ACL 2026

2,650 papers

Global Adaptive Momentum Meets Local Personalized Perturbation: Efficient Federated LLM Fine-Tuning with Zeroth-Order Gradients

Zihan Chen, Howard Hao Yang, Tony Quek, Kai Fong Ernest Chong

Decoding-Unlearning: Fact Forgetting via Entropy-Guided Inference

Jingwen Pu, Mingjun Shi, Xinrui Ren, Yizhe Wang, Xinyu Zhang

Language Statistics and False Belief Reasoning: Evidence from 41 Open-Weight LMs

Sean Trott, Samuel M. Taylor, Cameron Robert Jones, James A. Michaelov, Pamela D. Rivière

Libra-VLA: Achieving Learning Equilibrium via Asynchronous Coarse-to-Fine Dual-System

Yifei Wei, Linqing Zhong, Yi Liu, Yuxiang Lu, Xindong He

MedEinst: Benchmarking the Einstellung Effect in Medical LLMs through Counterfactual Differential Diagnosis

Wenting Chen, Guolin Huang, Wenxuan Wang, Zhongrui Zhu

Evaluating LLMs on Large-Scale Graph Property Estimation via Random Walks

Sunil Kumar Maurya, Xin Liu

AttnPO: Attention-Guided Process Supervision for Efficient Reasoning

Shuaiyi Nie, Dingsiyu, Wenyuan Zhang, Linhao Yu, Tianmeng Yang

LLM Safety From Within: Detecting Harmful Content with Internal Representations

Difan Jiao, Yilun Liu, Ye Yuan, Zhenwei Tang, Linfeng Du

ASTRA: An Automated Framework for Strategy Discovery, Retrieval, and Evolution for Jailbreaking LLMs

Xu Liu, Yan Chen, Kan Ling, Yichi Zhu, Hengrun Zhang

PDTrim: Targeted Pruning for Prefill-Decode Disaggregation in Inference

Hao Zhang, Lyu Mengsi, Zhuo Chen, Yulong Ao, Yonghua Lin

Rethinking Depression Prediction from a Fine-Grained Subscore Modeling Perspective via Multi-Task Learning

Zhenguang Wang, Bo Li, Wenhui Tan, Peng Cao, Yang Wang

KnowRL: Exploring Knowledgeable Reinforcement Learning for Factuality

Baochang Ren, Shuofei Qiao, Ningyu Zhang, Da Zheng, Huajun Chen

DARM: Distribution-Aware Reward Modeling by Alleviating Biases from Low Preference-Context Dependency Data

Shaofan Liu, Guoqiang Zhang, Shihan Dou, Huiyuan Zheng, Yiming Zhou

Deep Supervised Contrastive Learning of Pitch Contours for Robust Pitch Accent Classification in Seoul Korean

Hyunjung Joo, GyeongTaek Lee

LoRA on the Go: Instance-level Dynamic LoRA Selection and Merging

Seungeon Lee, Soumi Das, Manish Gupta, Krishna P. Gummadi

Towards Trustworthy Smart Contract Synthesis: A Multi-Agent Framework with Lean-Based Verification

Bowei Zhang, Hanbing Liu, Qixin Tian, Siyu Chen, Ziyuan Wang

Robust Membership Inference for Large Language Models under Adversarial Generative Corruption

Yuanhong Huang, Huili Wang, Xueying Bai, Jinrui Wang, Jiajun Liu

Chain-of-Thought as a Lens: Evaluating Structured Reasoning Alignment between Human Preferences and Large Language Models

Boxuan Wang, Zhuoyun Li, Xinmiao Huang, Xiaowei Huang, Yi Dong

NoisyCausal: A Benchmark for Evaluating Causal Reasoning Under Structured Noise

Zhi Xu, Yun Fu

Zero-shot Large Language Models for Automatic Readability Assessment

Riley Grossman, Yi Chen

Beyond Experience Retrieval: Learning to Generate Utility-Optimized Structured Experience for Frozen LLMs

