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 12228 信号源:cs.CL, cs.AI, cs.LG

1. 其他LLM 12228 篇

2304.02839 2023-04-07 cs.CY cs.AI 77%

Whose Text Is It Anyway? Exploring BigCode, Intellectual Property, and Ethics

Madiha Zahrah Choksi, David Goedicke

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

Comments 3 pages, submitted to the Second Workshop on Intelligent and Interactive Writing Assistants co-located with the ACM CHI Conference on Human Factors in Computing Systems (CHI 2023)

详情

展开后加载摘要…

URL PDF HTML 收藏
2303.16104 2023-03-29 cs.CL 77%

Hallucinations in Large Multilingual Translation Models

Nuno M. Guerreiro, Duarte Alves, Jonas Waldendorf, Barry Haddow, Alexandra Birch, Pierre Colombo, André F. T. Martins

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2303.06430 2023-03-15 cs.AI 77%

Mapping the Design Space of Interactions in Human-AI Text Co-creation Tasks

Zijian Ding, Joel Chan

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2303.05546 2023-03-13 cs.CV cs.AI 77%

Weakly-Supervised HOI Detection from Interaction Labels Only and Language/Vision-Language Priors

Mesut Erhan Unal, Adriana Kovashka

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

Comments 8 pages, 3 figures and 5 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2302.11382 2023-02-23 cs.SE cs.AI 77%

A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT

Jules White, Quchen Fu, Sam Hays, Michael Sandborn, Carlos Olea, Henry Gilbert, Ashraf Elnashar, Jesse Spencer-Smith, Douglas C. Schmidt

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2302.05733 2023-02-14 cs.CR cs.LG 77%

Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks

Daniel Kang, Xuechen Li, Ion Stoica, Carlos Guestrin, Matei Zaharia, Tatsunori Hashimoto

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2301.10016 2023-01-25 cs.CY cs.AI cs.HC 77%

A Case Study in Engineering a Conversational Programming Assistant's Persona

Steven I. Ross, Michael Muller, Fernando Martinez, Stephanie Houde, Justin D. Weisz

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

Comments 11 pages. Submitted to the 4th Workshop on Human-AI Co-Creation with Generative Models (HAI-GEN) at IUI 2023

详情

展开后加载摘要…

URL PDF HTML 收藏
2212.09656 2022-12-20 cs.CL cs.IR 77%

Visconde: Multi-document QA with GPT-3 and Neural Reranking

Jayr Pereira, Robson Fidalgo, Roberto Lotufo, Rodrigo Nogueira

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2208.06213 2022-10-18 cs.HC cs.AI cs.PL 77%

What is it like to program with artificial intelligence?

Advait Sarkar, Andrew D. Gordon, Carina Negreanu, Christian Poelitz, Sruti Srinivasa Ragavan, Ben Zorn

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

Comments Proceedings of the 33rd Annual Conference of the Psychology of Programming Interest Group (PPIG 2022)

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.14532 2025-08-21 cs.SE cs.LO 76%

Preguss: It Analyzes, It Specifies, It Verifies

Zhongyi Wang, Tengjie Lin, Mingshuai Chen, Mingqi Yang, Haokun Li, Xiao Yi, Shengchao Qin, Jianwei Yin

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

Comments Position paper to appear in the 1st International Workshop on Language Models and Programming Languages (LMPL '25)

详情

展开后加载摘要…

URL PDF HTML 收藏
2409.16701 2025-02-12 cs.SE 76%

Vulnerability-Triggering Test Case Generation from Third-Party Libraries

Yi Gao, Xing Hu, Zirui Chen, Xiaohu Yang

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

Comments Published in 2nd Conference on AI Foundation Models and Software Engineering (FORGE 2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2312.16549 2023-12-29 cs.LG cs.AI cs.CL 76%

How Robust are LLMs to In-Context Majority Label Bias?

