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 12251 信号源:cs.CL, cs.AI, cs.LG

1. 其他LLM 12251 篇

2607.26591 2026-07-30 cs.SE 新提交 86%

MultiFixer: A Coordinator-Proposer Based Multi-Agent Framework For Fixing Multi-Hunk Bugs

MultiFixer:一种用于修复多块漏洞的基于协调者-提议者的多智能体框架

Haichuan Hu, Chunrong Fang, Ye Shang, Jiawei Liu, Weifeng Sun, Guoqing Xie, Chenxing Zhong, Quanjun Zhang

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

AI总结 该研究针对现有LLM-based APR方法难以修复多块漏洞的问题,提出MultiFixer多智能体框架,经多基准测试,其在Defects4J等数据集上达到最优修复效果,能有效修复多块漏洞。

Comments Accepted to 41st IEEE/ACM International Conference on Automated Software Engineering (ASE 2026)

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.13357 2026-07-24 cs.HC 版本更新 86%

TANDE: Disentangling Verbal and Nonverbal Backchannels in Emotional AI-Avatar Conversations with Young Adults

TANDE:在与年轻人的情感人工智能-虚拟化身对话中区分言语和非言语反馈渠道

Ann-Kareen Gedeus, Jack Good, Nadine Wagener, Angelique Taylor

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

AI总结 研究在与年轻人的情感人工智能-虚拟化身对话中反馈渠道模式的影响,引入TANDE这个由LLM驱动的ECA,通过实验探讨其对融洽关系、同理心和参与度的作用及性别差异,得出相关设计启示。

Comments This paper has been accepted for publication at the 28th ACM International Conference on Multimodal Interaction (ICMI 2026)

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.00445 2026-07-02 cs.HC 新提交 86%

Gaze-Informed Proactive AI Assistance for Children's Picture Exploration

基于注视的主动式AI辅助儿童图画探索

Zekun Wu, Man Su, Huiyong Li, Tomohiro Nagashima, Anna Maria Feit

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

AI总结 提出Ollie系统,利用儿童注视估计注意力并触发LLM描述相关图画区域,实验表明注视辅助比随机辅助更有效维持注意力并引导探索。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.25550 2026-06-25 cs.SE 新提交 86%

On the Viability of Requirements Generation From Code: An Experience Report

从代码生成需求的可行性:经验报告

Alexander Korn, Jone Bartel, Max Unterbusch, Andreas Vogelsang

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

AI总结 本文通过实验评估基于LLM和RAG的代理方法从源代码生成需求,发现LLM无法可靠生成未实现需求、高质量需求或引入需求气味,且单一人工难以检测气味,表明该方法尚不可行。

Comments Accepted for publication at the 13th International Workshop on Artificial Intelligence and Requirements Engineering (AIRE'26)

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.13317 2026-06-25 cs.CL cs.AI cs.CY cs.LG cs.SI 版本更新 86%

Paid Voices vs. Public Feeds: Interpretable Cross-Platform Theme-Based Analysis of Climate Discourse

付费声音 vs. 公共信息流:可解释的跨平台主题式气候话语分析

Samantha Sudhoff, Pranav Perumal, Zhaoqing Wu, Tunazzina Islam

机构 * Department of Computer Science, Purdue University(普渡大学计算机科学系)

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

AI总结 提出可解释的主题发现流程,通过语义聚类和LLM标注,比较Meta付费广告与Bluesky公共帖子中的气候话语,发现两者在主题、语气和焦点上存在系统性差异。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.18276 2026-06-18 cs.MA cs.SI physics.soc-ph 新提交 86%

Characterizing Opinion Evolution of Networked LLMs

表征网络化大语言模型的意见演化

Caleb Probine, Yigit Ege Bayiz, Filippos Fotiadis, Samuel Li, Yunhao Yang, Ufuk Topcu

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

AI总结 研究经典意见动力学模型能否描述多智能体系统中大语言模型(LLM)的意见传播,发现引入偏置项可显著提升建模精度,将平均意见误差降低高达88%。

Comments 19 pages, 2 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.01694 2026-05-25 cs.HC 86%

Beyond the Single Turn: Reframing Refusals as Dynamic Experiences Embedded in the Context of Mental Health Support Interactions with LLMs

超越单轮交互:将拒绝重新定义为嵌入心理健康支持互动情境的动态体验

Ningjing Tang, Alice Qian, Qiaosi Wang, Esther Howe, Blake Bullwinkel, Paola Pedrelli, Jina Suh, Hoda Heidari, Hong Shen

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

AI总结 通过混合方法研究,揭示LLM在心理健康支持中的拒绝行为是多阶段动态体验,并提出多阶段评估框架和设计建议。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.20500 2026-05-21 cs.SE 86%

A Multi-Layer Testing Framework for Automated Data Quality Assurance in Cloud-Native ELT Pipelines

