语言大模型 / LLM - arXivDaily 专题

2511.19489 2025-11-26 cs.SE cs.AI 85%

Evolution without an Oracle: Driving Effective Evolution with LLM Judges

无Oracle的进化：通过LLM裁判驱动有效进化

Zhe Zhao, Yuheng Yang, Haibin Wen, Xiaojie Qiu, Zaixi Zhang, Qingfu Zhang

机构 * Stanford University（斯坦福大学）； City University of Hong Kong（香港城市大学）； Princeton University（普林斯顿大学）

专题命中指令微调：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

AI总结本文提出MADE框架，通过问题规范减少LLM反馈噪声，实现无Oracle的进化优化，在软件需求满足和复杂指令跟随任务中取得显著成效。

Comments 14 pages, 5 figures

2511.10229 2025-11-14 cs.CL 85%

LangGPS: Language Separability Guided Data Pre-Selection for Joint Multilingual Instruction Tuning

Yangfan Ye, Xiaocheng Feng, Xiachong Feng, Lei Huang, Weitao Ma, Qichen Hong, Yunfei Lu, Duyu Tang, Dandan Tu, Bing Qin

专题命中指令微调：instruction tuning(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

Comments AAAI2026 Main Track Accepted

2509.02615 2025-11-13 astro-ph.IM cs.AI 85%

Radio Astronomy in the Era of Vision-Language Models: Prompt Sensitivity and Adaptation

Mariia Drozdova, Erica Lastufka, Vitaliy Kinakh, Taras Holotyak, Daniel Schaerer, Slava Voloshynovskiy

机构 * University of Geneva（日内瓦大学）

专题命中指令微调：language model(title,abstract)；pretraining(abstract)；prompting(abstract)；分类 cs.AI

Comments Machine Learning and the Physical Sciences Workshop, NeurIPS 2025

2511.06490 2025-11-11 cs.CV cs.AI 85%

Zooming into Comics: Region-Aware RL Improves Fine-Grained Comic Understanding in Vision-Language Models

Yule Chen, Yufan Ren, Sabine Süsstrunk

机构 * School of Computer and Communication Sciences, EPFL（瑞士联邦理工学院计算机与通信科学学院）； Department of Computer Science and Engineering, Chalmers University of Technology（楚科奇技术大学计算机科学与工程系）； IVRL, EPFL（EPFL智能机器人实验室）

专题命中指令微调：language model(title,abstract)；post-training(abstract)；SFT(abstract)；分类 cs.AI

2510.23595 2025-10-31 cs.AI 85%

Multi-Agent Evolve: LLM Self-Improve through Co-evolution

Yixing Chen, Yiding Wang, Siqi Zhu, Haofei Yu, Tao Feng, Muhan Zhang, Mostofa Patwary, Jiaxuan You

机构 * University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）； Peking University（北京大学）； NVIDIA（英伟达）

专题命中指令微调：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

Comments 29 pages, 4 figures

2510.24331 2025-10-29 cs.LG cs.CV 85%

What do vision-language models see in the context? Investigating multimodal in-context learning

Gabriel O. dos Santos, Esther Colombini, Sandra Avila

机构 * Instituto de Computação, Universidade Estadual de Campinas (UNICAMP)（计算机学院，Campinas州立大学（UNICAMP））

专题命中指令微调：language model(title,abstract)；large language model(abstract)；instruction tuning(abstract)；分类 cs.LG

2510.05024 2025-10-29 cs.LG 85%

Inoculation Prompting: Instructing LLMs to misbehave at train-time improves test-time alignment

Nevan Wichers, Aram Ebtekar, Ariana Azarbal, Victor Gillioz, Christine Ye, Emil Ryd, Neil Rathi, Henry Sleight, Alex Mallen, Fabien Roger, Samuel Marks

专题命中指令微调：prompting(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.LG

Comments v2 Updates references. v3 Updates references; Adds IFEval results; Improves appendix readability; Adds author contributions

2510.23160 2025-10-28 cs.CL 85%

ENTP: Enhancing Low-Quality SFT Data via Neural-Symbolic Text Purge-Mix

Zile Yang, Ling Li, Na Di, Jinlong Pang, Yao Zhou, Hao Cheng, Bo Han, Jiaheng Wei

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州））； University of California, Santa Cruz（加州大学圣克鲁兹分校）； Hong Kong Baptist University（香港 Baptist 大学）

