语言大模型 / LLM - arXivDaily 专题

2503.15573 2025-05-19 cs.LG 85%

Task-Specific Data Selection for Instruction Tuning via Monosemantic Neuronal Activations

Da Ma, Gonghu Shang, Zhi Chen, Libo Qin, Yijie Luo, Lei Pan, Shuai Fan, Lu Chen, Kai Yu

机构 * X-LANCE Lab, Department of Computer Science and Engineering（X-LANCE实验室，计算机科学与工程系）； MoE Key Lab of Artificial Intelligence, SJTU AI Institute（人工智能MOE实验室，SJTU人工智能研究所）； Shanghai Jiao Tong University（上海交通大学）； AISpeech Co., Ltd.（AISpeech公司）； School of Computer Science and Engineering, Central South University（计算机科学与工程学院，中南大学）

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

Comments preprint, (20 pages, 7 figures, 13 tables)

2505.07782 2025-05-13 cs.LG 85%

MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering

Rushi Qiang, Yuchen Zhuang, Yinghao Li, Dingu Sagar V K, Rongzhi Zhang, Changhao Li, Ian Shu-Hei Wong, Sherry Yang, Percy Liang, Chao Zhang, Bo Dai

机构 * Georgia Institute of Technology（佐治亚理工学院）； Stanford University（斯坦福大学）

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

2505.05189 2025-05-09 cs.CV cs.AI 85%

Biomed-DPT: Dual Modality Prompt Tuning for Biomedical Vision-Language Models

Wei Peng, Kang Liu, Jianchen Hu, Meng Zhang

机构 * School of Future Technology（未来技术学院）； Xi’an Jiaotong University（西安交通大学）； School of Automation Science and Engineering（自动化科学与工程学院）

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

2504.21187 2025-05-01 cs.LG 85%

LIFT: LLM-Based Pragma Insertion for HLS via GNN Supervised Fine-Tuning

Neha Prakriya, Zijian Ding, Yizhou Sun, Jason Cong

机构 * Computer Science Department, University of California - Los Angeles（加州大学洛杉矶分校计算机科学系）

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

2405.20774 2025-05-01 cs.CR cs.AI 85%

Can We Trust Embodied Agents? Exploring Backdoor Attacks against Embodied LLM-based Decision-Making Systems

Ruochen Jiao, Shaoyuan Xie, Justin Yue, Takami Sato, Lixu Wang, Yixuan Wang, Qi Alfred Chen, Qi Zhu

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

Comments Accepted paper at ICLR 2025, 31 pages, including main paper, references, and appendix

2504.07288 2025-04-15 cs.CL 85%

MDIT: A Model-free Data Interpolation Method for Diverse Instruction Tuning

Yangning Li, Zihua Lan, Lv Qingsong, Yinghui Li, Hai-Tao Zheng

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

2504.07615 2025-04-15 cs.CV cs.CL 85%

VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model

Haozhan Shen, Peng Liu, Jingcheng Li, Chunxin Fang, Yibo Ma, Jiajia Liao, Qiaoli Shen, Zilun Zhang, Kangjia Zhao, Qianqian Zhang, Ruochen Xu, Tiancheng Zhao

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

Comments 11 pages, fix some minor typos in the previous version

2504.07198 2025-04-11 cs.CV cs.AI cs.HC 85%

Face-LLaVA: Facial Expression and Attribute Understanding through Instruction Tuning

Ashutosh Chaubey, Xulang Guan, Mohammad Soleymani

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

Comments Project Page: https://face-llava.github.io

2410.02916 2025-04-10 cs.CR cs.AI 85%

LLM Safeguard is a Double-Edged Sword: Exploiting False Positives for Denial-of-Service Attacks

Qingzhao Zhang, Ziyang Xiong, Z. Morley Mao

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

2504.02953 2025-04-07 cs.CL 85%

Cultural Learning-Based Culture Adaptation of Language Models

Chen Cecilia Liu, Anna Korhonen, Iryna Gurevych

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

2405.08295 2025-03-26 cs.CL cs.SD eess.AS 85%

SpeechVerse: A Large-scale Generalizable Audio Language Model

Nilaksh Das, Saket Dingliwal, Srikanth Ronanki, Rohit Paturi, Zhaocheng Huang, Prashant Mathur, Jie Yuan, Dhanush Bekal, Xing Niu, Sai Muralidhar Jayanthi, Xilai Li, Karel Mundnich, Monica Sunkara, Sravan Bodapati, Sundararajan Srinivasan, Kyu J Han, Katrin Kirchhoff

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

Comments Single Column, 13 page

2502.14502 2025-03-25 cs.CL 85%

How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM?

