语言大模型 / LLM

Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning

Changsheng Wang, Yihua Zhang, Jinghan Jia, Parikshit Ram, Dennis Wei, Yuguang Yao, Soumyadeep Pal, Nathalie Baracaldo, Sijia Liu

机构 * Michigan State University（密歇根州立大学） ； IBM Research（IBM研究院） 纠错

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

Comments Accepted by ICML 2025

LLP: LLM-based Product Pricing in E-commerce

Hairu Wang, Sheng You, Qiheng Zhang, Xike Xie, Shuguang Han, Yuchen Wu, Fei Huang, Jufeng Chen

机构 * University of Science and Technology of China（中国科学技术大学） ； Xianyu of Alibaba（阿里巴巴闲鱼） 纠错

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

QGuard:Question-based Zero-shot Guard for Multi-modal LLM Safety

Taegyeong Lee, Jeonghwa Yoo, Hyoungseo Cho, Soo Yong Kim, Yunho Maeng

机构 * FnGuide Inc.（FnGuide公司） ； Safe Generative AI Lab, MODULABS（MODULABS安全生成AI实验室） ； A.I.MATICS Inc.（A.I.MATICS公司） ； Ewha Womans University（成均馆大学） 纠错

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

Comments Accept to ACLW 2025 (WOAH); fix typo

Journal ref ACL Workshop 2025

Safety is Not Only About Refusal: Reasoning-Enhanced Fine-tuning for Interpretable LLM Safety

Yuyou Zhang, Miao Li, William Han, Yihang Yao, Zhepeng Cen, Ding Zhao

机构 * Carnegie Mellon University（卡内基梅隆大学） 纠错

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

Comments ACL 2025 Findings

Tool Calling for Arabic LLMs: Data Strategies and Instruction Tuning

Asim Ersoy, Enes Altinisik, Husrev Taha Sencar, Kareem Darwish

机构 * Qatar Computing Research Institute, HBKU（卡塔尔计算研究所，哈塔姆大学） 纠错

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

Journal ref ArabicNLP 2025

We Politely Insist: Your LLM Must Learn the Persian Art of Taarof

Nikta Gohari Sadr, Sahar Heidariasl, Karine Megerdoomian, Laleh Seyyed-Kalantari, Ali Emami

机构 * Brock University（布鲁克大学） ； Zoorna AI ； York University（约克大学） ； Emory University（埃默里大学） 纠错

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

Comments Accepted to EMNLP 2025 Main Conference

M3PO: Multimodal-Model-Guided Preference Optimization for Visual Instruction Following

Ruirui Gao, Emily Johnson, Bowen Tan, Yanfei Qian

机构 * University of Massachusetts, Amherst（马萨诸塞大学阿姆赫斯特分校） 纠错

专题命中 指令微调 ：preference optimization(title,abstract)；language model(abstract)；SFT(abstract)；RLHF(abstract)

Classifier Language Models: Unifying Sparse Finetuning and Adaptive Tokenization for Specialized Classification Tasks

Adit Krishnan, Chu Wang, Chris Kong

机构 * Amazon Web Services Inc.（亚马逊网络服务公司） 纠错

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

Comments 10 pages, 4 figures, currently under review

Aligning Instruction Tuning with Pre-training

Yiming Liang, Tianyu Zheng, Xinrun Du, Ge Zhang, Jiaheng Liu, Xingwei Qu, Wenqiang Zu, Xingrun Xing, Chujie Zheng, Lei Ma, Guoyin Wang, Zhaoxiang Zhang, Wenhao Huang, Xiang Yue, Jiajun Zhang

机构 * School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院） ； Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所） ； Peking University（北京大学） 纠错

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

Few-Shot Prompting for Extractive Quranic QA with Instruction-Tuned LLMs

Mohamed Basem, Islam Oshallah, Ali Hamdi, Ammar Mohammed

机构 * Faculty of Computer Science MSA University Giza, Egypt（计算机科学学院 MSA大学 埃及吉扎） ； Faculty of Computer Science MSA University Egypt（计算机科学学院 MSA大学 埃及） 纠错

