语言大模型 / LLM - arXivDaily 专题

2504.15801 2026-04-16 cs.CL cs.AI cs.CY 91%

A closer look at how large language models trust humans: patterns and biases

深入探讨大型语言模型如何信任人类：模式与偏见

Valeria Lerman, Yaniv Dover

机构 * The Hebrew University Business School（希伯来大学商学院）； The Federmann Center for the study of Rationality（费德曼理性研究中心）； The Hebrew University of Jerusalem（特拉维夫希伯来大学）

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

AI总结研究探讨大型语言模型在决策场景中对人类的信任发展，分析信任维度和人口变量的影响，发现模型信任与人类信任相似但存在偏差。

Journal ref Proceedings of the Royal Society A 482 2335 20251113 (2026)

2603.10098 2026-03-12 cs.GT cs.AI cs.LG 91%

Code-Space Response Oracles: Generating Interpretable Multi-Agent Policies with Large Language Models

代码空间响应预言机：利用大语言模型生成可解释的多智能体策略

Daniel Hennes, Zun Li, John Schultz, Marc Lanctot

机构 * Google（谷歌）； DeepMind（深度思维）

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

AI总结本文提出代码空间响应预言机，利用大语言模型生成可解释的多智能体策略，通过代码生成任务提升策略的可解释性和复杂策略发现能力。

Comments Accepted as an Extended Abstract at the Twenty-Fifth International Conference on Autonomous Agents and Multiagent Systems (AAMAS)

2509.00482 2025-10-14 cs.CL cs.AI cs.HC 91%

Talk Less, Call Right: Enhancing Role-Play LLM Agents with Automatic Prompt Optimization and Role Prompting

Saksorn Ruangtanusak, Pittawat Taveekitworachai, Kunat Pipatanakul

机构 * SCBX R&D（SCBX研发部）； SCB 10X R&D（SCB 10X研发部）

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

Comments EMNLP 2025 Wordplay Workshop (Spotlight)

2506.21602 2025-08-26 cs.CL cs.AI 91%

BiMark: Unbiased Multilayer Watermarking for Large Language Models

Xiaoyan Feng, He Zhang, Yanjun Zhang, Leo Yu Zhang, Shirui Pan

机构 * Griffith University, Brisbane（格里菲斯大学）； RMIT University, Melbourne（皇家墨尔本理工大学）； University of Technology Sydney, Sydney（悉尼大学）

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

Comments This paper is accepted by International Conference on Machine Learning (ICML) 2025

2506.16575 2025-06-23 cs.AI cs.CL 91%

Advancing Harmful Content Detection in Organizational Research: Integrating Large Language Models with Elo Rating System

Mustafa Akben, Aaron Satko

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

Comments Submitted for HICSS 2025 (Hawaii International Conference on System Sciences); under review

2505.19838 2025-05-27 cs.CL cs.AI 91%

FoodTaxo: Generating Food Taxonomies with Large Language Models

Pascal Wullschleger, Majid Zarharan, Donnacha Daly, Marc Pouly, Jennifer Foster

机构 * ADAPT Centre, School of Computing, Dublin City University（ADAPT中心、计算学院、都柏林城市大学）； Lucerne School of Computer Science and Information Technology (HSLU)（卢塞恩计算机科学与信息科技学院（HSLU））

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

Comments To be published in ACL 2025 Industry Track. Paper website: https://foodtaxo.github.io/

2505.02659 2025-05-07 cs.LG cs.AI 91%

A Note on Statistically Accurate Tabular Data Generation Using Large Language Models

Andrey Sidorenko

机构 * MOSTLY AI

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

2307.00184 2025-03-13 cs.CL cs.AI cs.CY cs.HC 91%

Personality Traits in Large Language Models

Greg Serapio-García, Mustafa Safdari, Clément Crepy, Luning Sun, Stephen Fitz, Peter Romero, Marwa Abdulhai, Aleksandra Faust, Maja Matarić

