语言大模型 / LLM - arXivDaily 专题

2308.10443 2023-08-22 cs.AI cs.CL cs.CY 90%

Using Large Language Models for Cybersecurity Capture-The-Flag Challenges and Certification Questions

Wesley Tann, Yuancheng Liu, Jun Heng Sim, Choon Meng Seah, Ee-Chien Chang

专题命中领域大模型：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.AI

2308.06111 2023-08-15 cs.CL cs.AI 90%

Improving Zero-Shot Text Matching for Financial Auditing with Large Language Models

Lars Hillebrand, Armin Berger, Tobias Deußer, Tim Dilmaghani, Mohamed Khaled, Bernd Kliem, Rüdiger Loitz, Maren Pielka, David Leonhard, Christian Bauckhage, Rafet Sifa

专题命中领域大模型：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.AI

Comments Accepted at DocEng 2023, 4 pages, 1 figure, 2 tables

2303.16756 2023-08-08 cs.CL cs.AI 90%

Large Language Models for Healthcare Data Augmentation: An Example on Patient-Trial Matching

Jiayi Yuan, Ruixiang Tang, Xiaoqian Jiang, Xia Hu

专题命中领域大模型：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.AI

2308.02432 2023-08-07 cs.CY cs.AI cs.CL 90%

Performance of Large Language Models in a Computer Science Degree Program

Tim Krüger, Michael Gref

专题命中领域大模型：large language model(title,abstract)；language model(title,abstract)；prompting(abstract)；分类 cs.CL、cs.AI

Comments Submitted to AI4AI Workshop 2023

2304.05368 2023-08-01 cs.CL cs.AI 90%

Are Large Language Models Ready for Healthcare? A Comparative Study on Clinical Language Understanding

Yuqing Wang, Yun Zhao, Linda Petzold

专题命中领域大模型：large language model(title,abstract)；language model(title,abstract)；prompting(abstract)；分类 cs.CL、cs.AI

Comments 24 pages

Journal ref Machine Learning for Healthcare Conference, PMLR, 2023

2307.02792 2023-07-10 cs.CY cs.AI cs.CL 90%

What Should Data Science Education Do with Large Language Models?

Xinming Tu, James Zou, Weijie J. Su, Linjun Zhang

专题命中领域大模型：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.AI

2307.01128 2023-07-04 cs.CL cs.AI 90%

Iterative Zero-Shot LLM Prompting for Knowledge Graph Construction

Salvatore Carta, Alessandro Giuliani, Leonardo Piano, Alessandro Sebastian Podda, Livio Pompianu, Sandro Gabriele Tiddia

专题命中领域大模型：prompting(title,abstract)；LLM(title)；large language model(abstract)；language model(abstract)

2206.12839 2023-06-21 cs.LG cs.AI cs.PL cs.SE 90%

Repository-Level Prompt Generation for Large Language Models of Code

Disha Shrivastava, Hugo Larochelle, Daniel Tarlow

专题命中领域大模型：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.AI、cs.LG

Comments ICML 2023 (Camera-Ready version)

Journal ref ICML, 2023

2306.09928 2023-06-19 cs.CY cs.AI cs.HC cs.LG 90%

Friend or Foe? Exploring the Implications of Large Language Models on the Science System

Benedikt Fecher, Marcel Hebing, Melissa Laufer, Jörg Pohle, Fabian Sofsky

专题命中领域大模型：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.AI、cs.LG

Comments 31 pages, 2 figures

2306.05715 2023-06-12 cs.CY cs.AI cs.CL cs.HC cs.SE 90%

Exploring the Responses of Large Language Models to Beginner Programmers' Help Requests

Arto Hellas, Juho Leinonen, Sami Sarsa, Charles Koutcheme, Lilja Kujanpää, Juha Sorva

专题命中领域大模型：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.AI

Comments 13 pages, 1 figure. To be published in Proceedings of the 2023 ACM Conference on International Computing Education Research V.1 (ICER '23 V1)

2306.01779 2023-06-06 cs.CL cs.AI 90%

Conceptual Design Generation Using Large Language Models

Kevin Ma, Daniele Grandi, Christopher McComb, Kosa Goucher-Lambert

专题命中领域大模型：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.AI

Comments Proceedings of the ASME 2023 International Design Engineering Technical Conferences and Computers and Information in Engineering Conferences

2302.12832 2023-06-05 cs.CL cs.AI 90%

Fluid Transformers and Creative Analogies: Exploring Large Language Models' Capacity for Augmenting Cross-Domain Analogical Creativity