Xuancheng Li, Haitao Li, Yujia Zhou, Yiqun Liu, Qingyao Ai

ConsistRM: Improving Generative Reward Models via Consistency-Aware Self-Training

Yu Liang, Liangxin Liu, Longzheng Wang, Wangyan, Zhang Yueyang

A Survey of Deep Learning for Geometry Problem Solving

Jianzhe Ma, Wenxuan Wang, Qin Jin

MARCH: Multi-Agent Reinforced Check for Hallucination

Zhuo Li, Yupeng Zhang, Pengyu Cheng, Jiajun Song, Mengyu Zhou

Figure It Out: Improve the Frontier of Reasoning with Executable Visual States

Meiqi Chen, Fandong Meng, Jie Zhou

REaR : Retrieve, Expand and Refine for Effective Multitable Retrieval

Rishita Agarwal, Himanshu Singhal, Peter Baile Chen, Manan Roy Choudhury, Dan Roth

ERCThinker: Fast-Slow Thinking for Emotion Recognition in Conversation

Yumeng Fu, Weitao Huang, Junjie Wu, Hao Teng, Shouduo Shang

Knowledge Injection Exists in MoE? Exploring Expert-Aware Contrast Decoding in MoE for Mitigating LLMs’ Hallucinations

Xinyue Fang, Zhiliang Tian, Zhen Huang, Ziyi Pan, Zhihua Wen

Please refuse to answer me! Mitigating Over-Refusal in Large Language Models via Adaptive Contrastive Decoding

Yupeng Qi, Ziyu Lyu, Lixin Cui, Lu Bai, Feng Xia

On-policy Reinforcement Fine-tuning with Offline reward for Multi-step Embodied Planning

Di Wu, Jiaxin Fan, Chloe Gu, Guanbo Wang, Wei Yin

Mitigating Safety Context Amnesia in Multimodal Reasoning Models via Intent-Guided Safety Reasoning

Xiyao Dong, Guangsheng Cheng, Yilong Chen, Xiaojin Zhang, Kun He

Black-Box Membership Inference Attacks for Video Training Data in Multimodal Large Language Models

Jinrui Wang, Zhenfeng Gao, Wendan Wang, Huili Wang, Zichen Qin

BlindGuard: Safeguarding LLM-based Multi-Agent Systems under Unknown Attacks

Rui Miao, Yixin Liu, Yili Wang, Xu Shen, Yue Tan

False Friends or Cognates? A Cross-lingual Semantic Ambiguity Evaluation for Galician, Portuguese and Spanish

Marta Vázquez Abuín, Jose Camacho-Collados, Marcos Garcia

Towards Fast and Accurate Modeling for Cross-Lingual Label Projection

Thang Le, Huy Huu Nguyen, Anh Tuan Luu, Thamar Solorio, Thien Huu Nguyen

Putting HUMANS first: Efficient LAM Evaluation with Human Preference Alignment

Woody Haosheng Gan, William Barr Held, Diyi Yang

HowToNarrate: A General-Domain Benchmark for Synchronized Video Narration with External Knowledge

Xueyan Wang, Dingyi Yang, Qin Jin

Surprisal Minimisation over Goal-directed Alternatives Predicts Production Choice in Dialogue

Thomas P. Utting, Mario Giulianelli, Arabella Sinclair

EmoS: A High-Fidelity Multimodal Benchmark for Fine-grained Streaming Emotional Understanding

Pengze Guo, Jingxi Liang, Zhiwen Xie, Qifeng Wang, Derek F. Wong

From Where Words Come: Efficient Regularization of Code Tokenizers Through Source Attribution

Pavel Chizhov, Egor Bogomolov, Ivan P. Yamshchikov

REAL: REtrieval-reAsoning and Logic-constructed Attention Behaviors for Long-Context KV Cache Compression

