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 12266 信号源:cs.CL, cs.AI, cs.LG

1. 其他LLM 12266 篇

2510.11151 2025-10-14 cs.CL cs.CR 87%

TypePilot: Leveraging the Scala Type System for Secure LLM-generated Code

Alexander Sternfeld, Andrei Kucharavy, Ljiljana Dolamic

机构 * Institute of Entrepreneurship & Management, HES-SO Le Foyer, Techno-Pôle 1 Sierre, Switzerland(创业与管理学院,HES-SO莱福院,技术园区1,瑞士) Institute of Informatics, HES-SO Techno-Pôle 3 Sierre, Switzerland(信息学院,HES-SO技术园区3,瑞士) Cyber-Defence Campus armasuisse, Science and Technology Thun, Switzerland(网络安全校区,armasuisse,科技,瑞士)

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
2508.17164 2025-08-26 cs.CL 87%

The Impact of Annotator Personas on LLM Behavior Across the Perspectivism Spectrum

Olufunke O. Sarumi, Charles Welch, Daniel Braun, Jörg Schlötterer

机构 * University of Marburg(马尔堡大学) McMaster University(麦马斯特大学) University of Mannheim(曼海姆大学)

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

Comments Accepted at ICNLSP 2025, Odense, Denmark

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.00762 2025-08-04 cs.CL 87%

ITUNLP at SemEval-2025 Task 8: Question-Answering over Tabular Data: A Zero-Shot Approach using LLM-Driven Code Generation

Atakan Site, Emre Hakan Erdemir, Gülşen Eryiğit

机构 * Department of Artificial Intelligence and Data Engineering(人工智能与数据工程系)

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
2507.00657 2025-07-02 cs.HC cs.AI cs.SI 87%

Generative Exaggeration in LLM Social Agents: Consistency, Bias, and Toxicity

Jacopo Nudo, Mario Edoardo Pandolfo, Edoardo Loru, Mattia Samory, Matteo Cinelli, Walter Quattrociocchi

机构 * Sapienza University of Rome(罗马萨皮恩扎大学)

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
2411.11521 2025-06-16 cs.CR cs.LG 87%

Preempting Text Sanitization Utility in Resource-Constrained Privacy-Preserving LLM Interactions

Robin Carpentier, Benjamin Zi Hao Zhao, Hassan Jameel Asghar, Dali Kaafar

机构 * Macquarie University(麦考瑞大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.22867 2025-05-30 cs.CL 87%

GateNLP at SemEval-2025 Task 10: Hierarchical Three-Step Prompting for Multilingual Narrative Classification

Iknoor Singh, Carolina Scarton, Kalina Bontcheva

机构 * Department of Computer Science, University of Sheffield (UK)(计算机科学系,谢菲尔德大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.02074 2025-04-04 cs.HC cs.AI 87%

Trapped by Expectations: Functional Fixedness in LLM-Enabled Chat Search

Jiqun Liu, Jamshed Karimnazarov, Ryen W. White

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
2411.01992 2025-02-24 cs.LG cs.CC 87%

Ask, and it shall be given: On the Turing completeness of prompting

Ruizhong Qiu, Zhe Xu, Wenxuan Bao, Hanghang Tong

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

Comments ICLR 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2308.11236 2025-02-18 cs.RO cs.AI 87%

ROSGPT_Vision: Commanding Robots Using Only Language Models' Prompts

Bilel Benjdira, Anis Koubaa, Anas M. Ali

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

Journal ref Future Generation Computer Systems Volume 12, Issue 12,ISSN: 0167-739X, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.05315 2024-12-10 cs.CL cs.CY 87%

Text Is Not All You Need: Multimodal Prompting Helps LLMs Understand Humor

Ashwin Baluja

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.18209 2024-10-25 cs.CL 87%

CorrectionLM: Self-Corrections with SLM for Dialogue State Tracking

Chia-Hsuan Lee, Hao Cheng, Mari Ostendorf

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.06121 2024-10-10 cs.CL 87%

Less is More: Making Smaller Language Models Competent Subgraph Retrievers for Multi-hop KGQA

Wenyu Huang, Guancheng Zhou, Hongru Wang, Pavlos Vougiouklis, Mirella Lapata, Jeff Z. Pan

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

Comments Accepted by EMNLP 2024 Findings

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.12680 2024-10-07 cs.CL 87%

Measuring Psychological Depth in Language Models

Fabrice Harel-Canada, Hanyu Zhou, Sreya Muppalla, Zeynep Yildiz, Miryung Kim, Amit Sahai, Nanyun Peng

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

Comments EMNLP 2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.06799 2024-09-24 cs.DC cs.CL 87%

