语言大模型 / LLM

Grounded Vision-Language Navigation for UAVs with Open-Vocabulary Goal Understanding

Yuhang Zhang, Haosheng Yu, Jiaping Xiao, Mir Feroskhan

机构 * School of Mechanical and Aerospace Engineering, Nanyang Technological University（机械与航空航天工程学院，南洋理工大学） 纠错

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

GraphThought: Graph Combinatorial Optimization with Thought Generation

Zixiao Huang, Lifeng Guo, Wenhao Li, Junjie Sheng, Chuyun Shen, Haosheng Chen, Bo Jin, Changhong Lu, Xiangfeng Wang

机构 * East China Normal University（东华大学） ； Tongji University（同济大学） ； Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University（上海智能自主系统研究院，同济大学） ； Key Laboratory of Mathematics and Engineering Applications, MoE, East China Normal University（数学与工程应用重点实验室，教育部，东华大学） 纠错

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

Comments 41 pages, 5 figures, 13 tables

Logits-Based Finetuning

Jingyao Li, Senqiao Yang, Sitong Wu, Han Shi, Chuanyang Zheng, Hong Xu, Jiaya Jia

机构 * The Chinese University of Hong Kong（香港中文大学） ； Huawei Noah’s Ark Lab（华为诺亚实验室） ； Hong Kong University of Science and Technology（香港科技大学） 纠错

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

FlowBERT: Prompt-tuned BERT for variable flow field prediction

Weihao Zou, Weibing Feng, Pin Wu

机构 * School of Computer Engineering and Science, Shanghai University, Shanghai 200444, China（计算机工程与科学学院，上海大学，上海200444，中国） 纠错

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

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior

Penghao Wu, Shengnan Ma, Bo Wang, Jiaheng Yu, Lewei Lu, Ziwei Liu

机构 * S-Lab, Nanyang Technological University（南洋理工大学S实验室） ； SenseTime Research（商汤科技研究院） 纠错

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

Comments Project Page at https://penghao-wu.github.io/GUI_Reflection/

Hallucination at a Glance: Controlled Visual Edits and Fine-Grained Multimodal Learning

Tianyi Bai, Yuxuan Fan, Jiantao Qiu, Fupeng Sun, Jiayi Song, Junlin Han, Zichen Liu, Conghui He, Wentao Zhang, Binhang Yuan

机构 * HKUST（香港科技大学） ； Shanghai AI Lab（上海人工智能实验室） ； Peking University（北京大学） ； HKUST(GZ)（香港科技大学（广州）） ； Oxford University（牛津大学） ； Imperial College London（伦敦帝国理工学院） 纠错

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

Semantic-preserved Augmentation with Confidence-weighted Fine-tuning for Aspect Category Sentiment Analysis

Yaping Chai, Haoran Xie, Joe S. Qin

机构 * Lingnan University（岭南大学） 纠错

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

Comments 10 pages, 7 figures, 4 tables

Mixture of Small and Large Models for Chinese Spelling Check

Ziheng Qiao, Houquan Zhou, Zhenghua Li

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

Does It Run and Is That Enough? Revisiting Text-to-Chart Generation with a Multi-Agent Approach

James Ford, Anthony Rios

机构 * Department of Information Systems and Cyber Security（信息系统与网络安全系） ； The University of Texas at San Antonio（德克萨斯大学圣安东尼奥分校） 纠错

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

Comments 8 pages

WiNGPT-3.0 Technical Report

Boqin Zhuang, Chenxiao Song, Huitong Lu, Jiacheng Qiao, Mingqian Liu, Mingxing Yu, Ping Hong, Rui Li, Xiaoxia Song, Xiangjun Xu, Xu Chen, Yaoyao Ma, Yujie Gao

机构 * WiNGPT Team（WiNGPT团队） 纠错

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

An Exploration of Self-Supervised Mutual Information Alignment for Multi-Task Settings

Soham V. Govande

机构 * Stanford University（斯坦福大学） 纠错

专题命中 指令微调 ：language model(abstract)；SFT(abstract)；preference optimization(abstract)；分类 cs.CL

InSerter: Speech Instruction Following with Unsupervised Interleaved Pre-training

Dingdong Wang, Jin Xu, Ruihang Chu, Zhifang Guo, Xiong Wang, Jincenzi Wu, Dongchao Yang, Shengpeng Ji, Junyang Lin

机构 * The Chinese University of Hong Kong（香港中文大学） ； Alibaba Group（阿里巴巴集团） 纠错

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

Comments Accepted to ACL 2025; Data is available at: https://huggingface.co/datasets/ddwang2000/SpeechInstructBench

FusionAudio-1.2M: Towards Fine-grained Audio Captioning with Multimodal Contextual Fusion

Shunian Chen, Xinyuan Xie, Zheshu Chen, Liyan Zhao, Owen Lee, Zhan Su, Qilin Sun, Benyou Wang

机构 * The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）） 纠错

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

LoRA-BAM: Input Filtering for Fine-tuned LLMs via Boxed Abstraction Monitors over LoRA Layers

Changshun Wu, Tianyi Duan, Saddek Bensalem, Chih-Hong Cheng

机构 * Université Grenoble Alpes（格勒诺布尔大学） ； Chalmers University of Technology（挑战大学） ； CSX-AI ； University of Gothenburg（哥德堡大学） 纠错

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

CC-Tuning: A Cross-Lingual Connection Mechanism for Improving Joint Multilingual Supervised Fine-Tuning

Yangfan Ye, Xiaocheng Feng, Zekun Yuan, Xiachong Feng, Libo Qin, Lei Huang, Weitao Ma, Yichong Huang, Zhirui Zhang, Yunfei Lu, Xiaohui Yan, Duyu Tang, Dandan Tu, Bing Qin

