Papers by Ye Shen

NeuronMerge: Merging Models via Functional Neuron Groups (2025.findings-acl)

Challenge:	Current scientific reasoning models struggle with generalization across domains and fall short of multimodal perception.
Approach:	They propose to use multimodal large language models to integrate text, images, and other modalities to enhance scientific reasoning.
Outcome:	The proposed models can integrate text, images, and other modalities and improve reasoning across disciplines.

Copied to clipboard

Wangyun Gu, Qianghua Gao, Zhang Li-Xin, Xu Shen, Jieping Ye

Experience-driven Multi-turn Reinforcement Learning for GUI Agents (2026.acl-long)

Challenge:	Recent studies show that task arithmetic improves performance by combining model parameters with output features.
Approach:	They propose a neuron-based task arithmetic merging method that improves model linearity . they group neurons by function and propose combining them with existing models .
Outcome:	The proposed method improves performance across tasks and scales.

Copied to clipboard

Zhengxi Lu, Jiabo Ye, Fei Tang, Yongliang Shen, Haiyang Xu, Ziwei Zheng, Weiming Lu, Ming Yan, Fei Huang, Jun Xiao, Yueting Zhuang

Challenge:	GUI agents have demonstrated remarkable progress in automating complex user interface interactions . training such agents for long-horizon tasks remains challenging due to limited rewards and prohibitive costs.
Approach:	They propose a method that leverages expert trajectories as environment experiences for on-policy multi-turn training.
Outcome:	The proposed method achieves significant gains over the base model with 1K public trajectories as RL experiences . it achieves competitive performance against strong baselines such as UI-TARS-7B and GPT-4o .

One Battle After Another: Probing LLMs’ Limits on Multi-Turn Instruction Following with a Benchmark Evolving Framework (2026.acl-long)

Copied to clipboard

Qi Jia, Ye Shen, Xiujie Song, Kaiwei Zhang, Shibo Wang, Dun Pei, Xiangyang Zhu, Guangtao Zhai

Dialogue Systems & Conversational Agents

Challenge:	Existing benchmarks for instruction-following in multi-topic dialogues are limited to a fixed number of turns, susceptible to saturation and failing to account for users’ interactive experience.
Approach:	They propose a framework featuring a three-layer tracking mechanism and a query synthesis agent to mimic sequential user behaviors.
Outcome:	The proposed framework outperforms existing benchmarks in the evaluation of instruction following in multi-topic dialogues and demonstrates deficiencies in failure recovery and fine-grained instruction following.

GeAR: Graph-enhanced Agent for Retrieval-augmented Generation (2025.findings-acl)

Copied to clipboard

Zhili Shen, Chenxin Diao, Pavlos Vougiouklis, Pascual Merita, Shriram Piramanayagam, Enting Chen, Damien Graux, Andre Melo, Ruofei Lai, Zeren Jiang, Zhongyang Li, Ye Qi, Yang Ren, Dandan Tu, Jeff Z. Pan

Interpretable Composition Attribution Enhancement for Visio-linguistic Compositional Understanding (2024.emnlp-main)

Challenge:	Retrieval-augmented Generation (RAG) relies on effective retrieval capabilities, yet traditional sparse and dense retrievers struggle with multi-hop retrieval scenarios.
Approach:	They propose a graph expansion mechanism that augments any conventional base retriever and an agent framework that incorporates the resulting graph-based retrieval into a multi-step retrieval framework.
Outcome:	The proposed system achieves state-of-the-art results on three multi-hop question answering datasets while consuming fewer tokens and requiring fewer iterations than existing multi-step retrieval systems.

Copied to clipboard

Wei Li, Zhen Huang, Xinmei Tian, Le Lu, Houqiang Li, Xu Shen, Jieping Ye

Explainability & Interpretability in NLP

Challenge:	Despite promising progress, vision-language models still exhibit significant challenges in understanding visio-linguistic concepts beyond object terms.
Approach:	They propose a framework that encourages the model to pay greater attention to composition words denoting relationships and attributes within the text.
Outcome:	The proposed framework improves the ability to discern intricate details and construct more sophisticated interpretations of combined visual and linguistic elements.

