语言大模型 / LLM - arXivDaily 专题

2509.25593 2025-10-01 cs.AI cs.CL cs.HC cs.IR 86%

Causal Autoencoder-like Generation of Feedback Fuzzy Cognitive Maps with an LLM Agent

Akash Kumar Panda, Olaoluwa Adigun, Bart Kosko

机构 * Department of Electrical and Computer Engineering（电气与计算机工程系）； University of Southern California（南加州大学）； School of Computing and Information Sciences（计算与信息科学学院）； Florida International University（佛罗里达国际大学）

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

Comments 8 pages, 4 figures

2505.02091 2025-09-29 cs.CL cs.LG 86%

LLM-OptiRA: LLM-Driven Optimization of Resource Allocation for Non-Convex Problems in Wireless Communications

Xinyue Peng, Yanming Liu, Yihan Cang, Chaoqun Cao, Ming Chen

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

Comments 6 pages,4 figures

2503.07513 2025-09-25 cs.CL cs.AI 86%

Language Models Fail to Introspect About Their Knowledge of Language

Siyuan Song, Jennifer Hu, Kyle Mahowald

机构 * Department of Linguistics The University of Texas at Austin（语言学系德克萨斯大学奥斯汀分校）； Department of Cognitive Science Johns Hopkins University（认知科学系约翰霍普金斯大学）

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

Comments 23 pages, 10 figures, COLM 2025 camera ready

2509.04507 2025-09-08 cs.CL cs.AI 86%

From Silent Signals to Natural Language: A Dual-Stage Transformer-LLM Approach

Nithyashree Sivasubramaniam

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

2507.14240 2025-09-08 cs.CL cs.AI 86%

HuggingGraph: Understanding the Supply Chain of LLM Ecosystem

Mohammad Shahedur Rahman, Peng Gao, Yuede Ji

机构 * Department of Computer Science and Engineering（计算机科学与工程系）； The University of Texas at Arlington（德克萨斯理工大学）； Department of Computer Science（计算机科学系）； Virginia Tech（弗吉尼亚理工大学）

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

2509.00347 2025-09-03 cs.LG cs.AI 86%

LLM-Driven Policy Diffusion: Enhancing Generalization in Offline Reinforcement Learning

Hanping Zhang, Yuhong Guo

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

2508.14190 2025-08-21 cs.CR cs.CL cs.LG 86%

Two Birds with One Stone: Multi-Task Detection and Attribution of LLM-Generated Text

Zixin Rao, Youssef Mohamed, Shang Liu, Zeyan Liu

机构 * University of Georgia（佐治亚大学）； Egypt-Japan University of Science and Technology（埃及-日本科学技术大学）； University of Louisville（路易斯维尔大学）

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

Comments Securecomm 2025

2508.13124 2025-08-19 cs.CL cs.AI 86%

Spot the BlindSpots: Systematic Identification and Quantification of Fine-Grained LLM Biases in Contact Center Summaries

Kawin Mayilvaghanan, Siddhant Gupta, Ayush Kumar

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

2508.09021 2025-08-13 cs.CR cs.AI cs.LG 86%

Attacks and Defenses Against LLM Fingerprinting

Kevin Kurian, Ethan Holland, Sean Oesch

机构 * Oak Ridge National Laboratory（奥克兰国家实验室）

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

2412.09727 2025-08-04 q-bio.QM cs.AI cs.LG 86%

A Large Sensor Foundation Model Pretrained on Continuous Glucose Monitor Data for Diabetes Management

Junjie Luo, Abhimanyu Kumbara, Mansur Shomali, Rui Han, Anand Iyer, Ritu Agarwal, Gordon Gao

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

2507.21964 2025-07-30 cs.AI cs.LG 86%

Thou Shalt Not Prompt: Zero-Shot Human Activity Recognition in Smart Homes via Language Modeling of Sensor Data & Activities

Sourish Gunesh Dhekane, Thomas Ploetz

机构 * School of Interactive Computing, Georgia Institute of Technology（交互计算学院，佐治亚理工学院）

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

2507.21083 2025-07-30 cs.CL cs.AI 86%

ChatGPT Reads Your Tone and Responds Accordingly -- Until It Does Not -- Emotional Framing Induces Bias in LLM Outputs

Franck Bardol

机构 * Independent Researcher（独立研究者）

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

2505.10774 2025-07-30 cs.LG cs.AI 86%

Context-Aware Probabilistic Modeling with LLM for Multimodal Time Series Forecasting

Yueyang Yao, Jiajun Li, Xingyuan Dai, MengMeng Zhang, Xiaoyan Gong, Fei-Yue Wang, Yisheng Lv

机构 * Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）； University of Chinese Academy of Sciences（中国科学院大学）

