arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~

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 12169 信号源:cs.CL, cs.AI, cs.LG

1. 其他LLM 12169 篇

2604.17351 2026-04-21 cs.AI 81%

SOCIA-EVO: Automated Simulator Construction via Dual-Anchored Bi-Level Optimization

SOCIA-EVO: 通过双锚点双层优化实现自动模拟器构建

Yuncheng Hua, Sion Weatherhead, Mehdi Jafari, Hao Xue, Flora D. Salim

机构 * School of Computer Science and Engineering, University of New South Wales(新南威尔士大学计算机科学与工程学院)

专题命中 其他LLM :LLM(summary_cn,abstract);分类 cs.AI

AI总结 本文提出SOCIA-EVO框架,通过双锚点双层优化解决长周期LLM代理中的上下文漂移和优化不稳定问题,生成统计上与观测数据一致的模拟器。

Comments This paper has been accepted to the ACL 2026 Main Conference

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.17056 2026-04-21 cs.IR cs.AI 81%

RLM-on-KG: Heuristics First, LLMs When Needed: Adaptive Retrieval Control over Mention Graphs for Scattered Evidence

RLM-on-KG:先用启发式方法,必要时再用大语言模型:针对散落证据的提及图自适应检索控制

Andrea Volpini, Elie Raad

机构 * WordLift

专题命中 其他LLM :LLM(summary_cn,abstract);分类 cs.AI

AI总结 本文研究LLM在知识图谱探索中的优势,提出RLM-on-KG系统,通过实体优先多跳探索提升检索效果,发现LLM控制在证据分散时表现更优,且通过探索轨迹验证了结构化数据质量。

Comments Preprint. 32 pages, 9 figures. Code and data available at the project repository

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.16911 2026-04-21 cs.AI 81%

Skilldex: A Package Manager and Registry for Agent Skill Packages with Hierarchical Scope-Based Distribution

Skilldex:一种基于层级作用域的代理技能包包管理器和注册表

Sampriti Saha, Pranav Hemanth

专题命中 其他LLM :LLM(abstract,abstract_cn);large language model(abstract);language model(abstract);分类 cs.AI

AI总结 Skilldex通过编译器式格式一致性评分和技能集抽象解决代理技能包的格式验证与上下文一致性问题,提供三级作用域系统和开源实现。

Comments 8 pages, 1 figure, 5 tables. IEEE conference format

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.17238 2026-04-21 cs.CL 81%

Personalizing Student-Agent Interactions Using Log-Contextualized Retrieval-Augmented Generation (RAG)

基于日志上下文的检索增强生成在个性化学生代理互动中的应用

Clayton Cohn, Surya Rayala, Caitlin Snyder, Joyce Fonteles, Shruti Jain, Naveeduddin Mohammed, Umesh Timalsina, Sarah K. Burriss, Ashwin T S, Namrata Srivastava, Menton Deweese, Angela Eeds, Gautam Biswas

机构 * 1Department of Computer Science, Vanderbilt University, Nashville, USA 2College of Engineering \& Science, University of Detroit Mercy, Detroit, USA 3The School for Science Math, Vanderbilt University, Nashville, USA

专题命中 其他LLM :LLM(abstract,abstract_cn);large language model(abstract);language model(abstract);分类 cs.CL

AI总结 本文提出日志上下文化检索增强生成(LC-RAG)方法,通过环境日志增强协作对话的检索能力,使协作同伴代理Copa能提供个性化指导,支持学生在C2STEM环境中的批判性思维和知识决策。

Comments Peer reviewed; appeared in the International Conference on Artificial Intelligence in Education (AIED25) Workshop on Epistemics and Decision-Making in AI-Supported Education

Journal ref https://sites.google.com/view/edm-aied-2025/home

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.24968 2026-04-16 econ.GN cs.AI cs.CY q-fin.EC stat.AP 81%

Strategic Response of News Publishers to Generative AI

新闻出版商对生成式人工智能的战略回应

Hangcheng Zhao, Ron Berman

机构 * Rutgers Business School(罗格斯商学院) The Wharton School of the University of Pennsylvania(宾夕法尼亚大学沃顿商学院)