Sergey Pletenev, Maria Marina, Daniil Moskovskiy, Vasily Konovalov, Pavel Braslavski, Alexander Panchenko, Mikhail Salnikov

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

2410.18447 2025-03-18 cs.CL 85%

ToolFlow: Boosting LLM Tool-Calling Through Natural and Coherent Dialogue Synthesis

Zezhong Wang, Xingshan Zeng, Weiwen Liu, Liangyou Li, Yasheng Wang, Lifeng Shang, Xin Jiang, Qun Liu, Kam-Fai Wong

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

Comments Accepted by NAACL 2025

2503.01490 2025-03-04 cs.CL 85%

Improving Retrospective Language Agents via Joint Policy Gradient Optimization

Xueyang Feng, Bo Lan, Quanyu Dai, Lei Wang, Jiakai Tang, Xu Chen, Zhenhua Dong, Ji-Rong Wen

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

Comments NAACL2025

2410.12952 2025-03-04 cs.CL 85%

Facilitating Multi-turn Function Calling for LLMs via Compositional Instruction Tuning

Mingyang Chen, Haoze Sun, Tianpeng Li, Fan Yang, Hao Liang, Keer Lu, Bin Cui, Wentao Zhang, Zenan Zhou, Weipeng Chen

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

Comments Accepted to ICLR 2025

2502.20421 2025-03-03 cs.LG 85%

MobiLLM: Enabling LLM Fine-Tuning on the Mobile Device via Server Assisted Side Tuning

Liang Li, Xingke Yang, Wen Wu, Hao Wang, Tomoaki Ohtsuki, Xin Fu, Miao Pan, Xuemin Shen

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

2502.18990 2025-02-27 cs.CL 85%

GenTool: Enhancing Tool Generalization in Language Models through Zero-to-One and Weak-to-Strong Simulation

Jie He, Jennifer Neville, Mengting Wan, Longqi Yang, Hui Liu, Xiaofeng Xu, Xia Song, Jeff Z. Pan, Pei Zhou

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

2502.18910 2025-02-27 cs.LG cs.DC 85%

CLLoRA: An Approach to Measure the Effects of the Context Length for LLM Fine-Tuning

Ping Zhang, Zhaorui Zhang, Sheng Di, Yao Xin, Benben Liu

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

2502.10250 2025-02-25 cs.CL cs.CV 85%

VisCon-100K: Leveraging Contextual Web Data for Fine-tuning Vision Language Models

Gokul Karthik Kumar, Iheb Chaabane, Kebin Wu

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

Comments Accepted at PAKDD 2025

2502.16142 2025-02-25 cs.CL eess.AS 85%

Understanding Zero-shot Rare Word Recognition Improvements Through LLM Integration

Haoxuan Wang

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

2410.06101 2025-02-25 cs.AI cs.MA 85%

Coevolving with the Other You: Fine-Tuning LLM with Sequential Cooperative Multi-Agent Reinforcement Learning

Hao Ma, Tianyi Hu, Zhiqiang Pu, Boyin Liu, Xiaolin Ai, Yanyan Liang, Min Chen

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

Comments Accepted by NeurIPS '24

2502.15418 2025-02-24 cs.CL 85%

MHQA: A Diverse, Knowledge Intensive Mental Health Question Answering Challenge for Language Models

Suraj Racha, Prashant Joshi, Anshika Raman, Nikita Jangid, Mridul Sharma, Ganesh Ramakrishnan, Nirmal Punjabi

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

2410.02486 2025-02-24 cs.CR cs.LG 85%

Encryption-Friendly LLM Architecture

Donghwan Rho, Taeseong Kim, Minje Park, Jung Woo Kim, Hyunsik Chae, Ernest K. Ryu, Jung Hee Cheon

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

Comments 27 pages

2407.13561 2025-02-21 cs.CL 85%

Research on Tibetan Tourism Viewpoints information generation system based on LLM

Jinhu Qi, Shuai Yan, Wentao Zhang, Yibo Zhang, Zirui Liu, Ke Wang

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

Journal ref ICWOC 2024

2502.11433 2025-02-20 cs.AI cs.CE q-fin.TR 85%

FLAG-Trader: Fusion LLM-Agent with Gradient-based Reinforcement Learning for Financial Trading

