arXivDaily arXiv每日学术速递 周一至周五更新

AI 大模型

语言大模型 / LLM

大语言模型、预训练、指令微调、后训练和语言模型应用。

共收录 18875 信号源:cs.CL, cs.AI, cs.LG

1. 推理与问题求解 18875 篇

2605.11011 2026-05-13 cs.LG cs.AI 85%

LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models

LoopUS: 将预训练大语言模型转换为循环潜在细化模型

Taekhyun Park, Yongjae Lee, Dohee Kim, Hyerim Bae

机构 * Department of Data Science(数据科学系) Department of Industrial Engineering(工业工程系) Pusan National University(釜山国立大学) Changwon National University(昌原国立大学)

专题命中 推理与问题求解 :LLM(summary_cn,abstract);post-training(abstract);分类 cs.AI、cs.LG

AI总结 LoopUS通过循环架构提升LLM推理性能,无需重新训练,采用四个核心组件稳定模型并提高效率。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.10848 2026-05-12 cs.IR cs.AI cs.CL 85%

Rethinking Agentic Search with Pi-Serini: Is Lexical Retrieval Sufficient?

重新思考Pi-Serini中的代理搜索:词汇检索是否足够?

Tz-Huan Hsu, Jheng-Hong Yang, Jimmy Lin

机构 * University of Waterloo(滑铁卢大学) Stencilzeit University of Waterloo(斯泰尔齐特大学)

专题命中 推理与问题求解 :LLM(summary_cn,abstract_cn);large language model(abstract);language model(abstract);分类 cs.CL、cs.AI

AI总结 本文探讨了在代理循环中,随着LLM能力提升,词汇检索是否足够。通过结合BM25与前沿LLM,引入Pi-Serini搜索代理,展示其在BrowseComp-Plus上优于现有检索代理的性能。

Comments 15 pages, 4 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.18184 2026-05-12 cs.LG cs.AI 85%

ActivationReasoning: Logical Reasoning in Latent Activation Spaces

ActivationReasoning: 在潜在激活空间中的逻辑推理

Lukas Helff, Ruben Härle, Wolfgang Stammer, Felix Friedrich, Manuel Brack, Antonia Wüst, Hikaru Shindo, Patrick Schramowski, Kristian Kersting

机构 * TU Darmstadt(图恩-达姆施塔特大学) Lab1141(Lab1141实验室) Aleph Alpha Research(Aleph Alpha研究) MPI-Inf, SIC(马克斯·普朗克研究所(MPI-Inf)) Meta FAIR Adobe Applied Research(Adobe应用研究) DFKI(DFKI研究所) CERTAIN, Germany(德国CERTAIN)

专题命中 推理与问题求解 :LLM(summary_cn,abstract_cn);large language model(abstract);language model(abstract);分类 cs.AI、cs.LG

AI总结 本文提出ActivationReasoning框架,通过在LLM的潜在空间中嵌入显式逻辑推理,提升模型的推理能力、可控性和对齐性,验证了在多跳推理、抽象与鲁棒性、自然语言推理及安全任务中的有效性。

Comments Proceedings of the 14th International Conference on Learning Representations (ICLR 2026)

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.09920 2026-05-12 cs.LG cs.AI 85%

Verifier-Free RL for LLMs via Intrinsic Gradient-Norm Reward

通过内在梯度-范数奖励实现无需验证器的LLM强化学习

Xuexiang Wen, Hang Yu, Linchao Zhu, Gaoang Wang

机构 * Zhejiang University(浙江大学) Ant Group(蚂蚁集团)

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

AI总结 本文提出VIGOR,一种无需外部验证器的强化学习奖励机制,通过内在偏好信号提升政策优化效果,在数学推理和代码基准测试中表现优于现有方法。

Comments Accepted to Findings of ACL 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.09806 2026-05-12 cs.LG cs.AI 85%

LEAD: Length-Efficient Adaptive and Dynamic Reasoning for Large Language Models

LEAD:高效适应性与动态推理用于大语言模型

Songtao Wei, Yi Li, Zhikai Li, Xu Hu, Yuede Ji, Guanpeng Li, Feng Chen, Carl Yang, Zhichun Guo, Bingzhe Li

机构 * University of Texas at Dallas(德克萨斯大学达拉斯分校) Emory University(埃默里大学) Individual Researcher(独立研究员) University of Texas at Arlington(德克萨斯大学阿灵顿分校) University of Florida(佛罗里达大学)

