语言大模型 / LLM - arXivDaily 专题

2503.24307 2025-04-01 cs.CL cs.AI cs.IR cs.LG 87%

A Systematic Evaluation of LLM Strategies for Mental Health Text Analysis: Fine-tuning vs. Prompt Engineering vs. RAG

Arshia Kermani, Veronica Perez-Rosas, Vangelis Metsis

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

2402.09906 2025-03-04 cs.CL cs.AI cs.LG 87%

Generative Representational Instruction Tuning

Niklas Muennighoff, Hongjin Su, Liang Wang, Nan Yang, Furu Wei, Tao Yu, Amanpreet Singh, Douwe Kiela

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

Comments 67 pages (16 main), 25 figures, 34 tables

2502.09369 2025-02-14 cs.LG cs.AI cs.CL cs.CY 87%

Language Agents as Digital Representatives in Collective Decision-Making

Daniel Jarrett, Miruna Pîslar, Michiel A. Bakker, Michael Henry Tessler, Raphael Köster, Jan Balaguer, Romuald Elie, Christopher Summerfield, Andrea Tacchetti

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

2502.04997 2025-02-10 cs.CL cs.AI cs.LG 87%

Aligning Black-box Language Models with Human Judgments

Gerrit J. J. van den Burg, Gen Suzuki, Wei Liu, Murat Sensoy

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 Accepted for publication at NAACL 2025 (Findings)

2502.01116 2025-02-04 cs.AI cs.CL cs.LG 87%

Picky LLMs and Unreliable RMs: An Empirical Study on Safety Alignment after Instruction Tuning

Guanlin Li, Kangjie Chen, Shangwei Guo, Jie Zhang, Han Qiu, Chao Zhang, Guoyin Wang, Tianwei Zhang, Jiwei Li

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

2501.17186 2025-01-31 cs.AI cs.CL cs.LG 87%

Complete Chess Games Enable LLM Become A Chess Master

Yinqi Zhang, Xintian Han, Haolong Li, Kedi Chen, Shaohui Lin

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 NAACL 2025

2501.04675 2025-01-09 cs.CL cs.AI cs.CV cs.LG 87%

Enhancing Financial VQA in Vision Language Models using Intermediate Structured Representations

Archita Srivastava, Abhas Kumar, Rajesh Kumar, Prabhakar Srinivasan

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

2409.19878 2025-01-06 cs.SD eess.AS 87%

HDMoLE: Mixture of LoRA Experts with Hierarchical Routing and Dynamic Thresholds for Fine-Tuning LLM-based ASR Models

Bingshen Mu, Kun Wei, Qijie Shao, Yong Xu, Lei Xie

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

Comments Accepted by ICASSP 2025

2408.14512 2024-12-20 cs.LG cs.AI cs.CL 87%

LLMs as Zero-shot Graph Learners: Alignment of GNN Representations with LLM Token Embeddings

Duo Wang, Yuan Zuo, Fengzhi Li, Junjie 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、cs.LG

2412.12417 2024-12-18 cs.CL cs.AI cs.LG 87%

Bridging the Gap: Enhancing LLM Performance for Low-Resource African Languages with New Benchmarks, Fine-Tuning, and Cultural Adjustments

Tuka Alhanai, Adam Kasumovic, Mohammad Ghassemi, Aven Zitzelberger, Jessica Lundin, Guillaume Chabot-Couture

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 to AAAI 2025. Main content is 9 pages, 3 figures. Includes supplementary materials

2310.00704 2024-12-11 cs.SD eess.AS 87%

UniAudio: An Audio Foundation Model Toward Universal Audio Generation

Dongchao Yang, Jinchuan Tian, Xu Tan, Rongjie Huang, Songxiang Liu, Xuankai Chang, Jiatong Shi, Sheng Zhao, Jiang Bian, Zhou Zhao, Xixin Wu, Helen Meng

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

2403.19211 2024-12-03 cs.LG cs.AI cs.CL 87%

Dual-Personalizing Adapter for Federated Foundation Models

Yiyuan Yang, Guodong Long, Tao Shen, Jing Jiang, Michael Blumenstein

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

2409.15367 2024-11-19 cs.LG cs.AI cs.CL 87%

Fine-Tuning a Time Series Foundation Model with Wasserstein Loss

Andrei Chernov

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

Comments 4 main pages; 2 figures

2411.09595 2024-11-15 cs.LG cs.AI cs.CL cs.CV 87%

LLaMA-Mesh: Unifying 3D Mesh Generation with Language Models

Zhengyi Wang, Jonathan Lorraine, Yikai Wang, Hang Su, Jun Zhu, Sanja Fidler, Xiaohui Zeng

