语言大模型 / LLM - arXivDaily 专题

2406.03007 2024-06-06 cs.CL cs.AI cs.CR cs.LG 87%

BadAgent: Inserting and Activating Backdoor Attacks in LLM Agents

Yifei Wang, Dizhan Xue, Shengjie Zhang, Shengsheng Qian

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

Comments Accepted by ACL 2024

2312.07533 2024-05-20 cs.CV 87%

VILA: On Pre-training for Visual Language Models

Ji Lin, Hongxu Yin, Wei Ping, Yao Lu, Pavlo Molchanov, Andrew Tao, Huizi Mao, Jan Kautz, Mohammad Shoeybi, Song Han

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

Comments CVPR 2024

2305.13068 2024-03-15 cs.CL cs.AI cs.HC cs.IR cs.LG 87%

Making Language Models Better Tool Learners with Execution Feedback

Shuofei Qiao, Honghao Gui, Chengfei Lv, Qianghuai Jia, Huajun Chen, Ningyu Zhang

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

Comments NAACL 2024

2403.00827 2024-03-05 cs.CL cs.AI cs.LG 87%

Self-Refinement of Language Models from External Proxy Metrics Feedback

Keshav Ramji, Young-Suk Lee, Ramón Fernandez Astudillo, Md Arafat Sultan, Tahira Naseem, Asim Munawar, Radu Florian, Salim Roukos

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

2402.07543 2024-02-13 cs.CL cs.AI cs.LG 87%

Show Me How It's Done: The Role of Explanations in Fine-Tuning Language Models

Mohamad Ballout, Ulf Krumnack, Gunther Heidemann, Kai-Uwe Kuehnberger

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

2402.02643 2024-02-06 cs.DB cs.AI cs.CL cs.LG 87%

LLM-Enhanced Data Management

Xuanhe Zhou, Xinyang Zhao, Guoliang Li

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

2401.15670 2024-01-30 cs.CL cs.AI cs.LG 87%

YODA: Teacher-Student Progressive Learning for Language Models

Jianqiao Lu, Wanjun Zhong, Yufei Wang, Zhijiang Guo, Qi Zhu, Wenyong Huang, Yanlin Wang, Fei Mi, Baojun Wang, Yasheng Wang, Lifeng Shang, Xin Jiang, Qun Liu

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

Comments 14 pages, 4 figures, 3 tables

2401.00579 2024-01-02 cs.CL cs.AI cs.LG 87%

Exploring the Effectiveness of Instruction Tuning in Biomedical Language Processing

Omid Rohanian, Mohammadmahdi Nouriborji, David A. Clifton

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

2311.18445 2023-12-01 cs.CV 87%

VTimeLLM: Empower LLM to Grasp Video Moments

Bin Huang, Xin Wang, Hong Chen, Zihan Song, Wenwu Zhu

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

2311.08172 2023-11-28 cs.MM cs.CV 87%

Vision-Language Instruction Tuning: A Review and Analysis

Chen Li, Yixiao Ge, Dian Li, Ying Shan

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

Comments 34 pages, 6 figures

2311.08401 2023-11-15 cs.CL cs.AI cs.LG 87%

Fine-tuning Language Models for Factuality

Katherine Tian, Eric Mitchell, Huaxiu Yao, Christopher D. Manning, Chelsea Finn

专题命中指令微调：language model(title,abstract)；RLHF(abstract)；preference optimization(abstract)；分类 cs.CL、cs.AI、cs.LG

2311.07687 2023-11-15 cs.CL cs.AI cs.LG 87%

Language Model-In-The-Loop: Data Optimal Approach to Learn-To-Recommend Actions in Text Games

Arjun Vaithilingam Sudhakar, Prasanna Parthasarathi, Janarthanan Rajendran, Sarath Chandar

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

2306.11816 2023-11-14 cs.LG cs.AI cs.CL 87%

Learning to Generate Better Than Your LLM

Jonathan D. Chang, Kiante Brantley, Rajkumar Ramamurthy, Dipendra Misra, Wen Sun

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

Comments 23 pages, 5 figures, 7 tables, 4 algorithms

2303.11366 2023-10-11 cs.AI cs.CL cs.LG 87%

Reflexion: Language Agents with Verbal Reinforcement Learning

Noah Shinn, Federico Cassano, Edward Berman, Ashwin Gopinath, Karthik Narasimhan, Shunyu Yao

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

Comments v4 contains a few additional experiments

2310.05915 2023-10-10 cs.CL cs.AI cs.LG 87%

FireAct: Toward Language Agent Fine-tuning

Baian Chen, Chang Shu, Ehsan Shareghi, Nigel Collier, Karthik Narasimhan, Shunyu Yao

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

Comments Code, data, and models are available at https://fireact-agent.github.io

2308.03629 2023-08-09 cs.CL cs.AI cs.LG 87%

MedMine: Examining Pre-trained Language Models on Medication Mining

Haifa Alrdahi, Lifeng Han, Hendrik Šuvalov, Goran Nenadic

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

Comments Open Research Project. 7 pages, 1 figure, 5 tables

2307.10719 2023-07-25 cs.AI cs.CL cs.CR cs.LG 87%

LLM Censorship: A Machine Learning Challenge or a Computer Security Problem?

