语言大模型 / LLM

GradientSpace: Unsupervised Data Clustering for Improved Instruction Tuning

GradientSpace: 无监督数据聚类以提升指令微调

Shrihari Sridharan, Deepak Ravikumar, Anand Raghunathan, Kaushik Roy

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

AI总结 GradientSpace通过直接在梯度空间中聚类样本，提升指令微调效果，减少推理延迟并提高准确性。

How to Train Long-Context Language Models (Effectively)

如何有效训练长上下文语言模型

Tianyu Gao, Alexander Wettig, Howard Yen, Danqi Chen

机构 * Princeton Language and Intelligence（普林斯顿语言与智能） 纠错

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

AI总结 ProLong-8B 通过有效利用长上下文数据，实现了在长上下文任务上的卓越性能，尽管训练数据量仅为 Llama-3.1-8B-Instruct 的 5%。

Comments Accepted to ACL 2025. Our code, data, and models are available at https://github.com/princeton-nlp/ProLong

TabTune: A Unified Library for Inference and Fine-Tuning Tabular Foundation Models

TabTune：用于推理和微调表格基础模型的统一库

Aditya Tanna, Pratinav Seth, Mohamed Bouadi, Utsav Avaiya, Vinay Kumar Sankarapu

机构 * Lexsi Labs（Lexsi实验室） 纠错

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

AI总结 TabTune是一个统一库，通过单一接口标准化表格基础模型的完整工作流程，支持多种适应策略并提升评估一致性。

Comments The library is open source and available at https://github.com/Lexsi-Labs/TabTune

Personalized LLM Decoding via Contrasting Personal Preference

通过对比个人偏好实现个性化大语言模型解码

Hyungjune Bu, Chanjoo Jung, Minjae Kang, Jaehyung Kim

机构 * Yonsei University（延世大学） ； Opt-AI Inc.（Opt-AI公司） 纠错

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

AI总结 本文提出CoPe方法，通过奖励引导解码实现个性化，提升ROUGE-L指标10.57%。

Comments EMNLP 2025 Main

Do Retrieval Augmented Language Models Know When They Don't Know?

Youchao Zhou, Heyan Huang, Yicheng Liu, Rui Dai, Xinglin Wang, Xingchen Zhang, Shumin Shi, Yang Deng

机构 * SMU（南密西西比大学） 纠错

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

Comments AAAI 2026 camera ready version. Extended version with Appendix is coming soon

GMTRouter: Personalized LLM Router over Multi-turn User Interactions

Encheng Xie, Yihang Sun, Tao Feng, Jiaxuan You

机构 * Antiquus S. Hippocampus, Natalia Cerebro & Amelie P. Amygdale Department of Computer Science Cranberry-Lemon University Pittsburgh, PA 15213, USA（计算机科学系，Cranberry-Lemon大学） ； Ji Q. Ren & Yevgeny LeNet Department of Computational Neuroscience University of the Witwatersrand Joburg, South Africa（计算神经科学系，沃特瓦特斯兰大学） 纠错

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

Comments Preprint

E2E-VGuard: Adversarial Prevention for Production LLM-based End-To-End Speech Synthesis

Zhisheng Zhang, Derui Wang, Yifan Mi, Zhiyong Wu, Jie Gao, Yuxin Cao, Kai Ye, Minhui Xue, Jie Hao

机构 * Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院） ； Beijing University of Posts and Telecommunications（北京邮电大学） ； CSIRO’s Data61（CSIRO数据61） ； Responsible AI Research (RAIR) Centre, The University of Adelaide（阿德莱德大学负责任人工智能研究（RAIR）中心） ； National University of Singapore（新加坡国立大学） ； The University of Hong Kong（香港大学） 纠错

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

Comments Accepted to NeurIPS 2025

Brotherhood at WMT 2024: Leveraging LLM-Generated Contextual Conversations for Cross-Lingual Image Captioning

Siddharth Betala, Ishan Chokshi

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

Comments Accepted at the Ninth Conference on Machine Translation (WMT24), co-located with EMNLP 2024

Journal ref https://aclanthology.org/2024.wmt-1.81/

Teaching According to Talents! Instruction Tuning LLMs with Competence-Aware Curriculum Learning

Yangning Li, Tingwei Lu, Yinghui Li, Yankai Chen, Wei-Chieh Huang, Wenhao Jiang, Hui Wang, Hai-Tao Zheng, Philip S. Yu

机构 * Tsinghua University（清华大学） ； Peng Cheng Laboratory（鹏城实验室） ； Cornell University（康奈尔大学） ； University of Illinois Chicago（伊利诺伊大学芝加哥分校） ； Guangming Laboratory（光明实验室） 纠错