Tracing and Dissecting How LLMs Recall Factual Knowledge for Real World Questions (2025.acl-long)

Copied to clipboard

Yiqun Wang, Chaoqun Wan, Sile Hu, Yonggang Zhang, Xiang Tian, Yaowu Chen, Xu Shen, Jieping Ye

CLEME: Debiasing Multi-reference Evaluation for Grammatical Error Correction (2023.emnlp-main)

Challenge:	Recent advances in large language models have shown promising ability to perform commonsense reasoning.
Approach:	They propose a two-dimensional analysis framework that incorporates token back-tracing and token decoding to uncover how LLMs conduct factual knowledge recall.
Outcome:	The proposed framework shows that LLMs lack relevant knowledge but struggle to select the most accurate information based on context during the retrieval and rerank phase.

Copied to clipboard

Jingheng Ye, Yinghui Li, Qingyu Zhou, Yangning Li, Shirong Ma, Hai-Tao Zheng, Ying Shen

Robustness in NLP

Challenge:	Evaluating the performance of Grammatical Error Correction systems is a challenging task due to its subjectivity.
Approach:	They propose a method to evaluate GEC systems in multi-reference evaluation setting . they use consistent edit boundaries to eliminate bias caused by inconsistent edit boundaries .
Outcome:	The proposed evaluation metric eliminates bias caused by inconsistent edit boundaries on six English reference sets.

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

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

Dialogue Systems & Conversational Agents

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 .

Visual Evidence Prompting Mitigates Hallucinations in Large Vision-Language Models (2025.acl-long)

Copied to clipboard

Wei Li, Zhen Huang, Houqiang Li, Le Lu, Yang Lu, Xinmei Tian, Xu Shen, Jieping Ye

P-FOLIO: Evaluating and Improving Logical Reasoning with Abundant Human-Written Reasoning Chains (2024.findings-emnlp)

Challenge:	LVLMs have shown impressive progress by integrating visual perception with linguistic understanding to produce contextually grounded outputs.
Approach:	They propose a visual evidence prompting method to mitigate hallucinations in large vision-language models by using small visual models to complement them.
Outcome:	The proposed method reduces hallucinations by reducing false activation and enhancing correct ones.

Copied to clipboard

Simeng Han, Aaron Yu, Rui Shen, Zhenting Qi, Martin Riddell, Wenfei Zhou, Yujie Qiao, Yilun Zhao, Semih Yavuz, Ye Liu, Shafiq Joty, Yingbo Zhou, Caiming Xiong, Dragomir Radev, Rex Ying, Arman Cohan

Information Extraction & Text Mining

Challenge:	Existing methods on understanding the capabilities of LLMs in logical reasoning rely on binary entailment classification or synthetically derived rationales.
Approach:	They propose to annotate a human-annotated dataset consisting of diverse and complex reasoning chains for a set of realistic logical reasoning stories also written by humans.
Outcome:	The proposed model outperforms existing methods on understanding the capabilities of LLMs in logical reasoning by 10% or more.

AnaloBench: Benchmarking the Identification of Abstract and Long-context Analogies (2024.emnlp-main)

Copied to clipboard

Xiao Ye, Andrew Wang, Jacob Choi, Yining Lu, Shreya Sharma, Lingfeng Shen, Vijay Murari Tiyyala, Nicholas Andrews, Daniel Khashabi

SalaMAnder: Shapley-based Mathematical Expression Attribution and Metric for Chain-of-Thought Reasoning (2025.findings-emnlp)

Challenge:	Analogical reasoning is an important part of human communication, says a new study . a benchmark to determine analogical reasoning ability in language models is needed .
Approach:	They propose to benchmark analogical reasoning ability in language models by collecting 340 analogies from human writings.
Outcome:	The proposed benchmark aims to determine analogical reasoning ability in language models.

