语言大模型 / LLM

Are They the Same? Exploring Visual Correspondence Shortcomings of Multimodal LLMs

Yikang Zhou, Tao Zhang, Shilin Xu, Shihao Chen, Qianyu Zhou, Yunhai Tong, Shunping Ji, Jiangning Zhang, Lu Qi, Xiangtai Li

机构 * Wuhan University（武汉大学） ； Bytedance Seed（字节跳动种子） ； Peking University（北京大学） ； Zhejiang University（浙江大学） ； SJTU（上海交通大学） 纠错

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

Comments Accepted by ICCV2025

Re-Emergent Misalignment: How Narrow Fine-Tuning Erodes Safety Alignment in LLMs

Jeremiah Giordani

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

LLMREI: Automating Requirements Elicitation Interviews with LLMs

Alexander Korn, Samuel Gorsch, Andreas Vogelsang

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

Dynamic Context-oriented Decomposition for Task-aware Low-rank Adaptation with Less Forgetting and Faster Convergence

Yibo Yang, Sihao Liu, Chuan Rao, Bang An, Tiancheng Shen, Philip H. S. Torr, Ming-Hsuan Yang, Bernard Ghanem

机构 * King Abdullah University of Science and Technology, Saudi Arabia（卡布尔大学） ； University of California, Merced, USA（加州大学梅尔德分校） ； University of Oxford, U.K.（牛津大学） 纠错

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

RARL: Improving Medical VLM Reasoning and Generalization with Reinforcement Learning and LoRA under Data and Hardware Constraints

Tan-Hanh Pham, Chris Ngo

机构 * Harvard Medical School（哈佛医学院） ； Knovel Engineering Lab（Knovel工程实验室） 纠错

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

Comments Under review

Alpha-SQL: Zero-Shot Text-to-SQL using Monte Carlo Tree Search

Boyan Li, Jiayi Zhang, Ju Fan, Yanwei Xu, Chong Chen, Nan Tang, Yuyu Luo

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

Comments ICML 2025

PFDial: A Structured Dialogue Instruction Fine-tuning Method Based on UML Flowcharts

Ming Zhang, Yuhui Wang, Yujiong Shen, Tingyi Yang, Changhao Jiang, Yilong Wu, Shihan Dou, Qinhao Chen, Zhiheng Xi, Zhihao Zhang, Yi Dong, Zhen Wang, Zhihui Fei, Mingyang Wan, Tao Liang, Guojun Ma, Qi Zhang, Tao Gui, Xuanjing Huang

机构 * College of Computer Science and Artificial Intelligence, Fudan University（复旦大学计算机科学与人工智能学院） ； Douyin Co., Ltd.（抖音公司） ； Institute of Modern Languages and Linguistics, Fudan University（复旦大学现代语言与语言学研究所） ； Institute of Trustworthy Embodied Artificial Intelligence, Fudan University（复旦大学可信具身人工智能研究所） ； Graduate School of Arts and Sciences, Columbia University（哥伦比亚大学艺术与科学院） 纠错

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

Towards Understanding Fine-Tuning Mechanisms of LLMs via Circuit Analysis

Xu Wang, Yan Hu, Wenyu Du, Reynold Cheng, Benyou Wang, Difan Zou

机构 * School of Computing（计算学院） ； Data Science, The University of Hong Kong（数据科学，香港大学） ； School of Data Science, The Chinese University of Hong Kong, Shenzhen（数据科学学院，香港中文大学（深圳）） 纠错

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

Comments 25 pages

ClusterUCB: Efficient Gradient-Based Data Selection for Targeted Fine-Tuning of LLMs

Zige Wang, Qi Zhu, Fei Mi, Minghui Xu, Ruochun Jin, Wenjing Yang

机构 * School of Computer Science, Peking University（北京大学计算机学院） ； College of Computer Science and Technology, National University of Defense Technology（国防科技大学计算机科学与技术学院） 纠错

