语言大模型 / LLM - arXivDaily 专题

2307.03917 2023-10-03 eess.AS cs.CL cs.SD 89%

On decoder-only architecture for speech-to-text and large language model integration

Jian Wu, Yashesh Gaur, Zhuo Chen, Long Zhou, Yimeng Zhu, Tianrui Wang, Jinyu Li, Shujie Liu, Bo Ren, Linquan Liu, Yu Wu

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

2307.04172 2023-10-02 cs.CL cs.SD eess.AS 89%

Can Generative Large Language Models Perform ASR Error Correction?

Rao Ma, Mengjie Qian, Potsawee Manakul, Mark Gales, Kate Knill

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

2305.03701 2023-09-29 cs.CV cs.AI 89%

LMEye: An Interactive Perception Network for Large Language Models

Yunxin Li, Baotian Hu, Xinyu Chen, Lin Ma, Yong Xu, Min Zhang

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

Comments working in progress

2309.15088 2023-09-27 cs.IR cs.CL 89%

RankVicuna: Zero-Shot Listwise Document Reranking with Open-Source Large Language Models

Ronak Pradeep, Sahel Sharifymoghaddam, Jimmy Lin

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

2309.11000 2023-09-21 cs.CL cs.SD eess.AS 89%

Towards Joint Modeling of Dialogue Response and Speech Synthesis based on Large Language Model

Xinyu Zhou, Delong Chen, Yudong Chen

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

2309.06490 2023-09-14 cs.CL 89%

Leveraging Large Language Models for Automated Dialogue Analysis

Sarah E. Finch, Ellie S. Paek, Jinho D. Choi

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

Comments Accepted to SIGDIAL 2023

2308.16529 2023-09-01 cs.RO cs.AI cs.HC 89%

Developing Social Robots with Empathetic Non-Verbal Cues Using Large Language Models

Yoon Kyung Lee, Yoonwon Jung, Gyuyi Kang, Sowon Hahn

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

Journal ref In Proceedings of 2023 IEEE International Conference on Robot & Human Interactive Communication (RO-MAN)

2308.03099 2023-08-23 cs.CL cs.SE 89%

LARCH: Large Language Model-based Automatic Readme Creation with Heuristics

Yuta Koreeda, Terufumi Morishita, Osamu Imaichi, Yasuhiro Sogawa

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

Comments This is a pre-print of a paper accepted at CIKM'23 Demo. Refer to the DOI URL for the original publication

Journal ref In Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, October 21-25, 2023, Birmingham, United Kingdom. ACM, New York, NY, USA, 5 pages

2303.10130 2023-08-22 econ.GN cs.AI cs.CY q-fin.EC 89%

GPTs are GPTs: An Early Look at the Labor Market Impact Potential of Large Language Models

Tyna Eloundou, Sam Manning, Pamela Mishkin, Daniel Rock

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

2308.08102 2023-08-17 cs.HC cs.AI cs.SE 89%

ChatLogo: A Large Language Model-Driven Hybrid Natural-Programming Language Interface for Agent-based Modeling and Programming

John Chen, Uri Wilensky

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

Comments Constructionism 2023 Conference

2307.09793 2023-07-20 cs.DL cs.CL 89%

On the Origin of LLMs: An Evolutionary Tree and Graph for 15,821 Large Language Models

Sarah Gao, Andrew Kean Gao

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

Comments 14 pages, 6 figures, 1 table

2209.12106 2023-06-21 cs.CL 89%

Moral Mimicry: Large Language Models Produce Moral Rationalizations Tailored to Political Identity

Gabriel Simmons

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

Comments 16 pgs incl. references, 8 figures

2305.07667 2023-06-01 cs.AI cs.HC 89%

Davinci the Dualist: the mind-body divide in large language models and in human learners

Iris Berent, Alexzander Sansiveri

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

2305.16917 2023-05-29 cs.CL 89%

Large Language Models Are Partially Primed in Pronoun Interpretation

Suet-Ying Lam, Qingcheng Zeng, Kexun Zhang, Chenyu You, Rob Voigt

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

Comments Accepted at Findings of ACL 2023

2211.15718 2023-05-29 cs.CL 89%

Contrastive Novelty-Augmented Learning: Anticipating Outliers with Large Language Models

Albert Xu, Xiang Ren, Robin Jia

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

Comments ACL 2023

2304.07830 2023-05-05 cs.CL cs.SD eess.AS 89%

The language of sounds unheard: Exploring musical timbre semantics of large language models

Kai Siedenburg, Charalampos Saitis

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

Comments 12 pages, 3 figures

2303.15473 2023-03-29 cs.HC cs.AI cs.SY eess.SY 89%

Can Large Language Models assist in Hazard Analysis?