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

Comments ACL2025 main conference, long paper

From Misleading Queries to Accurate Answers: A Three-Stage Fine-Tuning Method for LLMs

Guocong Li, Weize Liu, Yihang Wu, Ping Wang, Shuaihan Huang, Hongxia Xu, Jian Wu

机构 * Zhejiang University（浙江大学） ； Renmin University of China（中国人民大学） ； AI Research Center, WeDoctor Cloud（WeDoctor Cloud人工智能研究中心） 纠错

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

Comments Accepted to ACL 2025 (Findings)

Infinite-Instruct: Synthesizing Scaling Code instruction Data with Bidirectional Synthesis and Static Verification

Wenjing Xing, Wenke Lu, Yeheng Duan, Bing Zhao, Zhenghui kang, Yaolong Wang, Kai Gao, Lei Qiao

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

Improving Multilingual Social Media Insights: Aspect-based Comment Analysis

Longyin Zhang, Bowei Zou, Ai Ti Aw

机构 * Institute for Infocomm Research, A*STAR, Singapore（信息与通信研究所） 纠错

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

Comments The paper was peer-reviewed

BugWhisperer: Fine-Tuning LLMs for SoC Hardware Vulnerability Detection

Shams Tarek, Dipayan Saha, Sujan Kumar Saha, Farimah Farahmandi

机构 * Department of Electrical and Computer Engineering, University of Florida（电子与计算机工程系，佛罗里达大学） 纠错

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

Comments This paper was presented at IEEE VLSI Test Symposium (VTS) 2025

ChatHuman: Chatting about 3D Humans with Tools

Jing Lin, Yao Feng, Weiyang Liu, Michael J. Black

机构 * Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所） ； Stanford University（斯坦福大学） ； Meshcapade ； Tsinghua University（清华大学） ； University of Cambridge（剑桥大学） 纠错

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

Comments Project page: https://chathuman.github.io

ArgInstruct: Specialized Instruction Fine-Tuning for Computational Argumentation

Maja Stahl, Timon Ziegenbein, Joonsuk Park, Henning Wachsmuth

机构 * Leibniz University Hannover（汉诺威莱比锡大学） 纠错

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

Detecting Undesired Process Behavior by Means of Retrieval Augmented Generation

Michael Grohs, Adrian Rebmann, Jana-Rebecca Rehse

机构 * University of Mannheim（曼海姆大学） ； SAP Signavio 纠错

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

Comments Accepted at the BPM Forum, located at the International Conference on Business Process Management (BPM) 2025

KaFT: Knowledge-aware Fine-tuning for Boosting LLMs' Domain-specific Question-Answering Performance

Qihuang Zhong, Liang Ding, Xiantao Cai, Juhua Liu, Bo Du, Dacheng Tao

机构 * School of Computer Science, National Engineering Research Center for Multimedia Software, Institute of Artificial Intelligence and Hubei Key Laboratory of Multimedia and Network Communication Engineering（计算机科学学院、多媒体软件国家工程研究中心、人工智能研究院、多媒体与网络通信工程湖北省重点实验室） 纠错

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

Comments Accepted to ACL2025 Findings

Towards Objective Fine-tuning: How LLMs' Prior Knowledge Causes Potential Poor Calibration?

Ziming Wang, Zeyu Shi, Haoyi Zhou, Shiqi Gao, Qingyun Sun, Jianxin Li

机构 * SKLCCSE, School of Computer Science and Engineering, Beihang University（SKLCCSE，计算机科学与工程学院，北航） ； School of Software, Beihang University（软件学院，北航） ； Zhongguancun Laboratory, Beijing（中关村实验室，北京） 纠错

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

Comments Accepted to ACL2025 Main; The code will be released soon

HomeBench: Evaluating LLMs in Smart Homes with Valid and Invalid Instructions Across Single and Multiple Devices

Silin Li, Yuhang Guo, Jiashu Yao, Zeming Liu, Haifeng Wang

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

Comments Accepted by ACL 2025 Main

The Best of Both Worlds: Bridging Quality and Diversity in Data Selection with Bipartite Graph

Minghao Wu, Thuy-Trang Vu, Lizhen Qu, Gholamreza Haffari

机构 * Monash University（墨尔本大学） 纠错

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

Comments Accepted by ICML 2025

GC-KBVQA: A New Four-Stage Framework for Enhancing Knowledge Based Visual Question Answering Performance

Mohammad Mahdi Moradi, Sudhir Mudur

机构 * Concordia University（康科迪亚大学） 纠错

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

TNG-CLIP:Training-Time Negation Data Generation for Negation Awareness of CLIP

Yuliang Cai, Jesse Thomason, Mohammad Rostami

机构 * University of Southern California（南加州大学） 纠错

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

Comments 15 pages, 3 figures

Multi-Modality Expansion and Retention for LLMs through Parameter Merging and Decoupling

Junlin Li, Guodong DU, Jing Li, Sim Kuan Goh, Wenya Wang, Yequan Wang, Fangming Liu, Ho-Kin Tang, Saleh Alharbi, Daojing He, Min Zhang

机构 * Harbin Institute of Technology, Shenzhen, China（哈尔滨工业大学（深圳）） ； Xiamen University Malaysia（厦门大学马来西亚分校） ； Nanyang Technological University（南洋理工大学） ； Beijing Academy of Artificial Intelligence, China（北京人工智能研究院） ； Peng Cheng Laboratory, China（鹏城实验室） ； Shaqra University, Saudi Arabia（沙迦大学） 纠错

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

Elucidating Subspace Perturbation in Zeroth-Order Optimization: Theory and Practice at Scale

Sihwan Park, Jihun Yun, SungYub Kim, Souvik Kundu, Eunho Yang

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

Comments 49 pages, 9 figures