面向云原生ELT流水线的多层测试框架:自动化数据质量保障

Ismail Gargouri, Hassan Reza

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

AI总结 本文提出一种多层测试框架,结合 orchestration 层验证、dbt 声明性测试、LLM 生成的语义测试以及 DuckDB 与 Snowflake 之间的跨存储一致性检查,通过 Apache Airflow 协调,显著提升了数据质量验证的覆盖率和效率。

Comments 11 pages, 5 figures, 3 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.06996 2026-05-20 cs.NE 86%

Large Language Model-Driven Full-Component Evolution of Adaptive Large Neighborhood Search

基于大语言模型的自适应大邻域搜索全组件演化

Shaohua Yu, Tianyu Chen, Linyan Liu, Jakob Puchinger

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

AI总结 本文提出了一种闭环的大语言模型驱动的演化框架,通过解耦自适应大邻域搜索(ALNS)并自动重建其所有组件,提升了ALNS在生产物流优化中的适应性和效率。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.00458 2026-05-12 cs.SE 86%

LDMDroid: Leveraging LLMs for Detecting Data Manipulation Errors in Android Apps

LDMDroid:利用LLM检测Android应用中的数据操纵错误

Xiangyang Xiao, Huaxun Huang, Rongxin Wu

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

AI总结 本文提出利用LLM开发LDMDroid框架,通过状态感知过程生成UI事件序列以提高数据操纵功能触发成功率,并利用视觉特征识别数据状态变化,有效检测数据操纵错误。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.06216 2026-05-08 cs.CL cs.AI cs.LG 86%

TIDE: Every Layer Knows the Token Beneath the Context

TIDE:每层都知晓上下文中的token

Ajay Jaiswal, Lauren Hannah, Han-Byul Kim, Duc Hoang, Mehrdad Farajtabar, Minsik Cho

机构 * Apple(苹果公司)

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

AI总结 TIDE通过引入EmbeddingMemory解决LLM中token身份单次注入导致的稀有词问题和上下文坍缩问题,提升多语言模型和下游任务性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.05509 2026-05-08 cs.CR 86%

WAAA! Web Adversaries Against Agentic Browsers

WAAA! 网络对抗与代理浏览器

Sohom Datta, Alex Nahapetyan, William Enck, Alexandros Kapravelos

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

AI总结 本文提出首个针对代理浏览器的网络威胁模型,识别20种攻击类型,展示代理浏览器在传统和LLM威胁下的五种主要失效模式,强调需重新设计代理浏览器。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.06617 2026-03-27 eess.SP 86%

Teaching large language models to see in radar: aspect-distributed prototypes for few-shot HRRP ATR

教大语言模型‘看’雷达:面向少样本HRRP ATR的视角分布原型

De Bi, Chengbai Xu, Lingfeng Chen, Panhe Hu

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

AI总结 本文提出视角分布原型策略,提升少样本条件下雷达HRRP目标识别的视角鲁棒性,实验表明优于现有基准。

Comments This paper is a preprint of a paper submitted to the IET International Radar Conference (IRC 2025) and is subject to Institution of Engineering and Technology Copyright. If accepted, the copy of recordwill be available at IET Digital Library

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.00229 2026-02-09 cs.HC 86%

When and How to Integrate Multimodal Large Language Models in College Psychotherapy: Perspectives from Multi-stakeholders

何时以及如何将多模态大语言模型整合到大学生心理治疗中:来自多利益相关者的视角

Jiyao Wang, Youyu Sheng, Qihang He, Zian Zhang, Haolong Hu, Yumei Jing, Dengbo He

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

AI总结 本研究探讨了多模态大语言模型在大学生心理治疗中的整合时机与方式,指出其作为辅助工具的作用,并揭示了用户接受度受社交身份和相对地位影响的关键因素。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.05864 2026-02-06 cs.HC 86%

Prompting Destiny: Negotiating Socialization and Growth in an LLM-Mediated Speculative Gameworld

提示命运:在LLM中介的推测游戏世界中协商社会化与成长

Mandi Yang, Zhiqi Gao, Yibo Meng, Dongyijie Primo Pan

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

AI总结 本文提出了一款LLM中介的推测游戏,通过四季结构探讨社会化过程中道德责任与教育角色定位的反思机制,揭示了开放性表达与持续参与间的张力。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.17899 2026-02-03 cs.NE 86%

Evolving Interdependent Operators with Large Language Models for Multi-Objective Combinatorial Optimization

利用大语言模型进化相互依赖的算子用于多目标组合优化

Junhao Qiu, Xin Chen, Liang Ge, Liyong Lin, Zhichao Lu, Qingfu Zhang

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

AI总结 本文提出E2OC框架,利用大语言模型进化相互依赖的算子,提升多目标组合优化的性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.03826 2026-01-08 cs.CV 86%

FairT2I: Mitigating Social Bias in Text-to-Image Generation via Large Language Model-Assisted Detection and Attribute Rebalancing