专题命中 其他LLM :LLM(summary_cn,abstract);分类 cs.AI

AI总结 研究分析生成式人工智能对新闻出版商的影响,发现其通过封锁LLM访问、转向高质量内容及增加招聘需求等策略应对竞争威胁。

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.09087 2026-04-15 cs.AI 81%

The Stackelberg Speaker: Optimizing Persuasive Communication in Social Deduction Games

Stackelberg发言者:优化社会推断游戏中的说服性沟通

Zhang Zheng, Deheng Ye, Peilin Zhao, Hao Wang

机构 * The Hong Kong University of Science and Technology (Guangzhou)(香港科学与技术大学(广州)) Tencent(腾讯) Shanghai Jiao Tong University(上海交通大学)

专题命中 其他LLM :LLM(abstract,abstract_cn);large language model(abstract);language model(abstract);分类 cs.AI

AI总结 本文提出基于Stackelberg竞争的强化学习框架,用于优化社会推断游戏中说服性沟通,通过实验展示其在三种不同游戏中的优越性。

Comments Accepted by ACL 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.12440 2026-03-16 cs.DC cs.LG 81%

KernelFoundry: Hardware-aware evolutionary GPU kernel optimization

KernelFoundry: 带硬件意识的进化GPU内核优化

Nina Wiedemann, Quentin Leboutet, Michael Paulitsch, Diana Wofk, Benjamin Ummenhofer

机构 * Intel Corporation(英特尔公司)

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);prompting(abstract)

AI总结 KernelFoundry通过MAP-Elites搜索、元提示进化和模板参数优化,高效探索GPU内核设计空间,实现SYCL内核在KernelBench上的2.3倍加速。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.03317 2026-03-05 cs.CL 81%

Retcon -- a Prompt-Based Technique for Precise Control of LLMs in Conversations

Retcon -- 基于提示的LLM在对话中精确控制技术

David Kogan, Sam Nguyen, Masanori Suzuki, Feiyang Chen

机构 * Google(谷歌)

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);prompting(abstract)

AI总结 Retcon是一种基于提示的LLM对话控制技术,通过少量示例实现轮次级控制,优于零样本和传统少量样本提示方法。

Comments 5 pages, 2 figures, 3 appendixes with prompts and examples

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.22210 2026-03-03 cs.SE cs.AI 81%

LSPRAG: LSP-Guided RAG for Language-Agnostic Real-Time Unit Test Generation

LSPRAG: 语言无关的实时单元测试生成中的LSP引导RAG

Gwihwan Go, Quan Zhang, Chijin Zhou, Zhao Wei, Yu Jiang

机构 * Tsinghua University(清华大学) East China Normal University(华东师范大学) Tencent(腾讯)

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);prompting(abstract)

AI总结 LSPRAG通过利用语言服务器协议实现实时语言无关单元测试生成,显著提高了测试覆盖率。

Comments 13pages, 6 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.14270 2026-02-17 cs.CY cs.AI cs.HC 81%

A Rational Analysis of the Effects of Sycophantic AI

对趋炎附势AI影响的理性分析

Rafael M. Batista, Thomas L. Griffiths

机构 * School of Public and International Affairs, Princeton University(公共与国际事务学院,普林斯顿大学) Princeton University(普林斯顿大学) Department of Psychology, Princeton University(心理学系,普林斯顿大学)

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);prompting(abstract)

AI总结 本文研究了趋炎附势AI对信念的影响,通过实验发现无偏采样能显著提高发现率,而顺从反馈会扭曲现实,制造虚假确定性。

Comments 7 pages, 1 figure

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.09504 2026-02-11 q-fin.GN cs.AI 81%

Seeing the Goal, Missing the Truth: Human Accountability for AI Bias

看见目标,却错过真相:人类对AI偏见的责任

Sean Cao, Wei Jiang, Hui Xu

机构 * University of Maryland(马里兰大学) Robert H. Smith School of Business, University of Maryland, College Park(马里兰大学罗伯特·H·史密斯商学院) Emory University(埃默里大学) Lancaster University(兰卡斯特大学)

