语言大模型 / LLM - arXivDaily 专题

2307.04821 2023-07-12 cs.CL cs.AI cs.CY 88%

Amplifying Limitations, Harms and Risks of Large Language Models

Michael O'Neill, Mark Connor

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

2306.14905 2023-06-28 cs.CL cs.AI 88%

PRISMA-DFLLM: An Extension of PRISMA for Systematic Literature Reviews using Domain-specific Finetuned Large Language Models

Teo Susnjak

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

2302.08500 2023-06-28 cs.CL cs.AI cs.CY 88%

Auditing large language models: a three-layered approach

Jakob Mökander, Jonas Schuett, Hannah Rose Kirk, Luciano Floridi

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

Comments 22 pages, 2 figures. AI Ethics (2023)

2302.01308 2023-06-16 cs.CL cs.LG stat.ML 88%

Large language models predict human sensory judgments across six modalities

Raja Marjieh, Ilia Sucholutsky, Pol van Rijn, Nori Jacoby, Thomas L. Griffiths

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

Comments 9 pages, 3 figures

2305.15525 2023-05-26 cs.CL cs.LG 88%

Large Language Models are Few-Shot Health Learners

Xin Liu, Daniel McDuff, Geza Kovacs, Isaac Galatzer-Levy, Jacob Sunshine, Jiening Zhan, Ming-Zher Poh, Shun Liao, Paolo Di Achille, Shwetak Patel

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

2304.02213 2023-04-13 cs.CL cs.AI 88%

Large Language Models as Master Key: Unlocking the Secrets of Materials Science with GPT

Tong Xie, Yuwei Wan, Wei Huang, Yufei Zhou, Yixuan Liu, Qingyuan Linghu, Shaozhou Wang, Chunyu Kit, Clara Grazian, Wenjie Zhang, Bram Hoex

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

2212.03551 2023-02-17 cs.CL cs.LG 88%

Talking About Large Language Models

Murray Shanahan

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

2205.12689 2022-12-01 cs.CL cs.AI 88%

Large Language Models are Few-Shot Clinical Information Extractors

Monica Agrawal, Stefan Hegselmann, Hunter Lang, Yoon Kim, David Sontag

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

Comments Accepted as a long paper to The 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP)

2204.07667 2022-10-28 cs.CL cs.AI cs.CR 88%

Just Fine-tune Twice: Selective Differential Privacy for Large Language Models

Weiyan Shi, Ryan Shea, Si Chen, Chiyuan Zhang, Ruoxi Jia, Zhou Yu

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

Comments EMNLP 2022

2206.11861 2022-06-28 cs.SE cs.AI cs.CL 88%

Automatic Generation of Programming Exercises and Code Explanations using Large Language Models

Sami Sarsa, Paul Denny, Arto Hellas, Juho Leinonen

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

Comments 18 pages, 1 figure, accepted in ICER

2203.05115 2022-05-24 cs.CL cs.LG 88%

Internet-augmented language models through few-shot prompting for open-domain question answering

Angeliki Lazaridou, Elena Gribovskaya, Wojciech Stokowiec, Nikolai Grigorev

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

2102.02503 2021-02-05 cs.CL cs.LG 88%

Understanding the Capabilities, Limitations, and Societal Impact of Large Language Models

Alex Tamkin, Miles Brundage, Jack Clark, Deep Ganguli

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

2512.12447 2025-12-16 cs.CL 88%

Large language models have learned to use language

大型语言模型已学会使用语言

Gary Lupyan

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

AI总结本文探讨大型语言模型在语言使用上的学习能力，指出其可能推动语言科学的突破，并挑战传统评估观念。

Comments Commentary on Futrell & Mahowald's How Linguistics Learned to Stop Worrying and Love the Language Models (BBS, Forthcoming)

2511.16548 2025-11-21 cs.AI 88%

Utilizing Large Language Models for Zero-Shot Medical Ontology Extension from Clinical Notes

利用大型语言模型进行临床笔记的零样本医学本体扩展

Guanchen Wu, Yuzhang Xie, Huanwei Wu, Zhe He, Hui Shao, Xiao Hu, Carl Yang

机构 * Department of Computer Science（计算机科学系）； Emory University（埃默里大学）； College of Public Health（公共卫生学院）； Temple University（temple大学）； School of Information（信息学院）； Florida State University（佛罗里达州立大学）； Hubert Department of Global Health（全球健康部）； Nell Hodgson Woodruff School of Nursing（Nell Hodgson Woodruff护理学院）