David Glukhov, Ilia Shumailov, Yarin Gal, Nicolas Papernot, Vardan Papyan

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

2305.15444 2023-06-21 cs.CL cs.AI cs.LG 87%

PromptNER: Prompting For Named Entity Recognition

Dhananjay Ashok, Zachary C. Lipton

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

2306.11025 2023-06-21 cs.LG cs.AI cs.CL q-fin.ST 87%

Temporal Data Meets LLM -- Explainable Financial Time Series Forecasting

Xinli Yu, Zheng Chen, Yuan Ling, Shujing Dong, Zongyi Liu, Yanbin Lu

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

2305.02412 2023-05-09 cs.CL cs.AI cs.LG 87%

Plan, Eliminate, and Track -- Language Models are Good Teachers for Embodied Agents

Yue Wu, So Yeon Min, Yonatan Bisk, Ruslan Salakhutdinov, Amos Azaria, Yuanzhi Li, Tom Mitchell, Shrimai Prabhumoye

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

2212.09689 2022-12-20 cs.CL cs.AI cs.LG 87%

Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor

Or Honovich, Thomas Scialom, Omer Levy, Timo Schick

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

Comments 18 pages, 7 figures

2210.12607 2022-10-25 cs.CL cs.AI cs.LG 87%

Learning to Perform Complex Tasks through Compositional Fine-Tuning of Language Models

Victor S. Bursztyn, David Demeter, Doug Downey, Larry Birnbaum

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

Comments Accepted to findings of EMNLP 2022. Data and code available at https://github.com/vbursztyn/compositional-fine-tuning

2604.05134 2026-05-05 cs.LG cs.AI 87%

How Reasoning Evolves from Post-Training Data: An Empirical Study Using Chess

推理如何从训练数据中演变：使用国际象棋的实证研究

Lucas Dionisopoulos, Nicklas Majamaki, Prithviraj Ammanabrolu

机构 * Department of Computer Science and Engineering, University of California San Diego, San Diego, United States（计算机科学与工程系，加州大学圣地亚哥分校，圣地亚哥，美国）

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

AI总结研究语言模型推理从监督微调到强化学习的演变，发现直接预测最佳走法的微调能提升性能，但强化学习阶段导致不一致推理，而多步轨迹训练则能获得更稳定的推理。

Comments Accepted at ICML 2026. An earlier version appeared at the NeurIPS 2025 Foundations of Reasoning in Language Models (FoRLM) Workshop (Oral)

2503.15621 2025-08-01 cs.CV cs.AI cs.CL cs.MM 87%

LLaVA-MORE: A Comparative Study of LLMs and Visual Backbones for Enhanced Visual Instruction Tuning

Federico Cocchi, Nicholas Moratelli, Davide Caffagni, Sara Sarto, Lorenzo Baraldi, Marcella Cornia, Rita Cucchiara

机构 * University of Modena and Reggio Emilia（摩德纳和雷吉奥艾米利亚大学）； University of Pisa（比萨大学）； IIT-CNR（意大利国家研究 council（IIT））

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

Comments ICCV 2025 Workshop on What is Next in Multimodal Foundation Models

2407.14506 2025-07-21 cs.CV cs.AI cs.CL 87%

On Pre-training of Multimodal Language Models Customized for Chart Understanding

Wan-Cyuan Fan, Yen-Chun Chen, Mengchen Liu, Lu Yuan, Leonid Sigal

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

Comments NeurIPS 2024 Workshop on Adaptive Foundation Models

2409.02322 2025-02-12 cs.LG cs.AI 87%

TimeDiT: General-purpose Diffusion Transformers for Time Series Foundation Model

Defu Cao, Wen Ye, Yizhou Zhang, Yan Liu

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

Comments 31 Pages, 11 Figures, 22 Tables. First present at ICML 2024 Workshop on Foundation Models in the Wild

2309.05950 2024-05-15 cs.CL cs.CV cs.LG cs.MM 87%

Language Models as Black-Box Optimizers for Vision-Language Models

Shihong Liu, Zhiqiu Lin, Samuel Yu, Ryan Lee, Tiffany Ling, Deepak Pathak, Deva Ramanan

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

Comments Published at CVPR 2024. Project site: https://llm-can-optimize-vlm.github.io/