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

Comments 13 pages, 2 figures

2507.19334 2025-07-28 cs.LG cs.AI 86%

Doubling Your Data in Minutes: Ultra-fast Tabular Data Generation via LLM-Induced Dependency Graphs

Shuo Yang, Zheyu Zhang, Bardh Prenkaj, Gjergji Kasneci

机构 * Technical University of Munich（慕尼黑技术大学）

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

2507.18153 2025-07-28 cs.LG cs.AI 86%

When Noisy Labels Meet Class Imbalance on Graphs: A Graph Augmentation Method with LLM and Pseudo Label

Riting Xia, Rucong Wang, Yulin Liu, Anchen Li, Xueyan Liu, Yan Zhang

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

2504.11168 2025-07-15 cs.CR cs.AI cs.LG 86%

Bypassing LLM Guardrails: An Empirical Analysis of Evasion Attacks against Prompt Injection and Jailbreak Detection Systems

William Hackett, Lewis Birch, Stefan Trawicki, Neeraj Suri, Peter Garraghan

机构 * Mindgard ； Lancaster University（兰卡斯特大学）

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

Comments 14 pages, 5 figures, 11 tables. To be published in LLMSec 2025

2502.07776 2025-07-15 cs.CL cs.CR cs.LG 86%

Auditing Prompt Caching in Language Model APIs

Chenchen Gu, Xiang Lisa Li, Rohith Kuditipudi, Percy Liang, Tatsunori Hashimoto

机构 * stanford（斯坦福大学）

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

Comments Accepted at ICML 2025

2502.01573 2025-06-26 cs.SE cs.AI cs.LG cs.LO 86%

Next Steps in LLM-Supported Java Verification

Samuel Teuber, Bernhard Beckert

机构 * Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）

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

Comments Accepted to NSE 2025, 1st International Workshop on Neuro-Symbolic Software Engineering (ICSE Workshop), 6 pages, 3 figures

Journal ref in IEEE/ACM International Workshop on Neuro-Symbolic Software Engineering, 2025, pp. 1-4

2505.19675 2025-06-23 cs.CL cs.AI 86%

Calibrating Pre-trained Language Classifiers on LLM-generated Noisy Labels via Iterative Refinement

Liqin Ye, Agam Shah, Chao Zhang, Sudheer Chava

机构 * School of Computational Science \& Engineering Georgia Institute of Technology Atlanta GA USA ； Scheller College of Business Georgia Institute of Technology Atlanta GA USA ； Georgia Institute of Technology

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

Comments Accepted at KDD'25

2503.23243 2025-06-17 cs.CL cs.AI cs.CY 86%

Evaluating how LLM annotations represent diverse views on contentious topics

Megan A. Brown, Shubham Atreja, Libby Hemphill, Patrick Y. Wu

机构 * School of Information University of Michigan（信息学院密歇根大学）； Department of Computer Science American University（计算机科学系美国大学）

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

2506.09998 2025-06-12 cs.LG cs.CL 86%

Flipping Against All Odds: Reducing LLM Coin Flip Bias via Verbalized Rejection Sampling

Tim Z. Xiao, Johannes Zenn, Zhen Liu, Weiyang Liu, Robert Bamler, Bernhard Schölkopf

机构 * The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））； The Chinese University of Hong Kong（香港中文大学）

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

Comments Technical Report v1 (21 pages, 14 figures)

2411.04920 2025-06-05 cs.CL cs.AI cs.DB 86%

Enabling LLM Knowledge Analysis via Extensive Materialization

Yujia Hu, Tuan-Phong Nguyen, Shrestha Ghosh, Simon Razniewski

机构 * ScaDS.AI & TU Dresden（ScaDS.AI及德累斯顿技术大学）； Max Planck Institute for Informatics（马克斯·普朗克信息研究所）； University of Tübingen（图宾根大学）

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

Comments 14 pages, 4 tables, 12 figures

Journal ref ACL 2025

2410.02165 2025-06-05 cs.AI cs.CL 86%

A LLM-Powered Automatic Grading Framework with Human-Level Guidelines Optimization

Yucheng Chu, Hang Li, Kaiqi Yang, Harry Shomer, Hui Liu, Yasemin Copur-Gencturk, Jiliang Tang

机构 * Michigan State University（密歇根州立大学）

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

Comments EDM 2025 Long Paper

2408.03505 2025-06-03 cs.CL cs.AI cs.DC 86%

Optimus: Accelerating Large-Scale Multi-Modal LLM Training by Bubble Exploitation

Weiqi Feng, Yangrui Chen, Shaoyu Wang, Yanghua Peng, Haibin Lin, Minlan Yu

机构 * Harvard University（哈佛大学）； Bytedance（字节跳动）； University of Southern California（南加州大学）