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

AI总结 CLOZE利用大型语言模型从临床笔记中自动提取医学实体，实现零样本医学本体扩展，具有高准确性和隐私保护能力。

Comments BIBM 2025 (WS#44: Biological ontologies and knowledge bases (BiOK) in the LLM era)

2507.14681 2025-11-04 cs.CL 88%

Large Language Models as Medical Codes Selectors: a benchmark using the International Classification of Primary Care

Vinicius Anjos de Almeida, Vinicius de Camargo, Raquel Gómez-Bravo, Egbert van der Haring, Kees van Boven, Marcelo Finger, Luis Fernandez Lopez

机构 * Medical School, University of São Paulo（圣保罗大学医学院）； University of São Paulo（圣保罗大学）； Department of Epidemiology, School of Public Health, University of São Paulo（圣保罗大学流行病学系）； Rehaklinik, Centre Hospitalier Neuro-psychiatrique (CHNP)（康复诊所，神经精神病中心（CHNP））； Radboud University（拉德堡德大学）； Department of Primary and Community Care, Radboud University（初级与社区护理系，拉德堡德大学）； Institute of Mathematics and Statistics, University of Sao Paulo（数学与统计学研究所，圣保罗大学）

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

Comments Accepted at NeurIPS 2025 as a poster presentation in The Second Workshop on GenAI for Health: Potential, Trust, and Policy Compliance (https://openreview.net/forum?id=Kl7KZwJFEG). 33 pages, 10 figures (including appendix), 15 tables (including appendix). To be submitted to peer-reviewed journal. For associated code repository, see https://github.com/almeidava93/llm-as-code-selectors-paper

2308.04138 2023-08-09 cs.CL 88%

Large Language Model Prompt Chaining for Long Legal Document Classification

Dietrich Trautmann

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

Comments SwissText 2023 Late Breaking Work (Generative AI & LLM)

2602.19021 2026-07-21 cs.CR 版本更新 88%

Trustworthy AI LLM Scalability Risk Index (LSRI): A Cybersecurity Framework Assessing Agentic-AI Security & Software Model Supply Chain Safety Boosting AI-Generated Malware Defense & Explainability Mitigating Emerging Risks of Generative AI

大语言模型在代理AI中的可扩展性风险与模型供应链安全

Kiarash Ahi, Vaibhav Agrawal, Saeed Valizadeh

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

AI总结本文研究了大语言模型在代理AI中的可扩展性风险及模型供应链安全问题，提出LSRI指数和模型供应链框架，以提升安全关键环境下的LLM部署安全性。

Comments Accepted for publication in Journal of Computer Information Systems (2026). DOI: 10.1080/08874417.2026.2624670

Journal ref Journal of Computer Information Systems (2026)

2607.15738 2026-07-20 cs.CY 新提交 88%

EduGuard: A Safe RAG-Based LLM Tutor for Programming Education

EduGuard：一种用于编程教育的基于安全检索增强生成的语言模型导师

S M Asif Hossain, Ruksat Khan Shayoni, M. F. Mridha, Jungpil Shin

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

AI总结研究针对学生使用GenAI进行编程学习时的问题，提出EduGuard安全RAG辅导框架，集成多种功能。通过构建基准测试并与强基线比较，在正确性、基础等方面表现最佳，能提升准确率并降低过度依赖，证明安全GenAI辅导需多方面保障。

2601.00260 2026-07-01 cs.CV 版本更新 88%

TotalFM: An Organ-Separated 3D-CT Foundation Model Leveraging Large-Scale Routine Clinical Radiology Data

TotalFM：利用大规模常规临床放射学数据的器官分离3D-CT基础模型

Kohei Yamamoto, Tomohiro Kikuchi

机构 * Department of Radiology, Jichi Medical University（放射科，自治医科大学）； Data Science Center, Jichi Medical University（数据科学中心，自治医科大学）

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

AI总结提出TotalFM，一种基于器官分离的3D-CT放射学基础模型，通过自动化生成器官体积与发现句子对，结合VideoMAE自监督预训练和对比学习，在零样本器官级和发现级病变分类任务中优于现有模型。

2512.01693 2026-06-29 cs.DB cond-mat.mtrl-sci 版本更新 88%

LitMOF: An LLM Multi-Agent for Literature-Validated Metal-Organic Frameworks Database Correction and Expansion