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

Comments EMNLP 2025 Findings

Low-Rank Adaptation for Foundation Models: A Comprehensive Review

Menglin Yang, Jialin Chen, Jinkai Tao, Yifei Zhang, Jiahong Liu, Jiasheng Zhang, Qiyao Ma, Harshit Verma, Regina Zhang, Min Zhou, Irwin King, Rex Ying

机构 * Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）） ； Yale University（耶鲁大学） ； Nanyang Technological University（南洋理工大学） ； Central University of Finance and Economics（中央财经大学） ； The Chinese University of Hong Kong（香港中文大学） ； Xi’an University of Electronic Science and Technology（西安电子科技大学） ； University of California, Davis（加州大学戴维斯分校） ； The University of Cambridge（剑桥大学） ； LOGS AI 纠错

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

Loquetier: A Virtualized Multi-LoRA Framework for Unified LLM Fine-tuning and Serving

Yuchen Zhang, Hanyue Du, Chun Cao, Jingwei Xu

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

Comments 26 pages including 10 pages of main text, 6 figures, 39th Conference on Neural Information Processing Systems (NeurIPS 2025)

S'MoRE: Structural Mixture of Residual Experts for Parameter-Efficient LLM Fine-tuning

Hanqing Zeng, Yinglong Xia, Zhuokai Zhao, Chuan Jiang, Qiang Zhang, Jiayi Liu, Qunshu Zhang, Lizhu Zhang, Xiangjun Fan, Benyu Zhang

机构 * Meta AI 纠错

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

Comments NeurIPS 2025

Group-in-Group Policy Optimization for LLM Agent Training

Lang Feng, Zhenghai Xue, Tingcong Liu, Bo An

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

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

Comments NeurIPS 2025

Prompting is not Enough: Exploring Knowledge Integration and Controllable Generation

Tingjia Shen, Hao Wang, Chuan Qin, Ruijun Sun, Yang Song, Defu Lian, Hengshu Zhu, Enhong Chen

机构 * University of Science and Technology of China（中国科学技术大学） ； Computer Network Information Center, Chinese Academy of Sciences（中国科学院计算机网络信息中心） ； Chinese Academy of Sciences（中国科学院） ； BOSS Zhipin Career Science Lab（BOSS智联招聘科研实验室） 纠错

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

Comments 13 pages, 5 figures

VESSA: Video-based objEct-centric Self-Supervised Adaptation for Visual Foundation Models

Jesimon Barreto, Carlos Caetano, André Araujo, William Robson Schwartz

机构 * Departamento de Ciência da Computação, Universidade Federal de Minas Gerais (UFMG)（巴西联邦大学矿务学院计算机科学系（UFMG）） ； Recod.ai, Instituto de Computação, Universidade Estadual de Campinas (UNICAMP)（Recod.ai，计算机学院，坎皮纳斯州立大学（UNICAMP）） ； Google DeepMind（谷歌DeepMind） 纠错

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

Comments Conference on Neural Information Processing Systems (NeurIPS 2025)

Zhyper: Factorized Hypernetworks for Conditioned LLM Fine-Tuning

M. H. I. Abdalla, Zhipin Wang, Christian Frey, Steffen Eger, Josif Grabocka

机构 * Department of Computer Science University of Technology Nuremberg（计算机科学系图腾技术大学纽伦堡） 纠错

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

Repurposing Annotation Guidelines to Instruct LLM Annotators: A Case Study

Kon Woo Kim, Rezarta Islamaj, Jin-Dong Kim, Florian Boudin, Akiko Aizawa

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

Comments 11 pages, 2 figures, 3 tables, This is a preprint of the article accepted at NLDB 2025 (Springer LNCS). The final version is available at https://doi.org/10.1007/978-3-031-97144-0_13

Journal ref In International Conference on Applications of Natural Language to Information Systems, pp. 140-151. Cham: Springer Nature Switzerland, 2025

Self-Evolving LLMs via Continual Instruction Tuning

Jiazheng Kang, Le Huang, Cheng Hou, Zhe Zhao, Zhenxiang Yan, Ting Bai

机构 * Beijing University of Posts and Telecommunications（北京邮电大学） ； Tencent AI Lab（腾讯AI实验室） 纠错

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

MoRA: On-the-fly Molecule-aware Low-Rank Adaptation Framework for LLM-based Multi-Modal Molecular Assistant

Tao Yin, Xiaohong Zhang, Jiacheng Zhang, Li Huang, Zhibin Zhang, Yuansong Zeng, Jin Xie, Meng Yan

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

Early Detection and Reduction of Memorisation for Domain Adaptation and Instruction Tuning

Dean L. Slack, Noura Al Moubayed

机构 * Durham University（杜伦大学） 纠错

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

Comments Accepted to Transactions of the ACL (TACL), 2025. 15 pages, 6 figures, 3 tables