专题命中指令微调：SFT(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

2412.12710 2025-10-28 cs.CL 85%

Enhancing Naturalness in LLM-Generated Utterances through Disfluency Insertion

Syed Zohaib Hassan, Pierre Lison, Pål Halvorsen

专题命中指令微调：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

Comments 8 pages. Limitations, ethical considerations, and references are additional

2510.18250 2025-10-22 cs.AI 85%

ssToken: Self-modulated and Semantic-aware Token Selection for LLM Fine-tuning

Xiaohan Qin, Xiaoxing Wang, Ning Liao, Cancheng Zhang, Xiangdong Zhang, Mingquan Feng, Jingzhi Wang, Junchi Yan

机构 * Shanghai Jiao Tong University（上海交通大学）； Shanghai Innovation Institute（上海创新研究院）

专题命中指令微调：LLM(title)；large language model(abstract)；language model(abstract)；SFT(abstract)

2510.18228 2025-10-22 cs.LG 85%

Towards Fast LLM Fine-tuning through Zeroth-Order Optimization with Projected Gradient-Aligned Perturbations

Zhendong Mi, Qitao Tan, Grace Li Zhang, Zhaozhuo Xu, Geng Yuan, Shaoyi Huang

机构 * Stevens Institute of Technology（史蒂文斯理工学院）； University of Georgia（佐治亚大学）； Technical University of Darmstadt（达姆施塔特技术大学）

专题命中指令微调：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.LG

Comments 10 pages, 5 figures

2510.15993 2025-10-21 q-fin.PM cs.LG q-fin.ST 85%

Aligning Language Models with Investor and Market Behavior for Financial Recommendations

Fernando Spadea, Oshani Seneviratne

机构 * Rensselaer Polytechnic Institute（拉特兰理工学院）

专题命中指令微调：language model(title,abstract)；LLM(abstract)；large language model(abstract)；分类 cs.LG

2510.02569 2025-10-20 cs.CL 85%

Transcribe, Translate, or Transliterate: An Investigation of Intermediate Representations in Spoken Language Models

Tolúlopé Ògúnrèmí, Christopher D. Manning, Dan Jurafsky, Karen Livescu

机构 * Stanford University（斯坦福大学）； Toyota Technological Institute at Chicago（芝加哥丰田技术研究所）

专题命中指令微调：language model(title,abstract)；large language model(abstract)；instruction tuning(abstract)；分类 cs.CL

Comments ASRU 2025

2510.14200 2025-10-17 cs.CL 85%

RLSR: Reinforcement Learning with Supervised Reward Outperforms SFT in Instruction Following

Zhichao Wang, Andy Wong, Ruslan Belkin

机构 * Inflection AI

专题命中指令微调：SFT(title,abstract)；pretraining(abstract)；RLHF(abstract)；分类 cs.CL

2510.09030 2025-10-13 cs.CL 85%

Automated Refinement of Essay Scoring Rubrics for Language Models via Reflect-and-Revise

Keno Harada, Lui Yoshida, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo

机构 * The University of Tokyo（东京大学）

专题命中指令微调：language model(title,abstract)；LLM(abstract)；large language model(abstract)；分类 cs.CL

2510.01454 2025-10-03 cs.CV cs.LG 85%

Data Selection for Fine-tuning Vision Language Models via Cross Modal Alignment Trajectories

Nilay Naharas, Dang Nguyen, Nesihan Bulut, Mohammadhossein Bateni, Vahab Mirrokni, Baharan Mirzasoleiman

机构 * Department of Computer Science, University of California Los Angeles（加州大学洛杉矶分校计算机科学系）； Google Research（谷歌研究）

专题命中指令微调：language model(title,abstract)；large language model(abstract)；instruction tuning(abstract)；分类 cs.LG

Comments 30 pages, 10 figures, 5 tables, link: https://bigml-cs-ucla.github.io/XMAS-project-page/

2503.02296 2025-10-01 cs.AI 85%

Memorize or Generalize? Evaluating LLM Code Generation with Code Rewriting

Lizhe Zhang, Wentao Chen, Li Zhong, Letian Peng, Zilong Wang, Jingbo Shang

机构 * University of California, San Diego（加州大学圣地亚哥分校）

专题命中指令微调：LLM(title)；large language model(abstract)；language model(abstract)；SFT(abstract)

