语言大模型 / LLM

Understanding Forgetting in LLM Supervised Fine-Tuning and Preference Learning -- A Convex Optimization Perspective

Heshan Fernando, Han Shen, Parikshit Ram, Yi Zhou, Horst Samulowitz, Nathalie Baracaldo, Tianyi Chen

机构 * Rensselaer Polytechnic Institute（罗切斯特理工学院） ； IBM Research（IBM研究院） ； Cornell University（康奈尔大学） 纠错

专题命中 指令微调 ：LLM(title,abstract)；post-training(abstract)；SFT(abstract)；RLHF(abstract)

AMFT: Aligning LLM Reasoners by Meta-Learning the Optimal Imitation-Exploration Balance

Lixuan He, Jie Feng, Yong Li

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

Comments The paper is currently under investigation regarding concerns of potential academic misconduct. While the investigation is ongoing, the authors have voluntarily requested to withdraw the manuscript

Patient-specific Biomolecular Instruction Tuning

Irsyad Adam, Zekai Chen, David Laub, Shaun Porwal, Arda Pekis, Kevin Brown

机构 * Standard Model Biomedicine（标准模型生物医学） ； University of California, San Diego（加州大学圣地亚哥分校） 纠错

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

Enhancing LLM-Based Social Bot via an Adversarial Learning Framework

Fanqi Kong, Xiaoyuan Zhang, Xinyu Chen, Yaodong Yang, Song-Chun Zhu, Xue Feng

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

Forecasting Time Series with LLMs via Patch-Based Prompting and Decomposition

Mayank Bumb, Anshul Vemulapalli, Sri Harsha Vardhan Prasad Jella, Anish Gupta, An La, Ryan A. Rossi, Hongjie Chen, Franck Dernoncourt, Nesreen K. Ahmed, Yu Wang

机构 * University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校） ； Adobe（Adobe公司） ； Dolby Labs（Dolby实验室） ； Intel（英特尔公司） ； University of Oregon（俄勒冈大学） 纠错

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

Analyzing Fine-Grained Alignment and Enhancing Vision Understanding in Multimodal Language Models

Jiachen Jiang, Jinxin Zhou, Bo Peng, Xia Ning, Zhihui Zhu

机构 * Department of Computer Science and Engineering, The Ohio State University（计算机科学与工程系，俄亥俄州立大学） ； Translational Data Analytics Institute, The Ohio State University（转化数据分析研究所，俄亥俄州立大学） ； Department of Biomedical Informatics, The Ohio State University（生物医学信息学系，俄亥俄州立大学） 纠错

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

Think Inside the JSON: Reinforcement Strategy for Strict LLM Schema Adherence

Bhavik Agarwal, Ishan Joshi, Viktoria Rojkova

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

Optimal Brain Iterative Merging: Mitigating Interference in LLM Merging

Zhixiang Wang, Zhenyu Mao, Yixuan Qiao, Yunfang Wu, Biye Li

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

RuleR: Improving LLM Controllability by Rule-based Data Recycling

Ming Li, Han Chen, Chenguang Wang, Dang Nguyen, Dianqi Li, Tianyi Zhou

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

Comments NAACL2025 main, Camera-ready

MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Engine

Renrui Zhang, Xinyu Wei, Dongzhi Jiang, Ziyu Guo, Shicheng Li, Yichi Zhang, Chengzhuo Tong, Jiaming Liu, Aojun Zhou, Bin Wei, Shanghang Zhang, Peng Gao, Chunyuan Li, Hongsheng Li

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

Comments WData and Models will be released at https://github.com/ZrrSkywalker/MAVIS

Jellyfish: A Large Language Model for Data Preprocessing

Haochen Zhang, Yuyang Dong, Chuan Xiao, Masafumi Oyamada

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

Comments Accepted by EMNLP 2024, a.k.a. "Jellyfish: Instruction-Tuning Local Large Language Models for Data Preprocessing''

Upcycling Instruction Tuning from Dense to Mixture-of-Experts via Parameter Merging

Tingfeng Hui, Zhenyu Zhang, Shuohuan Wang, Yu Sun, Hua Wu, Sen Su

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

Comments work in progress

Calibrating Language Models with Adaptive Temperature Scaling

Johnathan Xie, Annie S. Chen, Yoonho Lee, Eric Mitchell, Chelsea Finn

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

Comments EMNLP 2024

A Multi-LLM Debiasing Framework

Deonna M. Owens, Ryan A. Rossi, Sungchul Kim, Tong Yu, Franck Dernoncourt, Xiang Chen, Ruiyi Zhang, Jiuxiang Gu, Hanieh Deilamsalehy, Nedim Lipka

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

Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation

Guanting Dong, Yutao Zhu, Chenghao Zhang, Zechen Wang, Zhicheng Dou, Ji-Rong Wen

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

Comments Work in progress

NExT-GPT: Any-to-Any Multimodal LLM

Shengqiong Wu, Hao Fei, Leigang Qu, Wei Ji, Tat-Seng Chua

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

Comments ICML 2024 (Oral)

Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning

Ming Li, Lichang Chen, Jiuhai Chen, Shwai He, Jiuxiang Gu, Tianyi Zhou

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

Comments ACL2024 (findings), Camera-ready

On Overcoming Miscalibrated Conversational Priors in LLM-based Chatbots

Christine Herlihy, Jennifer Neville, Tobias Schnabel, Adith Swaminathan

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

Comments Preprint of UAI'24 conference publication

Unfamiliar Finetuning Examples Control How Language Models Hallucinate

Katie Kang, Eric Wallace, Claire Tomlin, Aviral Kumar, Sergey Levine

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

Multilingual Instruction Tuning With Just a Pinch of Multilinguality

Uri Shaham, Jonathan Herzig, Roee Aharoni, Idan Szpektor, Reut Tsarfaty, Matan Eyal

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

Comments Findings of ACL 2024

LaFFi: Leveraging Hybrid Natural Language Feedback for Fine-tuning Language Models

Qianxi Li, Yingyue Cao, Jikun Kang, Tianpei Yang, Xi Chen, Jun Jin, Matthew E. Taylor

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

Comments Paper accepted in Human-Centric Representation Learning workshop at AAAI 2024 (https://hcrl-workshop.github.io/2024/)

SVIT: Scaling up Visual Instruction Tuning

Bo Zhao, Boya Wu, Muyang He, Tiejun Huang

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

Visual Instruction Tuning

Haotian Liu, Chunyuan Li, Qingyang Wu, Yong Jae Lee

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

Comments NeurIPS 2023 Oral; project page: https://llava-vl.github.io/

LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models

Marwa Abdulhai, Isadora White, Charlie Snell, Charles Sun, Joey Hong, Yuexiang Zhai, Kelvin Xu, Sergey Levine

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

PACE-LM: Prompting and Augmentation for Calibrated Confidence Estimation with GPT-4 in Cloud Incident Root Cause Analysis

Dylan Zhang, Xuchao Zhang, Chetan Bansal, Pedro Las-Casas, Rodrigo Fonseca, Saravan Rajmohan

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

RELISH: LLM REgression with a Latent Iterative State Head

基于潜在迭代状态头的大型语言模型回归

Yiheng Su, Matthew Lease

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

AI总结 RElish通过迭代优化潜在状态实现文本回归，优于三种主流回归方法，参数效率高。

Comments Accepted to the Third Conference on Language Modeling (COLM 2026)

ChatPlanner: A Large Language Model Framework for Personalized Public Transit Routing

ChatPlanner: 一个用于个性化公共交通路线规划的大型语言模型框架

Tingting Yang, Chenhao Xue, Jun Chen

机构 * School of Engineering and Materials Science, Queen Mary University of London（伦敦玛丽女王大学工程与材料科学学院） ； Department of Engineering Science, University of Oxford（牛津大学工程科学系） 纠错

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

AI总结 提出ChatPlanner框架，利用大型语言模型和检索增强生成技术从自然语言查询中提取用户偏好并融入路线规划算法，实验证明其能生成更符合个性化需求的可行路线方案。

Comments Under Review at Transportation Research Part C

Accuracy and Reliability of Large Language Models in Cosmetic Chemistry and Skin Health: A Benchmarking Study

大型语言模型在化妆品化学与皮肤健康领域的准确性与可靠性：一项基准测试研究

Amelia Liu

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

AI总结 本研究测试14个LLMs在化妆品化学与皮肤健康领域的表现，发现其总体准确性差、技术深度不足，无法可靠提供相关信息，需微调验证数据集并改进算法推理。

Comments 14 pages

Anatomy of Unlearning: The Dual Impact of Fact Salience and Model Fine-Tuning

遗忘的解剖：事实显著性与模型微调的双重影响

Anna Borisiuk, Andrey Savchenko, Alexander Panchenko, Elena Tutubalina

机构 * AIRI ； Sber AI Lab ； HSE University（HSE大学） ； Skoltech ； ISP RAS Research Center for Trusted Artificial Intelligence（ISP RAS可信人工智能研究中心） 纠错

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

AI总结 本研究通过构建DUET基准，分析了预训练与监督微调阶段的事实显著性对机器遗忘效果的影响，发现微调后的模型遗忘更平滑且保留率更高。

SEMA: Simple yet Effective Learning for Multi-Turn Jailbreak Attacks

SEMA: 简单却有效的多轮对抗攻击学习

Mingqian Feng, Xiaodong Liu, Weiwei Yang, Jialin Song, Xuekai Zhu, Chenliang Xu, Jianfeng Gao

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

AI总结 SEMA通过多阶段学习实现高效多轮对抗攻击，无需依赖现有策略，提升攻击成功率并增强安全测试能力。

Comments ICLR 2026, 37 pages, 13 tables, 7 figures