语言大模型 / LLM - arXivDaily 专题

2505.15090 2025-05-22 cs.CL cs.AI cs.LG 80%

DeFTX: Denoised Sparse Fine-Tuning for Zero-Shot Cross-Lingual Transfer

Sona Elza Simon, Preethi Jyothi

机构 * Indian Institute of Technology Bombay（印度理工学院班加罗尔）

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

2410.13852 2025-05-22 cs.CL cs.AI cs.CV cs.LG 80%

Retrospective Learning from Interactions

Zizhao Chen, Mustafa Omer Gul, Yiwei Chen, Gloria Geng, Anne Wu, Yoav Artzi

机构 * Department of Computer Science and Cornell Tech, Cornell University（计算机科学系和康奈尔科技学院，康奈尔大学）

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

2403.09727 2025-05-13 cs.CL cs.AI cs.LG 80%

Investigating the performance of Retrieval-Augmented Generation and fine-tuning for the development of AI-driven knowledge-based systems

Robert Lakatos, Peter Pollner, Andras Hajdu, Tamas Joo

机构 * Department of Data Science and Visualization, Faculty of Informatics, University of Debrecen（数据科学与可视化系，信息学院，德布勒恩大学）； Doctoral School of Informatics, University of Debrecen（信息学博士学校，德布勒恩大学）； Neumann Technology Platform, Neumann Nonprofit Ltd.（内梅尔技术平台，内梅尔非营利有限公司）； Data-Driven Health Division of National Laboratory for Health Security, Health Services Management Training Centre, Semmelweis University（国家安全国家实验室数据驱动健康部，卫生服务管理培训中心，塞梅尔维斯大学）

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

Journal ref Mach. Learn. Knowl. Extr. 2025, 7, 15

2505.03799 2025-05-08 cs.LG cs.AI cs.CL 80%

Scalability Matters: Overcoming Challenges in InstructGLM with Similarity-Degree-Based Sampling

Hyun Lee, Chris Yi, Maminur Islam, B. D. S. Aritra

机构 * Dept. of Computer Science, Trinity College, Hartford, Connecticut, USA（计算机科学系，特里尼蒂学院，哈特福德，康涅狄格州，美国）

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

Comments To be published in International Joint Conference on Neural Networks (IJCNN), 2025

2504.07957 2025-04-29 cs.CV 80%

MM-IFEngine: Towards Multimodal Instruction Following

Shengyuan Ding, Shenxi Wu, Xiangyu Zhao, Yuhang Zang, Haodong Duan, Xiaoyi Dong, Pan Zhang, Yuhang Cao, Dahua Lin, Jiaqi Wang

机构 * Fudan University（复旦大学）； Shanghai AI Laboratory（上海人工智能实验室）； Shanghai Jiaotong University（上海交通大学）； The Chinese University of Hong Kong（香港中文大学）； CPII under InnoHK（创新香港下的CPII）； Shanghai Innovation Institute（上海创新研究院）

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

2504.13958 2025-04-22 cs.LG cs.AI cs.CL 80%

ToolRL: Reward is All Tool Learning Needs

Cheng Qian, Emre Can Acikgoz, Qi He, Hongru Wang, Xiusi Chen, Dilek Hakkani-Tür, Gokhan Tur, Heng Ji

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）

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

Comments 19 Pages, 12 Figures, 12 Tables

2504.13730 2025-04-21 cs.CL cs.AI cs.LG 80%

Controlled Territory and Conflict Tracking (CONTACT): (Geo-)Mapping Occupied Territory from Open Source Intelligence

Paul K. Mandal, Cole Leo, Connor Hurley

机构 * Neurint LLC ； The University of Texas at Austin（德克萨斯大学奥斯汀分校）； T2S Solutions（T2S解决方案）

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

Comments 7 pages, 1 figure, 1 table

2504.04945 2025-04-08 cs.LG cs.AI cs.CL 80%

A Llama walks into the 'Bar': Efficient Supervised Fine-Tuning for Legal Reasoning in the Multi-state Bar Exam

Rean Fernandes, André Biedenkapp, Frank Hutter, Noor Awad

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

Comments COLM 2025 preprint, 9 pages, 3 figures, 16 appendix pages

2502.18778 2025-04-08 cs.LG cs.AI cs.CL 80%

M2-omni: Advancing Omni-MLLM for Comprehensive Modality Support with Competitive Performance

Qingpei Guo, Kaiyou Song, Zipeng Feng, Ziping Ma, Qinglong Zhang, Sirui Gao, Xuzheng Yu, Yunxiao Sun, Tai-Wei Chang, Jingdong Chen, Ming Yang, Jun Zhou

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

2503.23483 2025-04-01 cs.CL cs.AI cs.LG 80%

Order Independence With Finetuning

Katrina Brown, Reid McIlroy

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

Comments Published as a Bi-Align workshop paper at ICLR 2025

2412.11102 2025-03-26 cs.CV 80%

Empowering LLMs to Understand and Generate Complex Vector Graphics

Ximing Xing, Juncheng Hu, Guotao Liang, Jing Zhang, Dong Xu, Qian Yu

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

Comments Accepted by CVPR 2025. Project Page: https://ximinng.github.io/LLM4SVGProject/