LitMOF：用于文献验证的金属有机框架数据库校正与扩展的LLM多智能体系统

Honghui Kim, Dohoon Kim, Jihan Kim

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LitMOF框架，利用大语言模型多智能体从原始文献验证并修复MOF数据库中的结构错误，成功修复9227个无效条目并发现8771个新MOF，通过直接空气捕获案例证明结构错误严重影响材料筛选可靠性。

2606.05970 2026-06-05 cs.CL cs.AI cs.LG 88%

Measuring the sensitivity of LLM-based structured extraction to prompt, model, and schema choices in clinical discharge summaries

测量基于LLM的结构化提取对临床出院小结中提示、模型和模式选择的敏感性

Martin Murin

机构 * DryLabz GmbH（DryLabz公司）

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

AI总结本研究通过固定提取任务并逐一改变提示、模型和模式选择，测量了大型语言模型在临床文本结构化提取中输出对上游配置的敏感性，发现模式选择导致的差异集中在缺失与沉默的区分上，而模型选择在多类分类中主导提示措辞。

Comments 69 pages, 5 main figures, supplementary material included

2511.14224 2026-06-05 cs.SE 88%

Knowledge Matters: Injecting Project and Testing Knowledge into LLM-based Unit Test Generation

知识很重要：将项目和测试知识注入基于大语言模型的单元测试生成

Anji Li, Mingwei Liu, Zhenxi Chen, Zheng Pei, Zike Li, Dekun Dai, Yanlin Wang, Zibin Zheng

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

AI总结本文提出KTester框架，通过整合项目特定知识和测试领域知识，提升基于大语言模型的单元测试生成能力，实验表明其在多个关键指标上优于现有方法，提高了测试通过率和覆盖率，且生成的测试更易读易维护。

Comments Accepted at the 48th International Conference on Software Engineering(ICSE 2026),13 pages, 11 figures

2605.09481 2026-05-12 cs.NI 88%

TSNBench: Benchmarking LLM Proficiency in Time-Sensitive Networking

TSNBench：评估大语言模型在时间敏感网络中能力的基准测试

Rubi Debnath, Daniel Bujosa Mateu, Luxi Zhao, Silviu S. Craciunas, Paul Pop, Sebastian Steinhorst

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

AI总结本文提出TSNBench，首个评估大语言模型在时间敏感网络中的能力的基准测试，包含939道专家验证的多项选择题和100道开放性问题，揭示LLM在安全关键网络领域的能力不足。

2408.13366 2026-03-27 cs.CL cs.AI cs.LG 88%

CodeRefine: A Pipeline for Enhancing LLM-Generated Code Implementations of Research Papers

CodeRefine: 一种提升研究论文中大语言模型生成代码实现的管道

Ekaterina Trofimova, Emil Sataev, Abhijit Singh Jowhari

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

AI总结 CodeRefine通过多步骤方法将论文方法转化为功能代码，利用预定义本体构建知识图谱，并通过回顾性检索增强生成方法提升代码准确性，有效解决理论研究与实践实现之间的桥梁问题。

Comments The results mentioned in the paper are non-reproducible. We have rechecked the metrics, and they do not match with the ones that have been provided in the paper. Therefore, we accept that this article is neither suitable nor up to the mark for the scientific community and must be with-drawn. We fully understand the consequences, and would like to wishfully retract this article

2511.09540 2025-11-21 cs.CV 88%

vMFCoOp: Towards Equilibrium on a Unified Hyperspherical Manifold for Prompting Biomedical VLMs

vMFCoOp：在统一超球面流形上实现平衡的提示生物医学VLMs

Minye Shao, Sihan Guo, Xinrun Li, Xingyu Miao, Haoran Duan, Yang Long

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

AI总结 vMFCoOp通过统一超球面流形上的vMF分布估计，实现LLM与CLIP主干间的语义对齐，提升生物医学VLMs的提示效果和少样本分类性能。

Comments Accepted as an Oral Presentation at AAAI 2026 Main Technical Track (this version is not peer-reviewed; it is the extended version)

2404.09384 2025-10-08 cs.SE cs.AI cs.CL cs.LG 88%

Generative transformations and patterns in LLM-native approaches for software verification and falsification

Víctor A. Braberman, Flavia Bonomo-Braberman, Yiannis Charalambous, Juan G. Colonna, Lucas C. Cordeiro, Rosiane de Freitas

机构 * Department of Computer Science, The University of Manchester（曼彻斯特大学计算机科学系）； Instituto de Computação (ICOMP-UFAM), Universidade Federal do Amazonas（亚马逊联邦大学计算学院（ICOMP-UFAM））

