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 12157 信号源:cs.CL, cs.AI, cs.LG

1. 其他LLM 12157 篇

2507.10818 2025-08-08 cs.SE cs.AI cs.LG 88%

How Robust are LLM-Generated Library Imports? An Empirical Study using Stack Overflow

Jasmine Latendresse, SayedHassan Khatoonabadi, Emad Shihab

机构 * Concordia University(康科迪亚大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.06832 2025-06-24 cs.AI cs.CL cs.GT cs.IT cs.NE math.IT 88%

Cross-Entropy Games for Language Models: From Implicit Knowledge to General Capability Measures

Clément Hongler, Andrew Emil

机构 * EPFL(苏黎世联邦理工学院)

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

Comments 42 pages, 16 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.16794 2025-06-12 cs.SD cs.AI cs.CL cs.HC eess.AS 88%

AAD-LLM: Neural Attention-Driven Auditory Scene Understanding

Xilin Jiang, Sukru Samet Dindar, Vishal Choudhari, Stephan Bickel, Ashesh Mehta, Guy M McKhann, Daniel Friedman, Adeen Flinker, Nima Mesgarani

机构 * Department of Electrical Engineering(电气工程系) Department of Neurological Surgery(神经外科系) Mortimer B. Zuckerman Mind Brain Behavior Institute(莫提默·B·祖克曼心智-脑-行为研究所) Hofstra Northwell School of Medicine(霍夫曼斯特拉北well医学院) The Feinstein Institutes for Medical Research(费森特医学研究所) Neurology Department(神经病学系)

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

Comments Accepted by ACL 2025 Main Conference

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.02254 2025-04-04 cs.CL cs.AI 88%

LLMs as Deceptive Agents: How Role-Based Prompting Induces Semantic Ambiguity in Puzzle Tasks

Seunghyun Yoo

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

Comments 9 pages, 5 figures, 1 table

详情

展开后加载摘要…

URL PDF HTML 收藏
2404.08877 2025-02-24 cs.SE cs.CL cs.LG 88%

Aligning the Objective of LLM-based Program Repair

Junjielong Xu, Ying Fu, Shin Hwei Tan, Pinjia He

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

Comments Accepted by ICSE'25

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.13221 2025-02-20 cs.LG cs.AI cs.CY cs.GT 88%

Two Tickets are Better than One: Fair and Accurate Hiring Under Strategic LLM Manipulations

Lee Cohen, Jack Hsieh, Connie Hong, Judy Hanwen Shen

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2405.12856 2024-12-23 stat.ML cs.CL cs.LG 88%

LLM Processes: Numerical Predictive Distributions Conditioned on Natural Language

James Requeima, John Bronskill, Dami Choi, Richard E. Turner, David Duvenaud

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

Journal ref 38th Conference on Neural Information Processing Systems (NeurIPS 2024)

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.00231 2024-11-27 cs.IR cs.AI cs.CL 88%

LLM-RankFusion: Mitigating Intrinsic Inconsistency in LLM-based Ranking

Yifan Zeng, Ojas Tendolkar, Raymond Baartmans, Qingyun Wu, Lizhong Chen, Huazheng Wang

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2407.12508 2024-10-17 cs.CL cs.AI cs.CV 88%

MERLIN: Multimodal Embedding Refinement via LLM-based Iterative Navigation for Text-Video Retrieval-Rerank Pipeline

Donghoon Han, Eunhwan Park, Gisang Lee, Adam Lee, Nojun Kwak

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

Comments EMNLP 2024 Industry Track Accepted (Camera-Ready Version)

详情

展开后加载摘要…

URL PDF HTML 收藏
2409.07054 2024-10-08 cs.CL cs.AI 88%

Native vs Non-Native Language Prompting: A Comparative Analysis

Mohamed Bayan Kmainasi, Rakif Khan, Ali Ezzat Shahroor, Boushra Bendou, Maram Hasanain, Firoj Alam

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

Comments Foundation Models, Large Language Models, Arabic NLP, LLMs, Native, Contextual Understanding, Arabic LLM

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.02829 2024-10-07 cs.AI cs.HC cs.LG 88%

LLMs May Not Be Human-Level Players, But They Can Be Testers: Measuring Game Difficulty with LLM Agents

Chang Xiao, Brenda Z. Yang

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2407.12824 2024-07-19 cs.CL cs.AI 88%

Whispering Experts: Neural Interventions for Toxicity Mitigation in Language Models

Xavier Suau, Pieter Delobelle, Katherine Metcalf, Armand Joulin, Nicholas Apostoloff, Luca Zappella, Pau Rodríguez

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

Comments ICML 2024, 8 pages + appendix

详情

展开后加载摘要…

URL PDF HTML 收藏
2407.06146 2024-07-10 cs.CL cs.AI cs.SE 88%

Using Grammar Masking to Ensure Syntactic Validity in LLM-based Modeling Tasks

Lukas Netz, Jan Reimer, Bernhard Rumpe

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

Comments Preprint to be published in the MODELS Workshop "MDE Intelligence"