Karan Gupta, Sumegh Roychowdhury, Siva Rajesh Kasa, Santhosh Kumar Kasa, Anish Bhanushali, Nikhil Pattisapu, Prasanna Srinivasa Murthy

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

Comments 6 pages, 3 figures, 2 table. Accepted at Workshop on Responsible Language Modeling, AAAI 2024, (www.aaai.org)

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.22117 2026-08-25 cs.LG cs.CL 新提交 76%

TANGO: Token-Aggregated Nonlinear Gating Operators for Natural and Formal Language Modeling

TANGO:用于自然语言与形式语言建模的令牌聚合门控非线性算子

Joshua Nunley

机构 * Luddy School of Informatics, Computing, and Engineering(勒迪信息学、计算与工程学院) Indiana University Bloomington(印第安纳大学伯明顿分校)

专题命中 其他LLM :language model(title);分类 cs.CL、cs.LG

AI总结 该研究提出TANGO和WANGO两种模型,替换Transformer的自注意力与前馈子层,经对比实验,TANGO在多数据集上验证负对数似然最优,WANGO在线性复杂度架构中表现最佳且优于Recurrent Transformer++。

Comments 13 pages, 5 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.20569 2026-08-24 cs.AI cs.CL 新提交 76%

Open-Weight Masked Introspection: Measuring What Language Models Can Report About Their Own Computation

开放权重掩码内省:测量语言模型可报告自身计算的能力

Emilio Ferrara

机构 * University of Southern California(南加州大学)

专题命中 其他LLM :language model(title);分类 cs.CL、cs.AI

AI总结 本研究构建OWMI框架检验8个开放权重模型的内省能力,发现其无法区分真实干预与虚假运行,仅内部存在相关信息,失败源于内部状态到文本报告的路径,需对照内部参考验证模型证词。

Comments We release OWMI as a library so that this emerging ability can be measured as it develops. Hugging Face OWMI library: https://huggingface.co/emilioferrara/owmi

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.04021 2026-08-06 cs.CL cs.LG 新提交 76%

When More Becomes Less: Position-Dependent Repetition Effects in Language Models

当多变为少:语言模型中与位置相关的重复效应

Han-yu Wang

机构 * The University of Hong Kong(香港大学)

专题命中 其他LLM :language model(title);分类 cs.CL、cs.LG

AI总结 该研究发现语言模型中目标 token 的重复效应与读取位置相关,位移重复会呈现倒U型规律,且该效应经多语言和多模型验证,归因于精确词汇重复而非其他因素。

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.03123 2026-08-05 cs.LG cs.AI 新提交 76%

Trajectory-Guided Forget-Recover Network for Continual LLM Unlearning

用于持续大语言模型遗忘的轨迹引导遗忘-恢复网络

Zezheng Wu, Xinghe Cheng, Qinggang Zhang, Haoran Luo, Jiapu Wang, Qing Yang, Jingwei Zhang

专题命中 其他LLM :LLM(title);分类 cs.AI、cs.LG

AI总结 针对持续大语言模型遗忘的两大挑战,提出TFR-Net,通过跟踪通道级风险抑制持久目标相关通道、恢复休眠通道,在四个数据集上取得更优的遗忘效果与保留性能权衡。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.01558 2026-07-02 cs.LG cs.AI 版本更新 76%

Utilizing Earth Foundation Models to Enhance the Simulation Performance of Hydrological Models with AlphaEarth Embeddings

利用地球基础模型通过AlphaEarth嵌入增强水文模型的模拟性能

Pengfei Qu, Wenyu Ouyang, Chi Zhang, Yikai Chai, Shuolong Xu, Lei Ye, Yongri Piao, Miao Zhang, Huchuan Lu

机构 * School of Computer Science and Technology, Dalian University of Technology(大连理工大学计算机科学与技术学院) School of Infrastructure Engineering, Dalian University of Technology(大连理工大学建设工程学院) School of Information and Communication Engineering, Dalian University of Technology(大连理工大学信息与通信工程学院) School of Software, Dalian University of Technology(大连理工大学软件学院) School of Artificial Intelligence, Dalian University of Technology(大连理工大学人工智能学院)

专题命中 其他LLM :foundation model(title);分类 cs.AI、cs.LG

AI总结 研究利用AlphaEarth基础模型从卫星图像中学习的嵌入表征流域特征,相比传统属性更有效提升无测站流域的径流预测精度,并发现基于嵌入相似性选择捐赠流域可改善预测性能。

