语言大模型 / LLM - arXivDaily 专题

2502.11356 2025-02-18 cs.LG cs.AI cs.CL 85%

SAIF: A Sparse Autoencoder Framework for Interpreting and Steering Instruction Following of Language Models

Zirui He, Haiyan Zhao, Yiran Qiao, Fan Yang, Ali Payani, Jing Ma, Mengnan Du

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

Comments 21 pages, 11 figures, 6 tables

2405.15973 2025-02-11 cs.CV cs.AI cs.CL cs.LG 85%

Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement

Xiyao Wang, Jiuhai Chen, Zhaoyang Wang, Yuhang Zhou, Yiyang Zhou, Huaxiu Yao, Tianyi Zhou, Tom Goldstein, Parminder Bhatia, Furong Huang, Cao Xiao

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

Comments NAACL 2025 Findings

2501.12983 2025-02-10 eess.SP 85%

LLM4WM: Adapting LLM for Wireless Multi-Tasking

Xuanyu Liu, Shijian Gao, Boxun Liu, Xiang Cheng, Liuqing Yang

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

2502.01236 2025-02-04 cs.LG cs.AI cs.CL 85%

Eliciting Language Model Behaviors with Investigator Agents

Xiang Lisa Li, Neil Chowdhury, Daniel D. Johnson, Tatsunori Hashimoto, Percy Liang, Sarah Schwettmann, Jacob Steinhardt

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

Comments 20 pages, 7 figures

2501.14683 2025-01-27 cs.SE 85%

An Empirical Study on LLM-based Classification of Requirements-related Provisions in Food-safety Regulations

Shabnam Hassani, Mehrdad Sabetzadeh, Daniel Amyot

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

2311.09308 2025-01-15 cs.CL cs.AI cs.LG q-bio.NC 85%

Divergences between Language Models and Human Brains

Yuchen Zhou, Emmy Liu, Graham Neubig, Michael J. Tarr, Leila Wehbe

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

2501.05724 2025-01-13 cs.SE 85%

I Can't Share Code, but I need Translation -- An Empirical Study on Code Translation through Federated LLM

Jahnavi Kumar, Venkata Lakshmana Sasaank Janapati, Mokshith Reddy Tanguturi, Sridhar Chimalakonda

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

Comments 10 pages

2501.05228 2025-01-10 cs.CV 85%

Harnessing Large Language and Vision-Language Models for Robust Out-of-Distribution Detection

Pei-Kang Lee, Jun-Cheng Chen, Ja-Ling Wu

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

Comments 9 pages, 4 figures

2408.12470 2025-01-07 cs.IR 85%

DLCRec: A Novel Approach for Managing Diversity in LLM-Based Recommender Systems

Jiaju Chen, Chongming Gao, Shuai Yuan, Shuchang Liu, Qingpeng Cai, Peng Jiang

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

Comments Accepted by WSDM 2025

2410.09575 2025-01-03 cs.CV cs.AI cs.CL cs.LG 85%

Reconstructive Visual Instruction Tuning

Haochen Wang, Anlin Zheng, Yucheng Zhao, Tiancai Wang, Zheng Ge, Xiangyu Zhang, Zhaoxiang Zhang

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

2412.14164 2024-12-19 cs.CV 85%

MetaMorph: Multimodal Understanding and Generation via Instruction Tuning

Shengbang Tong, David Fan, Jiachen Zhu, Yunyang Xiong, Xinlei Chen, Koustuv Sinha, Michael Rabbat, Yann LeCun, Saining Xie, Zhuang Liu

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

Comments Project page at tsb0601.github.io/metamorph

2407.15838 2024-12-17 cs.CV 85%

MMInstruct: A High-Quality Multi-Modal Instruction Tuning Dataset with Extensive Diversity

Yangzhou Liu, Yue Cao, Zhangwei Gao, Weiyun Wang, Zhe Chen, Wenhai Wang, Hao Tian, Lewei Lu, Xizhou Zhu, Tong Lu, Yu Qiao, Jifeng Dai

