arXivDaily arXiv每日学术速递 周一至周五更新

AI 大模型

大模型推理能力

大模型数学、逻辑、规划、多步推理和测试时计算能力。

共收录 5891 信号源:cs.CL, cs.AI, cs.LG

1. 其他推理 5891 篇

2504.02708 2025-04-04 cs.CL 57%

The Hidden Space of Safety: Understanding Preference-Tuned LLMs in Multilingual context

Nikhil Verma, Manasa Bharadwaj

机构 * LG Toronto AI Research lab(LG多伦多人工智能研究实验室)

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

Comments 14 pages, 11 Figures, 2 Tables, currently under review at ACL 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.02417 2025-04-04 cs.CV cs.AI 57%

Leveraging Static Relationships for Intra-Type and Inter-Type Message Passing in Video Question Answering

Lili Liang, Guanglu Sun

机构 * School of Computer Science and Technology, Harbin University of Science and Technology(哈尔滨理工大学计算机科学与技术学院) Heilongjiang Provincial Key Laboratory of Intelligent Information Processing and Application(黑龙江省智能信息处理与应用重点实验室)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.02119 2025-04-04 cs.LG 57%

Efficient Model Selection for Time Series Forecasting via LLMs

Wang Wei, Tiankai Yang, Hongjie Chen, Ryan A. Rossi, Yue Zhao, Franck Dernoncourt, Hoda Eldardiry

机构 * Virginia Tech(弗吉尼亚理工大学) University of South California(南加利福尼亚大学) Dolby Labs(杜比实验室) Adobe Research(奥多比研究中心)

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

Comments 16 pages, 3 Figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2407.09025 2025-04-03 cs.AI 57%

SpreadsheetLLM: Encoding Spreadsheets for Large Language Models

Haoyu Dong, Jianbo Zhao, Yuzhang Tian, Junyu Xiong, Shiyu Xia, Mengyu Zhou, Yun Lin, José Cambronero, Yeye He, Shi Han, Dongmei Zhang

机构 * Microsoft Corporation(微软公司)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.00725 2025-04-02 cs.CL 57%

Aplicação de Large Language Models na Análise e Síntese de Documentos Jurídicos: Uma Revisão de Literatura

Matheus Belarmino, Rackel Coelho, Roberto Lotudo, Jayr Pereira

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

Comments in Portuguese language

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.00285 2025-04-02 cs.CL 57%

Do Large Language Models Exhibit Spontaneous Rational Deception?

Samuel M. Taylor, Benjamin K. Bergen

机构 * UC San Diego(加州大学圣迭戈分校)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.23360 2025-04-01 cs.CL 57%

Not All LoRA Parameters Are Essential: Insights on Inference Necessity

Guanhua Chen, Yutong Yao, Ci-Jun Gao, Lidia S. Chao, Feng Wan, Derek F. Wong

机构 * University of Macau(澳门大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.22726 2025-04-01 cs.GT cs.CL cs.HC cs.MA econ.GN q-fin.EC 57%

InfoBid: A Simulation Framework for Studying Information Disclosure in Auctions with Large Language Model-based Agents

Yue Yin

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

Comments AAAI 2025 Workshop: Economics of Modern ML: Markets, Incentives, and Generative AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.03439 2025-04-01 cs.CL 57%

ToolGen: Unified Tool Retrieval and Calling via Generation

Renxi Wang, Xudong Han, Lei Ji, Shu Wang, Timothy Baldwin, Haonan Li

机构 * LibrAI Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学) Microsoft(微软公司) University of California, Los Angeles(加州大学洛杉矶分校) The University of Melbourne(墨尔本大学)

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

Comments ICLR 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.20939 2025-03-28 cs.CL 57%

Hacia la interpretabilidad de la detección anticipada de riesgos de depresión utilizando grandes modelos de lenguaje

Horacio Thompson, Maximiliano Sapino, Edgardo Ferretti, Marcelo Errecalde

机构 * Universidad Nacional de San Luis(圣路易斯国立大学) Consejo Nacional de Investigaciones Científicas y Técnicas (CONICET)(国家科学技术研究委员会(CONICET))

