大模型推理能力

Enhancing Large Language Models with Reliable Knowledge Graphs

Qinggang Zhang

机构 * Department of Computing（计算系） 纠错

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

Comments Thesis

Step-by-step Instructions and a Simple Tabular Output Format Improve the Dependency Parsing Accuracy of LLMs

Hiroshi Matsuda, Chunpeng Ma, Masayuki Asahara

机构 * Megagon Labs（梅加贡实验室） ； Recruit Co., Ltd.（招聘公司） ； National Institute for Japanese Language and Linguistics（日本语言学研究所） 纠错

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

Comments 9 pages, 2 figures, accepted to SyntaxFest 2025

Co-occurrence is not Factual Association in Language Models

Xiao Zhang, Miao Li, Ji Wu

机构 * Department of Electronics Engineering（电子工程系） ； Tsinghua University（清华大学） ； Department of Electronics Engineering, College of AI（人工智能学院电子工程系） ； Beijing National Research Center for Information Science and Technology（北京信息科学国家研究中心） ； Center for Big Data and Clinical Research, Institute for Precision Medicine（精准医学研究院大数据与临床研究中心） 纠错

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

VideoQA in the Era of LLMs: An Empirical Study

Junbin Xiao, Nanxin Huang, Hangyu Qin, Dongyang Li, Yicong Li, Fengbin Zhu, Zhulin Tao, Jianxing Yu, Liang Lin, Tat-Seng Chua, Angela Yao

机构 * National University of Singapore（新加坡国立大学） ； Communication University of China（中国传媒大学） ； Sun Yat-Sen University（中山大学） 纠错

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

Comments IJCV'25

Applying Cognitive Design Patterns to General LLM Agents

Robert E. Wray, James R. Kirk, John E. Laird

机构 * Center for Integrated Cognition, IQMRI（整合认知中心，IQMRI） 纠错

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

Comments 10 pages + references, 2 figures, 3 tables. Accepted for oral presentation at AGI25

Quizzard@INOVA Challenge 2025 -- Track A: Plug-and-Play Technique in Interleaved Multi-Image Model

Dinh Viet Cuong, Hoang-Bao Le, An Pham Ngoc Nguyen, Liting Zhou, Cathal Gurrin

机构 * School of Computing, Dublin City University（都柏林城市大学计算机学院） ； ADAPT Centre（ADAPT中心） 纠错

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

Deontological Keyword Bias: The Impact of Modal Expressions on Normative Judgments of Language Models

Bumjin Park, Jinsil Lee, Jaesik Choi

机构 * KAIST AI（韩国科学技术院人工智能研究所） 纠错

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

Comments 20 pages including references and appendix; To appear in ACL 2025 main conference

Long-context Non-factoid Question Answering in Indic Languages

Ritwik Mishra, Rajiv Ratn Shah, Ponnurangam Kumaraguru

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

Comments Short version of this manuscript accepted at https://bda2025.iiitb.net/

Magistral

Mistral-AI, :, Abhinav Rastogi, Albert Q. Jiang, Andy Lo, Gabrielle Berrada, Guillaume Lample, Jason Rute, Joep Barmentlo, Karmesh Yadav, Kartik Khandelwal, Khyathi Raghavi Chandu, Léonard Blier, Lucile Saulnier, Matthieu Dinot, Maxime Darrin, Neha Gupta, Roman Soletskyi, Sagar Vaze, Teven Le Scao, Yihan Wang, Adam Yang, Alexander H. Liu, Alexandre Sablayrolles, Amélie Héliou, Amélie Martin, Andy Ehrenberg, Anmol Agarwal, Antoine Roux, Arthur Darcet, Arthur Mensch, Baptiste Bout, Baptiste Rozière, Baudouin De Monicault, Chris Bamford, Christian Wallenwein, Christophe Renaudin, Clémence Lanfranchi, Darius Dabert, Devon Mizelle, Diego de las Casas, Elliot Chane-Sane, Emilien Fugier, Emma Bou Hanna, Gauthier Delerce, Gauthier Guinet, Georgii Novikov, Guillaume Martin, Himanshu Jaju, Jan Ludziejewski, Jean-Hadrien Chabran, Jean-Malo Delignon, Joachim Studnia, Jonas Amar, Josselin Somerville Roberts, Julien Denize, Karan Saxena, Kush Jain, Lingxiao Zhao, Louis Martin, Luyu Gao, Lélio Renard Lavaud, Marie Pellat, Mathilde Guillaumin, Mathis Felardos, Maximilian Augustin, Mickaël Seznec, Nikhil Raghuraman, Olivier Duchenne, Patricia Wang, Patrick von Platen, Patryk Saffer, Paul Jacob, Paul Wambergue, Paula Kurylowicz, Pavankumar Reddy Muddireddy, Philomène Chagniot, Pierre Stock, Pravesh Agrawal, Romain Sauvestre, Rémi Delacourt, Sanchit Gandhi, Sandeep Subramanian, Shashwat Dalal, Siddharth Gandhi, Soham Ghosh, Srijan Mishra, Sumukh Aithal, Szymon Antoniak, Thibault Schueller, Thibaut Lavril, Thomas Robert, Thomas Wang, Timothée Lacroix, Valeriia Nemychnikova, Victor Paltz, Virgile Richard, Wen-Ding Li, William Marshall, Xuanyu Zhang, Yunhao Tang

