语言大模型 / LLM - arXivDaily 专题

2506.00574 2025-06-03 cs.LG cs.AI 86%

Prompt-Tuned LLM-Augmented DRL for Dynamic O-RAN Network Slicing

Fatemeh Lotfi, Hossein Rajoli, Fatemeh Afghah

机构 * Holcombe Department of Electrical and Computer Engineering, Clemson University（霍尔科姆电气与计算机工程系，克莱姆森大学）

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

2505.03793 2025-06-03 cs.LG cs.AI 86%

LENSLLM: Unveiling Fine-Tuning Dynamics for LLM Selection

Xinyue Zeng, Haohui Wang, Junhong Lin, Jun Wu, Tyler Cody, Dawei Zhou

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

Comments Accepted by ICML'2025

2408.05211 2025-06-02 cs.CV cs.AI cs.CL 86%

VITA: Towards Open-Source Interactive Omni Multimodal LLM

Chaoyou Fu, Haojia Lin, Zuwei Long, Yunhang Shen, Yuhang Dai, Meng Zhao, Yi-Fan Zhang, Shaoqi Dong, Yangze Li, Xiong Wang, Haoyu Cao, Di Yin, Long Ma, Xiawu Zheng, Rongrong Ji, Yunsheng Wu, Ran He, Caifeng Shan, Xing Sun

机构 * NJU（南京大学）； Tencent Youtu Lab（腾讯计算机系统有限公司视觉实验室）； XMU（厦门大学）； CASIA（中国科学院自动化研究所）

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

Comments Project Page: https://vita-home.github.io

2403.11838 2025-05-30 cs.CL cs.AI 86%

Ensuring Safe and High-Quality Outputs: A Guideline Library Approach for Language Models

Yi Luo, Zhenghao Lin, Yuhao Zhang, Jiashuo Sun, Chen Lin, Chengjin Xu, Xiangdong Su, Yelong Shen, Jian Guo, Yeyun Gong

机构 * XiaMen University（厦门大学）； Yanshan University（雁山大学）； IDEA Research（IDEA研究）； Inner Mongolia University（内蒙古大学）； Microsoft（微软）； Microsoft Research Asia（微软亚洲研究院）

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

Comments Accepted to NAACL 2024 main conference

Journal ref Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)

2403.10056 2025-05-28 cs.CL cs.AI 86%

Don't Half-listen: Capturing Key-part Information in Continual Instruction Tuning

Yongquan He, Wenyuan Zhang, Xuancheng Huang, Peng Zhang, Lingxun Meng, Xiang Zhou, Ke Zeng, Xunliang Cai

机构 * School of Cyber Science and Engineering Nanjing University of Science and Technology China（南京理工大学信息科学与工程学院）； Meituan China（美团）； Zhipu.AI China（智谱AI）； Institute of Information Engineering Chinese Academy of Sciences China（中国科学院信息工程研究所）

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

Comments 20 pages, 6 figures

2505.17632 2025-05-26 cs.SE cs.AI cs.LG 86%

ReqBrain: Task-Specific Instruction Tuning of LLMs for AI-Assisted Requirements Generation

Mohammad Kasra Habib, Daniel Graziotin, Stefan Wagner

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

2502.06846 2025-05-23 cs.LG cs.AI q-bio.BM 86%

Prot2Chat: Protein LLM with Early-Fusion of Text, Sequence and Structure

Zhicong Wang, Zicheng Ma, Ziqiang Cao, Changlong Zhou, Jun Zhang, Yiqin Gao

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

Comments 8 pages, 3 figures

2505.13973 2025-05-21 cs.CL cs.AI cs.CV 86%

Toward Effective Reinforcement Learning Fine-Tuning for Medical VQA in Vision-Language Models

Wenhui Zhu, Xuanzhao Dong, Xin Li, Peijie Qiu, Xiwen Chen, Abolfazl Razi, Aris Sotiras, Yi Su, Yalin Wang

机构 * Arizona State University（亚利桑那州立大学）； Clemson University（克莱姆森大学）； Washington University in St.Louis（华盛顿大学圣路易斯分校）； Banner Alzheimer’s Institute（Banner阿尔茨海默病研究所）

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

2505.12250 2025-05-20 cs.CL cs.AI 86%

Not All Documents Are What You Need for Extracting Instruction Tuning Data

Chi Zhang, Huaping Zhong, Hongtao Li, Chengliang Chai, Jiawei Hong, Yuhao Deng, Jiacheng Wang, Tian Tan, Yizhou Yan, Jiantao Qiu, Ye Yuan, Guoren Wang, Conghui He, Lei Cao

机构 * Department of Computer Science, Beijing Institute of Technology, Beijing, China（北京理工大学计算机科学系）； Sensetime Research, Shenzhen, China（深睿时代研究）； Shanghai Artificial Intelligence Laboratory, Shanghai, China（上海人工智能实验室）； University of Arizona, USA（亚利桑那大学）； Meta, USA（Meta）