专题命中 推理与问题求解 :large language model(title);language model(title);分类 cs.AI、cs.LG

AI总结 LEAD通过动态校准正确性与效率的权衡,提升大语言模型的推理效率与准确性,实现更短的输出。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.08625 2026-05-12 cs.LG cs.AI 85%

Reasoning-Aware Training for Time Series Forecasting

面向时间序列预测的推理感知训练

Md Atik Ahamed, Mihir Parmar, Palash Goyal, Chun-Liang Li, Qiang Cheng, Tomas Pfister, Jinsung Yoon

机构 * Google(谷歌) University of Kentucky(肯塔基大学)

专题命中 推理与问题求解 :LLM(summary_cn,abstract);foundation model(abstract);分类 cs.AI、cs.LG

AI总结 本文提出STRIDE框架,通过将LLM推理注入到时间序列基础模型的连续嵌入空间中,提升数值预测的准确性和可解释性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.26574 2026-05-12 cs.AI cond-mat.other cs.CL hep-th quant-ph 85%

Probing the Critical Point (CritPt) of AI Reasoning: a Frontier Physics Research Benchmark

探测人工智能推理的临界点(CritPt):一个前沿物理研究基准

Minhui Zhu, Minyang Tian, Xiaocheng Yang, Tianci Zhou, Lifan Yuan, Penghao Zhu, Eli Chertkov, Shengyan Liu, Yufeng Du, Ziming Ji, Indranil Das, Qingzhi Chen, Junyi Cao, Yufeng Du, Jiabin Yu, Peixue Wu, Jinchen He, Yifan Su, Yikun Jiang, Yujie Zhang, Chang Liu, Ze-Min Huang, Weizhen Jia, Yunkai Wang, Farshid Jafarpour, Yong Zhao, Xinan Chen, Jessie Shelton, Aaron W. Young, John Bartolotta, Wenchao Xu, Yue Sun, Anjun Chu, Victor Colussi, Chris Akers, Nathan Brooks, Wenbo Fu, Jinchao Zhao, Marvin Qi, Anqi Mu, Yubo Yang, Allen Zang, Yang Lyu, Peizhi Mai, Christopher Wilson, Xuefei Guo, Juntai Zhou, Daniel Inafuku, Chi Xue, Luyu Gao, Ze Yang, Yaïr Hein, Yonatan Kahn, Kevin Zhou, Di Luo, John Drew Wilson, Jarrod T. Reilly, Dmytro Bandak, Ofir Press, Liang Yang, Xueying Wang, Hao Tong, Nicolas Chia, Eliu Huerta, Hao Peng

机构 * Argonne National Laboratory(阿贡国家实验室) University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校) Virginia Tech(弗吉尼亚理工大学) Ohio State University(俄亥俄州立大学) Independent(独立) Northeastern University(东北大学) Caltech(加州理工学院) University of Florida(佛罗里达大学) University of Waterloo(滑铁卢大学) University of Maryland, College Park(马里兰大学学院公园分校) Columbia University(哥伦比亚大学) Perimeter Institute for Theoretical Physics(理论物理研究所) University of Connecticut(康涅狄格大学) University of Cologne(科隆大学) The Chinese University of Hong Kong(香港中文大学) Utrecht University(乌得勒支大学) Harvard University(哈佛大学) ETH Zürich(苏黎世联邦理工学院) Paul Scherrer Institute(保罗·谢尔研究所)

专题命中 推理与问题求解 :LLM(summary_cn,abstract_cn);large language model(abstract);language model(abstract);分类 cs.CL、cs.AI

AI总结 本文提出CritPt基准,用于测试LLM在未发表的科研级推理任务中的能力,涵盖现代物理多个领域,发现当前LLM在复杂科研挑战中表现有限,仅能实现5.7%的准确率。

Comments 40 pages, 6 figures, 6 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.16745 2026-05-08 cs.LG cs.AI 85%

Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling

超越记忆:通过递归、记忆和测试时计算扩展推理深度

Ivan Rodkin, Daniil Orel, Konstantin Smirnov, Arman Bolatov, Bilal Elbouardi, Besher Hassan, Yuri Kuratov, Aydar Bulatov, Preslav Nakov, Timothy Baldwin, Artem Shelmanov, Mikhail Burtsev

机构 * MBZUAI(马克斯·普朗克智能研究院) MIRAI Cognitive AI Systems Lab(认知人工智能系统实验室) London Institute for Mathematical Sciences(伦敦数学科学研究所)