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

Comments 18 pages, 8 figures, technical report

Journal ref Sci China Inf Sci, 2024

2412.09618 2024-12-13 cs.CV 85%

EasyRef: Omni-Generalized Group Image Reference for Diffusion Models via Multimodal LLM

Zhuofan Zong, Dongzhi Jiang, Bingqi Ma, Guanglu Song, Hao Shao, Dazhong Shen, Yu Liu, Hongsheng Li

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

Comments Tech report

2403.14896 2024-12-11 cs.CY 85%

Investigating Bias in LLM-Based Bias Detection: Disparities between LLMs and Human Perception

Luyang Lin, Lingzhi Wang, Jinsong Guo, Kam-Fai Wong

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

Comments COLING 2025

2402.15896 2024-12-09 cs.CV 85%

Multimodal Instruction Tuning with Conditional Mixture of LoRA

Ying Shen, Zhiyang Xu, Qifan Wang, Yu Cheng, Wenpeng Yin, Lifu Huang

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

Comments 12 pages, 7 figures, ACL 2024

2412.01072 2024-12-03 cs.SE 85%

When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair

Wenqiang Luo, Jacky Wai Keung, Boyang Yang, He Ye, Claire Le Goues, Tegawende F. Bissyande, Haoye Tian, Bach Le

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

2411.16775 2024-11-27 cs.CL cs.AI cs.LG 85%

Parameter Efficient Instruction Tuning: An Empirical Study

Pengfei He

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

Comments 7 pages, 7 figures

2406.02884 2024-11-27 cs.CV 85%

PosterLLaVa: Constructing a Unified Multi-modal Layout Generator with LLM

Tao Yang, Yingmin Luo, Zhongang Qi, Yang Wu, Ying Shan, Chang Wen Chen

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

Comments 13 pages; with PosterGen as extension; IEEE template

2404.15269 2024-11-26 cs.CL cs.AI cs.IR cs.LG 85%

Aligning LLM Agents by Learning Latent Preference from User Edits

Ge Gao, Alexey Taymanov, Eduardo Salinas, Paul Mineiro, Dipendra Misra

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

2411.12214 2024-11-20 cs.HC 85%

DexAssist: A Voice-Enabled Dual-LLM Framework for Accessible Web Navigation

Shridhar Mehendale, Ankit Walishetti

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

Comments Both authors contributed equally to this work. This paper will appear at the 16th International Conference on Intelligent Human Computer Interaction (IHCI 2024) and will be published under conference proceedings in Springer Lecture Notes in Computer Science (LNCS)

2411.07021 2024-11-19 cs.IR 85%

Invar-RAG: Invariant LLM-aligned Retrieval for Better Generation

Ziwei Liu, Liang Zhang, Qian Li, Jianghua Wu, Guangxu Zhu

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

2408.06634 2024-11-13 q-fin.CP cs.AI cs.CL cs.LG q-fin.ST 85%

Harnessing Earnings Reports for Stock Predictions: A QLoRA-Enhanced LLM Approach

Haowei Ni, Shuchen Meng, Xupeng Chen, Ziqing Zhao, Andi Chen, Panfeng Li, Shiyao Zhang, Qifu Yin, Yuanqing Wang, Yuxi Chan

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

Comments Accepted by 2024 6th International Conference on Data-driven Optimization of Complex Systems

Journal ref Proceedings of the 2024 6th International Conference on Data-driven Optimization of Complex Systems (DOCS), 2024, pp. 909-915

2411.02718 2024-11-06 eess.SP 85%

LLM-based Framework for Bearing Fault Diagnosis

Laifa Tao, Haifei Liu, Guoao Ning, Wenyan Cao, Bohao Huang, Chen Lu

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

Comments 25 pages, 11 figures

2406.11717 2024-11-01 cs.LG cs.AI cs.CL 85%

Refusal in Language Models Is Mediated by a Single Direction

Andy Arditi, Oscar Obeso, Aaquib Syed, Daniel Paleka, Nina Panickssery, Wes Gurnee, Neel Nanda

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

2406.15741 2024-10-30 cs.CL cs.AI cs.LG 85%

Ladder: A Model-Agnostic Framework Boosting LLM-based Machine Translation to the Next Level

