语言大模型 / LLM

Beyond English-Centric Training: How Reinforcement Learning Improves Cross-Lingual Reasoning in LLMs

Shulin Huang, Yiran Ding, Junshu Pan, Yue Zhang

机构 * Zhejiang University（浙江大学） ； Westlake University（西湖大学） 纠错

专题命中 推理与问题求解 ：large language model(abstract)；language model(abstract)；foundation model(abstract)；SFT(abstract)

Tagging the Thought: Unlocking Personalization Reasoning via Reinforcement Learning

Song Jin, Juntian Zhang, Yong Liu, Xun Zhang, Yufei Zhang, Fei Jiang, Guojun Yin, Wei Lin, Rui Yan

机构 * Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学人工智能学院） ； Meituan（美团） ； Wuhan University（武汉大学） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；SFT(abstract)

Revisiting Visual Understanding in Multimodal Reasoning through a Lens of Image Perturbation

Yuting Li, Lai Wei, Kaipeng Zheng, Jingyuan Huang, Guilin Li, Bo Wang, Linghe Kong, Lichao Sun, Weiran Huang

机构 * School of Computer Science, Shanghai Jiao Tong University（上海交通大学计算机科学学院） ； Shanghai Innovation Institute（上海创新研究院） ； Zhongguancun Academy（中关村学院） ； Tencent（腾讯） ； State Key Laboratory of General Artificial Intelligence, BIGAI（通用人工智能国家重点实验室，BIGAI） ； Lehigh University（莱斯大学） 纠错

专题命中 推理与问题求解 ：large language model(abstract)；language model(abstract)；post-training(abstract)；SFT(abstract)

Comments Technical Report

MMPlanner: Zero-Shot Multimodal Procedural Planning with Chain-of-Thought Object State Reasoning

Afrina Tabassum, Bin Guo, Xiyao Ma, Hoda Eldardiry, Ismini Lourentzou

机构 * Amazon（亚马逊公司） ； Alexa, Amazon（亚马逊Alexa部门） ； Virginia Tech（弗吉尼亚理工大学） ； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Comments 17 pages, 9 figures, 14 tables, Findings of the Association for Computational Linguistics: EMNLP 2025

UniSS: Unified Expressive Speech-to-Speech Translation with Your Voice

Sitong Cheng, Weizhen Bian, Xinsheng Wang, Ruibin Yuan, Jianyi Chen, Shunshun Yin, Yike Guo, Wei Xue

机构 * Hong Kong University of Science and Technology（香港理工大学） ； Soul AI Lab（Soul AI 实验室） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

MAPEX: A Multi-Agent Pipeline for Keyphrase Extraction

Liting Zhang, Shiwan Zhao, Aobo Kong, Qicheng Li

机构 * TMCC, College of Computer Science, Nankai University, Tianjin, China（天津大学计算机学院） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Premise-Augmented Reasoning Chains Improve Error Identification in Math reasoning with LLMs

Sagnik Mukherjee, Abhinav Chinta, Takyoung Kim, Tarun Anoop Sharma, Dilek Hakkani-Tür

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

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Comments Accepted at ICML 2025

Please Translate Again: Two Simple Experiments on Whether Human-Like Reasoning Helps Translation

Di Wu, Seth Aycock, Christof Monz

机构 * Language Technology Lab University of Amsterdam（语言技术实验室 阿姆斯特丹大学） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Comments EMNLP Main 2025 17 pages, 15 figures

EPIC: Generative AI Platform for Accelerating HPC Operational Data Analytics

Ahmad Maroof Karimi, Woong Shin, Jesse Hines, Tirthankar Ghosal, Naw Safrin Sattar, Feiyi Wang

机构 * National Center for Computational Sciences（国家计算科学中心） ； Oak Ridge National Laboratory（橡树岭国家实验室） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；foundation model(abstract)

Learning to Reason for Long-Form Story Generation

Alexander Gurung, Mirella Lapata

机构 * School of Informatics University of Edinburgh（信息学院爱丁堡大学） 纠错

专题命中 推理与问题求解 ：large language model(abstract)；language model(abstract)；SFT(abstract)；prompting(abstract)

Triadic Fusion of Cognitive, Functional, and Causal Dimensions for Explainable LLMs: The TAXAL Framework

David Herrera-Poyatos, Carlos Peláez-González, Cristina Zuheros, Virilo Tejedor, Rosana Montes, Francisco Herrera