专题命中 推理与问题求解 :LLM(summary_cn,abstract_cn);large language model(abstract);language model(abstract);分类 cs.AI、cs.LG

AI总结 研究通过细胞自动机框架探讨多步推理机制,发现LLM在推理步骤增加时性能下降,递归、记忆和测试时计算能提升结果但有限。

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.24803 2026-04-22 cs.LG cs.AI 85%

TimeOmni-1: Incentivizing Complex Reasoning with Time Series in Large Language Models

TimeOmni-1:通过时间序列激励大型语言模型的复杂推理

Tong Guan, Zijie Meng, Dianqi Li, Shiyu Wang, Chao-Han Huck Yang, Qingsong Wen, Zuozhu Liu, Sabato Marco Siniscalchi, Ming Jin, Shirui Pan

机构 * Griffith University(格里菲斯大学) Zhejiang University(浙江大学) NVIDIA(英伟达) Squirrel Ai Learning University of Palermo(帕尔米奥大学) Norwegian University of Science and Technology(挪威科学技术大学)

专题命中 推理与问题求解 :large language model(title);language model(title);分类 cs.AI、cs.LG

AI总结 本文提出TimeOmni-1,首个统一推理模型,通过时间序列推理解决多样化现实问题,提升因果发现和有效响应率。

Comments Accepted by the 14th International Conference on Learning Representations (ICLR 2026)

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.12651 2026-04-15 cs.CL cs.AI 85%

Learning Chain Of Thoughts Prompts for Predicting Entities, Relations, and even Literals on Knowledge Graphs

学习链式思维提示以预测知识图谱中的实体、关系以及甚至字面量

Alkid Baci, Luke Friedrichs, Caglar Demir, N'Dah Jean Kouagou, Axel-Cyrille Ngonga Ngomo

机构 * Department of Computer Science(计算机科学系)

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

AI总结 本文提出RALP方法,通过学习基于字符串的链式思维提示作为评分函数,提升知识图谱链接预测的性能,实验表明其在多个基准测试中均取得显著提升。

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.14264 2026-04-15 cs.LG cs.CL 85%

AAPO: Enhancing the Reasoning Capabilities of LLMs with Advantage Margin

AAPO: 通过优势边际增强大语言模型的推理能力

Jian Xiong, Jingbo Zhou, Jingyong Ye, Qiang Huang, Dejing Dou

机构 * College of Computer Science and Artificial Intelligence, Fudan University(复旦大学计算机科学与人工智能学院) Frontier Research Department, Baidu Inc.(百度公司前沿研究部)

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

AI总结 AAPO通过引入基于边际的估计方案优化交叉熵损失,有效解决传统分组相对优势估计方法的训练效率问题,在数学推理基准上表现出色。

Comments Accepted to ACL2026 Main Conference

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.08527 2026-04-10 cs.CL cs.LG 85%

Demystifying OPD: Length Inflation and Stabilization Strategies for Large Language Models

解开OPD之谜:大型语言模型中的长度膨胀与稳定策略

Feng Luo, Yu-Neng Chuang, Guanchu Wang, Zicheng Xu, Xiaotian Han, Tianyi Zhang, Vladimir Braverman

机构 * Department of Computer Science, Rice University, Houston, USA(莱斯大学计算机科学系,美国休斯顿) Department of Computer Science, University of North Carolina at Charlotte, Charlotte, USA(北卡罗来纳大学夏洛特分校计算机科学系,美国夏洛特) Department of Computer Science, Johns Hopkins University, Baltimore, USA(约翰霍普金斯大学计算机科学系,美国巴尔的摩) Department of Computer and Data Sciences, Case Western Reserve University(凯斯西储大学计算机与数据科学系)

专题命中 推理与问题求解 :large language model(title);language model(title);分类 cs.CL、cs.LG

AI总结 本文研究了OPD训练中长度膨胀问题,提出StableOPD框架结合参考 divergence 约束和rollout混合蒸馏,有效稳定训练并提升性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.13358 2026-04-01 cs.AI cs.LG 85%

The Geometry of Thought: How Scale Restructures Reasoning In Large Language Models