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

2503.04807 2025-05-19 cs.CL cs.AI 86%

Call for Rigor in Reporting Quality of Instruction Tuning Data

Hyeonseok Moon, Jaehyung Seo, Heuiseok Lim

机构 * Department of Computer Science and Engineering, Korea University（韩国大学计算机科学与工程系）

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

Comments Accepted to the ACL2025-main

2410.12609 2025-05-16 cs.LG cs.AI 86%

Towards Graph Foundation Models: Training on Knowledge Graphs Enables Transferability to General Graphs

Kai Wang, Siqiang Luo, Caihua Shan, Yifei Shen

机构 * Nanyang Technological University（南洋理工大学）； Microsoft Research Asia（微软亚洲研究院）

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 25 Pages, 5 figures

2505.02486 2025-05-06 cs.LG cs.AI 86%

SEFE: Superficial and Essential Forgetting Eliminator for Multimodal Continual Instruction Tuning

Jinpeng Chen, Runmin Cong, Yuzhi Zhao, Hongzheng Yang, Guangneng Hu, Horace Ho Shing Ip, Sam Kwong

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

2504.13629 2025-04-21 cs.CL cs.AI econ.GN q-fin.EC 86%

Divergent LLM Adoption and Heterogeneous Convergence Paths in Research Writing

Cong William Lin, Wu Zhu

机构 * Cornell University SC Johnson College of Business（康奈尔大学SC约翰逊商学院）； NBER（国家经济研究局）； Tsinghua University（清华大学）

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

2504.12185 2025-04-17 cs.CL cs.AI 86%

SALAD: Improving Robustness and Generalization through Contrastive Learning with Structure-Aware and LLM-Driven Augmented Data

Suyoung Bae, Hyojun Kim, YunSeok Choi, Jee-Hyong Lee

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

Comments Accepted to NAACL 2025 main. 15 pages, 4 figures

2410.17875 2025-04-09 cs.CL cs.AI 86%

Understanding Layer Significance in LLM Alignment

Guangyuan Shi, Zexin Lu, Xiaoyu Dong, Wenlong Zhang, Xuanyu Zhang, Yujie Feng, Xiao-Ming Wu

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

2503.23740 2025-04-01 cs.CL cs.AI 86%

LANID: LLM-assisted New Intent Discovery

Lu Fan, Jiashu Pu, Rongsheng Zhang, Xiao-Ming Wu

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

Comments Published in LREC-COLING 2024

2503.19206 2025-03-31 cs.CL cs.AI 86%

Overtrained Language Models Are Harder to Fine-Tune

Jacob Mitchell Springer, Sachin Goyal, Kaiyue Wen, Tanishq Kumar, Xiang Yue, Sadhika Malladi, Graham Neubig, Aditi Raghunathan

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

Comments 72 pages, 65 figures, 6 tables

2503.18986 2025-03-26 cs.LG cs.AI 86%

SplitFrozen: Split Learning with Device-side Model Frozen for Fine-Tuning LLM on Heterogeneous Resource-Constrained Devices

Jian Ma, Xinchen Lyu, Jun Jiang, Qimei Cui, Haipeng Yao, Xiaofeng Tao

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

2503.15924 2025-03-21 cs.CL cs.AI 86%

Towards Automatic Continual Learning: A Self-Adaptive Framework for Continual Instruction Tuning

Peiyi Lin, Fukai Zhang, Kai Niu, Hao Fu

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

2503.13507 2025-03-19 cs.CL cs.AI 86%

NeurIPS 2023 LLM Efficiency Fine-tuning Competition

Mark Saroufim, Yotam Perlitz, Leshem Choshen, Luca Antiga, Greg Bowyer, Christian Puhrsch, Driss Guessous, Supriya Rao, Geeta Chauhan, Ashvini Kumar, Jindal Pawan Kumar, Rajpoot Ankur Parikh, Joe Isaacson, Weiwei Yang

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

Comments 11 pages, 10 figures

2503.05132 2025-03-11 cs.AI cs.CV cs.LG 86%

R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model

Hengguang Zhou, Xirui Li, Ruochen Wang, Minhao Cheng, Tianyi Zhou, Cho-Jui Hsieh

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

Comments 10 pages, 6 figures

2502.01600 2025-03-11 cs.LG cs.AI 86%

Reinforcement Learning for Long-Horizon Interactive LLM Agents

Kevin Chen, Marco Cusumano-Towner, Brody Huval, Aleksei Petrenko, Jackson Hamburger, Vladlen Koltun, Philipp Krähenbühl

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

2503.05620 2025-03-10 cs.CL cs.AI 86%

Learning LLM Preference over Intra-Dialogue Pairs: A Framework for Utterance-level Understandings

Xuanqing Liu, Luyang Kong, Wei Niu, Afshin Khashei, Belinda Zeng, Steve Johnson, Jon Jay, Davor Golac, Matt Pope

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

Comments 7 pages, 4 figures

2503.02365 2025-03-07 cs.AI cs.CL 86%

EchoQA: A Large Collection of Instruction Tuning Data for Echocardiogram Reports

Lama Moukheiber, Mira Moukheiber, Dana Moukheiiber, Jae-Woo Ju, Hyung-Chul Lee

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

Comments NeurIPS SafeGenAI 2024

2503.01836 2025-03-04 cs.CL cs.AI 86%

CrowdSelect: Synthetic Instruction Data Selection with Multi-LLM Wisdom

Yisen Li, Lingfeng Yang, Wenxuan Shen, Pan Zhou, Yao Wan, Weiwei Lin, Dongping Chen

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

2502.19557 2025-02-28 cs.CL cs.AI 86%

Distill Not Only Data but Also Rewards: Can Smaller Language Models Surpass Larger Ones?