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

2411.11731 2024-11-19 cs.CL cs.AI 91%

Moral Persuasion in Large Language Models: Evaluating Susceptibility and Ethical Alignment

Allison Huang, Yulu Niki Pi, Carlos Mougan

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

2410.18906 2024-11-12 cs.CL cs.AI cs.CY 91%

PRISM: A Methodology for Auditing Biases in Large Language Models

Leif Azzopardi, Yashar Moshfeghi

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

2409.04056 2024-09-09 cs.AI cs.CL cs.IR 91%

Refining Wikidata Taxonomy using Large Language Models

Yiwen Peng, Thomas Bonald, Mehwish Alam

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

Comments ACM International Conference on Information and Knowledge Management, Oct 2024, Boise, Idaho, United States

2407.11190 2024-07-17 cs.CY cs.AI cs.CL 91%

In Silico Sociology: Forecasting COVID-19 Polarization with Large Language Models

Austin C. Kozlowski, Hyunku Kwon, James A. Evans

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

2406.07573 2024-06-13 cs.AI cs.LG 91%

Investigating the Potential of Using Large Language Models for Scheduling

Deddy Jobson, Yilin Li

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

2406.03299 2024-06-06 cs.AI cs.CL 91%

The Good, the Bad, and the Hulk-like GPT: Analyzing Emotional Decisions of Large Language Models in Cooperation and Bargaining Games

Mikhail Mozikov, Nikita Severin, Valeria Bodishtianu, Maria Glushanina, Mikhail Baklashkin, Andrey V. Savchenko, Ilya Makarov

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

2401.03729 2024-04-03 cs.CL cs.AI 91%

The Butterfly Effect of Altering Prompts: How Small Changes and Jailbreaks Affect Large Language Model Performance

Abel Salinas, Fred Morstatter

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

2309.14517 2024-01-18 cs.HC cs.AI cs.CL cs.CR cs.SI 91%

Watch Your Language: Investigating Content Moderation with Large Language Models

Deepak Kumar, Yousef AbuHashem, Zakir Durumeric

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

2312.17353 2024-01-03 eess.SY cs.AI cs.LG cs.SY 91%

Towards Auto-Modeling of Formal Verification for NextG Protocols: A Multimodal cross- and self-attention Large Language Model Approach

Jingda Yang, Ying Wang

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

2310.20320 2023-11-01 cs.CL cs.AI 91%

Theory of Mind in Large Language Models: Examining Performance of 11 State-of-the-Art models vs. Children Aged 7-10 on Advanced Tests

Max J. van Duijn, Bram M. A. van Dijk, Tom Kouwenhoven, Werner de Valk, Marco R. Spruit, Peter van der Putten

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

Comments 14 pages, 4 figures, Forthcoming in Proceedings of the 27th Conference on Computational Natural Language Learning (CoNLL)

2304.11060 2023-10-19 cs.CL cs.AI 91%

SkillGPT: a RESTful API service for skill extraction and standardization using a Large Language Model

Nan Li, Bo Kang, Tijl De Bie

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

2305.11473 2023-08-08 cs.HC cs.AI cs.CL 91%

Graphologue: Exploring Large Language Model Responses with Interactive Diagrams

Peiling Jiang, Jude Rayan, Steven P. Dow, Haijun Xia

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

2210.12353 2023-03-20 cs.CL cs.LG 91%

Leveraging Large Language Models for Multiple Choice Question Answering

Joshua Robinson, Christopher Michael Rytting, David Wingate

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

Comments Accepted for ICLR 2023

2608.16048 2026-08-18 quant-ph cs.NA math.NA physics.app-ph 新提交 90%

zenDot: An LLM-integrated quantum TCAD platform for semiconductor quantum-device design and optimization automation

zenDot：一款集成大语言模型（LLM）的量子TCAD平台，用于半导体量子器件设计与优化自动化

Zeheng Wang, Yan Liu, Yue Hao, Genquan Han

专题命中其他LLM ：LLM(title,title_cn)；language model(abstract)