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

2410.11674 2025-06-03 cs.LG cs.CL 86%

LLM-Mixer: Multiscale Mixing in LLMs for Time Series Forecasting

Md Kowsher, Md. Shohanur Islam Sobuj, Nusrat Jahan Prottasha, E. Alejandro Alanis, Ozlem Ozmen Garibay, Niloofar Yousefi

机构 * University of Central Florida（中央佛罗里达大学）； Anymate Me ； Microsoft（微软）

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

Comments Time series forecasting using LLMs

2505.20671 2025-05-28 cs.AI cs.LG 86%

LLM-Guided Reinforcement Learning: Addressing Training Bottlenecks through Policy Modulation

Heng Tan, Hua Yan, Yu Yang

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

2505.14499 2025-05-27 cs.CL cs.AI 86%

Enhanced Multimodal Aspect-Based Sentiment Analysis by LLM-Generated Rationales

Jun Cao, Jiyi Li, Ziwei Yang, Renjie Zhou

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

Comments 15 pages, 2 figures, 6 tables. Accepted by ICONIP2024

2505.00234 2025-05-20 cs.LG cs.CL 86%

Self-Generated In-Context Examples Improve LLM Agents for Sequential Decision-Making Tasks

Vishnu Sarukkai, Zhiqiang Xie, Kayvon Fatahalian

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

2504.10886 2025-04-16 cs.CY cs.AI cs.CL 86%

Exploring Persona-dependent LLM Alignment for the Moral Machine Experiment

Jiseon Kim, Jea Kwon, Luiz Felipe Vecchietti, Alice Oh, Meeyoung Cha

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

Comments Accepted to ICLR 2025 Workshop - BiAlign (Bidirectional Human-AI Alignment)

2503.20623 2025-03-27 cs.CL cs.AI 86%

Collaborative Storytelling and LLM: A Linguistic Analysis of Automatically-Generated Role-Playing Game Sessions

Alessandro Maisto

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

Comments 17 pages

1. 其他LLM 12157 篇

Causal Autoencoder-like Generation of Feedback Fuzzy Cognitive Maps with an LLM Agent

LLM-OptiRA: LLM-Driven Optimization of Resource Allocation for Non-Convex Problems in Wireless Communications

Language Models Fail to Introspect About Their Knowledge of Language

From Silent Signals to Natural Language: A Dual-Stage Transformer-LLM Approach

HuggingGraph: Understanding the Supply Chain of LLM Ecosystem

LLM-Driven Policy Diffusion: Enhancing Generalization in Offline Reinforcement Learning

Two Birds with One Stone: Multi-Task Detection and Attribution of LLM-Generated Text

Spot the BlindSpots: Systematic Identification and Quantification of Fine-Grained LLM Biases in Contact Center Summaries

Attacks and Defenses Against LLM Fingerprinting

A Large Sensor Foundation Model Pretrained on Continuous Glucose Monitor Data for Diabetes Management

Thou Shalt Not Prompt: Zero-Shot Human Activity Recognition in Smart Homes via Language Modeling of Sensor Data & Activities

ChatGPT Reads Your Tone and Responds Accordingly -- Until It Does Not -- Emotional Framing Induces Bias in LLM Outputs

Context-Aware Probabilistic Modeling with LLM for Multimodal Time Series Forecasting

Doubling Your Data in Minutes: Ultra-fast Tabular Data Generation via LLM-Induced Dependency Graphs

When Noisy Labels Meet Class Imbalance on Graphs: A Graph Augmentation Method with LLM and Pseudo Label

Bypassing LLM Guardrails: An Empirical Analysis of Evasion Attacks against Prompt Injection and Jailbreak Detection Systems

Auditing Prompt Caching in Language Model APIs

Next Steps in LLM-Supported Java Verification

Calibrating Pre-trained Language Classifiers on LLM-generated Noisy Labels via Iterative Refinement

Evaluating how LLM annotations represent diverse views on contentious topics

Flipping Against All Odds: Reducing LLM Coin Flip Bias via Verbalized Rejection Sampling

Enabling LLM Knowledge Analysis via Extensive Materialization

A LLM-Powered Automatic Grading Framework with Human-Level Guidelines Optimization

Optimus: Accelerating Large-Scale Multi-Modal LLM Training by Bubble Exploitation

LLM-Mixer: Multiscale Mixing in LLMs for Time Series Forecasting

LLM-Guided Reinforcement Learning: Addressing Training Bottlenecks through Policy Modulation

Enhanced Multimodal Aspect-Based Sentiment Analysis by LLM-Generated Rationales

Self-Generated In-Context Examples Improve LLM Agents for Sequential Decision-Making Tasks

Exploring Persona-dependent LLM Alignment for the Moral Machine Experiment

Collaborative Storytelling and LLM: A Linguistic Analysis of Automatically-Generated Role-Playing Game Sessions