Yudi Zhang, Lu Wang, Meng Fang, Yali Du, Chenghua Huang, Jun Wang, Qingwei Lin, Mykola Pechenizkiy, Dongmei Zhang, Saravan Rajmohan, Qi Zhang

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

Comments 14 pages, 7 figures

2411.07133 2025-02-27 cs.AI cs.CL 86%

Stronger Models are NOT Stronger Teachers for Instruction Tuning

Zhangchen Xu, Fengqing Jiang, Luyao Niu, Bill Yuchen Lin, Radha Poovendran

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

Comments This is paper is accepted at NAACL 2025

2502.14834 2025-02-21 cs.CV cs.AI cs.CL 86%

LongWriter-V: Enabling Ultra-Long and High-Fidelity Generation in Vision-Language Models

Shangqing Tu, Yucheng Wang, Daniel Zhang-Li, Yushi Bai, Jifan Yu, Yuhao Wu, Lei Hou, Huiqin Liu, Zhiyuan Liu, Bin Xu, Juanzi Li

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

2412.12499 2025-02-18 cs.CL cs.AI 86%

LinguaLIFT: An Effective Two-stage Instruction Tuning Framework for Low-Resource Language Reasoning

Hongbin Zhang, Kehai Chen, Xuefeng Bai, Yang Xiang, Min Zhang

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

2410.04064 2025-02-18 cs.LG cs.AI 86%

Text2Chart31: Instruction Tuning for Chart Generation with Automatic Feedback

Fatemeh Pesaran Zadeh, Juyeon Kim, Jin-Hwa Kim, Gunhee Kim

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

Comments EMNLP 2024 Main Oral. Code and dataset are released at https://github.com/fatemehpesaran310/Text2Chart31

1. 指令微调 11585 篇

Prompt-Tuned LLM-Augmented DRL for Dynamic O-RAN Network Slicing

LENSLLM: Unveiling Fine-Tuning Dynamics for LLM Selection

VITA: Towards Open-Source Interactive Omni Multimodal LLM

Ensuring Safe and High-Quality Outputs: A Guideline Library Approach for Language Models

Don't Half-listen: Capturing Key-part Information in Continual Instruction Tuning

ReqBrain: Task-Specific Instruction Tuning of LLMs for AI-Assisted Requirements Generation

Prot2Chat: Protein LLM with Early-Fusion of Text, Sequence and Structure

Toward Effective Reinforcement Learning Fine-Tuning for Medical VQA in Vision-Language Models

Not All Documents Are What You Need for Extracting Instruction Tuning Data

Call for Rigor in Reporting Quality of Instruction Tuning Data

Towards Graph Foundation Models: Training on Knowledge Graphs Enables Transferability to General Graphs

SEFE: Superficial and Essential Forgetting Eliminator for Multimodal Continual Instruction Tuning

Divergent LLM Adoption and Heterogeneous Convergence Paths in Research Writing

SALAD: Improving Robustness and Generalization through Contrastive Learning with Structure-Aware and LLM-Driven Augmented Data

Understanding Layer Significance in LLM Alignment

LANID: LLM-assisted New Intent Discovery

Overtrained Language Models Are Harder to Fine-Tune

SplitFrozen: Split Learning with Device-side Model Frozen for Fine-Tuning LLM on Heterogeneous Resource-Constrained Devices

Towards Automatic Continual Learning: A Self-Adaptive Framework for Continual Instruction Tuning

NeurIPS 2023 LLM Efficiency Fine-tuning Competition

R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model

Reinforcement Learning for Long-Horizon Interactive LLM Agents

Learning LLM Preference over Intra-Dialogue Pairs: A Framework for Utterance-level Understandings

EchoQA: A Large Collection of Instruction Tuning Data for Echocardiogram Reports

CrowdSelect: Synthetic Instruction Data Selection with Multi-LLM Wisdom

Distill Not Only Data but Also Rewards: Can Smaller Language Models Surpass Larger Ones?

Stronger Models are NOT Stronger Teachers for Instruction Tuning

LongWriter-V: Enabling Ultra-Long and High-Fidelity Generation in Vision-Language Models

LinguaLIFT: An Effective Two-stage Instruction Tuning Framework for Low-Resource Language Reasoning

Text2Chart31: Instruction Tuning for Chart Generation with Automatic Feedback