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

Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards

Xiaobao Wu

机构 * Nanyang Technological University（南洋理工大学） 纠错

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

Comments 36 Pages

A Proposal to Extend the Common Model of Cognition with Metacognition

John Laird, Christian Lebiere, Paul Rosenbloom, Andrea Stocco

机构 * IQMRI（IQMRI研究所） 纠错

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

Divide-Fuse-Conquer: Eliciting "Aha Moments" in Multi-Scenario Games

Xiaoqing Zhang, Huabin Zheng, Ang Lv, Yuhan Liu, Zirui Song, Xiuying Chen, Rui Yan, Flood Sung

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

Comments 25 pages, 13 figures, and 8 tables

(A)I Am Not a Lawyer, But...: Engaging Legal Experts towards Responsible LLM Policies for Legal Advice

Inyoung Cheong, King Xia, K. J. Kevin Feng, Quan Ze Chen, Amy X. Zhang

机构 * University of Washington（华盛顿大学） 纠错

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

Comments 14 pages

How Do People Revise Inconsistent Beliefs? Examining Belief Revision in Humans with User Studies

Stylianos Loukas Vasileiou, Antonio Rago, Maria Vanina Martinez, William Yeoh

机构 * Washington University in St. Louis（华盛顿大学圣路易斯分校） ； Imperial College London（伦敦帝国学院） ； Artificial Intelligence Research Institute (IIIA-CSIC)（人工智能研究所（IIIA-CSIC）） 纠错

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

Writing-Zero: Bridge the Gap Between Non-verifiable Tasks and Verifiable Rewards

Ruipeng Jia, Yunyi Yang, Yongbo Gai, Kai Luo, Shihao Huang, Jianhe Lin, Xiaoxi Jiang, Guanjun Jiang

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

Representation Shattering in Transformers: A Synthetic Study with Knowledge Editing

Kento Nishi, Rahul Ramesh, Maya Okawa, Mikail Khona, Hidenori Tanaka, Ekdeep Singh Lubana

机构 * CBS-NTT Program in Physics of Intelligence, Harvard University ； Harvard College ； Informatics Lab, NTT Research Inc. ； Information Science, University of Pennsylvania ； Department of Physics, Massachusetts Institute of Technology 纠错

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

Comments Accepted to ICML 2025

PGDA-KGQA: A Prompt-Guided Generative Framework with Multiple Data Augmentation Strategies for Knowledge Graph Question Answering

Xiujun Zhou, Pingjian Zhang, Deyou Tang

机构 * School of Software Engineering（软件工程学院） ； South China University of Technology（华南理工大学） 纠错

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

Comments 13 pages, 7 figures, 5 tables

From Generation to Generalization: Emergent Few-Shot Learning in Video Diffusion Models

Pablo Acuaviva, Aram Davtyan, Mariam Hassan, Sebastian Stapf, Ahmad Rahimi, Alexandre Alahi, Paolo Favaro

机构 * University of Bern（伯恩大学） ； EPFL（瑞士联邦理工学院） 纠错

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

Comments 27 pages, 23 figures, 9 tables. Project page: https://pabloacuaviva.github.io/Gen2Gen/

