大模型推理能力

LLMs cannot spot math errors, even when allowed to peek into the solution

KV Aditya Srivatsa, Kaushal Kumar Maurya, Ekaterina Kochmar

机构 * Mohamed bin Zayed University of Artificial Intelligence（莫莫德·宾·扎耶德人工智能大学） 纠错

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

Comments Accepted to EMNLP 2025

SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control

Quanfeng Lu, Zhantao Ma, Shuai Zhong, Jin Wang, Dahai Yu, Michael K. Ng, Ping Luo

机构 * The University of Hong Kong（香港大学） ； Hong Kong Baptist University（香港 Baptist 大学） ； TCL Corporate Research (Hong Kong) Co., Ltd（TCL 香港研究院） 纠错

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

Comments 28 pages, 12 figures

An Investigation on Group Query Hallucination Attacks

Kehao Miao, Xiaolong Jin

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

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

The Computational Complexity of Satisfiability in State Space Models

Eric Alsmann, Martin Lange

机构 * University of Kassel, Germany（卡塞尔大学） 纠错

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

Comments Accepted at ECAI 25

Test-Time Scaling Strategies for Generative Retrieval in Multimodal Conversational Recommendations

Hung-Chun Hsu, Yuan-Ching Kuo, Chao-Han Huck Yang, Szu-Wei Fu, Hanrong Ye, Hongxu Yin, Yu-Chiang Frank Wang, Ming-Feng Tsai, Chuan-Ju Wang

机构 * Research Center for Information Technology Innovation, Academia Sinica（资讯科技创新研究所以） ； NVIDIA（NVIDIA公司） ； Department of Computer Science, National Chengchi University（国立政治大学计算机科学系） 纠错

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

DropLoRA: Sparse Low-Rank Adaptation for Parameter-Efficient Fine-Tuning

Haojie Zhang

专题命中 数学推理 ：reasoning(abstract)；分类 cs.CL、cs.LG

Comments 8 pages

Evaluating Contrast Localizer for Identifying Causal Units in Social & Mathematical Tasks in Language Models

Yassine Jamaa, Badr AlKhamissi, Satrajit Ghosh, Martin Schrimpf

机构 * EPFL（苏黎世联邦理工学院） ； MIT（麻省理工学院） 纠错

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

Comments Accepted at the Interplay of Model Behavior and Model Internals Workshop co-located with COLM 2025

WST: Weak-to-Strong Knowledge Transfer via Reinforcement Learning

Haosen Ge, Shuo Li, Lianghuan Huang

机构 * Wharton AI & Analytics Initiative（沃顿人工智能与分析倡议） ； University of Pennsylvania（宾夕法尼亚大学） ； Department of Computer and Information Science（计算机与信息科学系） ； Department of Physics and Astronomy（物理学与天文学系） 纠错

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

Rethinking Addressing in Language Models via Contexualized Equivariant Positional Encoding

Jiajun Zhu, Peihao Wang, Ruisi Cai, Jason D. Lee, Pan Li, Zhangyang Wang

机构 * University of Texas at Austin（德克萨斯大学奥斯汀分校） ； Zhejiang University（浙江大学） ； Princeton University（普林斯顿大学） 纠错

专题命中 数学推理 ：reasoning(abstract)；分类 cs.CL、cs.LG

Comments ICML 2025

DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization

Shuaijie She, Yu Bao, Yu Lu, Lu Xu, Tao Li, Wenhao Zhu, Shujian Huang, Shanbo Cheng, Lu Lu, Yuxuan Wang

