语言大模型 / LLM

DiZiNER: Disagreement-guided Instruction Refinement via Pilot Annotation Simulation for Zero-shot Named Entity Recognition

DiZiNER：通过试点注释模拟的分歧引导指令细化用于零样本命名实体识别

Siun Kim, Hyung-Jin Yoon

机构 * Seltasquare Seoul, Korea（首尔韩国Seltasquare） ； Seoul National University College of Medicine（首尔国立大学医学院） ； Biomedical Research Institute, Seoul National University Hospital（首尔国立大学医院生物医学研究所） 纠错

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

AI总结 DiZiNER通过模拟试点注释过程，利用LLM作为标注者和监督者，通过多模型标注和分歧分析优化指令，实现零样本NER的SOTA结果，提升F1分数并缩小与监督系统差距。

Comments 9 pages, 3 figures; Accepted to the ACL 2026 Main Conference

LLMs Are Not a Silver Bullet: A Case Study on Software Fairness

LLMs并非银弹：软件公平性的一项案例研究

Xinyue Li, Sixuan Li, Ying Xiao, Jie M. Zhang, Zhou Yang, Xuanzhe Liu, Zhenpeng Chen

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

AI总结 本文通过对比传统机器学习与大语言模型在软件公平性中的表现，发现传统方法在公平性和预测性能上均优于LLM，指出LLM在现实数据中效果有限。

Long-Document QA with Chain-of-Structured-Thought and Fine-Tuned SLMs

长文档问答与结构化思维链及微调大语言模型

Zhuowen Liang, Xiaotian Lin, Zhengxuan Zhang, Yuyu Luo, Haixun Wang, Nan Tang

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）） ； EvenUp, USA（美国EvenUp公司） 纠错

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

AI总结 本文提出LiteCoST框架，通过结构化思维链和微调小语言模型，实现高精度低延迟的长文档问答，采用双支柱方法提升准确性和效率。

Comments 26 pages, 17 figures, 10 tables. Accepted at ICLR 2026

Attesting LLM Pipelines: Enforcing Verifiable Training and Release Claims

验证LLM流水线：强制执行可验证的训练和发布声明

Zhuoran Tan, Jeremy Singer, Christos Anagnostopoulos

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

AI总结 本文提出一个验证意识的提升门，用于确保在训练、微调和部署前，对训练和发布声明的证据进行验证，强制安全加载和静态扫描策略，并应用默认安全的部署约束，以减少高风险 artifact 的不确定性。

Comments This paper has been accepted at The 2nd International Workshop on Large Language Model Supply Chain Analysis (LLMSC 2026)

HIPO: Instruction Hierarchy via Constrained Reinforcement Learning

HIPO：通过约束强化学习实现指令层级

Keru Chen, Jun Luo, Sen Lin, Yingbin Liang, Alvaro Velasquez, Nathaniel Bastian, Shaofeng Zou

机构 * School of ECEE Arizona State University（亚利桑那州立大学电子与计算机工程学院） ； Department of ECE The Ohio State University（俄亥俄州立大学电子工程系） ； Computer Science Department University of Houston（休斯顿大学计算机科学系） ； College of Engineering & Applied Science CU Boulder（科罗拉多大学博尔德分校工程与应用科学学院） ； Dept. of Electrical Engineering & Computer Science United States Military Academy（美国军事学院电子工程与计算机科学系） 纠错

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

AI总结 HIPO通过约束马尔可夫决策过程解决层级指令遵循问题，提升系统合规性与用户效用。

Comments 9 pages + appendix. Under review

Generalization of RLVR Using Causal Reasoning as a Testbed

使用因果推理作为测试平台的RLVR泛化

Brian Lu, Hongyu Zhao, Shuo Sun, Hao Peng, Rui Ding, Hongyuan Mei

机构 * Johns Hopkins University（约翰霍普金斯大学） ； University of Maryland, College Park（马里兰大学学院公园分校） ； University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） ； Microsoft Research Asia（微软亚洲研究院） ； Toyota Technological Institute at Chicago（芝加哥丰田技术研究所） 纠错

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

AI总结 本文通过实验证明，RLVR在特定模型规模和训练查询层次下能提升因果推理能力，尤其在复杂查询中表现更优。

Distilling Expert Surgical Knowledge: How to train local surgical VLMs for anatomy explanation in Complete Mesocolic Excision

萃取专家手术知识：如何训练局部手术VLMs用于完全网膜切除术的解剖解释

Lennart Maack, Julia-Kristin Graß, Lisa-Marie Toscha, Nathaniel Melling, Alexander Schlaefer

机构 * 1 Institute of Medical Technology ； Intelligent Systems, Hamburg University of Technology, Hamburg, Germany 2 Department of General, Visceral ； Thoracic Surgery, University Medical Center Hamburg-Eppendorf, Hamburg, Germany 纠错