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

Comments In Spanish language, In 30° Congreso Argentino de Ciencias de la Computación (CACIC 2024), La Plata, Argentina

Journal ref In Libro de Actas CACIC 2024, pp. 72-81

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.20836 2025-03-28 cs.CL 57%

Named Entity Recognition in Context

Colin Brisson, Ayoub Kahfy, Marc Bui, Frédéric Constant

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

Journal ref Second Workshop on Ancient Language Processing, Mar 2025, Albuquerque, United States

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.20791 2025-03-28 cs.CL 57%

ECLAIR: Enhanced Clarification for Interactive Responses in an Enterprise AI Assistant

John Murzaku, Zifan Liu, Vaishnavi Muppala, Md Mehrab Tanjim, Xiang Chen, Yunyao Li

机构 * Adobe(奥多比公司)

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

Comments 3 pages, 1 figure

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.19523 2025-03-27 cs.LG cs.CV 57%

One Framework to Rule Them All: Unifying RL-Based and RL-Free Methods in RLHF

Xin Cai

机构 * Independent Researcher 2em Personal Webpage

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2403.01390 2025-03-26 cs.CL 57%

Right for Right Reasons: Large Language Models for Verifiable Commonsense Knowledge Graph Question Answering

Armin Toroghi, Willis Guo, Mohammad Mahdi Abdollah Pour, Scott Sanner

机构 * University of Toronto(多伦多大学) Vector Institute of Artificial Intelligence(向量人工智能研究所)

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

Comments 33 pages, EMNLP24

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.19257 2025-03-26 cs.CL cs.DL 57%

SCI-IDEA: Context-Aware Scientific Ideation Using Token and Sentence Embeddings

Farhana Keya, Gollam Rabby, Prasenjit Mitra, Sahar Vahdati, Sören Auer, Yaser Jaradeh

机构 * TIB—Leibniz Information Centre for Science and Technology(莱布尼茨科学与技术信息中心) L3S Research Center, Leibniz University Hannover(汉诺威莱布尼茨大学L3S研究中心)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.18695 2025-03-25 cs.CV cs.LG 57%

OCRT: Boosting Foundation Models in the Open World with Object-Concept-Relation Triad

Luyao Tang, Yuxuan Yuan, Chaoqi Chen, Zeyu Zhang, Yue Huang, Kun Zhang

机构 * Xiamen University(厦门大学) Shenzhen University(深圳大学) The Australian National University(澳大利亚国立大学) Carnegie Mellon University(卡内基梅隆大学) Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)

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

Comments Accepted by CVPR 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.15723 2025-03-25 cs.IR cs.AI cs.DB 57%

Balancing Content Size in RAG-Text2SQL System

Prakhar Gurawa, Anjali Dharmik

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.17073 2025-03-24 cs.CL cs.IR 57%

A Study into Investigating Temporal Robustness of LLMs

Jonas Wallat, Abdelrahman Abdallah, Adam Jatowt, Avishek Anand

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

Comments 8 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.16437 2025-03-24 cs.HC cs.AI q-bio.NC 57%

Haunted House: A text-based game for comparing the flexibility of mental models in humans and LLMs

Brett Puppart, Paul-Henry Paltmann, Jaan Aru

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.16131 2025-03-24 cs.CL 57%

MKG-Rank: Enhancing Large Language Models with Knowledge Graph for Multilingual Medical Question Answering

Feiyang Li, Yingjian Chen, Haoran Liu, Rui Yang, Han Yuan, Yuang Jiang, Tianxiao Li, Edison Marrese Taylor, Hossein Rouhizadeh, Yusuke Iwasawa, Douglas Teodoro, Yutaka Matsuo, Irene Li

机构 * University of Tokyo(东京大学) Texas A&M University(德克萨斯农工大学) Duke-NUS Medical School(杜克-新加坡国立大学医学院) Smartor LLC(斯马特有限责任公司) NEC Laboratories America(美国电气公司实验室) University of Geneva(日内瓦大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2308.09474 2025-03-24 cs.AI cs.SC math.OC 57%