思维的几何学:大规模语言模型中规模如何重构推理

Samuel Cyrenius Anderson

专题命中 推理与问题求解 :large language model(title);language model(title);分类 cs.AI、cs.LG

AI总结 研究揭示大规模语言模型中推理能力的几何重构特性,通过分析不同领域和规模的推理轨迹,发现神经规模定律触发领域特定的相变而非均匀能力提升,提出神经推理算子并识别出跨领域和规模的振荡特征。

Comments The theoretical framework has been shown to be wrong and should not be followed for future research direction

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.21720 2026-03-24 cs.CL cs.AI 85%

SemEval-2026 Task 12: Abductive Event Reasoning: Towards Real-World Event Causal Inference for Large Language Models

SemEval-2026任务12:归纳事件推理:面向大规模语言模型的现实事件因果推断

Pengfei Cao, Mingxuan Yang, Yubo Chen, Chenlong Zhang, Mingxuan Liu, Kang Liu, Jun Zhao

机构 * The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China(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,北京,中国) School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China(人工智能学院,中国科学院大学,北京,中国)

专题命中 推理与问题求解 :large language model(title);language model(title);分类 cs.CL、cs.AI

AI总结 本文提出面向现实事件因果推断的归纳事件推理任务,通过多选基准测试解决分布式证据、间接背景因素和语义相关但非因果干扰等挑战,评估了122个参与者的518份提交结果。

Comments 9 pages, 3 figures, semeval 2026 task 12 description paper

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.19017 2026-03-20 cs.CL cs.AI 85%

What Really Controls Temporal Reasoning in Large Language Models: Tokenisation or Representation of Time?

真正控制大语言模型时间推理的是令牌化还是时间表示?

Gagan Bhatia, Ahmad Muhammad Isa, Maxime Peyrard, Wei Zhao

机构 * University of Aberdeen(阿伯丁大学) Université Grenoble Alpes & CNRS(格勒诺布尔阿尔卑斯大学及国家科学研究中心)

专题命中 推理与问题求解 :large language model(title);language model(title);分类 cs.CL、cs.AI

AI总结 本研究通过MultiTempBench验证了大语言模型时间推理的核心因素,发现令牌化质量是资源依赖型瓶颈,同时时间线性度在高资源语言中是主要预测因素,而碎片化在低资源语言中更显著。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.17053 2026-03-13 cs.CL cs.AI cs.DB 85%

Knowledge Distillation with Structured Chain-of-Thought for Text-to-SQL

基于结构化思维链的知识蒸馏用于文本到SQL

Khushboo Thaker, Yony Bresler

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

AI总结 本文提出Struct-SQL框架,通过结构化思维链知识蒸馏提升小型语言模型在文本到SQL任务中的性能,实现8.1%的准确率提升。

Comments Accepted at the 39th Canadian Conference on Artificial Intelligence (Canadian AI 2026). This is the extended version containing additional details and appendices omitted from the camera-ready proceedings due to space constraints

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.01464 2026-03-03 cs.AI cs.CL 85%

ProtRLSearch: A Multi-Round Multimodal Protein Search Agent with Large Language Models Trained via Reinforcement Learning

ProtRLSearch: 一种基于大语言模型的多轮多模态蛋白质搜索代理,通过强化学习进行训练

Congying Liu, Taihao Li, Ming Huang, Xingyuan Wei, Peipei Liu, Yiqing Shen, Yanxu Mao, Tiehan Cui

机构 * University of Chinese Academy of Sciences(中国科学院大学) Hangzhou Institute for Advanced Study(杭州高等研究院) Shenzhen Institutes of Advanced Technology(深圳先进技术研究所) Institute of Information Engineering(信息工程研究所) Johns Hopkins University(约翰霍普金斯大学) Henan University(河南大学)

专题命中 推理与问题求解 :large language model(title);language model(title);分类 cs.CL、cs.AI

AI总结 ProtRLSearch通过强化学习训练,利用多模态输入提升蛋白质搜索的准确性和效率,解决传统方法在多模态整合和搜索过程约束上的不足。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.09384 2026-02-11 cs.CL cs.AI 85%

Contractual Deepfakes: Can Large Language Models Generate Contracts?

合同型深度伪造:大语言模型能生成合同吗?