Simon Diemert, Jens H Weber

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

2303.06074 2023-03-13 cs.CL 89%

Susceptibility to Influence of Large Language Models

Lewis D Griffin, Bennett Kleinberg, Maximilian Mozes, Kimberly T Mai, Maria Vau, Matthew Caldwell, Augustine Marvor-Parker

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

Comments 24 pages, 6 figures, 7 tables, 53 references

2509.10830 2026-03-20 cs.HC 89%

The Siren Song of LLMs: How Users Perceive and Respond to Dark Patterns in Large Language Models

大语言模型的 sirensong：用户如何感知和回应大语言模型中的黑暗模式

Yike Shi, Qing Xiao, Qing Hu, Hong Shen, Hua Shen

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

AI总结研究探讨用户如何感知和回应大语言模型中的黑暗模式，通过场景研究发现对话中的操控性行为影响用户响应，并提出设计、倡导和治理的建议以保护用户自主权。

Comments 23 pages, 7 figures. Accepted at CHI 2026 (ACM Conference on Human Factors in Computing Systems), Barcelona, Spain. Project website: https://llm-dark-pattern.com

Journal ref In Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems (CHI '26), April 13-17, 2026, Barcelona, Spain. ACM, New York, NY, USA, 23 pages

2601.01954 2026-01-06 cs.SE 89%

Reporting LLM Prompting in Automated Software Engineering: A Guideline Based on Current Practices and Expectations

报告LLM提示在自动化软件工程中的使用：基于当前实践和期望的指南

Alexander Korn, Lea Zaruchas, Chetan Arora, Andreas Metzger, Sven Smolka, Fanyu Wang, Andreas Vogelsang

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

AI总结本文提出了一项基于当前实践和期望的指南，旨在提高LLM在自动化软件工程中的透明度、可重复性和方法学严谨性。

Comments To be published at The 3rd ACM International Conference on AI Foundation Models and Software Engineering FORGE 2026

2604.01489 2026-06-05 cs.LG cs.AI cs.DC cs.PF cs.SE 89%

CuTeGen: An LLM-Based Agentic Framework for Generation and Optimization of High-Performance GPU Kernels using CuTe

CuTeGen: 基于LLM的代理框架用于使用CuTe生成和优化高性能GPU内核

Tara Saba, Zhiyang Chen, Jikai Jason Li, Anne Ouyang, Xujie Si, Fan Long

机构 * Department of Computer Science, University of Toronto（计算机科学系，多伦多大学）

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

AI总结本文提出CuTeGen，一种基于LLM的代理框架，通过CuTe抽象层实现GPU内核的生成和优化，通过结构化生成-测试-优化工作流，在标准基准测试中实现了比PyTorch快1.71倍的速度提升，并在生成成本相近的情况下优于现有代理基线CudaForge。

2606.00308 2026-06-02 cs.SE cs.AI cs.LG 89%

How Generation Architecture Shapes Code Complexity in Multi-Agent LLM Systems: A Paired Study on HumanEval

生成架构如何塑造多智能体LLM系统中的代码复杂度：基于HumanEval的配对研究

Nazmus Ashrafi

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

AI总结通过配对实验比较六种多智能体架构在HumanEval上的代码复杂度，发现架构复杂度与功能正确性无正相关，最简架构在准确率上持平或超越复杂架构。

Comments 16 pages, 7 figures, 7 tables

2604.21251 2026-05-18 cs.LG cs.AI 89%

CAP: Controllable Alignment Prompting for Unlearning in LLMs

CAP：用于大语言模型中去学习的可控对齐提示

Zhaokun Wang, Jinyu Guo, Jingwen Pu, Hongli Pu, Meng Yang, Xunlei Chen, Jie Ou, Wenyi Li, Guangchun Luo, Wenhong Tian

机构 * School of Information and Software Engineering, University of Electronic Science and Technology of China（电子科技大学信息与软件学院）

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

AI总结本文提出CAP框架，通过强化学习将去学习过程转化为可学习的提示优化，实现可控的去学习，无需更新模型参数，解决了现有方法的计算成本高、遗忘边界不可控等问题。

Comments Accpeted to ACL 2026 Main Conference

2510.01685 2026-05-11 cs.CL cs.AI 89%

How Do Language Models Compose Functions?

语言模型如何组合函数？

Apoorv Khandelwal, Ellie Pavlick

机构 * Department of Computer Science（计算机科学系）

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

AI总结研究语言模型在解决两跳事实回忆任务时的组合机制，发现现代LLM存在组合性差距，通过分析残差流发现两种处理机制，并发现嵌入空间几何与所用机制密切相关。

2604.05242 2026-04-17 cs.CL cs.AI cs.CR 89%

XMark: Reliable Multi-Bit Watermarking for LLM-Generated Texts

XMark：用于LLM生成文本的可靠多比特水印

Jiahao Xu, Rui Hu, Olivera Kotevska, Zikai Zhang

机构 * University of Nevada, Reno（内华达大学林肯分校）； Oak Ridge National Laboratory（橡树岭国家实验室）

