大模型推理能力

MTalk-Bench: Evaluating Speech-to-Speech Models in Multi-Turn Dialogues via Arena-style and Rubrics Protocols

Yuhao Du, Qianwei Huang, Guo Zhu, Zhanchen Dai, Shunian Chen, Qiming Zhu, Le Pan, Minghao Chen, Yuhao Zhang, Li Zhou, Benyou Wang, Haizhou Li

机构 * School of Data Science, The Chinese University of Hong Kong, Shenzhen（数据科学学院，香港中文大学（深圳）） 纠错

专题命中 推理评测 ：reasoning(abstract)；分类 cs.CL、cs.AI

We Argue to Agree: Towards Personality-Driven Argumentation-Based Negotiation Dialogue Systems for Tourism

Priyanshu Priya, Saurav Dudhate, Desai Vishesh Yasheshbhai, Asif Ekbal

机构 * Department of Computer Science and Engineering, Indian Institute of Technology Patna（计算机科学与工程系，印度理工学院帕纳布） 纠错

专题命中 推理评测 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments Paper is accepted at EMNLP (Findings) 2025

Adaptive Monitoring and Real-World Evaluation of Agentic AI Systems

Manish Shukla

机构 * Independent Researcher（独立研究者） 纠错

专题命中 推理评测 ：planning(abstract)；分类 cs.CL、cs.AI

MARS-Bench: A Multi-turn Athletic Real-world Scenario Benchmark for Dialogue Evaluation

Chenghao Yang, Yinbo Luo, Zhoufutu Wen, Qi Chu, Tao Gong, Longxiang Liu, Kaiyuan Zhang, Jianpeng Jiao, Ge Zhang, Wenhao Huang, Nenghai Yu

机构 * University of Science and Technology of China（中国科学技术大学） 纠错

专题命中 推理评测 ：reasoning(abstract)；分类 cs.CL、cs.AI

Comments 29 pages, 13 figures, Accepted as EMNLP2025 Findings

Smart Trial: Evaluating the Use of Large Language Models for Recruiting Clinical Trial Participants via Social Media

Xiaofan Zhou, Zisu Wang, Janice Krieger, Mohan Zalake, Lu Cheng

机构 * University of Illinois at Chicago（伊利诺伊大学香槟分校） ； Colorado State University（科罗拉多州立大学） 纠错

专题命中 推理评测 ：reasoning(abstract)；分类 cs.CL、cs.AI

CBP-Tuning: Efficient Local Customization for Black-box Large Language Models

Jiaxuan Zhao, Naibin Gu, Yuchen Feng, Xiyu Liu, Peng Fu, Zheng Lin, Weiping Wang

机构 * Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所） ； School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络安全学院） 纠错

专题命中 推理评测 ：reasoning(abstract)；分类 cs.CL

GitTaskBench: A Benchmark for Code Agents Solving Real-World Tasks Through Code Repository Leveraging

Ziyi Ni, Huacan Wang, Shuo Zhang, Shuo Lu, Ziyang He, Wang You, Zhenheng Tang, Yuntao Du, Bill Sun, Hongzhang Liu, Sen Hu, Ronghao Chen, Bo Li, Xin Li, Chen Hu, Binxing Jiao, Daxin Jiang, Pin Lyu

机构 * UCAS（中国科学技术大学） ； CASIA（中国科学院自动化研究所） ； BUPT（北京理工大学） ； NUS（新加坡国立大学） ； StepFun ； HKUST（香港理工大学） ； SDU（山东大学） ； PINAI ； USYD（悉尼大学） ； PKU（北京大学） ； USTC（中国科学技术大学） 纠错

专题命中 推理评测 ：reasoning(abstract)；分类 cs.AI

Comments Highly practical, Well-motivated, Actionable

Confusion is the Final Barrier: Rethinking Jailbreak Evaluation and Investigating the Real Misuse Threat of LLMs

Yu Yan, Sheng Sun, Zhe Wang, Yijun Lin, Zenghao Duan, zhifei zheng, Min Liu, Zhiyi yin, Jianping Zhang

机构 * State Key Lab of Processors, Institute of Computing Technology, CAS（中国科学院计算技术研究所状态关键实验室） ； University of Chinese Academy of Sciences（中国科学院大学） ； People’s Public Security University of China（中国人民公安大学） ； Chinese University of Hong Kong（香港大学） 纠错