Everything Can Be Described in Words: A Simple Unified Multi-Modal Framework with Semantic and Temporal Alignment

Xiaowei Bi, Zheyuan Xu

机构 * Northwestern University（西北大学） ； IEEE Member（IEEE会员） 纠错

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

Conservative Bias in Large Language Models: Measuring Relation Predictions

Toyin Aguda, Erik Wilson, Allan Anzagira, Simerjot Kaur, Charese Smiley

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

Comments 10 pages

Reinforcement Pre-Training

Qingxiu Dong, Li Dong, Yao Tang, Tianzhu Ye, Yutao Sun, Zhifang Sui, Furu Wei

机构 * Microsoft Research（微软研究院） ； Peking University（北京大学） ； Tsinghua University（清华大学） 纠错

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

Reliable Collaborative Conversational Agent System Based on LLMs and Answer Set Programming

Yankai Zeng, Gopal Gupta

机构 * Department of Computer Science University of Texas at Dallas（计算机科学系德克萨斯大学达拉斯分校） 纠错

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

Comments 9 pages

Synergizing Unsupervised Episode Detection with LLMs for Large-Scale News Events

Priyanka Kargupta, Yunyi Zhang, Yizhu Jiao, Siru Ouyang, Jiawei Han

机构 * Siebel School of Computing and Data Science（塞比尔计算与数据科学学院） ； 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 其他推理 ：reasoning(abstract)；分类 cs.CL

Comments ACL 2025 Main Conference. Code available here: https://github.com/pkargupta/epimine

Evaluating Large Language Model Capabilities in Assessing Spatial Econometrics Research

Giuseppe Arbia, Luca Morandini, Vincenzo Nardelli

机构 * Department of Statistical Sciences, Università Cattolica del Sacro Cuore（统计科学系，天主教圣心大学） ； School of Computing and Information Systems, The University of Melbourne（计算与信息系统学院，墨尔本大学） 纠错

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

LLM4DSR: Leveraging Large Language Model for Denoising Sequential Recommendation

Bohao Wang, Feng Liu, Changwang Zhang, Jiawei Chen, Yudi Wu, Sheng Zhou, Xingyu Lou, Jun Wang, Yan Feng, Chun Chen, Can Wang

机构 * Zhejiang University（浙江大学） ； OPPO Co Ltd（OPPO公司） 纠错

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

Leopard: A Vision Language Model For Text-Rich Multi-Image Tasks

Mengzhao Jia, Wenhao Yu, Kaixin Ma, Tianqing Fang, Zhihan Zhang, Siru Ouyang, Hongming Zhang, Dong Yu, Meng Jiang

机构 * University of Notre Dame（诺丁汉大学） ； Tencent AI Seattle Lab（腾讯AI西雅图实验室） ； UIUC（伊利诺伊大学香槟分校） 纠错

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

Comments Our code is available at https://github.com/tencent-ailab/Leopard

Pseudo Relevance Feedback is Enough to Close the Gap Between Small and Large Dense Retrieval Models

Hang Li, Xiao Wang, Bevan Koopman, Guido Zuccon

机构 * The University of Queensland（昆士兰大学） ； University of International Business and Economics（国际商务经济大学） ； CSIRO（澳大利亚联邦科学与工业研究组织） 纠错

专题命中 其他推理 ：chain-of-thought(abstract)；分类 cs.LG

Normative Conflicts and Shallow AI Alignment

Raphaël Millière

机构 * Raphaël Millière 纠错

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

Comments Published in Philosophical Studies

Journal ref Milliere, R. (2025). Normative conflicts and shallow AI alignment. Philosophical Studies, 1-44

TaDA: Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering

Vinay Joshi, Pratik Prabhanjan Brahma, Zicheng Liu, Emad Barsoum

机构 * AMD 纠错

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

Comments ACL-2025 industry-track accepted

Is the end of Insight in Sight ?

Jean-Michel Tucny, Mihir Durve, Sauro Succi

机构 * Department of Civil, Computer Science, and Aeronautical Technologies Engineering, Università degli Studi Roma Tre（罗马三大学土木、计算机科学与航空技术工程系） ； Center for Life Nano- & Neuro-Science, Italian Institute of Technology (IIT)（生命纳米与神经科学中心，意大利理工学院） 纠错

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

Comments 15 pages, 2 figures