AI总结 zenDot是集成LLM的量子TCAD平台，可连接器件物理与LLM驱动的设计探索，在Si/SiO₂双量子点验证中完成18次设计迭代，将最差门保真度降低近30倍。

2603.03919 2026-08-03 cs.CR 版本更新 90%

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG

当安全成为漏洞：利用LLM对齐同质性进行可转移阻塞在RAG中

Junchen Li, Liang Xu, Qizhi Chen, Rongzheng Wang, Chao Qi, Shihao He, Di Liang, Haibo Shi, Shuang Liang

专题命中其他LLM ：LLM(title,title_cn)；large language model(abstract)；language model(abstract)

AI总结 TabooRAG通过利用LLM对齐同质性，在黑盒环境下实现跨模型的可转移阻塞攻击，针对安全对齐机制提出新型攻击框架。

Comments Expanded the scale of the experimental evaluation

2512.05929 2026-07-01 cs.CY 版本更新 90%

LLM Harms: A Taxonomy and Discussion

LLM 危害：分类与讨论

Kevin Chen, Saleh Afroogh, Abhejay Murali, David Atkinson, Amit Dhurandhar, Junfeng Jiao

专题命中其他LLM ：LLM(title,title_cn)；large language model(abstract)；language model(abstract)

AI总结本研究针对大型语言模型（LLM）在人工智能领域中的危害进行分类，提出开发前、直接输出、误用与恶意应用以及下游应用五类危害，并讨论缓解策略与动态审计系统。

2606.17612 2026-06-17 cs.SE 新提交 90%

PracRepair: LLM-Empowered Automated Program Repair Inspired by Human-Like Debugging Practices

PracRepair: 受人类调试实践启发的大语言模型赋能自动化程序修复

Yu Cheng, Zhongxin Liu, Zhenchang Xing, Chao Ni, Qing Huang, Xiaoxue Ren

专题命中其他LLM ：LLM(title,summary_cn)；large language model(abstract)；language model(abstract)；foundation model(abstract)

AI总结提出PracRepair框架，通过构建按需静态-动态上下文、进行问题驱动的故障诊断并迭代细化补丁，利用动态信息提升LLM在程序修复中的效果，在Defects4J和真实世界漏洞上取得最优性能。

2605.16308 2026-05-19 cs.GR 90%

Conformal Geometric Algebra as a Symbolic Interface for LLM-Driven 3D Scene Editing

共形几何代数作为LLM驱动3D场景编辑的符号接口

Manos Kamarianakis, Pandelis Sofianos, George Papagiannakis

专题命中其他LLM ：LLM(title,title_cn)；prompting(abstract)

AI总结研究探讨了共形几何代数在LLM驱动3D场景编辑中的可靠性与效率，发现其在保持操作顺序和降低token消耗方面优于传统方法。

Comments 34 pages, 15 figures, 28 tables

2605.10133 2026-05-12 cs.CR cs.SE 90%

Usability as a Weapon: Attacking the Safety of LLM-Based Code Generation via Usability Requirements

可用性作为武器：通过可用性需求攻击基于LLM的代码生成的安全性

Yue Li, Xiao Li, Hao Wu, Yue Zhang, Yechao Zhang, Yating Liu, Fengyuan Xu, Sheng Zhong

专题命中其他LLM ：LLM(title,title_cn)；large language model(abstract)；language model(abstract)

AI总结研究通过可用性需求攻击LLM生成代码的安全性，提出U-SPLOIT框架，利用可用性压力导致安全约束被忽略，成功率达98.1%。

2604.17716 2026-04-21 cs.CL cs.AI cs.LG 90%

Concurrent Criterion Validation of a Validity Screen for LLM Confidence Signals via Selective Prediction