2509.24961 2025-09-30 cs.CL 85%

SemanticShield: LLM-Powered Audits Expose Shilling Attacks in Recommender Systems

Kaihong Li, Huichi Zhou, Bin Ma, Fangjun Huang

机构 * Sun Yat-sen University（中山大学）； University College London（伦敦大学学院）； Qilu University of Technology（青岛科技大学）

专题命中指令微调：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

2509.20805 2025-09-26 cs.CL cs.IR 85%

Few-Shot and Training-Free Review Generation via Conversational Prompting

Genki Kusano

专题命中指令微调：prompting(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

2502.12566 2025-09-22 cs.AI 85%

Exploring the Impact of Personality Traits on LLM Bias and Toxicity

Shuo Wang, Renhao Li, Xi Chen, Yulin Yuan, Derek F. Wong, Min Yang

机构 * University of Macau（澳门大学）； Shenzhen Key Laboratory for High Performance Data Mining, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（深圳高性能数据挖掘重点实验室，深圳先进技术研究院，中国科学院）； Nanyang Technological University（南洋理工大学）； Department of Chinese Language and Literature, University of Macau（中文语言文学系，澳门大学）

专题命中指令微调：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

2509.14943 2025-09-19 cs.CL 85%

Explicit vs. Implicit Biographies: Evaluating and Adapting LLM Information Extraction on Wikidata-Derived Texts

Alessandra Stramiglio, Andrea Schimmenti, Valentina Pasqual, Marieke van Erp, Francesco Sovrano, Fabio Vitali

机构 * DISI Departement of Computer Science and Engineering, University of Bologna（博洛尼亚大学计算机科学与工程系）； Automobili Lamborghini SpA（法拉利公司）； Digital Humanities Advanced Research Center（数字人文高级研究中心）； KNAW Humanities Cluster, DHLab（KNAW 人文集群，DHLab）； ETH Zurich, Collegium Helveticum（苏黎世联邦理工学院，瑞士学院）

专题命中指令微调：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

2506.10943 2025-09-19 cs.LG 85%

Self-Adapting Language Models

Adam Zweiger, Jyothish Pari, Han Guo, Ekin Akyürek, Yoon Kim, Pulkit Agrawal

机构 * Massachusetts Institute of Technology（麻省理工学院）

专题命中指令微调：language model(title,abstract)；large language model(abstract)；SFT(abstract)；分类 cs.LG

2509.12625 2025-09-17 cs.AI 85%

ECG-aBcDe: Overcoming Model Dependence, Encoding ECG into a Universal Language for Any LLM

Yong Xia, Jingxuan Li, YeTeng Sun, Jiarui Bu

专题命中指令微调：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

Comments 14pages, 6 figures

2509.10478 2025-09-16 cs.NI cs.LG cs.SY eess.SY 85%

The LLM as a Network Operator: A Vision for Generative AI in the 6G Radio Access Network

Oluwaseyi Giwa, Michael Adewole, Tobi Awodumila, Pelumi Aderinto

机构 * African Institute for Mathematical Sciences（非洲数学科学研究所）

专题命中指令微调：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.LG

Comments Submitted to Workshop on AI and ML for Next-Generation Wireless Communications and Networking, NeurIPS 2025

2509.06200 2025-09-09 cs.CL 85%

MSLEF: Multi-Segment LLM Ensemble Finetuning in Recruitment

Omar Walid, Mohamed T. Younes, Khaled Shaban, Mai Hassan, Ali Hamdi

机构 * Dept. of Computer Science, Qatar University, Doha, Qatar（计算机科学系，卡塔尔大学，多哈）

专题命中指令微调：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

Comments Accepted in AICCSA 2025

2509.00731 2025-09-03 cs.CL 85%

LLM Encoder vs. Decoder: Robust Detection of Chinese AI-Generated Text with LoRA

Houji Jin, Negin Ashrafi, Armin Abdollahi, Wei Liu, Jian Wang, Ganyu Gui, Maryam Pishgar, Huanghao Feng

机构 * Suzhou University of Technology（苏州科技大学）； University of Southern California（南加州大学）

专题命中指令微调：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

2508.19074 2025-08-27 cs.RO cs.AI cs.PL 85%

An LLM-powered Natural-to-Robotic Language Translation Framework with Correctness Guarantees

ZhenDong Chen, ZhanShang Nie, ShiXing Wan, JunYi Li, YongTian Cheng, Shuai Zhao

机构 * School of Computer Science and Engineering（计算机科学与工程学院）； Sun Yat-Sen University（中山大学）