Copied to clipboard

Yue Xin, Chen Shen, Shaotian Yan, Xiaosong Yuan, Yaoming Wang, Xiaofeng Zhang, Chenxi Huang, Jieping Ye

Automatic and Reliable Evaluation for Academic Caption-to-Figure Generation with LMMs (2026.acl-long)

Challenge:	Chain-of-Thought prompting improves the math reasoning capability of large language models.
Approach:	They propose a method for attribution of component-level contributions in CoT reasoning using Shapley value and a stratified sampling algorithm that significantly reduces computational complexity.
Outcome:	The proposed method reduces computational complexity and provides robust correlations with model performance.

Copied to clipboard

Guanghui Ye, Huan Zhao, Qin Zhu, Fengnan Li, Jiaqi Li, Yixian Shen, Zhonghao Ren, Zhihua Jiang

LLM Agents for Education: Advances and Applications (2025.findings-emnlp)

Challenge:	Existing datasets for evaluating text-to-image generation focus mostly on real-life images, which poses challenges for assessing academic figure generation given real scientific captions.
Approach:	They propose a dataset that first provides a Holistic Evaluation for Academic caption-to-Figure Generation (HE4AFG) they collect real figure captions from 8 scientific domains and generate 3,900 evaluation samples .
Outcome:	The proposed model provides high-quality human ratings in terms of three aspects—scientific aesthetic (SA), topic relevance (TR), and attribute correctness (AC).

Copied to clipboard

Zhendong Chu, Shen Wang, Jian Xie, Tinghui Zhu, Yibo Yan, Jingheng Ye, Aoxiao Zhong, Xuming Hu, Jing Liang, Philip S. Yu, Qingsong Wen

PALT: Parameter-Lite Transfer of Language Models for Knowledge Graph Completion (2022.findings-emnlp)

Challenge:	Large Language Model (LLM) agents are transforming education by automating complex tasks and enhancing both teaching and learning processes.
Approach:	This survey analyzes recent advances in applying Large Language Model agents to educational settings . it highlights ethical issues, hallucination and overreliance, and integration with existing ecosystems .
Outcome:	The authors analyze the technologies enabling LLM agents and highlight key challenges in deploying them in educational settings.

Copied to clipboard

Jianhao Shen, Chenguang Wang, Ye Yuan, Jiawei Han, Heng Ji, Koushik Sen, Ming Zhang, Dawn Song

Universally Empowering Zeroth-Order Optimization via Adaptive Layer-wise Sampling (2026.findings-acl)

Challenge:	Pretrained language models (LMs) are a powerful transfer learning approach for knowledge graph (KG) completion.
Approach:	They propose a parameter-lite transfer learning approach for pretrained language models for knowledge graph (KG) completion.
Outcome:	The proposed model outperforms the state-of-the-art models on a knowledge graph completion benchmark by tuning 1% of the parameters.

Copied to clipboard

Fei Wang, Li Shen, Liang Ding, Chao Xue, Ye Liu, Changxing Ding

Green & Sustainable NLP

Challenge:	Existing methods for fine-tuning Large Language Models are slow and lack of performance.
Approach:	They propose a Zeroth-Order optimization framework that uses forward passes to fine-tune Large Language Models.
Outcome:	The proposed framework achieves 1.7 to 3.0 wall-clock acceleration on LLaMA and OPT models.

From Redundancy to Relevance: Information Flow in LVLMs Across Reasoning Tasks (2025.naacl-long)

Copied to clipboard

Xiaofeng Zhang, Yihao Quan, Chen Shen, Xiaosong Yuan, Shaotian Yan, Liang Xie, Wenxiao Wang, Chaochen Gu, Hao Tang, Jieping Ye

TRIGO: Benchmarking Formal Mathematical Proof Reduction for Generative Language Models (2023.emnlp-main)

Challenge:	Large visionlanguage models (LVLMs) are a powerful visual-language reasoning tool.
Approach:	They propose to integrate attention analysis with LLaVA-CAM to determine interactions between visual representations.
Outcome:	The proposed approach can be used to determine interactions between visual representations.