Comments 12 pages, 11 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.07222 2026-04-17 cs.LG cs.CL 76%

Pay Less Attention to Function Words for Free Robustness of Vision-Language Models

减少对功能词的关注以实现视觉语言模型的自由鲁棒性

Qiwei Tian, Chenhao Lin, Zhengyu Zhao, Chao Shen

机构 * School of Cyber Science and Engineering, Xi’an Jiaotong University, Xi’an 710049, China(西安交通大学计算机科学与工程学院,西安 710049,中国)

专题命中 其他LLM :language model(title);分类 cs.CL、cs.LG

AI总结 本文提出FDA方法,通过减少功能词的注意力影响,提升视觉语言模型在跨模态对抗攻击下的鲁棒性,实验显示在检索任务中ASR下降18%/13%/53%,性能损失极小。

Comments The paper has been accepted by ICLR26

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.04756 2026-04-08 cs.LG cs.CL 76%

Darkness Visible: Reading the Exception Handler of a Language Model

黑暗可见:语言模型异常处理程序的解读

Peter Balogh

专题命中 其他LLM :language model(title);分类 cs.CL、cs.LG

AI总结 研究揭示GPT-2 Small最终MLP层存在可读的路由程序,通过分解神经元发现其异常处理机制及知识存储方式,实验显示知识神经元在路由中起作用而非存储事实。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.19062 2026-01-28 cs.CY cs.AI cs.CL cs.HC 76%

Who's in Charge? Disempowerment Patterns in Real-World LLM Usage

谁在掌控?现实世界LLM使用中的去赋能模式

Mrinank Sharma, Miles McCain, Raymond Douglas, David Duvenaud

机构 * ACS Research Group(ACS研究组) University of Toronto(多伦多大学)

专题命中 其他LLM :LLM(title);分类 cs.CL、cs.AI

AI总结 研究揭示现实世界中AI助手交互中去赋能模式的分布与影响,指出其对人类赋权的潜在威胁,并呼吁设计更支持人类自主的AI系统。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.05925 2025-12-08 cs.AI cs.CL 76%

To Err Is Human: Systematic Quantification of Errors in Published AI Papers via LLM Analysis

出错是人之常情:通过LLM分析系统性量化已发表AI论文中的错误

Federico Bianchi, Yongchan Kwon, Zachary Izzo, Linjun Zhang, James Zou

机构 * Together AI NEC Labs America(NEC美国实验室) Rutgers University(罗格斯大学) Stanford University(斯坦福大学)

专题命中 其他LLM :LLM(title);分类 cs.CL、cs.AI

AI总结 通过LLM分析发现已发表AI论文中存在大量客观错误,错误数量随时间增加,AI检查器能有效识别并纠正大部分错误,提升文献的准确性和可重复性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.00004 2025-12-02 cs.IR cs.AI cs.LG 76%

Enhancing Talent Search Ranking with Role-Aware Expert Mixtures and LLM-based Fine-Grained Job Descriptions

通过角色感知专家混合与基于大语言模型的细粒度职位描述增强人才搜索排名

Jihang Li, Bing Xu, Zulong Chen, Chuanfei Xu, Minping Chen, Suyu Liu, Ying Zhou, Zeyi Wen

机构 * HKUST (GZ)(香港科技大学(广州)) Alibaba Group(阿里巴巴集团) HKUST(香港科技大学) Zhijiang Lab(浙江实验室) Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)(广东人工智能与数字经济实验室(深圳))

专题命中 其他LLM :LLM(title);分类 cs.AI、cs.LG

AI总结 本文提出基于大语言模型和角色感知专家混合的方法,提升人才搜索排名效果,通过细粒度职位描述提取和行为建模,提升CTR和CVR,实现招聘效率和成本节约。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.16018 2025-11-21 cs.AI cs.CL 76%

SpellForger: Prompting Custom Spell Properties In-Game using BERT supervised-trained model

SpellForger: 使用BERT监督训练模型在游戏中自定义咒语属性

Emanuel C. Silva, Emily S. M. Salum, Gabriel M. Arantes, Matheus P. Pereira, Vinicius F. Oliveira, Alessandro L. Bicho

