语言大模型 / LLM - arXivDaily 专题

2510.12080 2025-10-15 cs.AI 90%

Evaluating the Quality of Randomness and Entropy in Tasks Supported by Large Language Models

Rabimba Karanjai, Yang Lu, Ranjith Chodavarapu, Lei Xu, Weidong Shi

机构 * University Of Houston（休斯敦大学）； Kent State University（肯特州立大学）

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

2506.14973 2025-06-19 eess.AS cs.AI 90%

Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition

Jiamin Xie, Ju Lin, Yiteng Huang, Tyler Vuong, Zhaojiang Lin, Zhaojun Yang, Peng Su, Prashant Rawat, Sangeeta Srivastava, Ming Sun, Florian Metze

机构 * Center for Robust Speech Systems (CRSS)（鲁棒语音系统中心）

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

Comments Accepted to Interspeech 2025

2506.00001 2025-06-03 cs.AR cs.CL 90%

Enhancing Finite State Machine Design Automation with Large Language Models and Prompt Engineering Techniques

Qun-Kai Lin, Cheng Hsu, Tian-Sheuan Chang

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

Comments published in 2024 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS 2024)

2504.20469 2025-04-30 cs.CL cs.CY 90%

Fane at SemEval-2025 Task 10: Zero-Shot Entity Framing with Large Language Models

Enfa Fane, Mihai Surdeanu, Eduardo Blanco, Steven R. Corman

机构 * University of Arizona（亚利桑那大学）； Arizona State University（亚利桑那州立大学）

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

Comments Accepted to The 19th International Workshop on Semantic Evaluation (Semeval 2025)

2504.05570 2025-04-09 cs.CL 90%

Can Large Language Models Match Tutoring System Adaptivity? A Benchmarking Study

Conrad Borchers, Tianze Shou

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

Comments Accepted as full paper to the 26th International Conference on Artificial Intelligence in Education (AIED 2025)

2405.15614 2025-02-14 cs.CR cs.AI cs.SE 90%

Harnessing Large Language Models for Software Vulnerability Detection: A Comprehensive Benchmarking Study

Karl Tamberg, Hayretdin Bahsi

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

2306.16564 2024-12-20 cs.CL stat.ML 90%

Pareto Optimal Learning for Estimating Large Language Model Errors

Theodore Zhao, Mu Wei, J. Samuel Preston, Hoifung Poon

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

Journal ref Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024

2412.11878 2024-12-17 cs.CL 90%

Using Instruction-Tuned Large Language Models to Identify Indicators of Vulnerability in Police Incident Narratives

Sam Relins, Daniel Birks, Charlie Lloyd

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

Comments 33 pages, 6 figures Submitted to Journal of Quantitative Criminology

2403.08492 2024-11-21 cs.CL 90%

Rich Semantic Knowledge Enhanced Large Language Models for Few-shot Chinese Spell Checking

Ming Dong, Yujing Chen, Miao Zhang, Hao Sun, Tingting He

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

Comments This paper is accepted by Findings of the Association for Computational Linguistics: ACL 2024

2409.19270 2024-10-01 cs.SD cs.AI eess.AS 90%

OpenSep: Leveraging Large Language Models with Textual Inversion for Open World Audio Separation

Tanvir Mahmud, Diana Marculescu

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

Comments Accepted in EMNLP 2024 Main

2409.09354 2024-09-17 cs.RO cs.AI 90%

PeriGuru: A Peripheral Robotic Mobile App Operation Assistant based on GUI Image Understanding and Prompting with LLM

Kelin Fu, Yang Tian, Kaigui Bian

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

2405.04960 2024-06-18 cs.CL 90%

P-ICL: Point In-Context Learning for Named Entity Recognition with Large Language Models

Guochao Jiang, Zepeng Ding, Yuchen Shi, Deqing Yang

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

2406.04528 2024-06-10 cs.CL 90%

llmNER: (Zero|Few)-Shot Named Entity Recognition, Exploiting the Power of Large Language Models