Zijian Ding, Arvind Srinivasan, Stephen MacNeil, Joel Chan

专题命中领域大模型：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.AI

2302.12813 2023-03-10 cs.CL cs.AI 90%

Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback

Baolin Peng, Michel Galley, Pengcheng He, Hao Cheng, Yujia Xie, Yu Hu, Qiuyuan Huang, Lars Liden, Zhou Yu, Weizhu Chen, Jianfeng Gao

专题命中领域大模型：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.AI

Comments 15 pages

2210.07313 2023-02-14 cs.CL cs.LG 90%

Bootstrapping Multilingual Semantic Parsers using Large Language Models

Abhijeet Awasthi, Nitish Gupta, Bidisha Samanta, Shachi Dave, Sunita Sarawagi, Partha Talukdar

专题命中领域大模型：large language model(title,abstract)；language model(title,abstract)；prompting(abstract)；分类 cs.CL、cs.LG

Comments EACL-23

2301.10095 2023-01-31 cs.CL cs.AI cs.CY 90%

Large Language Models as Fiduciaries: A Case Study Toward Robustly Communicating With Artificial Intelligence Through Legal Standards

John J. Nay

专题命中领域大模型：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.AI

Comments arXiv admin note: substantial text overlap with arXiv:2209.13020

2212.01326 2022-12-12 cs.CL cs.AI 90%

Legal Prompting: Teaching a Language Model to Think Like a Lawyer

Fangyi Yu, Lee Quartey, Frank Schilder

专题命中领域大模型：language model(title,abstract)；prompting(title,abstract)；large language model(abstract)；分类 cs.CL、cs.AI

Comments 12 pages, 6 figures, 4 tables. Accepted by NLLP 2022 (EMNLP workshop)

2606.20868 2026-06-23 cs.CR cs.AI 新提交 90%

Can LLMs Reason About Brand Ownership? An Empirical Study of Domain Attribution Intelligence

LLM能否推理品牌所有权？领域归属智能的实证研究

Fathima Mashood, Mohamed Nabeel

机构 * Google（谷歌）； Microsoft（微软）

专题命中领域大模型：LLM(title_cn,summary_cn)；large language model(abstract)；language model(abstract)；分类 cs.AI

AI总结针对品牌域名归属歧义问题，首次系统评估LLM在域名枚举、开放归属和二元分类三项任务中的品牌智能表现，发现模型依赖外部工具（如WHOIS）才能实现高精度所有权验证。

Comments llm, brand intelligence, whois, search, squatting domains, brand domains

2410.21868 2024-12-23 cs.CL 90%

Improving In-Context Learning with Small Language Model Ensembles

M. Mehdi Mojarradi, Lingyi Yang, Robert McCraith, Adam Mahdi

专题命中领域大模型：language model(title,abstract)；small language model(title,abstract)；large language model(abstract)；分类 cs.CL

Comments Presented at NeurIPS 2024 Workshop on Adaptive Foundation Models

2310.07225 2024-10-14 cs.CL 90%

Do Large Language Models have Shared Weaknesses in Medical Question Answering?

Andrew M. Bean, Karolina Korgul, Felix Krones, Robert McCraith, Adam Mahdi

专题命中领域大模型：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL

Comments 8 pages, 10 figures. To appear in NeurIPS 2024 Advancements in Medical Foundation Models Workshop

2406.12033 2024-06-21 cs.CL 90%

Unveiling and Mitigating Bias in Mental Health Analysis with Large Language Models

Yuqing Wang, Yun Zhao, Sara Alessandra Keller, Anne de Hond, Marieke M. van Buchem, Malvika Pillai, Tina Hernandez-Boussard

专题命中领域大模型：large language model(title,abstract)；language model(title,abstract)；prompting(abstract)；分类 cs.CL

Comments In submission; Data and code are available at: https://github.com/EternityYW/BiasEval-LLM-MentalHealth

2605.30384 2026-08-14 astro-ph.IM astro-ph.GA 版本更新 89%

The EPS Research Astro-RAG Platform: A Unified Open-Science Infrastructure for Cross-Epoch Astrophysical Kinematic Analysis, LLM-Assisted Research Workflows, and Educational Outreach

EPS Research Astro-RAG平台：用于跨纪元天体物理运动学分析、LLM辅助研究工作流程和教育推广的统一开放科学基础设施

David C. Flynn

专题命中领域大模型：LLM(title,title_cn)

AI总结提出一个开放科学平台，整合四个跨纪元天体物理语料库、120个可执行Jupyter笔记本示例，并利用LLM辅助检索增强生成（RAG）研究工作流程，通过ω运动学校正揭示从z=0到z~5的角速度符号反转。