LLM-dCache: Improving Tool-Augmented LLMs with GPT-Driven Localized Data Caching

Simranjit Singh, Michael Fore, Andreas Karatzas, Chaehong Lee, Yanan Jian, Longfei Shangguan, Fuxun Yu, Iraklis Anagnostopoulos, Dimitrios Stamoulis

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

Comments ICECS 2024 Camera-Ready

详情

展开后加载摘要…

URL PDF HTML 收藏
2402.10811 2024-06-18 cs.CL cs.CY 87%

Quantifying the Persona Effect in LLM Simulations

Tiancheng Hu, Nigel Collier

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

Comments ACL 2024 Main

详情

展开后加载摘要…

URL PDF HTML 收藏
2403.14719 2024-03-25 cs.CR cs.CV cs.LG 87%

Bypassing LLM Watermarks with Color-Aware Substitutions

Qilong Wu, Varun Chandrasekaran

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
2402.06625 2024-02-12 cs.CL 87%

Understanding the Effects of Iterative Prompting on Truthfulness

Satyapriya Krishna, Chirag Agarwal, Himabindu Lakkaraju

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2307.05074 2023-09-06 cs.IR cs.AI cs.DB 87%

Retrieval-augmented GPT-3.5-based Text-to-SQL Framework with Sample-aware Prompting and Dynamic Revision Chain

Chunxi Guo, Zhiliang Tian, Jintao Tang, Shasha Li, Zhihua Wen, Kaixuan Wang, Ting Wang

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.07444 2026-07-09 cs.ET 新提交 87%

LLM Assisted Verification Assertion Generation: Challenges and Future Directions

大语言模型辅助验证断言生成:挑战与未来方向

Bhabesh Mali, Chandan Karfa

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

AI总结 探讨基于大语言模型辅助验证断言生成的挑战与未来方向,研究如何从设计规范生成 SystemVerilog 断言,提出核心问题并给出解决挑战的指导方针,以实现系统化、质量可控的断言生成。

Comments The paper contains a series of guidelines to generate SystemVerilog assertions using LLM

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.24840 2026-03-27 cs.CV cs.AI cs.CL cs.LG 87%

The LLM Bottleneck: Why Open-Source Vision LLMs Struggle with Hierarchical Visual Recognition

大语言模型的瓶颈:为何开源视觉大语言模型在层级视觉识别上遇到困难

Yuwen Tan, Yuan Qing, Boqing Gong

机构 * Boston University(波士顿大学)

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

AI总结 本文指出开源大语言模型缺乏对视觉世界的层级知识,导致视觉大语言模型在识别如水母鱼但无法识别脊椎动物时存在瓶颈,通过构建六种分类学和四个图像数据集的百万级多项选择视觉问答任务验证了这一问题。

Comments Accepted to CVPR 2026. Project page and code: https://yuanqing-ai.github.io/llm-hierarchy/

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.13606 2026-03-10 q-bio.NC cs.AI cs.CL cs.CV cs.LG 87%

LaVCa: LLM-assisted Visual Cortex Captioning

LaVCa: 基于大语言模型的视觉皮层描述生成

Takuya Matsuyama, Shinji Nishimoto, Yu Takagi

机构 * University of Osaka(大阪大学) National Institute of Information and Communications Technology(信息与通信技术国家研究所) Nagoya Institute of Technology(名古屋技术大学)

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

AI总结 LaVCa利用大语言模型生成视觉皮层体素选择性的详细描述,提升对大脑表示的理解。

Comments Accepted to ICLR 2026. Website: https://sites.google.com/view/lavca-llm/

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.06621 2025-02-11 cs.CL cs.AI cs.LG 87%

LinkQ: An LLM-Assisted Visual Interface for Knowledge Graph Question-Answering

Harry Li, Gabriel Appleby, Ashley Suh

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

Comments Open-source code: https://github.com/mit-ll/linkq

Journal ref H. Li, G. Appleby and A. Suh, "LinkQ: An LLM-Assisted Visual Interface for Knowledge Graph Question-Answering," 2024 IEEE Visualization and Visual Analytics (VIS)

详情

展开后加载摘要…

URL PDF HTML 收藏
2309.13788 2024-04-25 cs.CL cs.AI cs.CR cs.HC cs.LG 87%

Can LLM-Generated Misinformation Be Detected?