Fabián Villena, Luis Miranda, Claudio Aracena

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

2310.07170 2023-10-12 cs.CL 90%

PHALM: Building a Knowledge Graph from Scratch by Prompting Humans and a Language Model

Tatsuya Ide, Eiki Murata, Daisuke Kawahara, Takato Yamazaki, Shengzhe Li, Kenta Shinzato, Toshinori Sato

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

2209.08655 2023-02-21 cs.HC cs.AI 90%

Enabling Conversational Interaction with Mobile UI using Large Language Models

Bryan Wang, Gang Li, Yang Li

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

Comments Published as a conference paper at CHI 2023

2210.02441 2022-11-22 cs.CL 90%

Ask Me Anything: A simple strategy for prompting language models

Simran Arora, Avanika Narayan, Mayee F. Chen, Laurel Orr, Neel Guha, Kush Bhatia, Ines Chami, Frederic Sala, Christopher Ré

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

2603.25638 2026-04-03 cs.CL cs.AI cs.CY cs.DL cs.LG 90%

Beyond Via: Analysis and Estimation of the Impact of Large Language Models in Academic Papers

超越Via：分析和估计大语言模型在学术论文中的影响

Mingmeng Geng, Yuhang Dong, Thierry Poibeau

机构 * Laboratoire Lattice（拉蒂斯实验室）

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

AI总结研究通过分析arXiv论文，发现大语言模型影响了学术论文中的词汇使用，如标题中'beyond'和'via'的增加，以及摘要中'the'和'of'的减少，揭示了LLM使用在现实中的异质性和动态性。

Comments Visualization of word usage patterns in arXiv abstracts: https://llm-impact.github.io/

2409.09785 2025-12-02 cs.CL cs.AI cs.LG cs.SD eess.AS 90%

Large Language Model Based Generative Error Correction: A Challenge and Baselines for Speech Recognition, Speaker Tagging, and Emotion Recognition

基于大语言模型的生成性错误校正：语音识别、说话人标注和情感识别的挑战与基线

Chao-Han Huck Yang, Taejin Park, Yuan Gong, Yuanchao Li, Zhehuai Chen, Yen-Ting Lin, Chen Chen, Yuchen Hu, Kunal Dhawan, Piotr Żelasko, Chao Zhang, Yun-Nung Chen, Yu Tsao, Jagadeesh Balam, Boris Ginsburg, Sabato Marco Siniscalchi, Eng Siong Chng, Peter Bell, Catherine Lai, Shinji Watanabe, Andreas Stolcke

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

AI总结本文提出GenSEC挑战，通过大语言模型提升语音识别、说话人标注和情感识别任务的准确性与实用性。

Comments IEEE SLT 2024. The initial draft version has been done in December 2023. Post-ASR Text Processing and Understanding Community and LlaMA-7B pre-training correction model: https://huggingface.co/GenSEC-LLM/SLT-Task1-Llama2-7b-HyPo-baseline

2608.18008 2026-08-19 cs.LG cs.AI 新提交 90%

Policy-Invariant Reward Shaping from LLM Feedback: A Framework for Hybrid RL Agents

基于大语言模型反馈的策略不变奖励塑形：混合强化学习智能体框架

Christophe D. Hounwanou, John Emeka Eze, Yaé U. Gaba

机构 * AI Research and Innovation Nexus for Africa (AIRINA Labs)（非洲AI研究与创新中心（AIRINA实验室））； Sefako Makgatho Health Sciences University (SMU)（塞法科·马加托健康科学大学）； African Center for Advanced Studies (ACAS)（非洲高级研究中心）； African Institute for Mathematical Sciences（非洲数学科学学院）

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

AI总结该研究针对LLM衍生奖励信号的理论模糊问题，提出基于LLM反馈的策略不变奖励塑形框架，将混合架构形式化为目标增强MDP，证明其最优策略集保留保证更强，并通过数值实验验证了结果。