FairT2I: 通过大型语言模型辅助的检测与属性再平衡缓解文本到图像生成中的社会偏见

Jinya Sakurai, Yuki Koyama, Issei Sato

机构 * The University of Tokyo(东京大学)

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

AI总结 FairT2I通过大型语言模型辅助检测与属性再平衡,有效缓解文本到图像生成中的社会偏见问题。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.06468 2025-11-11 cs.HC 86%

Towards Attention-Aware Large Language Models: Integrating Real-Time Eye-Tracking and EEG for Adaptive AI Responses

Dan Zhang

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

Comments 9 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.11022 2025-09-29 cs.SE cs.AI cs.CL cs.CR cs.LG 86%

Security Degradation in Iterative AI Code Generation -- A Systematic Analysis of the Paradox

Shivani Shukla, Himanshu Joshi, Romilla Syed

机构 * Department of Analytics and Information Systems(分析与信息系统系) University of San Francisco(旧金山大学) Department of Applied AI and Industry Innovation(应用人工智能与产业创新系) Vector Institute for Artificial Intelligence(人工智能研究院) Department of Management Science and Information Systems(管理科学与信息系统系) University of Massachusetts Boston(马萨诸塞大学波士顿分校)

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

Comments Keywords - Large Language Models, Security Vulnerabilities, AI-Generated Code, Iterative Feedback, Software Security, Secure Coding Practices, Feedback Loops, LLM Prompting Strategies

详情

展开后加载摘要…

URL PDF HTML 收藏
2402.06071 2025-08-14 cs.HC 86%

Keyframer: Empowering Animation Design using Large Language Models

Tiffany Tseng, Ruijia Cheng, Jeffrey Nichols

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2408.04123 2025-07-18 cs.HC 86%

Knowledge-based Emotion Recognition using Large Language Models

Bin Han, Cleo Yau, Su Lei, Jonathan Gratch

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

Comments 9 pages, 5 figures, 3 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.23694 2025-07-01 cs.HC 86%

If You Had to Pitch Your Ideal Software -- Evaluating Large Language Models to Support User Scenario Writing for User Experience Experts and Laypersons

Patrick Stadler, Christopher Lazik, Christopher Katins, Thomas Kosch

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.08511 2025-06-11 q-bio.NC 86%

The Predictive Brain: Neural Correlates of Word Expectancy Align with Large Language Model Prediction Probabilities

Nikola Kölbl, Konstantin Tziridis, Andreas Maier, Thomas Kinfe, Ricardo Chavarriaga, Achim Schilling, Patrick Krauss

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.11932 2025-06-10 cs.LG cs.AI cs.CL 86%

Unveiling and Addressing Pseudo Forgetting in Large Language Models

Huashan Sun, Yizhe Yang, Yinghao Li, Jiawei Li, Yang Gao

机构 * School of Computer Science and Technology, Beijing Institute of Technology(计算机科学与技术学院,北京理工大学)

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

Comments ACL 2025 Findings

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.03728 2025-06-05 eess.SP 86%

Spatiotemporal Prediction of Electric Vehicle Charging Load Based on Large Language Models

Hang Fan, Mingxuan Li, Jingshi Cui, Zuhan Zhang, Wencai Run, Dunnan Liu

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.08763 2025-04-15 cs.IR cs.AI cs.CL cs.LG 86%

WebMap -- Large Language Model-assisted Semantic Link Induction in the Web

Shiraj Pokharel, Georg P. Roßrucker, Mario M. Kubek

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

Comments 11 pages, 3 figures, accepted at the 2024 24th International Conference on Innovations for Community Services (I4CS), June 12 - 14, Maastricht, The Netherlands, 2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2501.12469 2025-03-18 cs.PF cs.DC 86%

An Empirical Characterization of Outages and Incidents in Public Services for Large Language Models

Xiaoyu Chu, Sacheendra Talluri, Qingxian Lu, Alexandru Iosup

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

Journal ref 16th ACM/SPEC International Conference on Performance Engineering (ICPE 2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2403.19762 2024-11-26 q-bio.BM 86%

IDP-Bert: Predicting Properties of Intrinsically Disordered Proteins (IDP) Using Large Language Models

Parisa Mollaei, Danush Sadasivam, Chakradhar Guntuboina, Amir Barati Farimani

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

Comments 22 pages, 5 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2402.14086 2024-10-29 cs.CL cs.AI cs.LG 86%

LexC-Gen: Generating Data for Extremely Low-Resource Languages with Large Language Models and Bilingual Lexicons

Zheng-Xin Yong, Cristina Menghini, Stephen H. Bach

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

Comments EMNLP Findings 2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2409.13393 2024-09-23 cs.RO 86%

Hey Robot! Personalizing Robot Navigation through Model Predictive Control with a Large Language Model

Diego Martinez-Baselga, Oscar de Groot, Luzia Knoedler, Javier Alonso-Mora, Luis Riazuelo, Luis Montano

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

详情

展开后加载摘要…

URL PDF HTML 收藏