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

AI总结 本文提出一种隐私保护框架，通过从大型通用LLM中萃取知识，训练出高效的本地手术VLM，用于在完全网膜切除术中进行解剖解释。

R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization

Jingyi Zhang, Jiaxing Huang, Huanjin Yao, Shunyu Liu, Xikun Zhang, Shijian Lu, Dacheng Tao

机构 * Nanyang Technological University（南洋理工大学） 纠错

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

Comments ICCV 2025 Camera Ready

Is It Time To Treat Prompts As Code? A Multi-Use Case Study For Prompt Optimization Using DSPy

Francisca Lemos, Victor Alves, Filipa Ferraz

机构 * ALGORITMI Research Centre/LASI, University of Minho, Braga, 4710-057, Portugal（ALGORITMI研究中心/LASI，明霍大学，布拉加，4710-057，葡萄牙） 纠错

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

Comments 20 pages with 1 figure

ReCopilot: Reverse Engineering Copilot in Binary Analysis

Guoqiang Chen, Huiqi Sun, Daguang Liu, Zhiqi Wang, Qiang Wang, Bin Yin, Lu Liu, Lingyun Ying

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

SkyReels-V2: Infinite-length Film Generative Model

Guibin Chen, Dixuan Lin, Jiangping Yang, Chunze Lin, Junchen Zhu, Mingyuan Fan, Hao Zhang, Sheng Chen, Zheng Chen, Chengcheng Ma, Weiming Xiong, Wei Wang, Nuo Pang, Kang Kang, Zhiheng Xu, Yuzhe Jin, Yupeng Liang, Yubing Song, Peng Zhao, Boyuan Xu, Di Qiu, Debang Li, Zhengcong Fei, Yang Li, Yahui Zhou

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

Comments 31 pages,10 figures

InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Jinguo Zhu, Weiyun Wang, Zhe Chen, Zhaoyang Liu, Shenglong Ye, Lixin Gu, Hao Tian, Yuchen Duan, Weijie Su, Jie Shao, Zhangwei Gao, Erfei Cui, Xuehui Wang, Yue Cao, Yangzhou Liu, Xingguang Wei, Hongjie Zhang, Haomin Wang, Weiye Xu, Hao Li, Jiahao Wang, Nianchen Deng, Songze Li, Yinan He, Tan Jiang, Jiapeng Luo, Yi Wang, Conghui He, Botian Shi, Xingcheng Zhang, Wenqi Shao, Junjun He, Yingtong Xiong, Wenwen Qu, Peng Sun, Penglong Jiao, Han Lv, Lijun Wu, Kaipeng Zhang, Huipeng Deng, Jiaye Ge, Kai Chen, Limin Wang, Min Dou, Lewei Lu, Xizhou Zhu, Tong Lu, Dahua Lin, Yu Qiao, Jifeng Dai, Wenhai Wang

机构 * Shanghai AI Laboratory（上海人工智能实验室） ； SenseTime Research（商汤科技研究院） ； Tsinghua University（清华大学） ； Nanjing University（南京大学） ； Fudan University（复旦大学） ； The Chinese University of Hong Kong（香港中文大学） ； Shanghai Jiao Tong University（上海交通大学） 纠错

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

Comments Technical Report

SimpleAR: Pushing the Frontier of Autoregressive Visual Generation through Pretraining, SFT, and RL

Junke Wang, Zhi Tian, Xun Wang, Xinyu Zhang, Weilin Huang, Zuxuan Wu, Yu-Gang Jiang

专题命中 指令微调 ：SFT(title,abstract)；pretraining(title)

Comments technical report, work in progress

ChatGarment: Garment Estimation, Generation and Editing via Large Language Models

Siyuan Bian, Chenghao Xu, Yuliang Xiu, Artur Grigorev, Zhen Liu, Cewu Lu, Michael J. Black, Yao Feng

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

Comments CVPR 2025

A Multi-Encoder Frozen-Decoder Approach for Fine-Tuning Large Language Models

Kaustubh D. Dhole

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

Alzheimer's disease detection based on large language model prompt engineering

Tian Zheng, Xurong Xie, Xiaolan Peng, Hui Chen, Feng Tian

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

PSY: Posterior Sampling Based Privacy Enhancer in Large Language Models

Yulian Sun, Li Duan, Yong Li

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

Comments 10 pages, 2 figures

A Survey on LoRA of Large Language Models

Yuren Mao, Yuhang Ge, Yijiang Fan, Wenyi Xu, Yu Mi, Zhonghao Hu, Yunjun Gao

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

Comments The article has been accepted by Frontiers of Computer Science (FCS), with the DOI: {10.1007/s11704-024-40663-9}

Improving Multi-modal Large Language Model through Boosting Vision Capabilities

Yanpeng Sun, Huaxin Zhang, Qiang Chen, Xinyu Zhang, Nong Sang, Gang Zhang, Jingdong Wang, Zechao Li