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.03160 2026-08-19 cs.MM cs.CV 版本更新 88%

Caved or Convinced: Temporal Sampling Gates Claim Deference in Video Large Language Models

屈服还是信服:时序采样门控视频大语言模型的主张依从性

Yuxin Cao, Wei Song, Jingling Xue, Jin Song Dong

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

AI总结 该研究针对视频大语言模型的两种失败情况,区分了可用性与权重两个原因,提出反转测试缓解屈服于错误主张的问题,提升了顺序准确率并使模型可弃权而非猜测。

Comments 11 pages, 2 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.03847 2026-08-11 cs.SI 88%

Event-aware analysis of cross-city visitor flows using large language models and social media data

Xiaohan Wang, Zhan Zhao, Ruiyu Wang, Yang Xu

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.20851 2026-08-05 cs.CV 版本更新 88%

Poisoning Prompt-Guided Sampling in Video Large Language Models

针对视频大语言模型中提示引导采样的投毒攻击

Yuxin Cao, Wei Song, Jingling Xue, Jin Song Dong

机构 * National University of Singapore(新加坡国立大学) University of New South Wales(新南威尔士大学) CSIRO’s Data61(CSIRO数据61)

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

AI总结 该研究针对视频大语言模型的提示引导采样提出PoisonVID投毒攻击,在多种模型与采样器组合上实现高攻击成功率,揭示了PGS存在的结构性安全隐患。

Comments 16 pages, 5 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.25526 2026-07-29 cs.CY 新提交 88%

Estimating the Geopolitical Preferences of Large Language Models from United Nations Voting Data

从联合国投票数据估计大语言模型的地缘政治偏好

Maxim Chupilkin

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

AI总结 研究如何从联合国投票数据估计大语言模型的地缘政治偏好,采用动态序数理想点方法,将模型视为对相关决议全文的回应者,得出不同模型支持率及与五常关系等结果,发现模型地缘政治立场与开发者母国可能不同。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.17386 2026-07-21 cs.CV 新提交 88%

SkyVLaM: Multimodal Large Language Model for UAV Video Understanding in Remote Sensing

SkyVLaM:用于遥感中无人机视频理解的多模态大语言模型

Kaiwen Jing, Ruixu Jia, Bingyao Li, Ruizhe Ou, Ming Wu, Chuang Zhang

机构 * Beijing University of Posts and Telecommunications(北京邮电大学) Peking University(北京大学) Beijing Wuzi University(北京物资学院)

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

AI总结 针对无人机视频理解任务,提出多模态大语言模型SkyVLaM,通过时间基感知器构建稀疏令牌,正则化稀疏基,自适应选择密集段,联合大语言模型处理,还构建SkyVid,实验证明其能有效分配视觉令牌预算,提升语言条件视频分割效果。

Comments Accepted by WAICA 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.22338 2026-07-21 cs.SE 88%

Leveraging Design-Aware Context in Large Language Models for Code Comment Generation

利用设计感知上下文在大语言模型中生成代码注释

Aritra Mitra, Srijoni Majumdar, Anamitra Mukhopadhyay, Partha Pratim Das, Paul D Clough, Partha Pratim Chakrabarti

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

AI总结 本研究探讨利用设计文档作为上下文,通过大语言模型生成更实用的代码注释,以提高代码维护效率。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.08800 2026-07-13 cs.SD 新提交 88%

Dual-BEATs: Unlocking Zero-Shot Stereo Audio Perception in Audio Large Language Models via Dithering

双BEATs:通过抖动在音频大语言模型中解锁零样本立体声音频感知

Shuo-Chun Lin, Hen-Hsen Huang

机构 * Institute of Information Science, Academia Sinica(台湾中央研究院资讯科学研究所)

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

AI总结 研究针对多模态大语言模型空间感知局限,提出双BEATs架构,通过在编码前注入抖动噪声解决归一化问题,在三元方向分类任务中验证该方法有出色空间分辨率且能零样本泛化,证明标准模型经正则化可实现广义立体声音频理解。

Comments 14 pages, 3 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.21296 2026-06-23 cs.CY 新提交 88%

Discriminatory Compliance: How LLMs Answer Queries from Protected Groups

歧视性合规:LLM如何回答来自受保护群体的查询

Dinesh Ayyappan, Carlos Castillo

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

AI总结 研究LLM在回答受保护群体用户查询时表现出的歧视性合规现象,发现模型对少数群体身份角色提供的信息不一致且缺失关键信息。

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.10680 2026-06-16 cs.DB 88%

Evaluating SQL Understanding in Large Language Models

评估大型语言模型对SQL的理解能力

Ananya Rahaman, Anny Zheng, Mostafa Milani, Fei Chiang, Rachel Pottinger

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

AI总结 本文评估大型语言模型在SQL任务中的理解能力,通过检测语法错误、识别缺失token、预测查询性能等任务,揭示模型在语义理解和连贯性方面的局限。

Comments 12 pages conference submission

Journal ref Proc. EDBT 2025, pp. 909-921, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.25922 2026-05-26 cs.CV 88%