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);prompting(abstract)

AI总结 本研究发现,人类设定的目标会影响LLM的行为,导致生成有偏见的指标,但这种偏见并非算法问题,而是源于人类在设计中确保AI测量的统计有效性

Comments 17 pages, 3 figures, 5 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.04889 2026-01-09 cs.CL 81%

Faithful Summarisation under Disagreement via Belief-Level Aggregation

通过信念层面聚合实现分歧下的忠实总结

Favour Yahdii Aghaebe, Tanefa Apekey, Elizabeth Williams, Nafise Sadat Moosavi

机构 * University of Sheffield, UK(谢菲尔德大学)

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);prompting(abstract)

AI总结 本文提出一种通过信念层面聚合实现分歧意识的总结方法,结合结构化信念集和大语言模型生成,提升观点密集场景下的摘要忠实性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.11921 2025-12-18 cs.CL cs.CY cs.HC 81%

Designing LLMs for cultural sensitivity: Evidence from English-Japanese translation

为文化敏感性设计LLMs:来自英语-日语翻译的证据

Helene Tenzer, Oumnia Abidi, Stefan Feuerriegel

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);prompting(abstract)

AI总结 本文通过分析英语-日语翻译中不同提示策略对文化敏感性的影响,提出通过定制提示提升多语言环境中LLM文化适应性的方法。

Comments Posted premature without permission of all authors

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.03929 2025-12-09 cs.AI 81%

MOTIF: Multi-strategy Optimization via Turn-based Interactive Framework

MOTIF: 通过回合式交互框架进行多策略优化

Nguyen Viet Tuan Kiet, Dao Van Tung, Tran Cong Dao, Huynh Thi Thanh Binh

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);prompting(abstract)

AI总结 MOTIF通过回合式交互框架实现多策略优化,提升求解器设计的自动化水平。

Comments Accepted as an oral presentation at AAAI 2026. Code available at: https://github.com/HaiAu2501/MOTIF

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.02221 2025-12-08 cs.CL 81%

GDC Cohort Copilot: An AI Copilot for Curating Cohorts from the Genomic Data Commons

GDC队列助手:一种用于从基因组数据共同体中整理队列的AI助手

Steven Song, Anirudh Subramanyam, Zhenyu Zhang, Aarti Venkat, Robert L. Grossman

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);prompting(abstract)

AI总结 GDC队列助手通过自然语言处理技术帮助用户从基因组数据共同体中高效整理队列,采用本地开源模型优于GPT-4o。

Comments 12 pages, 1 figure, 7 tables. v2 updated to reflect migration to HF Spaces

Journal ref Bioinformatics Advances 5(1), vbaf295 (2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.01196 2025-11-19 cs.RO cs.AI cs.CV 81%

OG-VLA: Orthographic Image Generation for 3D-Aware Vision-Language Action Model

Ishika Singh, Ankit Goyal, Stan Birchfield, Dieter Fox, Animesh Garg, Valts Blukis

机构 * University of Southern California(美国南加州大学) NVIDIA(英伟达)

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);foundation model(abstract)

Comments 13 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.20127 2025-11-04 cs.AI 81%

Agentic AI Process Observability: Discovering Behavioral Variability

Fabiana Fournier, Lior Limonad, Yuval David

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);prompting(abstract)

Comments 12 pages, 7 figures

Journal ref PMAI 25 (CEUR proceedings); Vol 4087; 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.06594 2025-10-13 cs.CL 81%

Do Internal Layers of LLMs Reveal Patterns for Jailbreak Detection?