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

Tina: Tiny Reasoning Models via LoRA

Shangshang Wang, Julian Asilis, Ömer Faruk Akgül, Enes Burak Bilgin, Ollie Liu, Willie Neiswanger

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

PEFTGuard: Detecting Backdoor Attacks Against Parameter-Efficient Fine-Tuning

Zhen Sun, Tianshuo Cong, Yule Liu, Chenhao Lin, Xinlei He, Rongmao Chen, Xingshuo Han, Xinyi Huang

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

Comments 21 pages, 7 figures

Journal ref 2025 IEEE Symposium on Security and Privacy (SP)

LoRMA: Low-Rank Multiplicative Adaptation for LLMs

Harsh Bihany, Shubham Patel, Ashutosh Modi

机构 * Indian Institute of Technology Kanpur (IIT Kanpur)（印度理工学院坎浦尔学院） 纠错

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

Comments Accepted at ACL Findings 2025; 21 pages (9 main paper + 5 pages references + 7 pages appendix)

ModelForge: Using GenAI to Improve the Development of Security Protocols

Martin Duclos, Ivan A. Fernandez, Kaneesha Moore, Sudip Mittal, Edward Zieglar

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

Defensive Prompt Patch: A Robust and Interpretable Defense of LLMs against Jailbreak Attacks

Chen Xiong, Xiangyu Qi, Pin-Yu Chen, Tsung-Yi Ho

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

KnowCoder-X: Boosting Multilingual Information Extraction via Code

Yuxin Zuo, Wenxuan Jiang, Wenxuan Liu, Zixuan Li, Long Bai, Hanbin Wang, Yutao Zeng, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng

机构 * Key Laboratory of Network Data Science and Technology, Institute of Computing Technology, Chinese Academy of Sciences（网络数据科学与技术重点实验室，计算技术研究所，中国科学院） ； State Key Laboratory of AI Safety（人工智能安全国家重点实验室） ； School of Computer Science, University of Chinese Academy of Sciences（中国科学院大学计算机科学学院） ； School of Software, Northeastern University（东北大学软件学院） ； School of Software, Peking University（北京大学软件学院） 纠错

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

Comments ACL 2025 Findings

Enhancing LLMs' Reasoning-Intensive Multimedia Search Capabilities through Fine-Tuning and Reinforcement Learning

Jinzheng Li, Sibo Ju, Yanzhou Su, Hongguang Li, Yiqing Shen

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

Q-Insight: Understanding Image Quality via Visual Reinforcement Learning

Weiqi Li, Xuanyu Zhang, Shijie Zhao, Yabin Zhang, Junlin Li, Li Zhang, Jian Zhang

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

When LLMs Learn to be Students: The SOEI Framework for Modeling and Evaluating Virtual Student Agents in Educational Interaction

Yiping Ma, Shiyu Hu, Xuchen Li, Yipei Wang, Yuqing Chen, Shiqing Liu, Kang Hao Cheong

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

Does Low Rank Adaptation Lead to Lower Robustness against Training-Time Attacks?

Zi Liang, Haibo Hu, Qingqing Ye, Yaxin Xiao, Ronghua Li

机构 * Zi Liang（张利亚） ； Haibo Hu（胡浩波） ； Qingqing Ye（叶青青） ； Yaxin Xiao（肖亚欣） ； Ronghua Li（李荣华） 纠错

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

Comments To appear at ICML 25

Multi-Token Prediction Needs Registers

Anastasios Gerontopoulos, Spyros Gidaris, Nikos Komodakis

机构 * Archimedes, Athena Research Center University of Crete（阿基米德，亚特兰蒂斯研究中心，克里特大学） ； IACM-Forth（IACM-福蒂） 纠错