机构 * Nanjing University（南京大学） 纠错

专题命中 数学推理 ：reasoning(abstract)；分类 cs.CL、cs.LG

Comments 18 pages, 4 figures,

Apriel-Nemotron-15B-Thinker

Shruthan Radhakrishna, Soham Parikh, Gopal Sarda, Anil Turkkan, Quaizar Vohra, Raymond Li, Dhruv Jhamb, Kelechi Ogueji, Aanjaneya Shukla, Oluwanifemi Bamgbose, Toby Liang, Luke Kumar, Oleksiy Ostapenko, Shiva Krishna Reddy Malay, Aman Tiwari, Tara Bogavelli, Vikas Yadav, Jash Mehta, Saloni Mittal, Akshay Kalkunte, Pulkit Pattnaik, Khalil Slimi, Anirudh Sreeram, Jishnu Nair, Akintunde Oladipo, Shashank Maiya, Khyati Mahajan, Rishabh Maheshwary, Masoud Hashemi, Sai Rajeswar Mudumba, Sathwik Tejaswi Madhusudhan, Torsten Scholak, Sebastien Paquet, Sagar Davasam, Srinivas Sunkara

机构 * Apriel-Nemotron-15B-Thinker 纠错

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

ASPD: Unlocking Adaptive Serial-Parallel Decoding by Exploring Intrinsic Parallelism in LLMs

Keyu Chen, Zhifeng Shen, Daohai Yu, Haoqian Wu, Wei Wen, Jianfeng He, Ruizhi Qiao, Xing Sun

机构 * Youtu Team（你Tube团队） 纠错

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

Comments 20 pages, 9 figures

CLoQ: Enhancing Fine-Tuning of Quantized LLMs via Calibrated LoRA Initialization

Yanxia Deng, Aozhong Zhang, Selcuk Gurses, Naigang Wang, Zi Yang, Penghang Yin

机构 * Department of Mathematics and Statistics（数学与统计学系） ； University at Albany, SUNY（阿尔巴尼大学） ； IBM T. J. Watson Research Center（IBM 塔沃森研究中心） 纠错

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

Journal ref Transactions on Machine Learning Research (TMLR), 2025

DynaSwarm: Dynamically Graph Structure Selection for LLM-based Multi-agent System

Hui Yi Leong, Yuqing Wu

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

Comments content error

LLMs can be easily Confused by Instructional Distractions

Yerin Hwang, Yongil Kim, Jahyun Koo, Taegwan Kang, Hyunkyung Bae, Kyomin Jung

机构 * IPAI, Seoul National University（IPAI，首尔国立大学） ； LG AI Research（LG人工智能研究所） ； Dept. of ECE, Seoul National University（电子工程系，首尔国立大学） ； SNU-LG AI Research Center（SNU-LG人工智能研究所） 纠错

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

Comments 8 pages

Journal ref Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 19483-19496, Vienna, Austria, July 2025

Don't Forget Imagination!

Evgenii E. Vityaev, Andrei Mantsivoda

机构 * Sobolev Institute of mathematics SD RAS（索洛维耶夫数学研究所（SD RAS）） ； Irkutsk State University（伊尔库茨克州立大学） 纠错

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

Comments 14 pages, 2 figures

Temporal Self-Rewarding Language Models: Decoupling Chosen-Rejected via Past-Future

Yidong Wang, Xin Wang, Cunxiang Wang, Junfeng Fang, Qiufeng Wang, Jianing Chu, Xuran Meng, Shuxun Yang, Libo Qin, Yue Zhang, Wei Ye, Shikun Zhang

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

Comments 12 pages, 5 figures

Step-wise Adaptive Integration of Supervised Fine-tuning and Reinforcement Learning for Task-Specific LLMs

Jack Chen, Fazhong Liu, Naruto Liu, Yuhan Luo, Erqu Qin, Harry Zheng, Tian Dong, Haojin Zhu, Yan Meng, Xiao Wang

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

Tabular Data Understanding with LLMs: A Survey of Recent Advances and Challenges

Xiaofeng Wu, Alan Ritter, Wei Xu

机构 * College of Computing, Georgia Institute of Technology（计算学院、佐治亚理工学院） 纠错

专题命中 数学推理 ：reasoning(abstract)；分类 cs.CL、cs.LG

CHECK-MAT: Checking Hand-Written Mathematical Answers for the Russian Unified State Exam