专题命中指令微调：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

2505.12584 2025-08-27 cs.CL 85%

Improving Multilingual Language Models by Aligning Representations through Steering

Omar Mahmoud, Buddhika Laknath Semage, Thommen George Karimpanal, Santu Rana

机构 * Applied Artificial Intelligence Initiative, Deakin University, Australia（应用人工智能计划，德肯大学，澳大利亚）； School of Information Technology, Deakin University, Australia（信息技术学院，德肯大学，澳大利亚）

专题命中指令微调：language model(title,abstract)；large language model(abstract)；SFT(abstract)；分类 cs.CL

2508.15854 2025-08-25 cs.CL 85%

QU-NLP at QIAS 2025 Shared Task: A Two-Phase LLM Fine-Tuning and Retrieval-Augmented Generation Approach for Islamic Inheritance Reasoning

Mohammad AL-Smadi

机构 * Qatar University（卡塔尔大学）

专题命中指令微调：LLM(title)；large language model(abstract)；language model(abstract)；prompting(abstract)

2508.12031 2025-08-19 cs.CL 85%

Learning Wisdom from Errors: Promoting LLM's Continual Relation Learning through Exploiting Error Cases

Shaozhe Yin, Jinyu Guo, Kai Shuang, Xia Liu, Ruize Ou

机构 * Beijing University of Posts and Telecommunications（北京邮电大学）； University of Electronic Science and Technology of China（电子科技大学）； China National Institute of Standardization（中国标准化研究院）

专题命中指令微调：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

1. 指令微调 11585 篇

Evolution without an Oracle: Driving Effective Evolution with LLM Judges

LangGPS: Language Separability Guided Data Pre-Selection for Joint Multilingual Instruction Tuning

Radio Astronomy in the Era of Vision-Language Models: Prompt Sensitivity and Adaptation

Zooming into Comics: Region-Aware RL Improves Fine-Grained Comic Understanding in Vision-Language Models

Multi-Agent Evolve: LLM Self-Improve through Co-evolution

What do vision-language models see in the context? Investigating multimodal in-context learning

Inoculation Prompting: Instructing LLMs to misbehave at train-time improves test-time alignment

ENTP: Enhancing Low-Quality SFT Data via Neural-Symbolic Text Purge-Mix

Enhancing Naturalness in LLM-Generated Utterances through Disfluency Insertion

ssToken: Self-modulated and Semantic-aware Token Selection for LLM Fine-tuning

Towards Fast LLM Fine-tuning through Zeroth-Order Optimization with Projected Gradient-Aligned Perturbations

Aligning Language Models with Investor and Market Behavior for Financial Recommendations

Transcribe, Translate, or Transliterate: An Investigation of Intermediate Representations in Spoken Language Models

RLSR: Reinforcement Learning with Supervised Reward Outperforms SFT in Instruction Following

Automated Refinement of Essay Scoring Rubrics for Language Models via Reflect-and-Revise

Data Selection for Fine-tuning Vision Language Models via Cross Modal Alignment Trajectories

Memorize or Generalize? Evaluating LLM Code Generation with Code Rewriting

SemanticShield: LLM-Powered Audits Expose Shilling Attacks in Recommender Systems

Few-Shot and Training-Free Review Generation via Conversational Prompting

Exploring the Impact of Personality Traits on LLM Bias and Toxicity

Explicit vs. Implicit Biographies: Evaluating and Adapting LLM Information Extraction on Wikidata-Derived Texts

Self-Adapting Language Models

ECG-aBcDe: Overcoming Model Dependence, Encoding ECG into a Universal Language for Any LLM

The LLM as a Network Operator: A Vision for Generative AI in the 6G Radio Access Network

MSLEF: Multi-Segment LLM Ensemble Finetuning in Recruitment

LLM Encoder vs. Decoder: Robust Detection of Chinese AI-Generated Text with LoRA

An LLM-powered Natural-to-Robotic Language Translation Framework with Correctness Guarantees

Improving Multilingual Language Models by Aligning Representations through Steering

QU-NLP at QIAS 2025 Shared Task: A Two-Phase LLM Fine-Tuning and Retrieval-Augmented Generation Approach for Islamic Inheritance Reasoning

Learning Wisdom from Errors: Promoting LLM's Continual Relation Learning through Exploiting Error Cases