Comments 14 pages

2608.14339 2026-08-17 cs.AI cs.LG 新提交 90%

Clearing the Fog: Towards Installing and Refining Proactive Exploration Capabilities in LLM Agents

消除迷雾：为大语言模型智能体（LLM Agents）安装与优化主动探索能力

Zhizhao Guan, Chen Huang, Ziming Liu, Hongru Liang, Wenqiang Lei, See-Kiong Ng, Tat-Seng Chua, Anthony G Cohn

机构 * Engineering Research Center of Machine Learning and Industry Intelligence（机器学习与产业智能工程研究中心）； National University of Singapore（新加坡国立大学）； University of Leeds（利兹大学）； Sichuan University（四川大学）

专题命中其他LLM ：LLM(title,title_cn)；分类 cs.AI、cs.LG

AI总结该研究针对LLM智能体主动探索能力的两大瓶颈，提出含探索性数据构建、对比信号引导的RL优化的方法，经实验验证其有效性并公开代码。

2608.13742 2026-08-17 cs.SE cs.AI cs.LG 新提交 90%

Does ISO-Grounded NFR Specification Improve LLM Code Generation? A Comparison of Rich and Structured Interventions against a Natural-Language Baseline

基于ISO标准的非功能性需求（NFR）规范是否能提升大语言模型（LLM）的代码生成能力？针对丰富干预方式、结构化干预方式与自然语言基线的对比研究

Joào Pedro Monteiro Pereira, Vinicius Cardoso Garcia

专题命中其他LLM ：LLM(title,title_cn)；分类 cs.AI、cs.LG

AI总结该研究对比了ISO标准下丰富自然语言、结构化JSON与单行基线三种NFR规范对LLM代码生成的影响，发现前者可提升代码静态质量，且语义内容比格式更重要。

Comments 11 pages, 2 figures, Accepted for publication at the 20th Brazilian Symposium on Software Components, Architectures, and Reuse (SBCARS 2026)

2608.12713 2026-08-14 cs.CR cs.AI cs.CL 新提交 90%

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks

追踪来源并检测互补大语言模型水印的篡改

Xiaoyan Feng, Yanjun Zhang, He Zhang, Leo Yu Zhang, Shirui Pan

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

AI总结本研究提出一种互补LLM水印方法，通过嵌入鲁棒与脆弱双信号，实现来源追踪与篡改检测，在两类LLM和两类提示数据集上，其篡改检测率优于现有方法，且保持了良好的归属鲁棒性与困惑度。

Comments 11 pages, 7 figures, 4 tables

2608.11513 2026-08-13 cs.SE cs.AI cs.CL 新提交 90%

Do Influence Tactics Matter? Investigating Prompt Framing Effects in LLM Code Generation

影响策略重要吗？研究大语言模型代码生成中的提示词框架效应

Alex Deaconu, Anubhav Gupta, Manaal Basha, Nicholas Haydu, Gema Rodríguez-Pérez

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

AI总结本研究首次大规模实证探究基于心理学的影响策略诱导的提示词框架对LLM代码生成的影响，发现强调紧迫性的框架会降低代码正确性与安全性，为设计人机交互提供实践见解。

Comments Accepted for publication in Empirical Software Engineering. This is the accepted manuscript version. 37 pages, 3 figures

Journal ref Empirical Software Engineering 32 (2026) 13

2608.06992 2026-08-10 cs.CL cs.AI cs.DB 新提交 90%

GPTKB 2.0: Browsing, Querying, and Auditing a Disambiguated LLM-Derived Knowledge Base

GPTKB 2.0：浏览、查询与审计经消歧的大语言模型衍生知识库

Yujia Hu, Tuan-Phong Nguyen, Simon Razniewski

机构 * ScaDS.AI Dresden/Leipzig（ScaDS.AI德累斯顿/莱比锡）； TU Dresden（德累斯顿工业大学）； Institute for AI, VNU University of Engineering and Technology（越南国家大学工程技术学院人工智能研究所）