Mengjie Li, Yuan Feng, Xike Xie, William J. Song

Can Reasoning Path still be Effective as Input? Bridging Post-Reasoning to Chain-of-Thought Compression

Chengzhengxu Li, Xiaoming Liu, Zhaohan Zhang, Shengchao Liu, Guoxin Ma

Polymorphic Universal Transformer

Yilong Chen, Zitian Gao, Yihao Xiao, Jason Klein Liu, Xinyu Yang

Why Does Reinforcement Learning Generalize? A Feature-Level Mechanistic Study of Post-Training in Large Language Models

Dan Shi, Zhuowen Han, Simon Ostermann, Renren Jin, Josef van Genabith

One Refiner to Unlock Them All: Inference-Time Reasoning Elicitation via Reinforcement Query Refinement

Yixiao Zhou, Dongzhou Cheng, Zhiliang Wu, Yi Yang, Yu Cheng

Discovering a Shared Logical Subspace: Steering LLM Logical Reasoning via Alignment of Natural-Language and Symbolic Views

Feihao Fang, My T. Thai, Yuanyuan Lei

Fast and Accurate Fisher-Guided Quantization via Efficient Kronecker Factorization

Viktoriia A. Chekalina, Gerasin Timofey, Andrey Kuznetsov, Evgeny Frolov

MemCoRL: Alternating Co-Optimization of Memory Retrieval and Utilization via Collaborative Reinforcement Learning

Yuewen Liu, Peng Xu, Muxi Diao, Anyi Zhang, Yang Li

More Aligned, Less Diverse? Analyzing the Grammar and Lexicon of Two Generations of LLMs

Adrián Gude, Roi Santos-Rios, Francis Bond, Dan Flickinger, Carlos Gómez-Rodríguez

S^4: Operationalizing Speech Act Theory for Strategic Semi-Structured Psychiatric Interview

Guanqun Bi, Zhoufu Liu, Zhuang Chen, Dazhen Wan, Xiyao Xiao

Uncertainty-Aware Routing for Principled Alignment with MoE Dynamics

Yilong Chen, Junyuan Shang, Yuchen Feng, Zhenyu Zhang, Naibin Gu

JoPR: Joint Emotion Perception and Reasoning for Conversational Emotion Recognition

Yumeng Fu, Weitao Huang, Junjie Wu, Hao Teng, Meishan Zhang

BEFT: Bias-Efficient Fine-Tuning of Language Models in Low-Data Regimes

Baichuan Huang, Ananth Balashankar, Amir Aminifar

ReTraceQA: Evaluating Reasoning Traces of Small Language Models in Commonsense Question Answering

Francesco Maria Molfese, Luca Moroni, Ciro Porcaro, Simone Conia, Roberto Navigli

HalluAudio: A Comprehensive Benchmark for Hallucination Detection in Large Audio-Language Models

Feiyu Zhao, Yiming Chen, Wenhuan Lu, Daipeng Zhang, Xianghu Yue

ImpRIF: Stronger Implicit Reasoning Leads to Better Complex Instruction Following

Yuancheng Yang, Lin Yang, Xu Wang, Chao Tong, Haihua Yang

SciCoQA: Quality Assurance for Scientific Paper–Code Alignment

Tim Baumgärtner, Iryna Gurevych

G-IdiomAlign: A Gloss-Pivoted Benchmark for Cross-Lingual Idiom Alignment

Fengying Ye, Yanming Sun, Runzhe Zhan, Lidia S. Chao, Zheqi Zhang

SPARKLE: A Structured and Plug-and-play Agentic Retrieval Policy for Adaptive RAG Models

Jinyuan Fang, Zaiqiao Meng, Craig Macdonald

Trait Activation in Silicon: A Situation-Aware Framework for Psychologically Grounded Role-Playing