Guojun Xiong, Zhiyang Deng, Keyi Wang, Yupeng Cao, Haohang Li, Yangyang Yu, Xueqing Peng, Mingquan Lin, Kaleb E Smith, Xiao-Yang Liu, Jimin Huang, Sophia Ananiadou, Qianqian Xie

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

2502.11062 2025-02-18 cs.CL 85%

Beyond Similarity: A Gradient-based Graph Method for Instruction Tuning Data Selection

Yang Zhao, Li Du, Xiao Ding, Yangou Ouyang, Hepeng Wang, Kai Xiong, Jinglong Gao, Zhouhao Sun, Dongliang Xu, Yang Qing, Dongchen Li, Bing Qin, Ting Liu

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

2502.06990 2025-02-12 cs.CL 85%

Investigating the Zone of Proximal Development of Language Models for In-Context Learning

Peng Cui, Mrinmaya Sachan

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

Comments NAACL 2025 findings

2411.01595 2025-02-12 cs.CV cs.AI 85%

RS-MoE: A Vision-Language Model with Mixture of Experts for Remote Sensing Image Captioning and Visual Question Answering

Hui Lin, Danfeng Hong, Shuhang Ge, Chuyao Luo, Kai Jiang, Hao Jin, Congcong Wen

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

2502.06487 2025-02-11 cs.CL 85%

Adaptive Prompting: Ad-hoc Prompt Composition for Social Bias Detection

Maximilian Spliethöver, Tim Knebler, Fabian Fumagalli, Maximilian Muschalik, Barbara Hammer, Eyke Hüllermeier, Henning Wachsmuth

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

Comments Accepted to NAACL 2025

2406.10181 2025-02-11 cs.DC cs.AI 85%

Practical offloading for fine-tuning LLM on commodity GPU via learned sparse projectors

Siyuan Chen, Zhuofeng Wang, Zelong Guan, Yudong Liu, Phillip B. Gibbons

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

1. 指令微调 11667 篇

Task-Specific Data Selection for Instruction Tuning via Monosemantic Neuronal Activations

MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering

Biomed-DPT: Dual Modality Prompt Tuning for Biomedical Vision-Language Models

LIFT: LLM-Based Pragma Insertion for HLS via GNN Supervised Fine-Tuning

Can We Trust Embodied Agents? Exploring Backdoor Attacks against Embodied LLM-based Decision-Making Systems

MDIT: A Model-free Data Interpolation Method for Diverse Instruction Tuning

VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model

Face-LLaVA: Facial Expression and Attribute Understanding through Instruction Tuning

LLM Safeguard is a Double-Edged Sword: Exploiting False Positives for Denial-of-Service Attacks

Cultural Learning-Based Culture Adaptation of Language Models

SpeechVerse: A Large-scale Generalizable Audio Language Model

How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM?

ToolFlow: Boosting LLM Tool-Calling Through Natural and Coherent Dialogue Synthesis

Improving Retrospective Language Agents via Joint Policy Gradient Optimization

Facilitating Multi-turn Function Calling for LLMs via Compositional Instruction Tuning

MobiLLM: Enabling LLM Fine-Tuning on the Mobile Device via Server Assisted Side Tuning

GenTool: Enhancing Tool Generalization in Language Models through Zero-to-One and Weak-to-Strong Simulation

CLLoRA: An Approach to Measure the Effects of the Context Length for LLM Fine-Tuning

VisCon-100K: Leveraging Contextual Web Data for Fine-tuning Vision Language Models

Understanding Zero-shot Rare Word Recognition Improvements Through LLM Integration

Coevolving with the Other You: Fine-Tuning LLM with Sequential Cooperative Multi-Agent Reinforcement Learning

MHQA: A Diverse, Knowledge Intensive Mental Health Question Answering Challenge for Language Models

Encryption-Friendly LLM Architecture

Research on Tibetan Tourism Viewpoints information generation system based on LLM

FLAG-Trader: Fusion LLM-Agent with Gradient-based Reinforcement Learning for Financial Trading

Beyond Similarity: A Gradient-based Graph Method for Instruction Tuning Data Selection

Investigating the Zone of Proximal Development of Language Models for In-Context Learning

RS-MoE: A Vision-Language Model with Mixture of Experts for Remote Sensing Image Captioning and Visual Question Answering

Adaptive Prompting: Ad-hoc Prompt Composition for Social Bias Detection

Practical offloading for fine-tuning LLM on commodity GPU via learned sparse projectors