机构 * Department of Computer Science and Artificial Intelligence（计算机科学与人工智能系） ； Andalusian Institute of Data Science and Computational Intelligence（安达卢西亚数据科学与计算智能研究所） ； University of Granada（格拉纳达大学） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Comments 27 pages, 9 tables and 2 figures

Symbiotic Agents: A Novel Paradigm for Trustworthy AGI-driven Networks

Ilias Chatzistefanidis, Navid Nikaein

机构 * Eurecom（埃鲁埃康） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；SLM(abstract)

Comments Submitted to Computer Networks AI for 6G

Teaching LLMs to Think Mathematically: A Critical Study of Decision-Making via Optimization

Mohammad J. Abdel-Rahman, Yasmeen Alslman, Dania Refai, Amro Saleh, Malik A. Abu Loha, Mohammad Yahya Hamed

机构 * Data Science Department, Princess Sumaya University for Technology（普里姆斯萨大学技术学院数据科学系） ； Electrical and Computer Engineering Department, Virginia Tech（弗吉尼亚理工大学电气与计算机工程系） ； Computer Science Department, Princess Sumaya University for Technology（普里姆斯萨大学技术学院计算机科学系） ； Computer Science Department, King Fahd University of Petroleum and Minerals（国王法赫德石油与矿物大学计算机科学系） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Slow Tuning and Low-Entropy Masking for Safe Chain-of-Thought Distillation

Ziyang Ma, Qingyue Yuan, Linhai Zhang, Deyu Zhou

专题命中 推理与问题求解 ：large language model(abstract)；language model(abstract)；small language model(abstract)；SLM(abstract)

Comments Preprint

LLMs for Resource Allocation: A Participatory Budgeting Approach to Inferring Preferences

Sankarshan Damle, Boi Faltings

机构 * Artificial Intelligence Laboratory (LIA), EPFL（人工智能实验室（LIA），瑞士联邦理工学院） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Comments Published in the Proceedings of the 28th European Conference on Artificial Intelligence (ECAI 2025)

Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks

Lutfi Eren Erdogan, Nicholas Lee, Sehoon Kim, Suhong Moon, Hiroki Furuta, Gopala Anumanchipalli, Kurt Keutzer, Amir Gholami

机构 * University of Tokyo（东京大学） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；language agent(abstract)

Journal ref ICML 2025

Tree-of-Code: A Tree-Structured Exploring Framework for End-to-End Code Generation and Execution in Complex Task Handling

Ziyi Ni, Yifan Li, Ning Yang, Dou Shen, Pin Lv, Daxiang Dong

机构 * The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences（认知与决策智能复杂系统重点实验室，自动化研究所，中国科学院） ； School of Artificial Intelligence, University of Chinese Academy of Science（人工智能学院，中国科学院大学） ； Baidu, Inc.（百度公司） ； Global Innovation Exchange Institution, Tsinghua University（全球创新交换机构，清华大学） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；pretraining(abstract)

Comments This idea was first submitted to the NeuralPS Workshop "System 2 Reasoning At Scale" in September 2024. Its OpenReview: https://openreview.net/forum?id=8NKAL8Ngxk&noteId=8NKAL8Ngxk. It was then submitted to the NAACL 2025 in October 2024, which is recorded in: https://openreview.net/forum?id=S0ZUWD3Vy5&noteId=S0ZUWD3Vy5. Now this paper has been accepted for publication in ACL 2025 Findings

VerifyBench: A Systematic Benchmark for Evaluating Reasoning Verifiers Across Domains

Xuzhao Li, Xuchen Li, Shiyu Hu, Yongzhen Guo, Wentao Zhang

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Comments Preprint, Under review

Divide and Translate: Compositional First-Order Logic Translation and Verification for Complex Logical Reasoning

Hyun Ryu, Gyeongman Kim, Hyemin S. Lee, Eunho Yang

机构 * KAIST（韩国科学技术院） ； MIT（麻省理工学院） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Comments ICLR 2025 camera-ready version

Journal ref The Thirteenth International Conference on Learning Representations (ICLR 2025)

Introspection of Thought Helps AI Agents

Haoran Sun, Shaoning Zeng

机构 * Yangtze Delta Region Institute (Huzhou), University of Electronic and Science Technology of China（长江三角洲地区研究院（湖州），电子科技大学） ； School of Information and Software Engineering, University of Electronic and Science Technology of China（信息与软件工程学院，电子科技大学） ； Zhejiang Chuangjiekedong Ltd., Huzhou, Zhejiang, China（浙江创捷科技有限公司，湖州，浙江，中国） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；post-training(abstract)

Does Learning Mathematical Problem-Solving Generalize to Broader Reasoning?