2406.05797 2025-03-19 q-bio.BM cs.AI cs.CE cs.CL cs.LG 80%

3D-MolT5: Leveraging Discrete Structural Information for Molecule-Text Modeling

Qizhi Pei, Rui Yan, Kaiyuan Gao, Jinhua Zhu, Lijun Wu

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

Comments Accepted by ICLR 2025

2503.13383 2025-03-18 cs.CV cs.AI cs.CL cs.LG 80%

Cream of the Crop: Harvesting Rich, Scalable and Transferable Multi-Modal Data for Instruction Fine-Tuning

Mengyao Lyu, Yan Li, Huasong Zhong, Wenhao Yang, Hui Chen, Jungong Han, Guiguang Ding, Zhenheng Yang

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

Comments update comparison with sota and analysis

2503.01345 2025-03-04 cs.CL cs.AI cs.LG 80%

Same Question, Different Words: A Latent Adversarial Framework for Prompt Robustness

Tingchen Fu, Fazl Barez

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

2311.01314 2025-02-28 cs.IR 80%

Recommendations by Concise User Profiles from Review Text

Ghazaleh Haratinezhad Torbati, Anna Tigunova, Andrew Yates, Gerhard Weikum

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

2502.18487 2025-02-27 cs.SE cs.AI cs.CL cs.LG 80%

AuPair: Golden Example Pairs for Code Repair

Aditi Mavalankar, Hassan Mansoor, Zita Marinho, Masha Samsikova, Tom Schaul

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

2411.02571 2025-02-25 cs.CL cs.AI cs.CV cs.IR cs.LG 80%

MM-Embed: Universal Multimodal Retrieval with Multimodal LLMs

Sheng-Chieh Lin, Chankyu Lee, Mohammad Shoeybi, Jimmy Lin, Bryan Catanzaro, Wei Ping

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

Comments Accepted at ICLR 2025. We release the model weights at: https://huggingface.co/nvidia/MM-Embed

2410.12480 2025-02-18 cs.CL cs.AI cs.DB cs.LG 80%

KcMF: A Knowledge-compliant Framework for Schema and Entity Matching with Fine-tuning-free LLMs

Yongqin Xu, Huan Li, Ke Chen, Lidan Shou

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

Comments under reveiw; new results and analysis added, typos corrected

2409.16167 2025-02-17 cs.LG cs.AI cs.CL 80%

Merging LoRAs like Playing LEGO: Pushing the Modularity of LoRA to Extremes Through Rank-Wise Clustering

Ziyu Zhao, Tao Shen, Didi Zhu, Zexi Li, Jing Su, Xuwu Wang, Kun Kuang, Fei Wu

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

Journal ref https://openreview.net/forum?id=j6fsbpAllN&referrer=%5BAuthor%20Console%5D(%2Fgroup%3Fid%3DICLR.cc%2F2025%2FConference%2FAuthors%23your-submissions)

2411.14460 2025-02-11 cs.CL cs.AI cs.LG 80%

LLaSA: Large Language and Structured Data Assistant

Yao Xu, Shizhu He, Jiabei Chen, Zeng Xiangrong, Bingning Wang, Guang Liu, Jun Zhao, Kang Liu

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

Comments NAACL 2025 Main

2407.10994 2025-02-11 cs.CL cs.AI cs.HC cs.LG 80%

Panza: Design and Analysis of a Fully-Local Personalized Text Writing Assistant

Armand Nicolicioiu, Eugenia Iofinova, Andrej Jovanovic, Eldar Kurtic, Mahdi Nikdan, Andrei Panferov, Ilia Markov, Nir Shavit, Dan Alistarh

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

Comments Panza is available at https://github.com/IST-DASLab/PanzaMail

2502.02909 2025-02-06 cs.LG cs.AI cs.CL 80%

SPARC: Subspace-Aware Prompt Adaptation for Robust Continual Learning in LLMs

Dinithi Jayasuriya, Sina Tayebati, Davide Ettori, Ranganath Krishnan, Amit Ranjan Trivedi

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

2406.20095 2025-01-31 cs.RO cs.AI cs.CL cs.CV cs.LG 80%

LLaRA: Supercharging Robot Learning Data for Vision-Language Policy

Xiang Li, Cristina Mata, Jongwoo Park, Kumara Kahatapitiya, Yoo Sung Jang, Jinghuan Shang, Kanchana Ranasinghe, Ryan Burgert, Mu Cai, Yong Jae Lee, Michael S. Ryoo

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

Comments ICLR 2025

2501.17030 2025-01-29 cs.LG cs.AI cs.CL cs.CR 80%

Challenges in Ensuring AI Safety in DeepSeek-R1 Models: The Shortcomings of Reinforcement Learning Strategies