Copied to clipboard

Jing Xiong, Jianhao Shen, Ye Yuan, Haiming Wang, Yichun Yin, Zhengying Liu, Lin Li, Zhijiang Guo, Qingxing Cao, Yinya Huang, Chuanyang Zheng, Xiaodan Liang, Ming Zhang, Qun Liu

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

Challenge:	Automated theorem proving (ATP) benchmarks focus on symbolic inference but rarely involve understanding complex number combination reasoning.
Approach:	They propose a benchmark that requires a model to reduce a trigonometric expression with step-by-step proof and evaluates a generative LM’s reasoning ability on formulas and ability to manipulate, group, and factor number terms.
Outcome:	The proposed benchmark evaluates a generative LM’s reasoning ability on formulas and ability to manipulate, group, and factor number terms.

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

Dialogue Systems & Conversational Agents

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.

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

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

Too Good to be Bad: On the Failure of LLMs to Role-Play Villains (2026.findings-acl)

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.

Copied to clipboard

Zihao Yi, Qingxuan Jiang, Ruotian Ma, Xingyu Chen, Qu Yang, Mengru Wang, Fanghua Ye, Ying Shen, Zhaopeng Tu, Xiaolong Li, Liefeng Bo

Challenge:	Large Language Models (LLMs) are increasingly tasked with creative generation, but their ability to portray non-prosocial, antagonistic personas remains largely unexamined.
Approach:	They propose a moral alignment benchmark to test the safety of large language models . they find that models struggle with traits directly antithetical to safety principles .
Outcome:	The proposed model fails to accurately portray morally ambiguous or villainous characters . the model fails most with traits directly antithetical to safety principles .

SAC-KG: Exploiting Large Language Models as Skilled Automatic Constructors for Domain Knowledge Graph (2024.acl-long)

Copied to clipboard

Hanzhu Chen, Xu Shen, Qitan Lv, Jie Wang, Xiaoqi Ni, Jieping Ye

GLTW: Joint Improved Graph Transformer and LLM via Three-Word Language for Knowledge Graph Completion (2025.findings-acl)

Challenge:	Existing KG construction methods rely on human intervention to attain qualified KGs, which severely hinders the practical application of domain KG.
Approach:	They propose a general KG construction framework that uses large language models as "Skilled" Automatic Constructors for domain knowledge (Graph)
Outcome:	The proposed framework generates specialized multi-level knowledge graphs at the scale of over one million nodes and achieves 89.32% precision rate compared to state-of-the-art methods.

Copied to clipboard

Kangyang Luo, Yuzhuo Bai, Cheng Gao, Shuzheng Si, Zhu Liu, Yingli Shen, Zhitong Wang, Cunliang Kong, Wenhao Li, Yufei Huang, Ye Tian, Xuantang Xiong, Lei Han, Maosong Sun

DT-Solver: Automated Theorem Proving with Dynamic-Tree Sampling Guided by Proof-level Value Function (2023.acl-long)

Challenge:	Existing knowledge graphs lack the ability to integrate structural information into LLMs and output predictions deterministically.
Approach:	They propose a method which encodes structural information of KGs and merges it with LLMs to enhance KGC performance.
Outcome:	The proposed method improves the performance of KG Completion datasets on KGs by integrating structural information with LLMs.