专题命中 推理评测 ：planning(abstract)；分类 cs.AI

Assessing LLMs in Art Contexts: Critique Generation and Theory of Mind Evaluation

Takaya Arita, Wenxian Zheng, Reiji Suzuki, Fuminori Akiba

专题命中 推理评测 ：reasoning(abstract)；分类 cs.CL

Comments Corrected a typo in the metadata title only ("Assesing"->"Assessing"). No changes were made to the PDF or source files

Can LLMs assist with Ambiguity? A Quantitative Evaluation of various Large Language Models on Word Sense Disambiguation

T. G. D. K. Sumanathilaka, Nicholas Micallef, Julian Hough

专题命中 推理评测 ：CoT(abstract)；分类 cs.CL

Comments 12 pages,6 tables, 1 figure, Proceedings of the 1st International Conference on NLP & AI for Cyber Security

What is the Visual Cognition Gap between Humans and Multimodal LLMs?

Xu Cao, Yifan Shen, Bolin Lai, Wenqian Ye, Yunsheng Ma, Joerg Heintz, Jintai Chen, Meihuan Huang, Jianguo Cao, Aidong Zhang, James M. Rehg

机构 * Department of Computer Science, University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校计算机科学系） ； College of Computing, Georgia Institute of Technology（佐治亚理工学院计算机学院） ； Department of Computer Science, University of Virginia（弗吉尼亚大学计算机科学系） ； Digital Twin Lab, Purdue University（普渡大学数字孪生实验室） ； HKUST (Guangzhou)（香港科技大学（广州）） ； Department of Rehabilitation Medicine, Shenzhen Children’s Hospital（深圳儿童医院康复医学系） 纠错

专题命中 推理评测 ：reasoning(abstract)；分类 cs.AI

Comments COLM 2025

Large Foundation Models for Trajectory Prediction in Autonomous Driving: A Comprehensive Survey

Wei Dai, Shengen Wu, Wei Wu, Zhenhao Wang, Sisuo Lyu, Haicheng Liao, Limin Yu, Weiping Ding, Runwei Guan, Yutao Yue

机构 * Department of Mathematical Sciences, School of Physical sciences, University of Liverpool（利物浦大学数学科学系） ； Department of Communications and Networking, School of Advanced Technology, Xi’an Jiaotong-Liverpool University（西安交通大学利物浦大学通讯与网络系） ； Thrust of Artificial Intelligence, The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）人工智能方向） ； Deep Interdisciplinary Intelligence Lab, The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）深度跨学科智能实验室） ； School of Mathematics and Statistics, Shandong University（山东大学数学与统计学院） ； School of Artificial Intelligence and Computer Science, Nantong University（南通大学人工智能与计算机科学学院） ； Thrust of Data Science and Analytics, The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）数据科学与分析方向） ； Institute of Deep Perception Technology, Jiangsu（江苏深度感知技术研究院） 纠错

专题命中 推理评测 ：reasoning(abstract)；分类 cs.AI

Comments 22 pages, 6 figures

CLAIRE: A Dual Encoder Network with RIFT Loss and Phi-3 Small Language Model Based Interpretability for Cross-Modality Synthetic Aperture Radar and Optical Land Cover Segmentation

Debopom Sutradhar, Arefin Ittesafun Abian, Mohaimenul Azam Khan Raiaan, Reem E. Mohamed, Sheikh Izzal Azid, Sami Azam

机构 * Department of Computer Science and Engineering, United International University（计算机科学与工程系，国际大学） ； Faculty of Science and Information Technology, Charles Darwin University（科学与信息技术学院，查尔斯·达尔文大学） ； School of Engineering and Energy , Murdoch University（工程与能源学院，默多尼大学） ； Faculty of Science and Technology, Charles Darwin University（科学与技术学院，查尔斯·达尔文大学） 纠错

专题命中 推理评测 ：reasoning(abstract)

Comments 23 pages, 6 figures, 10 tables

Dr.V: A Hierarchical Perception-Temporal-Cognition Framework to Diagnose Video Hallucination by Fine-grained Spatial-Temporal Grounding