Eliza Mik

专题命中 推理与问题求解 :large language model(title);language model(title);分类 cs.CL、cs.AI

AI总结 本文指出大语言模型生成的合同可能不具法律效力,质疑其在法律领域应用的可行性。

Comments Accepted for publication

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.18730 2026-01-27 cs.CL cs.LG 85%

Reflect: Transparent Principle-Guided Reasoning for Constitutional Alignment at Scale

Reflect: 为大规模宪法对齐的透明原则引导推理

Henry Bell, Caroline Zhang, Mohammed Mobasserul Haque, Dhaval Potdar, Samia Zaman, Brandon Fain

机构 * Duke University(杜克大学) Independent Researcher(独立研究者)

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

AI总结 Reflect通过透明推理框架在不需训练数据的情况下提升大语言模型对多样原则的对齐能力,增强安全性和鲁棒性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.11407 2026-01-05 cs.CL cs.AI 85%

EXAONE 4.0: Unified Large Language Models Integrating Non-reasoning and Reasoning Modes

EXAONE 4.0:整合非推理与推理模式的统一大语言模型

Kyunghoon Bae, Eunbi Choi, Kibong Choi, Stanley Jungkyu Choi, Yemuk Choi, Kyubeen Han, Seokhee Hong, Junwon Hwang, Taewan Hwang, Joonwon Jang, Hyojin Jeon, Kijeong Jeon, Gerrard Jeongwon Jo, Hyunjik Jo, Jiyeon Jung, Euisoon Kim, Hyosang Kim, Jihoon Kim, Joonkee Kim, Seonghwan Kim, Soyeon Kim, Sunkyoung Kim, Yireun Kim, Yongil Kim, Youchul Kim, Edward Hwayoung Lee, Gwangho Lee, Haeju Lee, Honglak Lee, Jinsik Lee, Kyungmin Lee, Sangha Park, Young Min Paik, Yongmin Park, Youngyong Park, Sanghyun Seo, Sihoon Yang, Heuiyeen Yeen, Sihyuk Yi, Hyeongu Yun

机构 * LG AI Research(LG人工智能研究)

专题命中 推理与问题求解 :large language model(title);language model(title);分类 cs.CL、cs.AI

AI总结 EXAONE 4.0通过整合非推理与推理模式,实现了高性能与先进推理能力的统一,支持多语言并提供两种不同规模的模型版本。

Comments Technical Report, 30 Pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.03805 2025-12-02 cs.CL cs.AI 85%

Beyond Token Length: Step Pruner for Efficient and Accurate Reasoning in Large Language Models

超越标记长度:用于大语言模型高效准确推理的步剪枝

Canhui Wu, Qiong Cao, Chang Li, Zhenfang Wang, Chao Xue, Yuwei Fan, Wei Xi, Xiaodong He

机构 * Xi’an Jiaotong University(西安交通大学) JD Future Academy(京东未来学院)

专题命中 推理与问题求解 :large language model(title);language model(title);分类 cs.CL、cs.AI

AI总结 本文提出步剪枝框架,通过强化学习优化大语言模型的推理效率与准确性,显著减少响应长度并在多个基准测试中取得最佳性能。

Comments 21 pages, 9 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.01584 2025-12-01 cs.AI cs.LG 85%

ReasoningWeekly: A General Knowledge and Verbal Reasoning Challenge for Large Language Models

ReasoningWeekly: 一个面向大语言模型的通用知识和逻辑推理挑战

Zixuan Wu, Francesca Lucchetti, Aleksander Boruch-Gruszecki, Jingmiao Zhao, Carolyn Jane Anderson, Joydeep Biswas, Federico Cassano, Arjun Guha

机构 * Northeastern University(东北大学) Wellesley College(韦尔斯利学院) University of Texas at Austin(德克萨斯大学奥斯汀分校) Cursor

专题命中 推理与问题求解 :large language model(title);language model(title);分类 cs.AI、cs.LG

AI总结 ReasoningWeekly是一个基于NPR周日谜题挑战的通用知识和逻辑推理基准,揭示了现有评估中不明显的模型能力差距,并发现了新的推理失败类型。

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.18167 2025-10-23 cs.LG cs.AI 85%

Understanding Reasoning in Thinking Language Models via Steering Vectors

Constantin Venhoff, Iván Arcuschin, Philip Torr, Arthur Conmy, Neel Nanda

机构 * University of Oxford(牛津大学) University of Buenos Aires(布宜诺斯艾利斯大学)

专题命中 推理与问题求解 :language model(title,abstract);large language model(abstract,comments);分类 cs.AI、cs.LG

Comments Accepted to the Workshop on Reasoning and Planning for Large Language Models at ICLR 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.15524 2025-09-30 cs.CL cs.AI 85%