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

Comments 6 pages , 2 figures , Accepted in IMSA 2025,Egypt , https://imsa.msa.edu.eg/

FineMedLM-o1: Enhancing Medical Knowledge Reasoning Ability of LLM from Supervised Fine-Tuning to Test-Time Training

Hongzhou Yu, Tianhao Cheng, Yingwen Wang, Wen He, Qing Wang, Ying Cheng, Yuejie Zhang, Rui Feng, Xiaobo Zhang

机构 * Fudan University（复旦大学） ； Children’s Hospital of Fudan University（复旦大学附属儿童医院） 纠错

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

P4OMP: Retrieval-Augmented Prompting for OpenMP Parallelism in Serial Code

Wali Mohammad Abdullah, Azmain Kabir

机构 * Mathematics \& Information Technology Concordia University of Edmonton Edmonton, Alberta, Canada ； Computer Science University of Manitoba Winnipeg, Manitoba, Canada 纠错

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

BREAD: Branched Rollouts from Expert Anchors Bridge SFT & RL for Reasoning

Xuechen Zhang, Zijian Huang, Yingcong Li, Chenshun Ni, Jiasi Chen, Samet Oymak

机构 * University of Michigan（密歇根大学） 纠错

专题命中 指令微调 ：SFT(title,abstract)；language model(abstract)；small language model(abstract)；SLM(abstract)

sPhinX: Sample Efficient Multilingual Instruction Fine-Tuning Through N-shot Guided Prompting

Sanchit Ahuja, Kumar Tanmay, Hardik Hansrajbhai Chauhan, Barun Patra, Kriti Aggarwal, Luciano Del Corro, Arindam Mitra, Tejas Indulal Dhamecha, Ahmed Awadallah, Monojit Choudhary, Vishrav Chaudhary, Sunayana Sitaram

机构 * Microsoft Corporation（微软公司） ； Harvard University（哈佛大学） ； Adobe Research（Adobe研究） ； MBZUAI University（MBZUAI大学） ； Hippocratic AI ； Meta AI 纠错

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

Comments 20 pages, 12 tables, 5 figures

Lost in the Mix: Evaluating LLM Understanding of Code-Switched Text

Amr Mohamed, Yang Zhang, Michalis Vazirgiannis, Guokan Shang

机构 * MBZUAI ； Ecole Polytechnique（巴黎高等理工学院） 纠错

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

FedVLMBench: Benchmarking Federated Fine-Tuning of Vision-Language Models

Weiying Zheng, Ziyue Lin, Pengxin Guo, Yuyin Zhou, Feifei Wang, Liangqiong Qu

机构 * The University of Hong Kong（香港大学） ； UC Santa Cruz（圣克拉拉大学） 纠错

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

AdvBDGen: Adversarially Fortified Prompt-Specific Fuzzy Backdoor Generator Against LLM Alignment

Pankayaraj Pathmanathan, Udari Madhushani Sehwag, Michael-Andrei Panaitescu-Liess, Furong Huang

机构 * University of Maryland（马里兰大学） ； JPMorgan AI Research（摩根大通人工智能研究） ； University of Maryland Capital One（马里兰大学Capital One） 纠错

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

Comments Published at the Neurips Safe Generative AI Workshop 2024

From Macro to Micro: Probing Dataset Diversity in Language Model Fine-Tuning

Haoyu Li, Xuhong Li, Yiming Dong, Kun Liu

机构 * School of Automation, Beijing Institute of Technology（北京理工大学自动化学院） ； Baidu Inc.（百度公司） ； School of Physics, Peking University（北京大学物理学院） 纠错

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

Respond to Change with Constancy: Instruction-tuning with LLM for Non-I.I.D. Network Traffic Classification

Xinjie Lin, Gang Xiong, Gaopeng Gou, Wenqi Dong, Jing Yu, Zhen Li, Wei Xia

机构 * Zhongguancun Laboratory, Beijing 100094, China（中关村实验室，北京100094，中国） ； Institute of Information Engineering, Chinese Academy of Sciences（信息工程研究所，中国科学院） ； School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络安全学院） 纠错