Ruslan Khrulev

机构 * Moscow State University（莫斯科国立大学） 纠错

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

Comments 15 pages, 3 figures, 10 tables. Code is available at: https://github.com/Karifannaa/Auto-check-EGE-math

Step-3 is Large yet Affordable: Model-system Co-design for Cost-effective Decoding

StepFun, :, Bin Wang, Bojun Wang, Changyi Wan, Guanzhe Huang, Hanpeng Hu, Haonan Jia, Hao Nie, Mingliang Li, Nuo Chen, Siyu Chen, Song Yuan, Wuxun Xie, Xiaoniu Song, Xing Chen, Xingping Yang, Xuelin Zhang, Yanbo Yu, Yaoyu Wang, Yibo Zhu, Yimin Jiang, Yu Zhou, Yuanwei Lu, Houyi Li, Jingcheng Hu, Ka Man Lo, Ailin Huang, Binxing Jiao, Bo Li, Boyu Chen, Changxin Miao, Chang Lou, Chen Hu, Chen Xu, Chenfeng Yu, Chengyuan Yao, Daokuan Lv, Dapeng Shi, Deshan Sun, Ding Huang, Dingyuan Hu, Dongqing Pang, Enle Liu, Fajie Zhang, Fanqi Wan, Gulin Yan, Han Zhang, Han Zhou, Hanghao Wu, Hangyu Guo, Hanqi Chen, Hanshan Zhang, Hao Wu, Haocheng Zhang, Haolong Yan, Haoran Lv, Haoran Wei, Hebin Zhou, Heng Wang, Heng Wang, Hongxin Li, Hongyu Zhou, Hongyuan Wang, Huiyong Guo, Jia Wang, Jiahao Gong, Jialing Xie, Jian Zhou, Jianjian Sun, Jiaoren Wu, Jiaran Zhang, Jiayu Liu, Jie Cheng, Jie Luo, Jie Yan, Jie Yang, Jieyi Hou, Jinguang Zhang, Jinlan Cao, Jisheng Yin, Junfeng Liu, Junhao Huang, Junzhe Lin, Kaijun Tan, Kaixiang Li, Kang An, Kangheng Lin, Kenkun Liu, Lei Yang, Liang Zhao, Liangyu Chen, Lieyu Shi, Liguo Tan, Lin Lin, Lin Zhang, Lina Chen, Liwen Huang, Liying Shi, Longlong Gu, Mei Chen, Mengqiang Ren, Ming Li, Mingzhe Chen, Na Wang, Nan Wu, Qi Han, Qian Zhao, Qiang Zhang, Qianni Liu, Qiaohui Chen, Qiling Wu, Qinglin He, Qinyuan Tan, Qiufeng Wang, Qiuping Wu, Qiuyan Liang, Quan Sun, Rui Li, Ruihang Miao, Ruosi Wan, Ruyan Guo, Shangwu Zhong, Shaoliang Pang, Shengjie Fan, Shijie Shang, Shilei Jiang, Shiliang Yang, Shiming Hao, Shuli Gao, Siming Huang, Siqi Liu, Tiancheng Cao, Tianhao Cheng, Tianhao Peng, Wang You, Wei Ji, Wen Sun, Wenjin Deng, Wenqing He, Wenzhen Zheng, Xi Chen, Xiangwen Kong, Xianzhen Luo, Xiaobo Yang, Xiaojia Liu, Xiaoxiao Ren, Xin Han, Xin Li, Xin Wu, Xu Zhao, Yanan Wei, Yang Li, Yangguang Li, Yangshijie Xu, Yanming Xu, Yaqiang Shi, Yeqing Shen, Yi Yang, Yifei Yang, Yifeng Gong, Yihan Chen, Yijing Yang, Yinmin Zhang, Yizhuang Zhou, Yuanhao Ding, Yuantao Fan, Yuanzhen Yang, Yuchu Luo, Yue Peng, Yufan Lu, Yuhang Deng, Yuhe Yin, Yujie Liu, Yukun Chen, Yuling Zhao, Yun Mou, Yunlong Li, Yunzhou Ju, Yusheng Li, Yuxiang Yang, Yuxiang Zhang, Yuyang Chen, Zejia Weng, Zhe Xie, Zheng Ge, Zheng Gong, Zhenyi Lu, Zhewei Huang, Zhichao Chang, Zhiguo Huang, Zhirui Wang, Zidong Yang, Zili Wang, Ziqi Wang, Zixin Zhang, Binxing Jiao, Daxin Jiang, Heung-Yeung Shum, Xiangyu Zhang