专题命中 其他LLM :prompting(title);分类 cs.CL、cs.AI

AI总结 SpellForger利用BERT模型让玩家通过自然语言提示自定义游戏中的咒语属性,通过实时生成咒语验证AI作为游戏机制的可行性。

Comments Published in Anais Estendidos do XXIV Simpósio Brasileiro de Jogos e Entretenimento Digital (SBGames 2025)

Journal ref Anais Estendidos do XXIV Simpósio Brasileiro de Jogos e Entretenimento Digital (SBGames 2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2409.06263 2025-10-31 cs.CL cs.AI 76%

Speak & Spell: LLM-Driven Controllable Phonetic Error Augmentation for Robust Dialogue State Tracking

Jihyun Lee, Solee Im, Wonjun Lee, Gary Geunbae Lee

机构 * Graduate School of Artificial Intelligence, POSTECH, Republic of Korea(人工智能研究生院,POSTECH,韩国) Department of Computer Science and Engineering, POSTECH, Republic of Korea(计算机科学与工程系,POSTECH,韩国)

专题命中 其他LLM :LLM(title);分类 cs.CL、cs.AI

Comments Accepted to AACL-IJCNLP 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.13898 2025-10-29 cs.LG cs.AI cs.NE 76%

Do Language Models Use Their Depth Efficiently?

Róbert Csordás, Christopher D. Manning, Christopher Potts

机构 * Stanford University(斯坦福大学)

专题命中 其他LLM :language model(title);分类 cs.AI、cs.LG

Comments Accepted to NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.08775 2025-08-11 cs.CL cs.AI 76%

Layers at Similar Depths Generate Similar Activations Across LLM Architectures

Christopher Wolfram, Aaron Schein

机构 * Department of Computer Science University of Chicago(计算机科学系芝加哥大学) Department of Statistics University of Chicago(统计系芝加哥大学)

专题命中 其他LLM :LLM(title);分类 cs.CL、cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.19765 2025-06-03 cs.CL cs.LG 76%

EdiText: Controllable Coarse-to-Fine Text Editing with Diffusion Language Models

Che Hyun Lee, Heeseung Kim, Jiheum Yeom, Sungroh Yoon

机构 * Department of Electrical and Computer Engineering, Seoul National University(电子与计算机工程系,首尔国立大学) AIIS, ASRI, INMC, ISRC, and IPAI, Seoul National University(人工智能研究所、先进系统研究室、智能网络中心、信息科学研究中心和人工智能计划,首尔国立大学)

专题命中 其他LLM :language model(title);分类 cs.CL、cs.LG

Comments ACL 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.16359 2025-05-30 cs.CL cs.AI 76%

Human-Readable Adversarial Prompts: An Investigation into LLM Vulnerabilities Using Situational Context

Nilanjana Das, Edward Raff, Aman Chadha, Manas Gaur

机构 * University of Maryland, Baltimore County(马里兰大学巴尔的摩县分校) Amazon Web Services(亚马逊网络服务)

专题命中 其他LLM :LLM(title);分类 cs.CL、cs.AI

Comments arXiv admin note: text overlap with arXiv:2407.14644

详情

展开后加载摘要…

URL PDF HTML 收藏
2409.13931 2025-05-30 cs.LG cs.CL 76%

On-Device Collaborative Language Modeling via a Mixture of Generalists and Specialists

Dongyang Fan, Bettina Messmer, Nikita Doikov, Martin Jaggi

专题命中 其他LLM :language model(title);分类 cs.CL、cs.LG

Comments Camera-ready version

Journal ref ICML 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.01855 2025-05-27 cs.CL cs.AI 76%

Intra-Layer Recurrence in Transformers for Language Modeling

Anthony Nguyen, Wenjun Lin

专题命中 其他LLM :language model(title);分类 cs.CL、cs.AI

Comments Accepted at Canadian AI 2025. Code available at https://github.com/ant-8/Layer-Recurrent-Transformers

详情

展开后加载摘要…

URL PDF HTML 收藏