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

Convolutional Networks as Extremely Small Foundation Models: Visual Prompting and Theoretical Perspective

Jianqiao Wangni

专题命中 指令微调 ：prompting(title,abstract)；foundation model(title)

Sparse is Enough in Fine-tuning Pre-trained Large Language Models

Weixi Song, Zuchao Li, Lefei Zhang, Hai Zhao, Bo Du

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

Comments Accepted at ICML 2024 Spotlight

Navigating the Landscape of Large Language Models: A Comprehensive Review and Analysis of Paradigms and Fine-Tuning Strategies

Benjue Weng

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

ChartAssisstant: A Universal Chart Multimodal Language Model via Chart-to-Table Pre-training and Multitask Instruction Tuning

Fanqing Meng, Wenqi Shao, Quanfeng Lu, Peng Gao, Kaipeng Zhang, Yu Qiao, Ping Luo

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

Comments Updated and corrected experimental results, removal of inappropriate experiments, and a more comprehensive experimental setup

AI-TA: Towards an Intelligent Question-Answer Teaching Assistant using Open-Source LLMs

Yann Hicke, Anmol Agarwal, Qianou Ma, Paul Denny

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

Comments Updates for camera-ready submission

Journal ref NeurIPS Workshop on Generative AI for Education (GAIED), 2023

LINGUIST: Language Model Instruction Tuning to Generate Annotated Utterances for Intent Classification and Slot Tagging

Andy Rosenbaum, Saleh Soltan, Wael Hamza, Yannick Versley, Markus Boese

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

Comments Accepted to The 29th International Conference on Computational Linguistics (COLING 2022) October 12-17, 2022, Gyeongju, Republic of Korea https://coling2022.org/

Persona-Guided LLM Agents for Task-Oriented Dialogue

面向任务型对话的角色引导大语言模型智能体

Maryam Shoaeinaeini, Brent Harrison, A. B. Siddique

机构 * University of Kentucky（肯塔基大学） 纠错

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

AI总结 该研究构建无需训练的框架，通过三种情境评估多模型在SGD数据集上的表现，发现适应用户人格存在权衡，Try情境的线索式适应可更可靠实现感知人格的任务型对话。

Comments 8 pages

OraclePhys: A Systematic Framework for LLM Fine-Tuning on Structural Mechanics

OraclePhys：面向结构力学的大语言模型微调系统框架

Mingyu Li, Guorui Song, Jing Lin, Haoqian Wang

机构 * University of Houston（休斯顿大学） ； Tsinghua University（清华大学） 纠错

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

AI总结 本研究提出OraclePhys，一种面向结构力学的大语言模型微调系统框架，含自动评分基准、多形式监督数据集及对照训练研究，发现标签答案形式而非比特数决定微调效果，训练所得8B模型达空间结构响应任务数据精度前沿。

Comments 18 pages, 8 figures, 9 tables. Under review at ACL Rolling Review

Discrete Diffusion Language Models Are Training-Free Multi-Label Classifiers

离散扩散语言模型是无需训练的多标签分类器

Pawan Kumar

机构 * International Institute of Information Technology, Hyderabad（印度海得拉巴国际信息技术学院） 纠错

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

AI总结 本研究提出无需训练的多标签分类方法dLLM-SetScore，基于离散掩码扩散语言模型，在多个数据集上对比基准模型，验证了其性能优势并完成了相关理论分析。

Comments Accepted to SIAM SDM 2026, 39 pages

Moral Hazard in Multi-Agent Language Models

多智能体语言模型中的道德风险

Dane Malenfant

专题命中 指令微调 ：language model(title)；SFT(abstract,abstract_cn)；language agent(abstract)；分类 cs.AI

AI总结 研究多智能体语言模型中的道德风险，引入对话道德风险游戏，评估七个模型并分解行为，用多种优化机制更新，发现效果异质，强调应报告机制级行为而非仅团队成功。

Comments New frontier baselines, new open weight inference baselines

LoRA-based Adaptation Alone Is Not Enough: Understanding the Limits of Foundation Models for Face Presentation Attack Detection

仅基于LoRA的适配还不够：探究基础模型在人脸呈现攻击检测中的局限性

Peter Lorenz, Anjith George, Marcel Sébastien

机构 * Idiap Research Institute（伊迪亚普研究所） ； University of Lausanne (UNIL)（洛桑大学） 纠错

专题命中 指令微调 ：foundation model(title,abstract)；pretraining(abstract)；prompting(abstract)；分类 cs.LG

AI总结 本研究系统评估32种基础模型，发现LoRA适配仅优化数据集内人脸PAD性能，跨数据集泛化仍受限，指出仅靠LoRA适配不足以解决人脸PAD跨数据集性能下降问题。