Meng Luo, Shengqiong Wu, Liqiang Jing, Tianjie Ju, Li Zheng, Jinxiang Lai, Tianlong Wu, Xinya Du, Jian Li, Siyuan Yan, Jiebo Luo, William Yang Wang, Hao Fei, Mong-Li Lee, Wynne Hsu

专题命中 推理评测 ：reasoning(abstract)

Comments 25 pages, 16 figures

Seeing the Undefined: Chain-of-Action for Generative Semantic Labels

Meng Wei, Zhongnian Li, Peng Ying, Xinzheng Xu

机构 * 1 School of Computer Science ； Technology / School of Artificial Intelligence, China University of Mining ； Technology Xuzhou China 2 Mine Digitization Engineering Research Center of the Ministry of Education Xuzhou China ； Technology Xuzhou China 2 The State Key Laboratory of CAD\&CG, Zhejiang University Hangzhou China 3 Mine Digitization Engineering Research Center of the Ministry of Education Xuzhou China ； 2 Mine Digitization Engineering Research Center of the Ministry of Education ； 2 The State Key Laboratory of CAD\&CG, Zhejiang University ； 3 Mine Digitization Engineering Research Center of the Ministry of Education 纠错

专题命中 推理评测 ：reasoning(abstract)

Comments 15 pages, 8 figures

Enhancing IoMT Security with Explainable Machine Learning: A Case Study on the CICIOMT2024 Dataset

Mohammed Yacoubi, Omar Moussaoui, C. Drocourt

专题命中 推理评测 ：reasoning(abstract)

Journal ref The Third Edition of the International Conference on Connected Objects and Artificial Intelligence (COCIA'2025), Apr 2025, Casablanca (Maroc), Morocco

CAC-CoT: Connector-Aware Compact Chain-of-Thought for Efficient Reasoning Data Synthesis Across Dual-System Cognitive Tasks

Sunguk Choi, Yonghoon Kwon, Heondeuk Lee

专题命中 其他推理 ：reasoning(title,abstract)；chain-of-thought(title,abstract)；CoT(title,abstract)；分类 cs.CL、cs.AI

Comments Accepted at EMNLP 2025 findings

FairCoT: Enhancing Fairness in Text-to-Image Generation via Chain of Thought Reasoning with Multimodal Large Language Models

Zahraa Al Sahili, Ioannis Patras, Matthew Purver

机构 * School of Electronic Engineering and Computer Science, Queen Mary University of London（伦敦女王学院电子工程与计算机科学学院） ； Department of Knowledge Technologies, Jožef Stefan Institute（Jožef Stefan研究所知识技术系） 纠错

专题命中 其他推理 ：reasoning(title,abstract)；CoT(abstract)；分类 cs.AI、cs.LG

Comments Accepted at EMNLP 2025

Understanding the Uncertainty of LLM Explanations: A Perspective Based on Reasoning Topology

Longchao Da, Xiaoou Liu, Jiaxin Dai, Lu Cheng, Yaqing Wang, Hua Wei

机构 * Arizona State University（亚利桑那州立大学） ； University of Illinois Chicago（伊利诺伊大学芝加哥分校） ； Purdue University（普渡大学） 纠错

专题命中 其他推理 ：reasoning(title,abstract)；分类 cs.CL、cs.AI

Comments 28 pages, 9 figures; accepted at COLM'25

Gene-R1: Reasoning with Data-Augmented Lightweight LLMs for Gene Set Analysis

Zhizheng Wang, Yifan Yang, Qiao Jin, Zhiyong Lu

专题命中 其他推理 ：reasoning(title,abstract)；分类 cs.AI

Comments 14 pages, 4 figures, 6 tables, 40 references

D$^2$HScore: Reasoning-Aware Hallucination Detection via Semantic Breadth and Depth Analysis in LLMs

Yue Ding, Xiaofang Zhu, Tianze Xia, Junfei Wu, Xinlong Chen, Qiang Liu, Liang Wang

专题命中 其他推理 ：reasoning(title)；分类 cs.CL

Comments under review

EasyEdit2: An Easy-to-use Steering Framework for Editing Large Language Models

Ziwen Xu, Shuxun Wang, Kewei Xu, Haoming Xu, Mengru Wang, Xinle Deng, Yunzhi Yao, Guozhou Zheng, Huajun Chen, Ningyu Zhang