IPBench: Benchmarking the Knowledge of Large Language Models in Intellectual Property

Qiyao Wang, Guhong Chen, Hongbo Wang, Huaren Liu, Minghui Zhu, Zhifei Qin, Linwei Li, Yilin Yue, Shiqiang Wang, Jiayan Li, Yihang Wu, Ziqiang Liu, Longze Chen, Run Luo, Liyang Fan, Jiaming Li, Lei Zhang, Kan Xu, Chengming Li, Hamid Alinejad-Rokny, Shiwen Ni, Yuan Lin, Min Yang

机构 * Shenzhen Key Laboratory for High Performance Data Mining, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, China(深圳高性能数据挖掘重点实验室,深圳先进技术研究院,中国科学院,中国) University of Chinese Academy of Sciences, China(中国科学院大学,中国) Dalian University of Technology, China(大连理工大学,中国) School of Biomedical Engineering, UNSW Sydney, Australia(生物医学工程学院,新南威尔士大学悉尼分校,澳大利亚) Shenzhen MSU-BIT University, China(深圳MSU-BIT大学,中国) Shenzhen University of Advanced Technology, China(深圳大学先进技术学院,中国)

专题命中 推理与问题求解 :large language model(title);language model(title);分类 cs.CL、cs.AI

Comments 71 pages, 75 figures, 53 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.07238 2025-09-10 cs.LG cs.AI 85%

Systematic Optimization of Open Source Large Language Models for Mathematical Reasoning

Pranav Pawar, Dhwaj Jain, Varun Gupta, Kaustav Dedhia, Dashrath Kale, Sudhir Dhekane

机构 * Dwarkadas J. Sanghvi College of Engineering(达沃卡斯J·桑格维工程学院)

专题命中 推理与问题求解 :large language model(title);language model(title);分类 cs.AI、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.03995 2025-09-05 cs.CL cs.AI 85%

RTQA : Recursive Thinking for Complex Temporal Knowledge Graph Question Answering with Large Language Models

Zhaoyan Gong, Juan Li, Zhiqiang Liu, Lei Liang, Huajun Chen, Wen Zhang

机构 * Zhejiang University(浙江大学) Ant Group(蚂蚁集团) ZJU-Ant Group Joint Lab of Knowledge Graph(浙江大学-蚂蚁集团知识图谱联合实验室)

专题命中 推理与问题求解 :large language model(title);language model(title);分类 cs.CL、cs.AI

Comments EMNLP 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.20279 2025-08-29 cs.CV cs.AI cs.CL 85%

How Multimodal LLMs Solve Image Tasks: A Lens on Visual Grounding, Task Reasoning, and Answer Decoding

Zhuoran Yu, Yong Jae Lee

机构 * University of Wisconsin–Madison(威斯康星大学麦迪逊分校)

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

Comments Accepted by COLM 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.16315 2025-05-26 cs.AI cs.CL 85%

Incentivizing Dual Process Thinking for Efficient Large Language Model Reasoning

Xiaoxue Cheng, Junyi Li, Zhenduo Zhang, Xinyu Tang, Wayne Xin Zhao, Xinyu Kong, Zhiqiang Zhang

机构 * Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学人工智能学院) Department of Computer Science, National University of Singapore(新加坡国立大学计算机科学系) Ant Group(蚂蚁集团)

专题命中 推理与问题求解 :large language model(title);language model(title);分类 cs.CL、cs.AI

Comments work in progress

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.01795 2025-04-17 cs.LG cs.CL q-bio.GN 85%

Knowledge-Driven Feature Selection and Engineering for Genotype Data with Large Language Models

Joseph Lee, Shu Yang, Jae Young Baik, Xiaoxi Liu, Zhen Tan, Dawei Li, Zixuan Wen, Bojian Hou, Duy Duong-Tran, Tianlong Chen, Li Shen

专题命中 推理与问题求解 :large language model(title);language model(title);分类 cs.CL、cs.LG

Comments accepted by AMIA-IS'25: AMIA Informatics Summit [Marco Ramoni Distinguished Paper Award for Translational Bioinformatics]

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.05078 2025-02-10 cs.AI cs.CL 85%

Adaptive Graph of Thoughts: Test-Time Adaptive Reasoning Unifying Chain, Tree, and Graph Structures

Tushar Pandey, Ara Ghukasyan, Oktay Goktas, Santosh Kumar Radha

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

详情

展开后加载摘要…

URL PDF HTML 收藏