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 See the project website at https://research.nvidia.com/labs/toronto-ai/LLaMA-Mesh/

2411.05877 2024-11-12 cs.LG cs.AI cs.CL stat.ML 87%

Generative Adapter: Contextualizing Language Models in Parameters with A Single Forward Pass

Tong Chen, Hao Fang, Patrick Xia, Xiaodong Liu, Benjamin Van Durme, Luke Zettlemoyer, Jianfeng Gao, Hao Cheng

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

2410.07563 2024-10-23 cs.CL cs.AI cs.LG 87%

PLaMo-100B: A Ground-Up Language Model Designed for Japanese Proficiency

Preferred Elements, :, Kenshin Abe, Kaizaburo Chubachi, Yasuhiro Fujita, Yuta Hirokawa, Kentaro Imajo, Toshiki Kataoka, Hiroyoshi Komatsu, Hiroaki Mikami, Tsuguo Mogami, Shogo Murai, Kosuke Nakago, Daisuke Nishino, Toru Ogawa, Daisuke Okanohara, Yoshihiko Ozaki, Shotaro Sano, Shuji Suzuki, Tianqi Xu, Toshihiko Yanase

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

2406.00333 2024-10-17 cs.IR 87%

A Practice-Friendly LLM-Enhanced Paradigm with Preference Parsing for Sequential Recommendation

Dugang Liu, Shenxian Xian, Xiaolin Lin, Xiaolian Zhang, Hong Zhu, Yuan Fang, Zhen Chen, Zhong Ming

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

2402.10207 2024-10-17 cs.LG cs.AI cs.CL 87%

Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment

Rui Yang, Xiaoman Pan, Feng Luo, Shuang Qiu, Han Zhong, Dong Yu, Jianshu Chen

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

Comments Accepted by ICML 2024

2410.07471 2024-10-14 cs.LG cs.AI cs.CL 87%

SEAL: Safety-enhanced Aligned LLM Fine-tuning via Bilevel Data Selection

Han Shen, Pin-Yu Chen, Payel Das, Tianyi 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、cs.LG

2410.03743 2024-10-08 cs.CL cs.AI cs.LG 87%

Mitigating Training Imbalance in LLM Fine-Tuning via Selective Parameter Merging

Yiming Ju, Ziyi Ni, Xingrun Xing, Zhixiong Zeng, hanyu Zhao, Siqi Fan, Zheng Zhang

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

Comments EMNLP 2024

2409.12958 2024-09-20 cs.CL cs.AI cs.LG 87%

MURI: High-Quality Instruction Tuning Datasets for Low-Resource Languages via Reverse Instructions

Abdullatif Köksal, Marion Thaler, Ayyoob Imani, Ahmet Üstün, Anna Korhonen, Hinrich Schütze

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

2409.09383 2024-09-18 cs.LG cs.AI cs.CL 87%

LLM-Powered Ensemble Learning for Paper Source Tracing: A GPU-Free Approach

Kunlong Chen, Junjun Wang, Zhaoqun Chen, Kunjin Chen, Yitian 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、cs.LG

2408.14572 2024-08-28 cs.LG cs.AI cs.CL 87%

CURLoRA: Stable LLM Continual Fine-Tuning and Catastrophic Forgetting Mitigation

Muhammad Fawi

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 Code available at https://github.com/MNoorFawi/curlora

2408.04693 2024-08-15 cs.CL cs.AI cs.LG 87%

Understanding the Performance and Estimating the Cost of LLM Fine-Tuning

Yuchen Xia, Jiho Kim, Yuhan Chen, Haojie Ye, Souvik Kundu, Cong Hao, Nishil Talati

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 10 pages, conference

2408.06087 2024-08-13 cs.CL cs.AI cs.LG 87%

Building Decision Making Models Through Language Model Regime

Yu Zhang, Haoxiang Liu, Feijun Jiang, Weihua Luo, Kaifu 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

2407.15235 2024-07-23 cs.CL cs.AI cs.LG 87%

TAGCOS: Task-agnostic Gradient Clustered Coreset Selection for Instruction Tuning Data

Jipeng Zhang, Yaxuan Qin, Renjie Pi, Weizhong Zhang, Rui Pan, Tong 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、cs.LG