Zhaopeng Feng, Ruizhe Chen, Yan Zhang, Zijie Meng, Zuozhu Liu

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

Comments EMNLP 2024 Main. Data and code are available at https://github.com/fzp0424/MT-Ladder

2406.02888 2024-10-29 cs.CL cs.AI cs.LG 85%

HYDRA: Model Factorization Framework for Black-Box LLM Personalization

Yuchen Zhuang, Haotian Sun, Yue Yu, Rushi Qiang, Qifan Wang, Chao Zhang, Bo Dai

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

Comments Accepted in NeurIPS'24

2410.07113 2024-10-10 cs.CV 85%

Personalized Visual Instruction Tuning

Renjie Pi, Jianshu Zhang, Tianyang Han, Jipeng Zhang, Rui Pan, Tong Zhang

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

2410.03750 2024-10-08 cs.LG cs.AI cs.CL 85%

SQFT: Low-cost Model Adaptation in Low-precision Sparse Foundation Models

Juan Pablo Muñoz, Jinjie Yuan, Nilesh Jain

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

Comments To be published in EMNLP-24 Findings

2304.08460 2024-10-04 cs.CL cs.AI cs.LG 85%

LongForm: Effective Instruction Tuning with Reverse Instructions

Abdullatif Köksal, Timo Schick, Anna Korhonen, Hinrich Schütze

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

Comments EMNLP 2024 Findings. This version extends the training with recent LLMs, evaluation with new metrics, and NLU tasks

2402.12842 2024-09-30 cs.CL cs.AI cs.LG 85%

PromptKD: Distilling Student-Friendly Knowledge for Generative Language Models via Prompt Tuning

Gyeongman Kim, Doohyuk Jang, Eunho Yang

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

Comments EMNLP 2024 Findings. Our project page: https://promptkd.github.io

1. 指令微调 11653 篇

SAIF: A Sparse Autoencoder Framework for Interpreting and Steering Instruction Following of Language Models

Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement

LLM4WM: Adapting LLM for Wireless Multi-Tasking

Eliciting Language Model Behaviors with Investigator Agents

An Empirical Study on LLM-based Classification of Requirements-related Provisions in Food-safety Regulations

Divergences between Language Models and Human Brains

I Can't Share Code, but I need Translation -- An Empirical Study on Code Translation through Federated LLM

Harnessing Large Language and Vision-Language Models for Robust Out-of-Distribution Detection

DLCRec: A Novel Approach for Managing Diversity in LLM-Based Recommender Systems

Reconstructive Visual Instruction Tuning

MetaMorph: Multimodal Understanding and Generation via Instruction Tuning

MMInstruct: A High-Quality Multi-Modal Instruction Tuning Dataset with Extensive Diversity

EasyRef: Omni-Generalized Group Image Reference for Diffusion Models via Multimodal LLM

Investigating Bias in LLM-Based Bias Detection: Disparities between LLMs and Human Perception

Multimodal Instruction Tuning with Conditional Mixture of LoRA

When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair

Parameter Efficient Instruction Tuning: An Empirical Study

PosterLLaVa: Constructing a Unified Multi-modal Layout Generator with LLM

Aligning LLM Agents by Learning Latent Preference from User Edits

DexAssist: A Voice-Enabled Dual-LLM Framework for Accessible Web Navigation

Invar-RAG: Invariant LLM-aligned Retrieval for Better Generation

Harnessing Earnings Reports for Stock Predictions: A QLoRA-Enhanced LLM Approach

LLM-based Framework for Bearing Fault Diagnosis

Refusal in Language Models Is Mediated by a Single Direction

Ladder: A Model-Agnostic Framework Boosting LLM-based Machine Translation to the Next Level

HYDRA: Model Factorization Framework for Black-Box LLM Personalization

Personalized Visual Instruction Tuning

SQFT: Low-cost Model Adaptation in Low-precision Sparse Foundation Models

LongForm: Effective Instruction Tuning with Reverse Instructions

PromptKD: Distilling Student-Friendly Knowledge for Generative Language Models via Prompt Tuning