Copied to clipboard

Haiming Wang, Ye Yuan, Zhengying Liu, Jianhao Shen, Yichun Yin, Jing Xiong, Enze Xie, Han Shi, Yujun Li, Lin Li, Jian Yin, Zhenguo Li, Xiaodan Liang

On the Step Length Confounding in LLM Reasoning Data Selection (2026.findings-acl)

Challenge:	Recent advances in neural theorem-proving resort to large language models and tree searches.
Approach:	They propose a Dynamic-Tree Driven Theorem Solver to accommodate general theoremes by guiding the search procedure with state confidence and proof-level values.
Outcome:	The proposed method outperforms state-of-the-art methods on two popular theorem-proving datasets with a 6.65% improvement on average in terms of success rate.

Copied to clipboard

Bing Wang, Rui Miao, Chen Shen, Shaotian Yan, Kaiyuan Liu, Ximing Li, Xiaosong Yuan, Sinan Fan, Jun Zhang, Jieping Ye

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

Challenge:	Existing pipelines generate long reasoning data from more capable Large Language Models (LLMs) and apply manually heuristic or naturalness-based selection methods to filter high-quality samples.
Approach:	They propose to use supervised fine-tuning to generate long reasoning data from more capable Large Language Models and apply manually heuristic or naturalness-based selection methods to filter high-quality samples.
Outcome:	Experiments on four LLMs and five evaluation benchmarks show that the proposed approach is effective in mitigating step length confounding problem.

Copied to clipboard

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

Robustness in NLP

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.

Unveiling In-Context Learning: A Coordinate System to Understand Its Working Mechanism (2024.emnlp-main)

Copied to clipboard

Anhao Zhao, Fanghua Ye, Jinlan Fu, Xiaoyu Shen

Low-Resource NLP

Challenge:	Large language models exhibit remarkable in-context learning (ICL) capabilities, but the underlying working mechanism of ICL remains unclear.
Approach:	They propose a Two-Dimensional Coordinate System that unifies both views into a systematic framework that explains the behavior of ICL through two orthogonal variables: whether similar examples are presented in the demonstrations and whether LLMs can recognize the task.
Outcome:	The proposed method can interpret ICL for generation tasks effectively.

RISER: Orchestrating Latent Reasoning Skills for Adaptive Activation Steering (2026.findings-acl)

Copied to clipboard

Wencheng Ye, Xiaoyang Yuan, Yi Bin, Hengyu Jin, Liang Peng, Pengpeng Zeng, Heng Tao Shen

ToW: Thoughts of Words Improve Reasoning in Large Language Models (2025.naacl-long)

Challenge:	Existing methods for domain-specific reasoning with large language models require updating parameter updates.
Approach:	They propose a plug-and-play intervention framework that adaptively steers LLM reasoning in activation space.
Outcome:	The proposed framework achieves zero-shot accuracy improvements of 3.4–6.5% over the base model while outperforming chain-of-thought-style reasoning with 2–3 higher token efficiency and robust accuracy gains.

Copied to clipboard

Zhikun Xu, Ming Shen, Jacob Dineen, Zhaonan Li, Xiao Ye, Shijie Lu, Aswin Rrv, Chitta Baral, Ben Zhou

CURE: Critique-Driven Unified Reinforcement Learning for Test-Time Self-Improvement (2026.acl-long)

Challenge:	Unlike other data augmentation methods, thoughts of words (TOW) views next-word prediction as a core reasoning task and injects fine-grained thoughts into pre-training texts.
Approach:	They propose a training-time data-augmentation method called thoughts of words (TOW) that injects fine-grained thoughts directly into a next-word prediction task and teaches the model to understand how the observed next word is related to previous contexts.
Outcome:	The proposed method reduces model hallucination by 10% and improves reasoning performance by 7% to 9% on average.

Copied to clipboard

Guirong Chen, Shuqi Ye, Wenkai Yang, Shiqi Shen, Guangyao Shen, Yankai Lin

Challenge:	Existing critique-guided methods fail to equip models with the autonomous improvement capabilities required for test-time scaling.
Approach:	They propose a framework that jointly optimizes a single policy for standard solving, critiquing, and guided re-exploration.
Outcome:	The proposed framework maintains competitive single-turn performance and unlocks effective inference-time scaling.