机构 * StepFun Inc（StepFun公司） 纠错

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

TRPrompt: Bootstrapping Query-Aware Prompt Optimization from Textual Rewards

Andreea Nica, Ivan Zakazov, Nicolas Mario Baldwin, Saibo Geng, Robert West

机构 * EPFL（瑞士联邦理工学院） ； Microsoft Research（微软研究院） 纠错

专题命中 数学推理 ：reasoning(abstract)；分类 cs.CL、cs.LG

A Practical Two-Stage Recipe for Mathematical LLMs: Maximizing Accuracy with SFT and Efficiency with Reinforcement Learning

Hiroshi Yoshihara, Taiki Yamaguchi, Yuichi Inoue

机构 * Aillis Inc.（Aillis公司） ； Department of Health Policy（健康政策部门） ； Public Health, Graduate School of Pharmaceutical Sciences, The University of Tokyo, Tokyo, Japan（公共卫生，药学研究生院，东京大学，东京，日本） ； Rist Inc.（Rist公司） 纠错

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

Comments Presented at ICML 2025 Workshop on The second AI for MATH

Alpay Algebra V: Multi-Layered Semantic Games and Transfinite Fixed-Point Simulation

Bugra Kilictas, Faruk Alpay

机构 * Bahçeşehir University（巴切希尔大学） 纠错

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

Comments 18 pages, 2 figures

Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders

Shun Wang, Tyler Loakman, Youbo Lei, Yi Liu, Bohao Yang, Yuting Zhao, Dong Yang, Chenghua Lin

专题命中 数学推理 ：reasoning(abstract)；分类 cs.CL、cs.LG

MASS: Mathematical Data Selection via Skill Graphs for Pretraining Large Language Models

Jiazheng Li, Lu Yu, Qing Cui, Zhiqiang Zhang, Jun Zhou, Yanfang Ye, Chuxu Zhang

机构 * University of Connecticut, USA（美国康涅狄格大学） ； University of Notre Dame, USA（美国诺丁汉大学） 纠错

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

MANTA: Cross-Modal Semantic Alignment and Information-Theoretic Optimization for Long-form Multimodal Understanding

Ziqi Zhong, Daniel Tang

机构 * London School of Economics（伦敦经济学院） 纠错

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

Beyond Statistical Learning: Exact Learning Is Essential for General Intelligence

András György, Tor Lattimore, Nevena Lazić, Csaba Szepesvári

机构 * Google DeepMind（谷歌DeepMind） 纠错

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

TTRL: Test-Time Reinforcement Learning

Yuxin Zuo, Kaiyan Zhang, Li Sheng, Shang Qu, Ganqu Cui, Xuekai Zhu, Haozhan Li, Yuchen Zhang, Xinwei Long, Ermo Hua, Biqing Qi, Youbang Sun, Zhiyuan Ma, Lifan Yuan, Ning Ding, Bowen Zhou

专题命中 数学推理 ：reasoning(abstract)；分类 cs.CL、cs.LG

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently

Yuanhe Zhang, Fanghui Liu, Yudong Chen

机构 * Department of Statistics, University of Warwick, UK.（威斯敏斯特大学统计学系） ； Department of Computer Science, University of Warwick, UK.（威斯敏斯特大学计算机科学系） ； Centre for Discrete Mathematics and its Applications (DIMAP), University of Warwick, UK.（威斯敏斯特大学离散数学及其应用中心（DIMAP）） 纠错

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

Comments Accepted by ICML 2025 (Oral)