Comments 5 pages, no figures, no tables. Platform release: four open astrophysical corpora (772 objects, z=0 to z~6), 120 verified Jupyter notebooks, QuickStart reproducibility pathway, and High-School Exploration Track. Zenodo DOIs: 10.5281/zenodo.19563417, 10.5281/zenodo.20320362, 10.5281/zenodo.19907765, 10.5281/zenodo.20369285. GitHub: github.com/eps-research/rag-corpus-series

2608.08589 2026-08-11 cs.CV 新提交 89%

RobustDefect-LLM: Explainable and Robustness-Aware Industrial Surface Defect Classification with Decision Support and AI-Assisted Reporting

RobustDefect-LLM：具备决策支持与AI辅助报告的可解释、鲁棒性感知型工业表面缺陷分类方法

Nazlıcan Düşünmez, Halûk Gümüşkaya

专题命中领域大模型：LLM(title,title_cn)

AI总结本文提出RobustDefect-LLM框架，在NEU-DET数据集上评估四种CNN，选MobileNetV3-Large实现高准确率，结合Grad-CAM与置信度路由，集成AI辅助报告，验证了工业缺陷检测工作流的可行性。

Comments 27 pages, 11 figures, 16 tables, preprint manuscript, the source code is publicly available

2608.08583 2026-08-11 cs.IR 新提交 89%

Structure-Preserving Projection for Mitigating Modality Bias in LLM-Based Sequential Recommendation

面向基于大语言模型（LLM）的序列推荐中缓解模态偏差的结构保留投影

Tzu-Wei Chiu, Song-Duo Ma, Hsin-Yu Lin, Pu-Jen Cheng

专题命中领域大模型：LLM(title,title_cn)

AI总结本文针对基于LLM的序列推荐中投影引入的模态偏差问题，提出结构保留投影方法，通过专用损失维持协同嵌入关系几何，经实验验证可提升推荐性能。

Comments Accepted at RecSys 2026

2607.27002 2026-07-30 cs.IR 新提交 89%

IMFuse: Instance-Aware Multi-Layer Fusion for LLM-Enhanced Sequential Recommendation

IMFuse：面向大语言模型增强型序列推荐的实例感知多层融合方法

Yuheng Zheng, Yu Cui, Bin Wu, Jian Zhang, Ye Feng, Can Wang, Jiawei Chen

专题命中领域大模型：LLM(title,summary_cn)；large language model(abstract)；language model(abstract)

AI总结针对LLM增强型序列推荐中仅用最后一层表示的缺陷，提出IMFuse方法，通过实例感知多层融合策略生成个性化语义表示，在四个数据集上平均相对提升6.72%且开销有限。

Comments 12 pages, 5 figures, and 9 tables. Yuheng Zheng and Yu Cui contributed equally. Jiawei Chen is the corresponding author

2603.09181 2026-07-29 cs.DB 版本更新 89%

Evaluating the Practical Effectiveness of LLM-Driven Index Tuning on Microsoft SQL Server

评估基于大语言模型的索引优化的实用性效果：微软数据库优化顾问

Xiaoying Wang, Wentao Wu, Vivek Narasayya, Surajit Chaudhuri

专题命中领域大模型：LLM(title,summary_cn)；large language model(abstract)；language model(abstract)

AI总结本文通过工业基准和真实企业工作负载评估LLM驱动的索引优化效果，对比微软数据库优化顾问（DTA），发现LLM在部分情况下能提供更优执行时间配置，但生产环境中应用仍面临性能波动、集成影响和验证成本等挑战。

2601.06703 2026-07-29 cs.CY 89%

Mapping and Comparing Climate Equity Policy Practices Using RAG LLM-Based Semantic Analysis and Recommendation Systems

利用基于 RAG LLM 的语义分析和推荐系统映射和比较气候公平政策实践

Seung Jun Choi

专题命中领域大模型：LLM(title,title_cn)；large language model(abstract)；language model(abstract)

AI总结本文利用基于RAG LLM的语义分析和推荐系统，研究气候公平政策实践的比较与映射，揭示规划领域在AI时代的核心职责与政策趋势。

2607.15535 2026-07-20 cond-mat.mtrl-sci 新提交 89%

Symbolic Predicate-Guided Language Agents for Inverse Design of Perovskite Oxides

用于钙钛矿氧化物逆设计的符号谓词引导语言智能体

Dong Hyeon Mok, Seoin Back, Victor Fung, Guoxiang Hu

专题命中领域大模型：LLM(summary_cn,abstract)；language agent(title)；large language model(abstract)；language model(abstract)

AI总结研究钙钛矿氧化物逆设计，引入 DSL 引导策略，将自然语言规则转化为符号谓词，开发 ORCHESTRA 框架。该策略能增强 LLM 智能体推理能力，无需大量特定任务数据集或额外训练，提升材料设计性能。