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

AI总结 XMark通过改进编码器和解码器实现高效多比特水印，提升解码准确性并保持文本质量，在多种下游任务中表现优于现有方法。

Comments Accepted by ACL 2026 as a main conference paper

2601.05542 2026-01-12 cs.SE cs.AI cs.LG 89%

Understanding LLM-Driven Test Oracle Generation

理解由大语言模型驱动的测试 oracle 生成

Adam Bodicoat, Gunel Jahangirova, Valerio Terragni

机构 * University of Auckland（奥克兰大学）； King's College London（伦敦国王学院）

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

AI总结本文研究了大语言模型在生成测试 oracle 以暴露软件故障中的有效性，探讨了提示策略和上下文输入对 oracle 质量的影响。

Comments Accepted for presentation at the 2nd ACM/IEEE International Conference on AI-powered Software (AIware 2025)

Journal ref Proc. 2nd ACM/IEEE International Conference on AI-powered Software (AIware 2025), 2025

2406.10707 2024-06-18 cs.DC cs.LG 89%

DataStates-LLM: Lazy Asynchronous Checkpointing for Large Language Models

Avinash Maurya, Robert Underwood, M. Mustafa Rafique, Franck Cappello, Bogdan Nicolae

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

Comments Published at HPDC '24: The 33rd International Symposium on High-Performance Parallel and Distributed Computing. Source code at https://github.com/DataStates/datastates-llm

2402.16896 2024-03-08 cs.CR cs.LG cs.SE 89%

On Trojan Signatures in Large Language Models of Code

Aftab Hussain, Md Rafiqul Islam Rabin, Mohammad Amin Alipour

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

Comments This work has been accepted at the International Conference on Learning Representations 2024 Workshop on Secure and Trustworthy Large Language Models, SeT LLM @ ICLR 2024 (Vienna, Austria)

2601.20238 2026-08-17 econ.GN q-fin.EC 版本更新 89%

Large Language Models Polarize Ideologically but Moderate Affectively in Online Political Discourse

大型语言模型在在线政治讨论中加剧意识形态分歧但缓和情感对立

Gavin Wang, Srinaath Anbudurai, Oliver Sun, Xitong Li, Lynn Wu

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

AI总结大型语言模型在在线政治讨论中加剧意识形态分歧，但减少了情感对立，挑战了极端与不文明行为共存的假设。

2608.07505 2026-08-12 cs.CY cs.HC 版本更新 89%

Position: We Need Large Language Models Optimized For Our Well-Being

立场：我们需要针对人类福祉优化的大语言模型

Ashton Anderson, Harsh Kumar, Louis Tay, Karina Vold

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

AI总结本文指出大语言模型因追求即时认可出现谄媚问题，提出需开发针对长期福祉结果优化的可选大语言模型福祉模式，明确其设计的三大核心张力。

Comments Accepted to the ICML 2026 Position Paper Track

1. 其他LLM 12145 篇

On decoder-only architecture for speech-to-text and large language model integration

Can Generative Large Language Models Perform ASR Error Correction?

LMEye: An Interactive Perception Network for Large Language Models

RankVicuna: Zero-Shot Listwise Document Reranking with Open-Source Large Language Models

Towards Joint Modeling of Dialogue Response and Speech Synthesis based on Large Language Model

Leveraging Large Language Models for Automated Dialogue Analysis

Developing Social Robots with Empathetic Non-Verbal Cues Using Large Language Models

LARCH: Large Language Model-based Automatic Readme Creation with Heuristics

GPTs are GPTs: An Early Look at the Labor Market Impact Potential of Large Language Models

ChatLogo: A Large Language Model-Driven Hybrid Natural-Programming Language Interface for Agent-based Modeling and Programming

On the Origin of LLMs: An Evolutionary Tree and Graph for 15,821 Large Language Models

Moral Mimicry: Large Language Models Produce Moral Rationalizations Tailored to Political Identity

Davinci the Dualist: the mind-body divide in large language models and in human learners

Large Language Models Are Partially Primed in Pronoun Interpretation

Contrastive Novelty-Augmented Learning: Anticipating Outliers with Large Language Models

The language of sounds unheard: Exploring musical timbre semantics of large language models

Can Large Language Models assist in Hazard Analysis?

Susceptibility to Influence of Large Language Models

The Siren Song of LLMs: How Users Perceive and Respond to Dark Patterns in Large Language Models

Reporting LLM Prompting in Automated Software Engineering: A Guideline Based on Current Practices and Expectations

CuTeGen: An LLM-Based Agentic Framework for Generation and Optimization of High-Performance GPU Kernels using CuTe

How Generation Architecture Shapes Code Complexity in Multi-Agent LLM Systems: A Paired Study on HumanEval

CAP: Controllable Alignment Prompting for Unlearning in LLMs

How Do Language Models Compose Functions?

XMark: Reliable Multi-Bit Watermarking for LLM-Generated Texts

Understanding LLM-Driven Test Oracle Generation

DataStates-LLM: Lazy Asynchronous Checkpointing for Large Language Models

On Trojan Signatures in Large Language Models of Code

Large Language Models Polarize Ideologically but Moderate Affectively in Online Political Discourse

Position: We Need Large Language Models Optimized For Our Well-Being