Manojkumar Parmar, Yuvaraj Govindarajulu

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

Comments 9 pages, 1 table

2501.13297 2025-01-24 cs.CL cs.AI cs.IR cs.LG 80%

RAMQA: A Unified Framework for Retrieval-Augmented Multi-Modal Question Answering

Yang Bai, Christan Earl Grant, Daisy Zhe Wang

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

Comments Accepted by NAACL 2025 Findings

2501.08187 2025-01-16 cs.CL cs.AI cs.CE cs.HC cs.LG q-bio.CB 80%

A Multi-Modal AI Copilot for Single-Cell Analysis with Instruction Following

Yin Fang, Xinle Deng, Kangwei Liu, Ningyu Zhang, Jingyang Qian, Penghui Yang, Xiaohui Fan, Huajun Chen

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

Comments 37 pages; 13 figures; Code: https://github.com/zjunlp/Instructcell, Models: https://huggingface.co/zjunlp/Instructcell-chat, https://huggingface.co/zjunlp/InstructCell-instruct

2408.11869 2025-01-15 cs.CL cs.AI cs.LG 80%

ELDER: Enhancing Lifelong Model Editing with Mixture-of-LoRA

Jiaang Li, Quan Wang, Zhongnan Wang, Yongdong Zhang, Zhendong Mao

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

Comments Accepted by AAAI-25

2405.18359 2025-01-08 cs.CL cs.AI cs.LG 80%

Bridging the Gap: Dynamic Learning Strategies for Improving Multilingual Performance in LLMs

Somnath Kumar, Vaibhav Balloli, Mercy Ranjit, Kabir Ahuja, Tanuja Ganu, Sunayana Sitaram, Kalika Bali, Akshay Nambi

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

Comments arXiv admin note: text overlap with arXiv:2305.17740

2412.15563 2024-12-23 cs.CL cs.AI cs.LG 80%

In-context Continual Learning Assisted by an External Continual Learner

Saleh Momeni, Sahisnu Mazumder, Zixuan Ke, Bing Liu

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

2412.13922 2024-12-19 cs.CL cs.AI cs.LG 80%

Pipeline Analysis for Developing Instruct LLMs in Low-Resource Languages: A Case Study on Basque

Ander Corral, Ixak Sarasua, Xabier Saralegi

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

1. 指令微调 11653 篇

DeFTX: Denoised Sparse Fine-Tuning for Zero-Shot Cross-Lingual Transfer

Retrospective Learning from Interactions

Investigating the performance of Retrieval-Augmented Generation and fine-tuning for the development of AI-driven knowledge-based systems

Scalability Matters: Overcoming Challenges in InstructGLM with Similarity-Degree-Based Sampling

MM-IFEngine: Towards Multimodal Instruction Following

ToolRL: Reward is All Tool Learning Needs

Controlled Territory and Conflict Tracking (CONTACT): (Geo-)Mapping Occupied Territory from Open Source Intelligence

A Llama walks into the 'Bar': Efficient Supervised Fine-Tuning for Legal Reasoning in the Multi-state Bar Exam

M2-omni: Advancing Omni-MLLM for Comprehensive Modality Support with Competitive Performance

Order Independence With Finetuning

Empowering LLMs to Understand and Generate Complex Vector Graphics

3D-MolT5: Leveraging Discrete Structural Information for Molecule-Text Modeling

Cream of the Crop: Harvesting Rich, Scalable and Transferable Multi-Modal Data for Instruction Fine-Tuning

Same Question, Different Words: A Latent Adversarial Framework for Prompt Robustness

Recommendations by Concise User Profiles from Review Text

AuPair: Golden Example Pairs for Code Repair

MM-Embed: Universal Multimodal Retrieval with Multimodal LLMs

KcMF: A Knowledge-compliant Framework for Schema and Entity Matching with Fine-tuning-free LLMs

Merging LoRAs like Playing LEGO: Pushing the Modularity of LoRA to Extremes Through Rank-Wise Clustering

LLaSA: Large Language and Structured Data Assistant

Panza: Design and Analysis of a Fully-Local Personalized Text Writing Assistant

SPARC: Subspace-Aware Prompt Adaptation for Robust Continual Learning in LLMs

LLaRA: Supercharging Robot Learning Data for Vision-Language Policy

Challenges in Ensuring AI Safety in DeepSeek-R1 Models: The Shortcomings of Reinforcement Learning Strategies

RAMQA: A Unified Framework for Retrieval-Augmented Multi-Modal Question Answering

A Multi-Modal AI Copilot for Single-Cell Analysis with Instruction Following

ELDER: Enhancing Lifelong Model Editing with Mixture-of-LoRA

Bridging the Gap: Dynamic Learning Strategies for Improving Multilingual Performance in LLMs

In-context Continual Learning Assisted by an External Continual Learner

Pipeline Analysis for Developing Instruct LLMs in Low-Resource Languages: A Case Study on Basque