2504.12865 2026-07-03 cs.HC 版本更新 89%

DashChat: Interactive Authoring of Performance Dashboard Design Prototypes through Conversation with LLM-Powered Agent

DashChat: 通过与LLM驱动的智能体对话交互式创作性能仪表盘设计原型

Z. Lin, S. Shen, W. Liu, C. Xin, W. Dai, S. Chen, X. Wen, X. Lan

专题命中领域大模型：LLM(title,title_cn)

AI总结提出DashChat系统，通过LLM驱动的多智能体管道将文本需求转化为性能仪表盘原型，加速迭代并保证设计质量。

2606.27930 2026-06-29 cs.IR stat.AP 新提交 89%

An LLM-Powered Semantic Alignment Framework for Journal Recommendation

基于LLM的语义对齐框架用于期刊推荐

Yanglin Yan, Zicheng Xie, Tianchen Gao, Rui Pan, Hansheng Wang

专题命中领域大模型：LLM(title,title_cn)；large language model(abstract)；language model(abstract)

AI总结提出一种基于大语言模型的语义对齐框架，将期刊推荐转化为稿件内容与期刊范围描述之间的语义匹配问题，无需训练即可实现高效推荐。

2606.27231 2026-06-26 quant-ph physics.ins-det 新提交 89%

A hardware-safety-gated system for LLM-written native ARTIQ control code on a trapped-ion platform

基于硬件安全门控的LLM编写原生ARTIQ控制代码系统在离子阱平台上的应用

Duanyang Wang, Lu Qi, Yuanheng Xie, Norbert M. Linke, Kenneth R. Brown

专题命中领域大模型：LLM(title,title_cn)

AI总结提出一种硬件安全门控系统，通过令牌授权机制确保LLM代理在离子阱实验中安全自主地编写和执行控制代码，并在实验中验证了其有效性和可移植性。

Comments 15 pages, 5 figures

1. 领域大模型 12496 篇

Using Large Language Models for Cybersecurity Capture-The-Flag Challenges and Certification Questions

Improving Zero-Shot Text Matching for Financial Auditing with Large Language Models

Large Language Models for Healthcare Data Augmentation: An Example on Patient-Trial Matching

Performance of Large Language Models in a Computer Science Degree Program

Are Large Language Models Ready for Healthcare? A Comparative Study on Clinical Language Understanding

What Should Data Science Education Do with Large Language Models?

Iterative Zero-Shot LLM Prompting for Knowledge Graph Construction

Repository-Level Prompt Generation for Large Language Models of Code

Friend or Foe? Exploring the Implications of Large Language Models on the Science System

Exploring the Responses of Large Language Models to Beginner Programmers' Help Requests

Conceptual Design Generation Using Large Language Models

Fluid Transformers and Creative Analogies: Exploring Large Language Models' Capacity for Augmenting Cross-Domain Analogical Creativity

Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback

Bootstrapping Multilingual Semantic Parsers using Large Language Models

Large Language Models as Fiduciaries: A Case Study Toward Robustly Communicating With Artificial Intelligence Through Legal Standards

Legal Prompting: Teaching a Language Model to Think Like a Lawyer

Can LLMs Reason About Brand Ownership? An Empirical Study of Domain Attribution Intelligence

Improving In-Context Learning with Small Language Model Ensembles

Do Large Language Models have Shared Weaknesses in Medical Question Answering?

Unveiling and Mitigating Bias in Mental Health Analysis with Large Language Models

The EPS Research Astro-RAG Platform: A Unified Open-Science Infrastructure for Cross-Epoch Astrophysical Kinematic Analysis, LLM-Assisted Research Workflows, and Educational Outreach

RobustDefect-LLM: Explainable and Robustness-Aware Industrial Surface Defect Classification with Decision Support and AI-Assisted Reporting

Structure-Preserving Projection for Mitigating Modality Bias in LLM-Based Sequential Recommendation

IMFuse: Instance-Aware Multi-Layer Fusion for LLM-Enhanced Sequential Recommendation

Evaluating the Practical Effectiveness of LLM-Driven Index Tuning on Microsoft SQL Server

Mapping and Comparing Climate Equity Policy Practices Using RAG LLM-Based Semantic Analysis and Recommendation Systems

Symbolic Predicate-Guided Language Agents for Inverse Design of Perovskite Oxides

DashChat: Interactive Authoring of Performance Dashboard Design Prototypes through Conversation with LLM-Powered Agent

An LLM-Powered Semantic Alignment Framework for Journal Recommendation

A hardware-safety-gated system for LLM-written native ARTIQ control code on a trapped-ion platform