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

AI总结该研究推出了可浏览、查询、审计的GPTKB 2.0系统，其为经上下文引导消歧的LLM衍生知识库，规模达3840万条三元组，支持多种查询及实体链接功能，且提供网络演示与离线下载。

Comments 7 pages, 11 figures

2608.05204 2026-08-10 cs.AI cs.LG 版本更新 90%

SkillTrace: Multi-Trace Provenance Auditing for LLM-Agent Skill Reuse

SkillTrace：面向LLM智能体技能复用的多溯源审计

Jialuo Chen, Minghe Wang, Lingqi Jiang, Jianan Ma, Xinhao Deng, Xiaohu Du, Ruixiao Lin, Yunhao Feng, Linkang Du, Jingyi Wang

专题命中其他LLM ：LLM(title,title_cn)；分类 cs.AI、cs.LG

AI总结本文提出SKILLTRACE框架，通过提取三种溯源审计LLM智能体技能复用，在SKILLTRACE-BENCH上取得高指标，野外审计显示其能生成更具操作性的复用审查队列。

2605.03723 2026-07-17 cs.CL cs.AI stat.ME 版本更新 90%

Segmenting Human-LLM Co-authored Text via Change Point Detection

通过变化点检测对人类与大语言模型共同撰写的文本进行分割

Mengchu Li, Jin Zhu, Jinglai Li, Chengchun Shi

机构 * School of Mathematics University of Birmingham（数学系英国伯明翰大学）； Department of Statistics London School of Economics and Political Science（统计系伦敦政治经济学院）

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

AI总结针对大语言模型兴起后区分人类与LLM共同撰写文本的需求，提出类似时间序列变化点检测的算法，开发加权和广义算法，建立最优性，实验表明该方法性能优于现有基线。

2603.15727 2026-07-17 cs.CR cs.AI cs.LG cs.MA cs.SE 版本更新 90%

AgentWorm: Self-Propagating Attacks Across LLM Agent Ecosystems

ClawWorm：针对LLM代理生态系统自主传播的攻击

Yihao Zhang, Zeming Wei, Xiaokun Luan, Chengcan Wu, Zhixin Zhang, Jiangrong Wu, Haolin Wu, Huanran Chen, Jun Sun, Meng Sun

机构 * Peking University（北京大学）； Sun Yat-sen University（中山大学）； Wuhan University（武汉大学）； Tsinghua University（清华大学）； Singapore Management University（新加坡管理学院）

专题命中其他LLM ：LLM(title,title_cn)；分类 cs.AI、cs.LG

AI总结研究提出ClawWorm，首个自主传播的LLM代理框架攻击，通过单条消息实现持久化感染与多跳传播，揭示模型安全姿态差异及防御策略。

2606.22454 2026-06-23 cs.CL cs.AI 新提交 90%

CASPER in the Machine: Insights into Character Variety in LLM-Generated Stories

机器中的CASPER：LLM生成故事中角色多样性的洞察

Anneliese Brei, Abhisheik Sharma, Nicholas Sanaie, Lu Wang, Snigdha Chaturvedi

机构 * UNC Chapel Hill（北卡罗来纳大学教堂山分校）； Georgia Institute of Technology（佐治亚理工学院）； University of Michigan（密歇根大学）

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

AI总结本文借用叙事学定义，从八个维度分析LLM与人类创作故事中角色的刻画，发现两者在角色类型和多样性上既有相似也有差异。

Comments Proceedings of ACL, 2026

2606.20708 2026-06-23 cs.AI cs.CL cs.HC 新提交 90%

Simulated Customers Never Walk Away: Decision Fidelity of LLM User Simulators Measured Against Real Purchase Outcomes