Canyu Chen, Kai Shu

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

Comments Accepted to Proceedings of ICLR 2024. 9 pages for main paper, 40 pages including appendix. The code, results, dataset for this paper and more resources on "LLMs Meet Misinformation" have been released on the project website: https://llm-misinformation.github.io/

详情

展开后加载摘要…

URL PDF HTML 收藏
2307.15043 2023-12-22 cs.CL cs.AI cs.CR cs.LG 87%

Universal and Transferable Adversarial Attacks on Aligned Language Models

Andy Zou, Zifan Wang, Nicholas Carlini, Milad Nasr, J. Zico Kolter, Matt Fredrikson

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

Comments Website: http://llm-attacks.org/

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.05216 2026-08-28 cs.IR cs.AI cs.CL 版本更新 87%

Unleashing the Power of LLMs in Dense Retrieval with Query Likelihood Modeling

利用查询似然建模释放大型语言模型在密集检索中的能力

Hengran Zhang, Keping Bi, Jiafeng Guo, Xiaojie Sun, Shihao Liu, Daiting Shi, Dawei Yin, Xueqi Cheng

机构 * CAS Key Lab of Network Data Science and Technology, ICT, CAS(中国科学院网络数据科学与技术重点实验室) University of Chinese Academy of Sciences(中国科学院大学) Baidu Inc(百度公司)

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

AI总结 该研究针对LLM在密集检索中全局信息建模不足的问题,提出含注意力块和文档损坏组件的LLM-QL模型,通过查询似然最大化辅助任务增强检索器主干,在MS MARCO和BEIR数据集上优于其他LLM-based检索器。

Comments Accepted to CIKM 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.07023 2026-08-10 cs.CL cs.AI 新提交 87%

An Agentic Hybrid Top-Down and Bottom-Up Approach to Knowledge Graph Generation

一种用于知识图谱生成的智能体式混合自顶向下与自底向上方法

Emma Jouffroy, Warren Jouanneau, Marc Palyart

机构 * Malt

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

AI总结 针对HR平台的多语言非标准化技能声明问题,提出结合LLM与Wikidata KG的智能体式混合KG生成流水线,可生成可扩展可解释的技能KG。

详情

展开后加载摘要…

URL PDF HTML 收藏
2407.00740 2026-07-23 cs.CL cs.LG 版本更新 87%

LaSEr-Edit: Localized Span-level Error Editing with Energy-based Localization

LaSEr-Edit:基于能量定位的局部跨度级错误编辑

Hye Ryung Son, Saehee Eom, Mooho Song, Jay-Yoon Lee

机构 * Graduate School of Data Science(数据科学研究生院) Seoul National University(首尔国立大学) Georgia Institute of Technology(佐治亚理工学院)

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

AI总结 研究针对大语言模型满足约束问题,提出LaSEr-Edit方法。利用轻量级特定任务的基于能量的模型进行错误定位,提出LaSEr-LLM Edit和LaSEr-EBM Edit两种文本修订方法,实验表明该方法能有效控制文本,多约束下也表现良好。

Comments 38 pages, 7 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.13359 2026-07-21 cs.CL cs.CR cs.LG 版本更新 87%

Sockpuppetting: Jailbreaking LLMs by Combining Prefilling with Optimization

通过结合预填充与优化进行LLM的劫持:

Asen Dotsinski, Panagiotis Eustratiadis

机构 * University of Amsterdam(阿姆斯特丹大学)

专题命中 其他LLM :LLM(title_cn,summary_cn);分类 cs.CL、cs.LG

AI总结 本文提出通过结合预填充与优化的方法提升LLM劫持效果,展示了简单对抗者通过组合预填充变体可提高攻击成功率,并引入混合攻击策略以优化对抗性后缀,提升模型防御需求。

Comments 16 pages, 6 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.11817 2026-06-11 cs.CR cs.AI cs.CL cs.SE 新提交 87%

Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code

语法约束解码可诱使大语言模型生成恶意代码

Yitong Zhang, Shiteng Lu, Jia Li

机构 * College of AI, Tsinghua University(清华大学人工智能学院)

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

AI总结 本文发现语法约束解码(GCD)可被利用发起名为CodeSpear的越狱攻击,使LLM生成恶意代码;并提出安全对齐方法CodeShield,通过生成蜜罐代码防御该攻击。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.01738 2026-06-02 cs.CL cs.AI 87%

THRD: A Training-Free Multi-Turn Defense Framework for Jailbreak Attacks on Large Language Models

THRD:一种针对大语言模型越狱攻击的无训练多轮防御框架

Zhiqing Ma, Zhonghao Xu, Dong Yu, Chen Kang, Changliang Li, Pengyuan Liu

机构 * Beijing Language and Culture University(北京语言大学)

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

AI总结 提出无训练框架THRD,通过显式建模时间风险累积(包括逐轮风险评估、跨轮意图检测、响应评估和决策模块)防御多轮越狱攻击,将攻击成功率降至0.2-4.0%且模型效用损失小于1.5%。

详情

展开后加载摘要…

URL PDF HTML 收藏