Enhancing Chain-of-Thought Reasoning with Critical Representation Fine-tuning (2025.acl-long)

Copied to clipboard

Chenxi Huang, Shaotian Yan, Liang Xie, Binbin Lin, Sinan Fan, Yue Xin, Deng Cai, Chen Shen, Jieping Ye

Interpret and Improve In-Context Learning via the Lens of Input-Label Mappings (2025.acl-long)

Challenge:	Representation Fine-tuning (ReFT) is a proposed method for improving parameter efficiency . however, it yields suboptimal performance, as fixed-position representations have uncertain impact on outputs .
Approach:	They propose a method that fine-tunes critical representations in a low-rank linear subspace while freezing the base model.
Outcome:	The proposed method improves accuracy of LLaMA-2-7B and ReFT by 18.2 and 3.8 on GSM8K.

Copied to clipboard

Chenghao Sun, Zhen Huang, Yonggang Zhang, Le Lu, Houqiang Li, Xinmei Tian, Xu Shen, Jieping Ye

Discover and Prove: An Open-source Agentic Framework for Hard Mode Automated Theorem Proving in Lean 4 (2026.acl-long)

Challenge:	Large language models excel at downstream NLP tasks through in-context learning . however, the internal mechanisms behind ICL remain under-explored .
Approach:	They propose a PC patching approach to identify modules where input-label mappings function . they observe and verify that key heads utilize input-labeled mappings to generate target labels for new queries.
Outcome:	The proposed approach detects modules where input-label mappings function . it also detects that key heads use the mappings to generate labels for new queries .

Copied to clipboard

Chengwu Liu, Yichun Yin, Ye Yuan, Jiaxuan Xie, Botao Li, Siqi Li, Jianhao Shen, Yan Xu, Lifeng Shang, Ming Zhang

Position: LLMs Can be Good Tutors in English Education (2025.emnlp-main)

Challenge:	Existing approaches to solving mathematical problems fall into two broad categories: informal methods and formal methods.
Approach:	They propose to use LLM natural-language reasoning to discover answers . they introduce Discover And Prove framework that rewrites Hard Mode statements into Easy Mode ones for existing ATP provers.
Outcome:	The proposed framework can be used to prove hard mode statements on ATP benchmarks.

Copied to clipboard

Jingheng Ye, Shen Wang, Deqing Zou, Yibo Yan, Kun Wang, Hai-Tao Zheng, Ruitong Liu, Zenglin Xu, Irwin King, Philip S. Yu, Qingsong Wen

QA‐LIGN: Aligning LLMs through Constitutionally Decomposed QA (2025.findings-emnlp)

Challenge:	Recent efforts to integrate large language models into English education lack adaptability to language learning.
Approach:	They argue that large language models can be effective tutors in English education . they encourage interdisciplinary research to explore these roles, fostering innovation and risks .
Outcome:	The proposed models can play three critical roles: 1) as data enhancers, 2) as task predictors, 3) as agents, enabling personalized and inclusive education.

Copied to clipboard

Jacob Dineen, Aswin Rrv, Qin Liu, Zhikun Xu, Xiao Ye, Ming Shen, Zhaonan Li, Shijie Lu, Chitta Baral, Muhao Chen, Ben Zhou

Explainability & Interpretability in NLP

Challenge:	QA-LIGN decomposes monolithic rewards into interpretable principle-specific evaluations . scalar rewards obscure which objectives drive the training signal .
Approach:	a new method decomposes monolithic rewards into interpretable principle-specific evaluations . QA-LIGN reduces attack success rates by up to 68.7% while maintaining a 0.67% false refusal rate .
Outcome:	QA-LIGN reduces attack success rates by up to 68.7% while maintaining a 0.67% false refusal rate . the results outperform DPO and GRPO with state-of-the-art reward models given equivalent training .