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

2411.08870 2025-07-01 cs.CL cs.AI cs.LG 88%

The Limited Impact of Medical Adaptation of Large Language and Vision-Language Models

Daniel P. Jeong, Pranav Mani, Saurabh Garg, Zachary C. Lipton, Michael Oberst

机构 * Carnegie Mellon University（卡内基梅隆大学）； Abridge ； Mistral AI ； Johns Hopkins University（约翰霍普金斯大学）

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

Comments Extended version of EMNLP 2024 paper arXiv:2411.04118. Includes additional results on clinical note QA tasks and supervised fine-tuning evaluations

2407.01887 2025-06-10 cs.LG cs.AI cs.CL 88%

Beyond Numeric Rewards: In-Context Dueling Bandits with LLM Agents

Fanzeng Xia, Hao Liu, Yisong Yue, Tongxin Li

机构 * The Chinese University of Hong Kong Shenzhen（香港中文大学（深圳））； California Institute of Technology（加州理工学院）

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

Comments ACL 2025 Findings

2412.08385 2024-12-12 cs.CL cs.AI cs.IR cs.LG 88%

NyayaAnumana & INLegalLlama: The Largest Indian Legal Judgment Prediction Dataset and Specialized Language Model for Enhanced Decision Analysis

Shubham Kumar Nigam, Balaramamahanthi Deepak Patnaik, Shivam Mishra, Noel Shallum, Kripabandhu Ghosh, Arnab Bhattacharya

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

Comments Accepted on COLING 2025

2410.02741 2024-12-04 cs.CL cs.AI cs.LG 88%

Salient Information Prompting to Steer Content in Prompt-based Abstractive Summarization

Lei Xu, Mohammed Asad Karim, Saket Dingliwal, Aparna Elangovan

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

Comments Accepted to EMNLP 2024 Industry Track. Code available at https://github.com/amazon-science/SigExt

1. 领域大模型 12554 篇

Amplifying Limitations, Harms and Risks of Large Language Models

PRISMA-DFLLM: An Extension of PRISMA for Systematic Literature Reviews using Domain-specific Finetuned Large Language Models

Auditing large language models: a three-layered approach

Large language models predict human sensory judgments across six modalities

Large Language Models are Few-Shot Health Learners

Large Language Models as Master Key: Unlocking the Secrets of Materials Science with GPT

Talking About Large Language Models

Large Language Models are Few-Shot Clinical Information Extractors

Just Fine-tune Twice: Selective Differential Privacy for Large Language Models

Automatic Generation of Programming Exercises and Code Explanations using Large Language Models

Internet-augmented language models through few-shot prompting for open-domain question answering

Understanding the Capabilities, Limitations, and Societal Impact of Large Language Models

Large language models have learned to use language

Utilizing Large Language Models for Zero-Shot Medical Ontology Extension from Clinical Notes

Large Language Models as Medical Codes Selectors: a benchmark using the International Classification of Primary Care

Large Language Model Prompt Chaining for Long Legal Document Classification

Trustworthy AI LLM Scalability Risk Index (LSRI): A Cybersecurity Framework Assessing Agentic-AI Security & Software Model Supply Chain Safety Boosting AI-Generated Malware Defense & Explainability Mitigating Emerging Risks of Generative AI

EduGuard: A Safe RAG-Based LLM Tutor for Programming Education

TotalFM: An Organ-Separated 3D-CT Foundation Model Leveraging Large-Scale Routine Clinical Radiology Data

LitMOF: An LLM Multi-Agent for Literature-Validated Metal-Organic Frameworks Database Correction and Expansion

Measuring the sensitivity of LLM-based structured extraction to prompt, model, and schema choices in clinical discharge summaries

Knowledge Matters: Injecting Project and Testing Knowledge into LLM-based Unit Test Generation

TSNBench: Benchmarking LLM Proficiency in Time-Sensitive Networking

CodeRefine: A Pipeline for Enhancing LLM-Generated Code Implementations of Research Papers

vMFCoOp: Towards Equilibrium on a Unified Hyperspherical Manifold for Prompting Biomedical VLMs

Generative transformations and patterns in LLM-native approaches for software verification and falsification

The Limited Impact of Medical Adaptation of Large Language and Vision-Language Models

Beyond Numeric Rewards: In-Context Dueling Bandits with LLM Agents

NyayaAnumana & INLegalLlama: The Largest Indian Legal Judgment Prediction Dataset and Specialized Language Model for Enhanced Decision Analysis

Salient Information Prompting to Steer Content in Prompt-based Abstractive Summarization