Comments Preprint. Our code and models are available at: https://github.com/2003pro/TAGCOS

2403.12736 2024-07-18 cs.CV 87%

Towards Multimodal In-Context Learning for Vision & Language Models

Sivan Doveh, Shaked Perek, M. Jehanzeb Mirza, Wei Lin, Amit Alfassy, Assaf Arbelle, Shimon Ullman, Leonid Karlinsky

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

2305.14428 2024-07-11 cs.CV 87%

Prompting Language-Informed Distribution for Compositional Zero-Shot Learning

Wentao Bao, Lichang Chen, Heng Huang, Yu Kong

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

Comments ECCV 2024 Accepted

2401.12963 2024-07-03 cs.RO cs.AI cs.CL cs.CV cs.LG 87%

AutoRT: Embodied Foundation Models for Large Scale Orchestration of Robotic Agents

Michael Ahn, Debidatta Dwibedi, Chelsea Finn, Montse Gonzalez Arenas, Keerthana Gopalakrishnan, Karol Hausman, Brian Ichter, Alex Irpan, Nikhil Joshi, Ryan Julian, Sean Kirmani, Isabel Leal, Edward Lee, Sergey Levine, Yao Lu, Isabel Leal, Sharath Maddineni, Kanishka Rao, Dorsa Sadigh, Pannag Sanketi, Pierre Sermanet, Quan Vuong, Stefan Welker, Fei Xia, Ted Xiao, Peng Xu, Steve Xu, Zhuo Xu

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

Comments 26 pages, 9 figures, ICRA 2024 VLMNM Workshop

2406.19552 2024-07-01 cs.CL cs.AI cs.LG 87%

Rethinking harmless refusals when fine-tuning foundation models

Florin Pop, Judd Rosenblatt, Diogo Schwerz de Lucena, Michael Vaiana

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

Comments ICLR 2024 AGI Workshop Poster

1. 指令微调 11585 篇

A Systematic Evaluation of LLM Strategies for Mental Health Text Analysis: Fine-tuning vs. Prompt Engineering vs. RAG

Generative Representational Instruction Tuning

Language Agents as Digital Representatives in Collective Decision-Making

Aligning Black-box Language Models with Human Judgments

Picky LLMs and Unreliable RMs: An Empirical Study on Safety Alignment after Instruction Tuning

Complete Chess Games Enable LLM Become A Chess Master

Enhancing Financial VQA in Vision Language Models using Intermediate Structured Representations

HDMoLE: Mixture of LoRA Experts with Hierarchical Routing and Dynamic Thresholds for Fine-Tuning LLM-based ASR Models

LLMs as Zero-shot Graph Learners: Alignment of GNN Representations with LLM Token Embeddings

Bridging the Gap: Enhancing LLM Performance for Low-Resource African Languages with New Benchmarks, Fine-Tuning, and Cultural Adjustments

UniAudio: An Audio Foundation Model Toward Universal Audio Generation

Dual-Personalizing Adapter for Federated Foundation Models

Fine-Tuning a Time Series Foundation Model with Wasserstein Loss

LLaMA-Mesh: Unifying 3D Mesh Generation with Language Models

Generative Adapter: Contextualizing Language Models in Parameters with A Single Forward Pass

PLaMo-100B: A Ground-Up Language Model Designed for Japanese Proficiency

A Practice-Friendly LLM-Enhanced Paradigm with Preference Parsing for Sequential Recommendation

Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment

SEAL: Safety-enhanced Aligned LLM Fine-tuning via Bilevel Data Selection

Mitigating Training Imbalance in LLM Fine-Tuning via Selective Parameter Merging

MURI: High-Quality Instruction Tuning Datasets for Low-Resource Languages via Reverse Instructions

LLM-Powered Ensemble Learning for Paper Source Tracing: A GPU-Free Approach

CURLoRA: Stable LLM Continual Fine-Tuning and Catastrophic Forgetting Mitigation

Understanding the Performance and Estimating the Cost of LLM Fine-Tuning

Building Decision Making Models Through Language Model Regime

TAGCOS: Task-agnostic Gradient Clustered Coreset Selection for Instruction Tuning Data

Towards Multimodal In-Context Learning for Vision & Language Models

Prompting Language-Informed Distribution for Compositional Zero-Shot Learning

AutoRT: Embodied Foundation Models for Large Scale Orchestration of Robotic Agents

Rethinking harmless refusals when fine-tuning foundation models