Zuolong Li, Pingyu Wu, Xianwen Huang, Tianyi Wei, Wenbo Zhou

QuDAR: Query-Wise Dual-Perspective Adaptive Retrieval

Joeun Kim, Seunghyouk Yoon, Xuan-Bach Le, Youngeun Nam, Doyoung Kim

FLAIR: Steering LLM Mathematical Problem Solving based on A Fuzzy-Logic-AssIsted Reasoner

Hao Wu, Hongru Sun, Wanqing Li, Xinguo Yu, Hao Ming

Teaching LLMs Human-Like Editing of Inappropriate Argumentation via Reinforcement Learning

Timon Ziegenbein, Maja Stahl, Henning Wachsmuth

NaviMaster: Learning a Unified Policy for GUI and Embodied Navigation Tasks

ZhiHao Luo, Wentao Yan, Jingyu Gong, Min Wang, Zhizhong Zhang

Confidence Should Be Calibrated More Than One Turn Deep

Zhaohan Zhang, Chengzhengxu Li, Xiaoming Liu, Chao Shen, Ziquan Liu

Beyond Single Representations: Multi-Model Embedding Fusion for Stable Text Classification

Jiho Gwak, Yuchul Jung

v-HUB: A Benchmark for Video Humor Understanding from Vision and Sound

Zhengpeng Shi, Yanpeng Zhao, Jianqun Zhou, Yuxuan Wang, Qinrong Cui

Vision-Language Introspection: Mitigating Overconfident Hallucinations in MLLMs via Interpretable Bi-Causal Steering

Shuliang Liu, Songbo Yang, Dong Fang, Sihang Jia, Yuqi Tang

HumanLLM: Benchmarking and Improving LLM Anthropomorphism via Human Cognitive Patterns

Xintao Wang, Jian Yang, Weiyuan Li, Rui Xie, Jen-tse Huang

Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination

Yangneng Chen, Junlin Li, Weijun Yao, Xilai Ma, Guodong Du

CAMEC: Complexity-Aware Multi-Expert Collaboration for Reliable Chinese Medical Question Answering

Yukang Wu, Xiyuan Jia, Jiayi Wu, HongChen Yu, Yuhan Qiu

CheckRLM: Effective Knowledge–Thought Coherence Checking in Retrieval-Augmented Reasoning

Dingling Xu, Ruobing Wang, Qingfei Zhao, Yukun Yan, Zhichun Wang

CoMeT: Collaborative Memory Transformer for Efficient Long Context Modeling

Runsong Zhao, Shilei Liu, Jiwei Tang, Langming Liu, Haibin Chen

PHOTON: Hierarchical Autoregressive Modeling for Lightspeed and Memory-Efficient Language Generation

Yuma Ichikawa, Naoya Takagi, Takumi Nakagawa, Yuzi Kanazawa, Akira Sakai

CodeRipple: Wavelet-Based Detection of LLM-Generated Code

Xingyu Yao, Zhendong Mao, Quan Wang

Evolving Beyond Snapshots: Harmonizing Structure and Sequence via Entity State Tuning for Temporal Knowledge Graph Forecasting

Siyuan Li, Yunjia Wu, Yiyong Xiao, Pingyang Huang, Peize Li

When Efficiency Becomes a Vulnerability: Computational Cost Attacks on WebAgents

Liang-Bo Ning, Yuchen Zhu, Heqing Huang, Xin Wang, Yi Chang

ImmersiveTTS: Environment-Aware Text-to-Speech with Multimodal Diffusion Transformer and Domain-Specific Representation Alignment

Jun-Hak Yun, Seung-Bin Kim, Seong-Whan Lee

DetectRL-X: Towards Reliable Multilingual and Real-World LLM-Generated Text Detection