Evolving Scientific Discovery by Unifying Data and Background Knowledge with AI Hilbert

Ryan Cory-Wright, Cristina Cornelio, Sanjeeb Dash, Bachir El Khadir, Lior Horesh

机构 * Imperial College Business School(帝国理工商学院) Samsung AI(三星人工智能) IBM Thomas J. Watson Research Center(IBM托马斯·J·沃森研究中心)

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

Comments Revised version, including a significant number of new experiments+supplementary material in appendix, and a title change

Journal ref Nature Communications 15:5922, 2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.04905 2025-03-21 cs.CL cs.PL 57%

OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models

Siming Huang, Tianhao Cheng, J. K. Liu, Jiaran Hao, Liuyihan Song, Yang Xu, J. Yang, Jiaheng Liu, Chenchen Zhang, Linzheng Chai, Ruifeng Yuan, Zhaoxiang Zhang, Jie Fu, Qian Liu, Ge Zhang, Zili Wang, Yuan Qi, Yinghui Xu, Wei Chu

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.15342 2025-03-20 cs.CV cs.AI 57%

TruthLens:A Training-Free Paradigm for DeepFake Detection

Ritabrata Chakraborty, Rajatsubhra Chakraborty, Ali Khaleghi Rahimian, Thomas MacDougall

机构 * Manipal University Jaipur(斋浦尔马尼帕尔大学) University of North Carolina Charlotte(北卡罗来纳大学夏洛特分校)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.14254 2025-03-19 cs.RO cs.AI 57%

CTSAC: Curriculum-Based Transformer Soft Actor-Critic for Goal-Oriented Robot Exploration

Chunyu Yang, Shengben Bi, Yihui Xu, Xin Zhang

机构 * School of Information and Control Engineering, China University of Mining and Technology(中国矿业大学信息与控制工程学院)

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

Comments 7pages,7 figures,Thesis received by 2025 ICRA

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.13891 2025-03-19 cs.CV cs.CL 57%

Where do Large Vision-Language Models Look at when Answering Questions?

Xiaoying Xing, Chia-Wen Kuo, Li Fuxin, Yulei Niu, Fan Chen, Ming Li, Ying Wu, Longyin Wen, Sijie Zhu

机构 * Bytedance Intelligent Creation(字节跳动智能创作) Northwestern University(西北大学) Oregon State University(俄勒冈州立大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.13804 2025-03-19 cs.AI 57%

Empowering GraphRAG with Knowledge Filtering and Integration

Kai Guo, Harry Shomer, Shenglai Zeng, Haoyu Han, Yu Wang, Jiliang Tang

机构 * Michigan State University(密歇根州立大学) University of Oregon(俄勒冈大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2501.18291 2025-03-19 cs.AI cs.HC 57%

CueTip: An Interactive and Explainable Physics-aware Pool Assistant

Sean Memery, Kevin Denamganai, Jiaxin Zhang, Zehai Tu, Yiwen Guo, Kartic Subr

机构 * University of Edinburgh(爱丁堡大学) Lightspeed Studios(光速工作室) Independent Researcher(独立研究者)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.06169 2025-03-18 cs.CV cs.AI 57%

Treble Counterfactual VLMs: A Causal Approach to Hallucination

Shawn Li, Jiashu Qu, Yuxiao Zhou, Yuehan Qin, Tiankai Yang, Yue Zhao

机构 * University of Southern California(南加州大学) University of Cincinnati(辛辛那提大学) National University of Singapore(新加坡国立大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.11486 2025-03-17 cs.LG 57%

A Review of DeepSeek Models' Key Innovative Techniques

Chengen Wang, Murat Kantarcioglu

机构 * University of Texas at Dallas(德克萨斯大学达拉斯分校) Virginia Tech(弗吉尼亚理工大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2409.19338 2025-03-12 cs.SI cs.CL 57%

Decoding Echo Chambers: LLM-Powered Simulations Revealing Polarization in Social Networks

Chenxi Wang, Zongfang Liu, Dequan Yang, Xiuying Chen

机构 * Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)

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

Comments Accepted by COLING 2025

详情

展开后加载摘要…

URL PDF HTML 收藏