchao Hao, Manman Zhang, Zheng Wei, Bowen Xing, Xian Wu, Ye Li, Fen Miao, Yefeng Zheng

MMEvalPro: Calibrating Multimodal Benchmarks Towards Trustworthy and Efficient Evaluation (2025.naacl-long)

Challenge:	Existing preference-based methods for medical large vision-Language Models face limitations in medical settings . existing methods are limited by overfitting to superficial cues and pseudo convergence of the preference signal.
Approach:	They propose a framework that enables evidence-aware and adaptive preference learning for Med-LVLMs.
Outcome:	The proposed framework improves evidence-aware and adaptive preference learning for Med-LVLMs.

Copied to clipboard

Jinsheng Huang, Liang Chen, Taian Guo, Fu Zeng, Yusheng Zhao, Bohan Wu, Ye Yuan, Haozhe Zhao, Zhihui Guo, Yichi Zhang, Jingyang Yuan, Wei Ju, Luchen Liu, Tianyu Liu, Baobao Chang, Ming Zhang

TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing (2021.acl-demo)

Challenge:	Large Multimodal Models (LMMs) exhibit impressive cross-modal understanding and reasoning abilities, but many benchmarks suffer from systematic biases.
Approach:	They propose a benchmark to avoid Type-I errors by creating one perception question and one knowledge anchor question through a meticulous annotation process.
Outcome:	The proposed benchmark avoids Type-I errors while maintaining reliability of MCQ evaluations.

Copied to clipboard

Xiao Wang, Qin Liu, Tao Gui, Qi Zhang, Yicheng Zou, Xin Zhou, Jiacheng Ye, Yongxin Zhang, Rui Zheng, Zexiong Pang, Qinzhuo Wu, Zhengyan Li, Chong Zhang, Ruotian Ma, Zichu Fei, Ruijian Cai, Jun Zhao, Xingwu Hu, Zhiheng Yan, Yiding Tan, Yuan Hu, Qiyuan Bian, Zhihua Liu, Shan Qin, Bolin Zhu, Xiaoyu Xing, Jinlan Fu, Yue Zhang, Minlong Peng, Xiaoqing Zheng, Yaqian Zhou, Zhongyu Wei, Xipeng Qiu, Xuanjing Huang

OpenICL: An Open-Source Framework for In-context Learning (2023.acl-demo)

Challenge:	Existing approaches to textual robustness evaluation focus on slightly modifying the input data, which maintains the original meaning and results in a different prediction.
Approach:	They propose a multilingual robustness evaluation toolkit for NLP that integrates universal text transformations, task-specific transformations and adversarial attack.
Outcome:	The toolkit includes universal text transformation, task-specific transformation, adversarial attack, subpopulation, and their combinations to provide comprehensive robustness analyses.

Copied to clipboard

Zhenyu Wu, Yaoxiang Wang, Jiacheng Ye, Zhiyong Wu, Jiangtao Feng, Jingjing Xu, Yu Qiao

PRoLoRA: Partial Rotation Empowers More Parameter-Efficient LoRA (2024.acl-long)

Challenge:	In-context Learning (ICL) is a new paradigm for large language model evaluation.
Approach:	They propose an open-source toolkit for ICL and LLM evaluation.
Outcome:	The proposed framework is highly flexible and flexible and can be easily combined with other tools to suit users' needs.

Copied to clipboard

Sheng Wang, Boyang Xue, Jiacheng Ye, Jiyue Jiang, Liheng Chen, Lingpeng Kong, Chuan Wu

Green & Sustainable NLP

Challenge:	Partially Rotation-enhanced Low-Rank Adaptation (PRoLoRA) is an intra-layer sharing mechanism that circumvents the drawbacks of peer parameter-sharing methods.
Approach:	They propose a partially rotation-enhanced low-rank adaptation (PRoLoRA) that shares four components to reduce the cost of LoRA and improves model capacity.
Outcome:	Empirical results show that PRoLoRA outperforms LoRA on multiple instruction tuning datasets.

Improving Contextual Faithfulness of Large Language Models via Retrieval Heads-Induced Optimization (2025.acl-long)

Copied to clipboard

Lei Huang, Xiaocheng Feng, Weitao Ma, Yuchun Fan, Xiachong Feng, Yangfan Ye, Weihong Zhong, Yuxuan Gu, Baoxin Wang, Dayong Wu, Guoping Hu, Bing Qin