机构 * Zhejiang University（浙江大学） ； Ocean Research Center of Zhoushan, Zhejiang University（舟山海洋研究中心，浙江大学） 纠错

专题命中 其他推理 ：reasoning(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments EMNLP 2025 System Demonstrations. Demo: https://www.youtube.com/watch?v=AkfoiPfp5rQ; code: https://github.com/zjunlp/EasyEdit

HalluField: Detecting LLM Hallucinations via Field-Theoretic Modeling

Minh Vu, Brian K. Tran, Syed A. Shah, Geigh Zollicoffer, Nhat Hoang-Xuan, Manish Bhattarai

机构 * Center for Nonlinear Studies（非线性研究中心） ； Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室） ； T-1 Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室T-1部门） ； Applied Mathematics University of Colorado Boulder（科罗拉多大学博尔德分校应用数学系） ； T-4 Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室T-4部门） 纠错

专题命中 其他推理 ：reasoning(abstract)；分类 cs.AI、cs.LG

Mechanistic Interpretability of LoRA-Adapted Language Models for Nuclear Reactor Safety Applications

Yoon Pyo Lee

专题命中 其他推理 ：reasoning(abstract)；分类 cs.AI、cs.LG

Comments Accepted for publication in Nuclear Technology. 24 pages, 2 tables, 4 figures

XplaiNLP at CheckThat! 2025: Multilingual Subjectivity Detection with Finetuned Transformers and Prompt-Based Inference with Large Language Models

Ariana Sahitaj, Jiaao Li, Pia Wenzel Neves, Fedor Splitt, Premtim Sahitaj, Charlott Jakob, Veronika Solopova, Vera Schmitt

机构 * Quality and Usability Lab, Technische Universität Berlin, Berlin, Germany（柏林技术大学质量与可用性实验室） ； German Research Center for Artificial Intelligence (DFKI), Berlin, Germany（德国人工智能研究中心（DFKI）） 纠错

专题命中 其他推理 ：reasoning(abstract)；分类 cs.CL

Spec-LLaVA: Accelerating Vision-Language Models with Dynamic Tree-Based Speculative Decoding

Mingxiao Huo, Jiayi Zhang, Hewei Wang, Jinfeng Xu, Zheyu Chen, Huilin Tai, Yijun Chen

机构 * Carnegie Mellon University（卡内基梅隆大学） ； University of Nottingham（诺丁汉大学） ； The University of Hong Kong（香港大学） ； The Hong Kong Polytechnic University（香港理工大学） ； Columbia University（哥伦比亚大学） ； University of California, Berkeley（加州大学伯克利分校） 纠错

专题命中 其他推理 ：reasoning(abstract)；分类 cs.CL

Comments 7pages, accepted by ICML TTODLer-FM workshop

Safety Pretraining: Toward the Next Generation of Safe AI

Pratyush Maini, Sachin Goyal, Dylan Sam, Alex Robey, Yash Savani, Yiding Jiang, Andy Zou, Matt Fredrikson, Zacharcy C. Lipton, J. Zico Kolter

专题命中 其他推理 ：reasoning(abstract)；分类 cs.LG

A Survey on Retrieval And Structuring Augmented Generation with Large Language Models

Pengcheng Jiang, Siru Ouyang, Yizhu Jiao, Ming Zhong, Runchu Tian, Jiawei Han

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） 纠错

专题命中 其他推理 ：reasoning(abstract)；分类 cs.CL

Comments KDD'25 survey track

Humanizing Machines: Rethinking LLM Anthropomorphism Through a Multi-Level Framework of Design

Yunze Xiao, Lynnette Hui Xian Ng, Jiarui Liu, Mona T. Diab

机构 * Carnegie Mellon University（卡内基梅隆大学） 纠错

专题命中 其他推理 ：reasoning(abstract)；分类 cs.CL

Comments Accepted in EMNLP main proceedings; Updated citations

LightEMMA: Lightweight End-to-End Multimodal Model for Autonomous Driving

Zhijie Qiao, Haowei Li, Zhong Cao, Henry X. Liu

机构 * Department of Civil and Environmental Engineering, University of Michigan（土木与环境工程系，密歇根大学） ； University of Michigan Transportation Research Institute（密歇根大学交通研究所） 纠错

专题命中 其他推理 ：reasoning(abstract)；分类 cs.AI