Sri Durga Sai Sowmya Kadali, Evangelos E. Papalexakis

机构 * Dept. of Computer Science and Engineering University of California, Riverside(计算机科学与工程系加州大学河滨分校)

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);prompting(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.15283 2025-08-22 cs.IR cs.CL 81%

Adversarial Attacks against Neural Ranking Models via In-Context Learning

Amin Bigdeli, Negar Arabzadeh, Ebrahim Bagheri, Charles L. A. Clarke

机构 * University of Waterloo(多伦多大学) University of California, Berkeley(加州大学伯克利分校) University of Toronto(多伦多大学)

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);prompting(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.22742 2025-07-01 cs.SE cs.AI 81%

RAILS: Retrieval-Augmented Intelligence for Learning Software Development

Wali Mohammad Abdullah, Md. Morshedul Islam, Devraj Parmar, Happy Hasmukhbhai Patel, Sindhuja Prabhakaran, Baidya Saha

机构 * Mathematics \& Information Technology Concordia University of Edmonton Edmonton, Alberta, Canada

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);prompting(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.02550 2025-06-12 cs.CV cs.AI 81%

Technical Report for Ego4D Long-Term Action Anticipation Challenge 2025

Qiaohui Chu, Haoyu Zhang, Yisen Feng, Meng Liu, Weili Guan, Yaowei Wang, Liqiang Nie

机构 * Harbin Institute of Technology (Shenzhen)(哈尔滨工业大学(深圳)) Pengcheng Laboratory(鹏城实验室) Shandong Jianzhu University(山东建筑大学)

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);foundation model(abstract)

Comments The champion solution for the Ego4D Long-Term Action Anticipation Challenge at the CVPR EgoVis Workshop 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.00829 2025-05-21 cs.LG cs.SI 81%

When Do LLMs Help With Node Classification? A Comprehensive Analysis

Xixi Wu, Yifei Shen, Fangzhou Ge, Caihua Shan, Yizhu Jiao, Xiangguo Sun, Hong Cheng

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);foundation model(abstract)

Comments Accepted by ICML 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2404.03657 2025-04-01 cs.CV cs.AI 81%

OW-VISCapTor: Abstractors for Open-World Video Instance Segmentation and Captioning

Anwesa Choudhuri, Girish Chowdhary, Alexander G. Schwing

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);foundation model(abstract)

Comments Project page: https://anwesachoudhuri.github.io/OpenWorldVISCap/

Journal ref NeurIPS 2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2408.16629 2025-03-31 cs.CY cs.AI cs.SI 81%

LLMs generate structurally realistic social networks but overestimate political homophily

Serina Chang, Alicja Chaszczewicz, Emma Wang, Maya Josifovska, Emma Pierson, Jure Leskovec

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);prompting(abstract)

Comments Accepted to International AAAI Conference on Web and Social Media 2025 (ICWSM'25)

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.02368 2025-02-05 cs.SE cs.AI 81%

Evaluating the Effectiveness of LLMs in Fixing Maintainability Issues in Real-World Projects

Henrique Nunes, Eduardo Figueiredo, Larissa Rocha, Sarah Nadi, Fischer Ferreira, Geanderson Esteves

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);prompting(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2404.03502 2025-01-22 cs.AI cs.CY 81%

AI and the Problem of Knowledge Collapse

Andrew J. Peterson

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);prompting(abstract)

Comments 37 pages, 9 figures

Journal ref AI and Society, 2025-01-19

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.19135 2024-10-28 cs.AI cs.PL 81%

PDL: A Declarative Prompt Programming Language

Mandana Vaziri, Louis Mandel, Claudio Spiess, Martin Hirzel

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);prompting(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.09063 2024-10-15 cs.CL 81%

Investigating the Impact of Text Summarization on Topic Modeling

Trishia Khandelwal

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);prompting(abstract)

Comments 7 pages, 2 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2409.07368 2024-09-26 cs.CR cs.AI 81%

Demo: SGCode: A Flexible Prompt-Optimizing System for Secure Generation of Code

Khiem Ton, Nhi Nguyen, Mahmoud Nazzal, Abdallah Khreishah, Cristian Borcea, NhatHai Phan, Ruoming Jin, Issa Khalil, Yelong Shen

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);prompting(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2408.12844 2024-08-26 cs.HC cs.AI 81%

Predicting Affective States from Screen Text Sentiment

Songyan Teng, Tianyi Zhang, Simon D'Alfonso, Vassilis Kostakos

专题命中 其他LLM :LLM(abstract);large language model(abstract);language model(abstract);prompting(abstract)

Comments 7 pages

详情

展开后加载摘要…

URL PDF HTML 收藏