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

Copied to clipboard

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

LexRel: Benchmarking Legal Relation Extraction for Chinese Civil Cases (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

Yida Cai, Ranjuexiao Hu, Huiyuan Xie, Chenyang Li, Yun Liu, Yuxiao Ye, Zhenghao Liu, Weixing Shen, Zhiyuan Liu

Information Extraction & Text Mining

Challenge:	Legal relations are an important analytical framework for dispute resolution in civil cases.
Approach:	They propose a comprehensive schema for legal relations in civil cases with hierarchical taxonomy and definitions of arguments.
Outcome:	The proposed schema shows that existing LLMs lack the ability to identify civil legal relations and performance improves on downstream tasks.

Measuring Social Norms of Large Language Models (2024.findings-naacl)

Copied to clipboard

Ye Yuan, Kexin Tang, Jianhao Shen, Ming Zhang, Chenguang Wang

Concise and Organized Perception Facilitates Reasoning in Large Language Models (2025.findings-naacl)

Challenge:	Existing datasets that evaluate a general understanding of social science are inadequate to understand social norms.
Approach:	They propose a multi-agent framework to improve large language models’ ability to understand social norms by comparing them to elementary students.
Outcome:	The proposed framework improves large language models to be on par with humans.

Copied to clipboard

Junjie Liu, Shaotian Yan, Chen Shen, Zhengdong Xiao, Liang Xie, Wenxiao Wang, Jieping Ye

Beyond Scaling: Measuring and Predicting the Upper Bound of Knowledge Retention in Language Model Pre-Training (2026.acl-long)

Challenge:	Extensive experimental results on several popular logical benchmarks (ProofWriter, PrOntoQA, PrONtoQA-OOD, and FOLIO) and mathematical benchmark (DI-GSM) show that COP significantly outperforms previous state-of-the-art methods.
Approach:	They propose a reasoning approach called Concise and Organized Perception (COP) that carefully analyzes the given statements to identify the most pertinent information while eliminating redundancy efficiently.
Outcome:	The proposed approach outperforms state-of-the-art methods on several popular logical benchmarks and mathematical benchmarks.

Copied to clipboard

Changhao Jiang, Ming Zhang, Yifei Cao, Junjie Ye, Xiaoran Fan, Shihan Dou, Zhiheng Xi, Jiajun Sun, Yi Dong, Yujiong Shen, Jingqi Tong, Baoyu Fan, Tao Gui, Qi Zhang, Xuanjing Huang

When Life Gives You Samples: The Benefits of Scaling up Inference Compute for Multilingual LLMs (2025.emnlp-main)

Challenge:	Existing methods to predict performance of large language models are lacking . authors propose a size-dependent mutual information predictor for closed-book question answering accuracy .
Approach:	They propose a size-dependent mutual information predictor that integrates knowledge frequency, knowledge specificity, and model size to forecast closed-book question answering accuracy.
Outcome:	The proposed method outperforms baseline models and achieves R2 > 0.7 in predicting QA accuracy without additional training.

Copied to clipboard

Ammar Khairi, Daniel D’souza, Ye Shen, Julia Kreutzer, Sara Hooker

Multilinguality

Challenge:	Recent advances in large language models have shifted focus toward scaling inference-time compute.
Approach:	They propose to scale inference-time compute in a multilingual, multi-task setting . they propose to use m-ArenaHard-v2.0 prompts to sample multiple outputs in parallel .
Outcome:	The proposed solutions achieve an average +6.8 jump in win-rates for 8B models on m-ArenaHard-v2.0 prompts in non-English languages against proprietary models like Gemini.

When TableQA Meets Noise: A Dual Denoising Framework for Complex Questions and Large-scale Tables (2026.acl-long)

Copied to clipboard

Shenghao Ye, Yu Guo, Dong Jin, Yuxiang Wang, Yikai Shen, Yunpeng Hou, Shuangwu Chen, null Jianyang, Xiaofeng Jiang