Closed-Loop Bidirectional Prompting for Adversarial Robustness of Vision Language Models

闭环双向提示用于视觉语言模型的对抗鲁棒性

Xiao Liu, Jiaxiang Liu, Boci Peng, Boren Hu, Yusong Wang, Xiwen Chen, Prayag Tiwari, Liming Zhang, Mingkun Xu

机构 * University of Macau(澳门大学) Guangdong Institute of Intelligence Science and Technology(广东智能科学与技术研究院) Peking University(北京大学) Independent Researcher(独立研究员) Institute of Science Tokyo(东京科学研究院) Morgan Stanley(摩根大通) Halmstad University(哈马碧大学)

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

AI总结 针对视觉语言模型在对抗扰动下跨模态语义对齐脆弱的问题,提出闭环双向提示方法,通过动态反馈循环恢复跨模态一致性,并引入语义锚点约束循环更新,实现实例自适应保护,在11个数据集上达到最先进的鲁棒性和泛化性能。

Comments 24 pages, 8 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.15842 2026-05-18 physics.soc-ph cs.SI 88%

Reconstructing temporal multi-relational firm networks at scale using large language models. The case of the semiconductor industry

利用大语言模型重建大规模时间多关系企业网络:半导体行业案例

Seyda Köse, Christian Diem, Elma Dervic, Klaus Friesenbichler, Georg Heiler, Jan Hurt, Hernan Picatto, Peter Klimek

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

AI总结 本文利用大语言模型和开放网络数据重建半导体行业企业网络,识别供应链、合作关系和所有权链接,揭示2022年芯片短缺期间的网络变化及AI供应链瓶颈企业的中心性变化。

Comments 32 pages, 5 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.13080 2026-05-14 cs.CV 88%

Learning to See What You Need: Gaze Attention for Multimodal Large Language Models

学习你需要看到的东西:多模态大语言模型的注视注意力

Junha Song, Byeongho Heo, Geonmo Gu, Jaegul Choo, Dongyoon Han, Sangdoo Yun

机构 * NAVER AI Lab(NAVER AI实验室)

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

AI总结 本文提出Gaze Attention机制,使多模态大语言模型在生成过程中选择性关注任务相关的视觉区域,减少冗余计算并提升聚焦效果,实验表明其在图像和视频理解任务中性能优于密集注意力基线。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.07490 2026-05-11 cs.CR 88%

Cross-Modal Backdoors in Multimodal Large Language Models

多模态模型中的跨模态后门

Runhe Wang, Li Bai, Haibo Hu, Songze Li

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

AI总结 研究提出一种利用轻量级连接器漏洞的跨模态后门攻击,通过污染连接器实现跨模态后门激活,展示攻击的有效性和可迁移性,揭示多模态对齐中的基本漏洞。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.20981 2026-04-22 cs.NE q-bio.PE 88%

Diversifying Toxicity Search in Large Language Models Through Speciation

通过种群化扩大大型语言模型毒性搜索

Onkar Shelar, Travis Desell

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

AI总结 本文提出ToxSearch-S,通过种群化方法在大型语言模型中扩展毒性搜索,提高毒性峰值并扩大语义覆盖范围,同时在嵌入空间中形成行为差异化的niche。

Comments Preprint. 4 pages, Accepted at GECCO as short paper

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.01583 2026-04-03 cs.CR 88%

Assertain: Automated Security Assertion Generation Using Large Language Models

Assertain:利用大语言模型实现自动安全断言生成

Shams Tarek, Dipayan Saha, Khan Thamid Hasan, Sujan Kumar Saha, Mark Tehranipoor, Farimah Farahmandi

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

AI总结 本文提出Assertain框架,通过RTL分析、CWE映射和威胁模型智能,利用大语言模型生成安全属性和可执行SystemVerilog断言,提升硬件安全验证效率与准确性。

Comments This paper will be presented at the 35th Microelectronics Design and Test Symposium (IEEE MDTS 2026)

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.02344 2026-04-03 cs.CR 88%

An End-to-End Model for Logits-Based Large Language Models Watermarking

面向基于logits的大语言模型水印的端到端模型

Kahim Wong, Jicheng Zhou, Jiantao Zhou, Yain-Whar Si

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

AI总结 本文提出端到端logits扰动方法,提升大语言模型水印的鲁棒性与文本质量,在改写和下游任务中表现更优。

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.01000 2026-04-01 cs.HC 88%

Togedule: Scheduling Meetings with Large Language Models and Adaptive Representations of Group Availability

Togedule: 利用大语言模型和群体可用性自适应表示进行会议安排

Jaeyoon Song, Zahra Ashktorab, Thomas W. Malone

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

AI总结 本文提出Togedule,一种利用大语言模型动态调整会议安排选项的工具,通过实验发现其能降低参会者认知负荷,提升组织者决策效率与质量。

Comments This paper has been accepted at CSCW 2025

详情

展开后加载摘要…

URL PDF HTML 收藏