2604.13538 2026-08-27 cs.CL 版本更新 86%

Synthesizing Instruction-Tuning Datasets with Contrastive Decoding

通过对比解码合成指令微调数据集

Tatsuya Ichinose, Youmi Ma, Masanari Oi, Ryuto Koike, Naoaki Okazaki

机构 * Department of Computer Science, School of Computing, Institute of Science Tokyo（东京科学大学计算机科学系）； National Institute of Advanced Industrial Science and Technology（国家先进工业科学与技术研究院）； Research and Development Center for Large Language Models, NII（大型语言模型研究与开发中心，日本信息产业技术综合研究所）

专题命中指令微调：LLM(abstract,abstract_cn)；large language model(abstract)；language model(abstract)；instruction tuning(abstract)

AI总结本文提出CoDIT方法，通过对比解码分离预训练知识与指令遵循能力，提升指令微调效果。实验表明基于CoDIT构建的数据集在多个基准上表现更优。

Comments 26 pages, 7 figures

2608.21750 2026-08-25 cs.CL 新提交 86%

FCPRAG: Fusion-Controller Parametric Retrieval-Augmented Generation for Stable Multi-Passage LoRA Injection

FCPRAG：融合控制器参数化检索增强生成，用于稳定多段落LoRA注入

Jinchang Zhu, Jindong Li, Yi Ding, Xiaojian Nie, Rong Fu, Shuangyong Song, Haowei He, Menglin Yang

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））； University of Macau（澳门大学）； Institute of Artificial Intelligence (TeleAI), China Telecom（中国电信人工智能研究院（TeleAI））

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

AI总结 FCPRAG是一种融合控制的参数化RAG框架，通过轻量控制器实现样本级适配器融合，在多个数据集和LLM主干上提升了RAG的F1值，降低调优成本并增强鲁棒性。

Comments Accepted to EMNLP 2026

2608.20314 2026-08-21 cs.AI 新提交 86%

MidTool: Mid-training Data Synthesis for Agentic Tool Use

MidTool：面向智能体工具使用的训练中期数据合成

Fengqing Jiang, Yite Wang, Boyi Liu, Zhaoyang Wang, Canwen Xu, Zhewei Yao, Radha Poovendran, Yuxiong He

机构 * University of Washington（华盛顿大学）； Snowflake（雪花公司）； University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）

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

AI总结本研究提出MidTool流水线，构建面向智能体工具使用的训练中期数据，在MidTool-Mix上微调Qwen3模型，可显著提升工具使用相关下游任务性能，证明通用工具使用需专门训练中期调整。

Comments Data & Model: https://hf.co/collections/MidTool/midtool-release

1. 指令微调 11692 篇

BadAgent: Inserting and Activating Backdoor Attacks in LLM Agents

VILA: On Pre-training for Visual Language Models

Making Language Models Better Tool Learners with Execution Feedback

Self-Refinement of Language Models from External Proxy Metrics Feedback

Show Me How It's Done: The Role of Explanations in Fine-Tuning Language Models

LLM-Enhanced Data Management

YODA: Teacher-Student Progressive Learning for Language Models

Exploring the Effectiveness of Instruction Tuning in Biomedical Language Processing

VTimeLLM: Empower LLM to Grasp Video Moments

Vision-Language Instruction Tuning: A Review and Analysis

Fine-tuning Language Models for Factuality

Language Model-In-The-Loop: Data Optimal Approach to Learn-To-Recommend Actions in Text Games

Learning to Generate Better Than Your LLM

Reflexion: Language Agents with Verbal Reinforcement Learning

FireAct: Toward Language Agent Fine-tuning

MedMine: Examining Pre-trained Language Models on Medication Mining

LLM Censorship: A Machine Learning Challenge or a Computer Security Problem?

PromptNER: Prompting For Named Entity Recognition

Temporal Data Meets LLM -- Explainable Financial Time Series Forecasting

Plan, Eliminate, and Track -- Language Models are Good Teachers for Embodied Agents

Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor

Learning to Perform Complex Tasks through Compositional Fine-Tuning of Language Models

How Reasoning Evolves from Post-Training Data: An Empirical Study Using Chess

LLaVA-MORE: A Comparative Study of LLMs and Visual Backbones for Enhanced Visual Instruction Tuning

On Pre-training of Multimodal Language Models Customized for Chart Understanding

TimeDiT: General-purpose Diffusion Transformers for Time Series Foundation Model

Language Models as Black-Box Optimizers for Vision-Language Models

Synthesizing Instruction-Tuning Datasets with Contrastive Decoding

FCPRAG: Fusion-Controller Parametric Retrieval-Augmented Generation for Stable Multi-Passage LoRA Injection

MidTool: Mid-training Data Synthesis for Agentic Tool Use