Fine-tuning with RAG for Improving LLM Learning of New Skills

Humaid Ibrahim, Nikolai Rozanov, Marek Rei

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

Comments Under review at ICLR 2026

UniErase: Towards Balanced and Precise Unlearning in Language Models

Miao Yu, Liang Lin, Guibin Zhang, Xinfeng Li, Junfeng Fang, Xingrui Yu, Ivor Tsang, Ningyu Zhang, Kun Wang, Yang Wang

机构 * University of Science and Technology of China（中国科学技术大学） ； University of the Chinese Academy of Sciences（中国科学院大学） ； National University of Singapore（新加坡国立大学） ； Nanyang Technological University（南洋理工大学） ； A*STAR（科技研究局） ； Zhejiang University（浙江大学） 纠错

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

ClaimIQ at CheckThat! 2025: Comparing Prompted and Fine-Tuned Language Models for Verifying Numerical Claims

Anirban Saha Anik, Md Fahimul Kabir Chowdhury, Andrew Wyckoff, Sagnik Ray Choudhury

机构 * Department of Data Science, University of North Texas, Denton, TX, USA（数据科学系，北卡罗来纳州立大学，德顿，得克萨斯州，美国） ； Department of Computer Science and Engineering, University of North Texas, Denton, TX, USA（计算机科学与工程系，北卡罗来纳州立大学，德顿，得克萨斯州，美国） ； Department of Computer Science（计算机科学系） 纠错

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

Comments Notebook for the CheckThat! Lab at CLEF 2025

Revealing the Inherent Instructability of Pre-Trained Language Models

Seokhyun An, Minji Kim, Hyounghun Kim

机构 * Department of Computer Science and Engineering, UNIST（UNIST计算机科学与工程系） ； Graduate School of Artificial Intelligence, POSTECH（POSTECH人工智能研究生院） ； Department of Computer Science and Engineering, POSTECH（POSTECH计算机科学与工程系） 纠错

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

Comments Findings of EMNLP 2025 (32 pages). Code available at https://github.com/seokhyunan/response-tuning

Enhancing Dialogue Annotation with Speaker Characteristics Leveraging a Frozen LLM

Thomas Thebaud, Yen-Ju Lu, Matthew Wiesner, Peter Viechnicki, Najim Dehak

机构 * Electrical and Computer Engineering Department, Johns Hopkins University, Baltimore, MD, USA（约翰霍普金斯大学电气与计算机工程系） ； Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA（约翰霍普金斯大学人机语言技术卓越中心） 纠错

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

Comments Accepted in the 2025 IEEE Automatic Speech Recognition and Understanding Workshop

SLiNT: Structure-aware Language Model with Injection and Contrastive Training for Knowledge Graph Completion

Mengxue Yang, Chun Yang, Jiaqi Zhu, Jiafan Li, Jingqi Zhang, Yuyang Li, Ying Li

机构 * University of Chinese Academy of Sciences（中国科学院大学） ； Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所） ； National Astronomical Observatories, Chinese Academy of Sciences（中国科学院国家天文台） 纠错

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

Comments Accepted by EMNLP Findings 2025

Memento: Fine-tuning LLM Agents without Fine-tuning LLMs

Huichi Zhou, Yihang Chen, Siyuan Guo, Xue Yan, Kin Hei Lee, Zihan Wang, Ka Yiu Lee, Guchun Zhang, Kun Shao, Linyi Yang, Jun Wang

机构 * AI Centre, UCL（UCL人工智能中心） ； Huawei Noah’s Ark Lab, UK（华为诺亚实验室（英国）） ； Jilin University（吉林大学） ； Institute of Automation, CAS（中国科学院自动化研究所） 纠错

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

Rethinking Table Instruction Tuning

Naihao Deng, Rada Mihalcea

机构 * University of Michigan（密歇根大学） 纠错

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

Comments Accepted to ACL 2025 Findings. Updates: 07/2025: We release the TAMA-QWen2.5 and TAMA-QWen3 models. 06/2025: We release our project page: https://lit.eecs.umich.edu/TAMA/, code: https://github.com/MichiganNLP/TAMA, huggingface models: https://huggingface.co/collections/MichiganNLP/tama-684eeb3e7f262362856eccd1, and data: https://huggingface.co/datasets/MichiganNLP/TAMA_Instruct

Reviving Your MNEME: Predicting The Side Effects of LLM Unlearning and Fine-Tuning via Sparse Model Diffing

Aly M. Kassem, Zhuan Shi, Negar Rostamzadeh, Golnoosh Farnadi

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

Reinforcement learning fine-tuning of language model for instruction following and math reasoning

Yifu Han, Geo Zhang

机构 * Stanford University（斯坦福大学） 纠错

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