Junchao Wu, Yefeng Liu, Chenyu Zhu, Hao Zhang, Zeyu Wu

Foresight Optimization for Strategic Reasoning in Large Language Models

Jessie Wang, Jiawen Duan, Jian Wang, Kaitao Song, Chunpu Xu

EvoRoute: Experience-Driven Self-Routing LLM Agent Systems

Guibin Zhang, Haiyang Yu, Kaiming Yang, Bingli Wu, Fei Huang

Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs

Nikita Afonin, Nikita Andriianov, Vahagn Hovhannisyan, Nikhil Bageshpura, Kyle Liu

Tears or Cheers? Benchmarking LLMs via Culturally Elicited Distinct Affective Responses

Chongyuan Dai, Yaling Shen, Zihan Gao, Jia Li, Yishun Jiang

When Background Matters: Breaking Medical Vision Language Models by Transferable Attack

Akash Ghosh, Subhadip Baidya, Sriparna Saha, Xiuying Chen

Theory-optimal Quantization Based on Flatness

Xiusheng Huang, Zhe Li, Xuanwu Yin, Lu Wang, Yequan Wang

Think How to Think: Mitigating Overthinking with Autonomous Difficulty Cognition in Large Reasoning Models

Yongjiang Liu, Haoxi Li, Xiaosong Ma, Jie Zhang, Song Guo

TaxPraBen: A Scalable Benchmark for Structured Evaluation of LLMs in Chinese Real-World Tax Practice

Gang Hu, Yating Chen, Haiyan Ding, Wang Gao, Huang Jiajia

Dynamic Generation of Multi LLM Agents Communication Topologies with Graph Diffusion Models

Eric Hanchen Jiang, Levina Li, Frank Wan, Xiao Liang, Sophia Yin

UPDESH: Synthesizing Grounded Instruction Tuning Data for 13 Indic Languages

Pranjal A Chitale, Varun Gumma, Sanchit Ahuja, Prashant Kodali, Manan Uppadhyay

AlignCultura: Towards Culturally Aligned Large Language Models?

Gautam Siddharth Kashyap, Mark Dras, Usman Naseem

Cross-Examination Framework: A Task-Agnostic Diagnostic for Information Fidelity in Text-to-Text Generation

Tathagata Raha, Clément Christophe, Nada Saadi, Hamza A Javed, Marco AF Pimentel

Refining and Reusing Annotation Guidelines for LLM Annotation

Kon Woo Kim, Jin-Dong Kim, Akiko Aizawa

Mitigating Over-Refusal in Aligned Large Language Models via Inference-Time Activation Energy

Eric Hanchen Jiang, Weixuan Ou, Run Liu, Shengyuan Pang, Guancheng Wan

AdaDPI: Document-level Translation Adaptive Agent via Dynamic Parametric Internalization

Hong Ren, Liting Deng, Shaolin Zhu, Deyi Xiong

FairQE: Multi-Agent Framework for Mitigating Gender Bias in Translation Quality Estimation

Jinhee Jang, Juhwan Choi, Dongjin Lee, Seunguk Yu, YoungBin Kim

Social Dynamics as Critical Vulnerabilities that Undermine Objective Decision-Making in LLM Collectives

Changgeon Ko, Jisu Shin, Hoyun Song, Huije Lee, Eui Jun Hwang

StepHint: Multi-level Stepwise Hints Enhance Reinforcement Learning to Reason

Kaiyi Zhang, Ang Lv, Jinpeng Li, Yongbo Wang, Feng Wang

Revealing Procedural Reasoning Structures in Chain-of-Thought Training via Span-Level Gradient Organization

Jia Liu, Jiaxin Luo, Weiwen Xu, Jonathan M. Garibaldi, Xiao-Kun Wu

Omni-I2C: A Holistic Benchmark for High-Fidelity Image-to-Code Generation

Jiawei Zhou, Chi Zhang, Xiang Feng, Qiming ZHANG, Haibo Qiu

CE-GPPO: Coordinating Entropy via Gradient-Preserving Clipping Policy Optimization in Reinforcement Learning

Zhenpeng Su, Leiyu Pan, Minxuan Lv, Yuntao Li, Wenping Hu