Ruochen Zhou, Minrui Xu, Shiqi Chen, Junteng Liu, Yunqi Li, Xinxin Lin, Zhengyu Chen, Junxian He

机构 * City University of Hong Kong（香港城市大学） ； HKUST（香港科技大学） ； Meituan（美团） 纠错

专题命中 推理与问题求解 ：large language model(abstract)；language model(abstract)；instruction tuning(abstract)；pretraining(abstract)

CodeAgents: A Token-Efficient Framework for Codified Multi-Agent Reasoning in LLMs

Bruce Yang, Xinfeng He, Huan Gao, Yifan Cao, Xiaofan Li, David Hsu

机构 * National University of Singapore（新加坡国立大学） ； School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院） ； Sapiens AI 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Data Diversification Methods In Alignment Enhance Math Performance In LLMs

Berkan Dokmeci, Qingyang Wu, Ben Athiwaratkun, Ce Zhang, Shuaiwen Leon Song, James Zou

机构 * Washington University in St. Louis（华盛顿大学圣路易斯分校） ； Together AI ； University of Chicago（芝加哥大学） ； Stanford University（斯坦福大学） 纠错

专题命中 推理与问题求解 ：large language model(abstract)；language model(abstract)；preference optimization(abstract)；prompting(abstract)

MiCoTA: Bridging the Learnability Gap with Intermediate CoT and Teacher Assistants

Dongyi Ding, Tiannan Wang, Chenghao Zhu, Meiling Tao, Yuchen Eleanor Jiang, Wangchunshu Zhou

机构 * South China Agricultural University（华南农业大学） ； The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）） ； University of Electronic Science and Technology of China（电子科技大学） 纠错

专题命中 推理与问题求解 ：large language model(abstract)；language model(abstract)；small language model(abstract)；SLM(abstract)

Comments Work in progress

Is External Information Useful for Stance Detection with LLMs?

Quang Minh Nguyen, Taegyoon Kim

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Comments ACL Findings 2025

Debate-Driven Multi-Agent LLMs for Phishing Email Detection

Ngoc Tuong Vy Nguyen, Felix D Childress, Yunting Yin

机构 * Department of Computer Science（计算机科学系） ； Earlham College（埃尔哈姆学院） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Comments Accepted to the 13th International Symposium on Digital Forensics and Security (ISDFS 2025)

Journal ref 2025 13th International Symposium on Digital Forensics and Security (ISDFS)

RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1

Yu Xie, Xingkai Ren, Ying Qi, Yao Hu, Lianlei Shan

机构 * Xiaohongshu（小红书） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；SFT(abstract)

InspireDebate: Multi-Dimensional Subjective-Objective Evaluation-Guided Reasoning and Optimization for Debating

Fuyu Wang, Jiangtong Li, Kun Zhu, Changjun Jiang

机构 * Key Laboratory of Embedded System and Service Computing, Ministry of Education, Tongji University（嵌入式系统与服务计算重点实验室，教育部，同济大学） ； School of Computer Science and Technology, Tongji University（计算机科学与技术学院，同济大学） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；preference optimization(abstract)

Comments 20 pages; Accepted to ACL 2025 Main

Leveraging LLMs to Assess Tutor Moves in Real-Life Dialogues: A Feasibility Study

Danielle R. Thomas, Conrad Borchers, Jionghao Lin, Sanjit Kakarla, Shambhavi Bhushan, Erin Gatz, Shivang Gupta, Ralph Abboud, Kenneth R. Koedinger

机构 * Carnegie Mellon University（卡内基梅隆大学） ； Learning Engineering Virtual Institute（学习工程虚拟研究所） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Comments Short research paper accepted at EC-TEL 2025

GraphRAG-Causal: A novel graph-augmented framework for causal reasoning and annotation in news

Abdul Haque, Umm e Hani, Ahmad Din, Muhammad Babar, Ali Abbas, Insaf Ullah

机构 * Dept. of Artificial Intelligence & Data Science FAST School of Computing NUCES（人工智能与数据科学系 FAST 计算学院 NUCES） ； Dept. of Computing and Electronics Engineering Middle East College（计算与电子工程系 中东学院） ； Institute for Analytics and Data Science University of Essex（分析与数据科学研究所 埃塞克斯大学） 纠错

专题命中 推理与问题求解 ：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Comments 18 pages, 8 figures