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

Batch Augmentation with Unimodal Fine-tuning for Multimodal Learning

H M Dipu Kabir, Subrota Kumar Mondal, Mohammad Ali Moni

机构 * AI and Cyber Futures Institute, Charles Sturt University, Australia（人工智能与网络未来研究所，查尔斯·斯特劳特大学，澳大利亚） ； Rural Health Research Institute, Charles Sturt University, Australia（农村健康研究研究所，查尔斯·斯特劳特大学，澳大利亚） ； School of Computer Science and Engineering, Macau University of Science and Technology, Macao（计算机科学与工程学院，澳门科学技术大学，澳门） 纠错

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

Evaluating Contrastive Feedback for Effective User Simulations

Andreas Konstantin Kruff, Timo Breuer, Philipp Schaer

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

An Empirical Study on the Capability of LLMs in Decomposing Bug Reports

Zhiyuan Chen, Vanessa Nava-Camal, Ahmad Suleiman, Yiming Tang, Daqing Hou, Weiyi Shang

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

Automating Function-Level TARA for Automotive Full-Lifecycle Security

Yuqiao Yang, Yongzhao Zhang, Wenhao Liu, Jun Li, Pengtao Shi, DingYu Zhong, Jie Yang, Ting Chen, Sheng Cao, Yuntao Ren, Yongyue Wu, Xiaosong Zhang

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

TLAC: Two-stage LMM Augmented CLIP for Zero-Shot Classification

Ans Munir, Faisal Z. Qureshi, Muhammad Haris Khan, Mohsen Ali

机构 * Information Technology University（信息科技大学） ； University of Ontario Institute of Technology（Ontario Institute of Technology 大学） ； Mohamed Bin Zayed University of AI（穆罕默德·本·扎耶德人工智能大学） 纠错

专题命中 指令微调 ：LLM(abstract)；pretraining(abstract)；prompting(abstract)

Comments Added code link in the abstract

PathVLM-R1: A Reinforcement Learning-Driven Reasoning Model for Pathology Visual-Language Tasks

Jianyu Wu, Hao Yang, Xinhua Zeng, Guibing He, Zhiyu Chen, Zihui Li, Xiaochuan Zhang, Yangyang Ma, Run Fang, Yang Liu

机构 * Fudan University（复旦大学） 纠错

专题命中 指令微调 ：language model(abstract)；post-training(abstract)；SFT(abstract)

Sculpting Subspaces: Constrained Full Fine-Tuning in LLMs for Continual Learning

Nikhil Shivakumar Nayak, Krishnateja Killamsetty, Ligong Han, Abhishek Bhandwaldar, Prateek Chanda, Kai Xu, Hao Wang, Aldo Pareja, Oleg Silkin, Mustafa Eyceoz, Akash Srivastava

机构 * Red Hat AI Innovation（红帽AI创新中心） ； IBM Research（IBM研究院） ； IIT Bombay（印度理工学院孟买分校） ； MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室） 纠错

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

Comments 25 pages, 13 figures, 6 tables

DeepSeek-V3, GPT-4, Phi-4, and LLaMA-3.3 generate correct code for LoRaWAN-related engineering tasks

Daniel Fernandes, João P. Matos-Carvalho, Carlos M. Fernandes, Nuno Fachada

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

Comments The peer-reviewed version of this paper is published in Electronics at https://doi.org/10.3390/electronics14071428. This version is typeset by the authors and differs only in pagination and typographical detail

Journal ref Electronics. 2025; 14(7):1428

The H-Elena Trojan Virus to Infect Model Weights: A Wake-Up Call on the Security Risks of Malicious Fine-Tuning

Virilo Tejedor, Cristina Zuheros, Carlos Peláez-González, David Herrera-Poyatos, Andrés Herrera-Poyatos, Francisco Herrera

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

GeoRAG: A Question-Answering Approach from a Geographical Perspective

Jian Wang, Zhuo Zhao, Zeng Jie Wang, Bo Da Cheng, Lei Nie, Wen Luo, Zhao Yuan Yu, Ling Wang Yuan

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