通过选择性预测验证LLM置信信号有效性的同时标准验证

Jon-Paul Cacioli

机构 * Independent Researcher（独立研究者）

专题命中其他LLM ：LLM(title,title_cn)；分类 cs.CL、cs.AI、cs.LG

AI总结本文通过评估20个前沿LLM在六个认知领域的524项任务表现，验证了LLM置信信号分类对选择性预测性能的预测能力，发现有效模型在AUROC上显著优于无效模型。

Comments 11 pages, 4 figures, 2 tables. Companion to arXiv:2604.15702

2602.12256 2026-02-13 cs.SE 90%

Automated Test Suite Enhancement Using Large Language Models with Few-shot Prompting

利用少量示例提示的大语言模型自动测试套件增强

Alex Chudic, Gül Çalıklı

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

AI总结本文研究利用少量示例提示生成高质量单元测试，通过评估不同测试来源对测试质量的影响，提升混合人类-人工智能代码库的测试套件质量。

Comments 13 pages, 3 figures, accepted to ICPC 2026 (34th International Conference on Program Comprehension)

2509.11353 2025-09-16 cs.IR 90%

Do Large Language Models Favor Recent Content? A Study on Recency Bias in LLM-Based Reranking

Hanpei Fang, Sijie Tao, Nuo Chen, Kai-Xin Chang, Tetsuya Sakai

专题命中其他LLM ：large language model(title,abstract)；language model(title,abstract)；LLM(title)

1. 其他LLM 12169 篇

A closer look at how large language models trust humans: patterns and biases

Code-Space Response Oracles: Generating Interpretable Multi-Agent Policies with Large Language Models

Talk Less, Call Right: Enhancing Role-Play LLM Agents with Automatic Prompt Optimization and Role Prompting

BiMark: Unbiased Multilayer Watermarking for Large Language Models

Advancing Harmful Content Detection in Organizational Research: Integrating Large Language Models with Elo Rating System

FoodTaxo: Generating Food Taxonomies with Large Language Models

A Note on Statistically Accurate Tabular Data Generation Using Large Language Models

Personality Traits in Large Language Models

Moral Persuasion in Large Language Models: Evaluating Susceptibility and Ethical Alignment

PRISM: A Methodology for Auditing Biases in Large Language Models

Refining Wikidata Taxonomy using Large Language Models

In Silico Sociology: Forecasting COVID-19 Polarization with Large Language Models

Investigating the Potential of Using Large Language Models for Scheduling

The Good, the Bad, and the Hulk-like GPT: Analyzing Emotional Decisions of Large Language Models in Cooperation and Bargaining Games

The Butterfly Effect of Altering Prompts: How Small Changes and Jailbreaks Affect Large Language Model Performance

Watch Your Language: Investigating Content Moderation with Large Language Models

Towards Auto-Modeling of Formal Verification for NextG Protocols: A Multimodal cross- and self-attention Large Language Model Approach

Theory of Mind in Large Language Models: Examining Performance of 11 State-of-the-Art models vs. Children Aged 7-10 on Advanced Tests

SkillGPT: a RESTful API service for skill extraction and standardization using a Large Language Model

Graphologue: Exploring Large Language Model Responses with Interactive Diagrams

Leveraging Large Language Models for Multiple Choice Question Answering

zenDot: An LLM-integrated quantum TCAD platform for semiconductor quantum-device design and optimization automation

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG

LLM Harms: A Taxonomy and Discussion

PracRepair: LLM-Empowered Automated Program Repair Inspired by Human-Like Debugging Practices

Conformal Geometric Algebra as a Symbolic Interface for LLM-Driven 3D Scene Editing

Usability as a Weapon: Attacking the Safety of LLM-Based Code Generation via Usability Requirements

Concurrent Criterion Validation of a Validity Screen for LLM Confidence Signals via Selective Prediction

Automated Test Suite Enhancement Using Large Language Models with Few-shot Prompting

Do Large Language Models Favor Recent Content? A Study on Recency Bias in LLM-Based Reranking