模拟客户永不离开：LLM用户模拟器与实际购买结果的决策保真度

Liang Chen

机构 * Chinese relationship-matchmaking service（中国婚恋服务平台）

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

AI总结本文提出决策保真度概念，通过对比LLM模拟器与真实客户在销售对话中的决策状态，发现模拟器高估非购买者的参与度，低估其拒绝意愿，导致系统偏差。

2606.14155 2026-06-15 cs.LG cs.CL 新提交 90%

Graph-based Target Back-Propagation for Context Adaptation in Multi-LLM Agentic Systems

基于图的目标反向传播用于多LLM智能体系统中的上下文自适应

Tan Zhu, Tong Yao, Kananart Kuwaranancharoen, Amit Singh, Yushang Lai, Deepa Mohan, Shankara Bhargava

机构 * Retail Intelligence, Walmart Global Tech（零售智能，沃尔玛全球技术）

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

AI总结提出GTBP框架，通过图结构反向传播局部目标输出，实现多LLM智能体工作流的上下文自适应，理论保证稳定性，实验优于基线。

1. 其他LLM 12169 篇

Evaluating the Quality of Randomness and Entropy in Tasks Supported by Large Language Models

Thinking in Directivity: Speech Large Language Model for Multi-Talker Directional Speech Recognition

Enhancing Finite State Machine Design Automation with Large Language Models and Prompt Engineering Techniques

Fane at SemEval-2025 Task 10: Zero-Shot Entity Framing with Large Language Models

Can Large Language Models Match Tutoring System Adaptivity? A Benchmarking Study

Harnessing Large Language Models for Software Vulnerability Detection: A Comprehensive Benchmarking Study

Pareto Optimal Learning for Estimating Large Language Model Errors

Using Instruction-Tuned Large Language Models to Identify Indicators of Vulnerability in Police Incident Narratives

Rich Semantic Knowledge Enhanced Large Language Models for Few-shot Chinese Spell Checking

OpenSep: Leveraging Large Language Models with Textual Inversion for Open World Audio Separation

PeriGuru: A Peripheral Robotic Mobile App Operation Assistant based on GUI Image Understanding and Prompting with LLM

P-ICL: Point In-Context Learning for Named Entity Recognition with Large Language Models

llmNER: (Zero|Few)-Shot Named Entity Recognition, Exploiting the Power of Large Language Models

PHALM: Building a Knowledge Graph from Scratch by Prompting Humans and a Language Model

Enabling Conversational Interaction with Mobile UI using Large Language Models

Ask Me Anything: A simple strategy for prompting language models

Beyond Via: Analysis and Estimation of the Impact of Large Language Models in Academic Papers

Large Language Model Based Generative Error Correction: A Challenge and Baselines for Speech Recognition, Speaker Tagging, and Emotion Recognition

Policy-Invariant Reward Shaping from LLM Feedback: A Framework for Hybrid RL Agents

Clearing the Fog: Towards Installing and Refining Proactive Exploration Capabilities in LLM Agents

Does ISO-Grounded NFR Specification Improve LLM Code Generation? A Comparison of Rich and Structured Interventions against a Natural-Language Baseline

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks

Do Influence Tactics Matter? Investigating Prompt Framing Effects in LLM Code Generation

GPTKB 2.0: Browsing, Querying, and Auditing a Disambiguated LLM-Derived Knowledge Base

SkillTrace: Multi-Trace Provenance Auditing for LLM-Agent Skill Reuse

Segmenting Human-LLM Co-authored Text via Change Point Detection

AgentWorm: Self-Propagating Attacks Across LLM Agent Ecosystems

CASPER in the Machine: Insights into Character Variety in LLM-Generated Stories

Simulated Customers Never Walk Away: Decision Fidelity of LLM User Simulators Measured Against Real Purchase Outcomes

Graph-based Target Back-Propagation for Context Adaptation in Multi-LLM Agentic Systems