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

Comments IEEE Transactions on Information Forensics and Security (TIFS) camera ready, 15 pages, 6 figures, 7 tables

Bridging the Gap: Self-Optimized Fine-Tuning for LLM-based Recommender Systems

Heng Tang, Feng Liu, Xinbo Chen, Jiawei Chen, Bohao Wang, Changwang Zhang, Jun Wang, Yuegang Sun, Bingde Hu, Can Wang

机构 * Zhejiang University（浙江大学） ； OPPO Research Institute（OPPO研究院） ； South China University of Technology（华南理工大学） ； Intelligence Indeed（智境科技） 纠错

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

ASMA-Tune: Unlocking LLMs' Assembly Code Comprehension via Structural-Semantic Instruction Tuning

Xinyi Wang, Jiashui Wang, Jinbo Su, Ke Wang, Peng Chen, Yanming Liu, Long Liu, Xiang Li, Yangdong Wang, Qiyuan Chen, Rongze Chen, Chunfu Jia

机构 * Nankai University（南开大学） ； Zhejiang University（浙江大学） ； Ant Group（蚂蚁集团） ； Renmin University of China（中国人民大学） ； University of the Chinese Academy of Sciences（中国科学院大学） 纠错

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

Comments 9 pages, multiple figures

VLM Q-Learning: Aligning Vision-Language Models for Interactive Decision-Making

Jake Grigsby, Yuke Zhu, Michael Ryoo, Juan Carlos Niebles

机构 * The University of Texas at Austin（德克萨斯大学奥斯汀分校） ； Salesforce AI Research（Salesforce人工智能研究） 纠错

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

Comments SSI-FM Workshop ICLR 2025

VARGPT-v1.1: Improve Visual Autoregressive Large Unified Model via Iterative Instruction Tuning and Reinforcement Learning

Xianwei Zhuang, Yuxin Xie, Yufan Deng, Dongchao Yang, Liming Liang, Jinghan Ru, Yuguo Yin, Yuexian Zou

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

Comments Code is available at: https://github.com/VARGPT-family/VARGPT-v1.1. arXiv admin note: text overlap with arXiv:2501.12327

Improving LLM-based Document-level Machine Translation with Multi-Knowledge Fusion

Bin Liu, Xinglin Lyu, Junhui Li, Daimeng Wei, Min Zhang, Shimin Tao, Hao Yang

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

BioMistral-NLU: Towards More Generalizable Medical Language Understanding through Instruction Tuning

Yujuan Velvin Fu, Giridhar Kaushik Ramachandran, Namu Park, Kevin Lybarger, Fei Xia, Ozlem Uzuner, Meliha Yetisgen

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

Comments 3 figures an 5 tables; Accepted by AMIA 2025 Informatics Summit

FuseChat-3.0: Preference Optimization Meets Heterogeneous Model Fusion

Ziyi Yang, Fanqi Wan, Longguang Zhong, Canbin Huang, Guosheng Liang, Xiaojun Quan

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

Comments Technical report

GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation

Runchuan Zhu, Zinco Jiang, Jiang Wu, Zhipeng Ma, Jiahe Song, Fengshuo Bai, Dahua Lin, Lijun Wu, Conghui He

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

Comments Equal contribution: Runchuan Zhu, Zinco Jiang, Jiang Wu; Corresponding author: Conghui He

SeDi-Instruct: Enhancing Alignment of Language Models through Self-Directed Instruction Generation

Jungwoo Kim, Minsang Kim, Sungjin Lee

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

Comments 12 pages, 12 figures

ProVision: Programmatically Scaling Vision-centric Instruction Data for Multimodal Language Models

Jieyu Zhang, Le Xue, Linxin Song, Jun Wang, Weikai Huang, Manli Shu, An Yan, Zixian Ma, Juan Carlos Niebles, Silvio Savarese, Caiming Xiong, Zeyuan Chen, Ranjay Krishna, Ran Xu

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

Comments code: https://github.com/JieyuZ2/ProVision dataset: https://huggingface.co/datasets/Salesforce/ProVision-10M

Online Learning from Strategic Human Feedback in LLM Fine-Tuning

Shugang Hao, Lingjie Duan

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