语言大模型 / LLM

Retrieval-Augmented Fine-Tuning With Preference Optimization For Visual Program Generation

Deokhyung Kang, Jeonghun Cho, Yejin Jeon, Sunbin Jang, Minsub Lee, Jawoon Cho, Gary Geunbae Lee

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

Comments Accepted at ACL 2025 (Main, long paper)

FisherSFT: Data-Efficient Supervised Fine-Tuning of Language Models Using Information Gain

Rohan Deb, Kiran Thekumparampil, Kousha Kalantari, Gaurush Hiranandani, Shoham Sabach, Branislav Kveton

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

Span-level Emotion-Cause-Category Triplet Extraction with Instruction Tuning LLMs and Data Augmentation

Xiangju Li, Dong Yang, Xiaogang Zhu, Faliang Huang, Peng Zhang, Zhongying Zhao

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

MergeIT: From Selection to Merging for Efficient Instruction Tuning

Hongyi Cai, Yuqian Fu, Hongming Fu, Bo Zhao

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

Are Smarter LLMs Safer? Exploring Safety-Reasoning Trade-offs in Prompting and Fine-Tuning

Ang Li, Yichuan Mo, Mingjie Li, Yifei Wang, Yisen Wang

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

Style Outweighs Substance: Failure Modes of LLM Judges in Alignment Benchmarking

Benjamin Feuer, Micah Goldblum, Teresa Datta, Sanjana Nambiar, Raz Besaleli, Samuel Dooley, Max Cembalest, John P. Dickerson

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

Comments ICLR 2025

Condor: Enhance LLM Alignment with Knowledge-Driven Data Synthesis and Refinement

Maosong Cao, Taolin Zhang, Mo Li, Chuyu Zhang, Yunxin Liu, Haodong Duan, Songyang Zhang, Kai Chen

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

Comments Tech Report. Github: https://github.com/InternLM/Condor

ProSwitch: Knowledge-Guided Instruction Tuning to Switch Between Professional and Non-Professional Responses

Chang Zong, Yuyan Chen, Weiming Lu, Jian Shao, Yongfeng Huang, Heng Chang, Yueting Zhuang

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

Comments 8 pages main body, 16 pages total

Calibrated Self-Rewarding Vision Language Models

Yiyang Zhou, Zhiyuan Fan, Dongjie Cheng, Sihan Yang, Zhaorun Chen, Chenhang Cui, Xiyao Wang, Yun Li, Linjun Zhang, Huaxiu Yao

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

Comments Added some experiments and charts, and redrew some figures V4

Evaluating Human Alignment and Model Faithfulness of LLM Rationale

Mohsen Fayyaz, Fan Yin, Jiao Sun, Nanyun Peng

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

Simultaneous Masking, Not Prompting Optimization: A Paradigm Shift in Fine-tuning LLMs for Simultaneous Translation

Matthew Raffel, Victor Agostinelli, Lizhong Chen

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

Comments Accepted at EMNLP 2024

Prefix Text as a Yarn: Eliciting Non-English Alignment in Foundation Language Model

Runzhe Zhan, Xinyi Yang, Derek F. Wong, Lidia S. Chao, Yue Zhang

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

Removing RLHF Protections in GPT-4 via Fine-Tuning

Qiusi Zhan, Richard Fang, Rohan Bindu, Akul Gupta, Tatsunori Hashimoto, Daniel Kang

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

Comments Accepted to NAACL 2024. (7 pages)

Language Models are Spacecraft Operators

Victor Rodriguez-Fernandez, Alejandro Carrasco, Jason Cheng, Eli Scharf, Peng Mun Siew, Richard Linares

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

Comments Source code available on Github at: https://github.com/ARCLab-MIT/kspdg

Instructed to Bias: Instruction-Tuned Language Models Exhibit Emergent Cognitive Bias

Itay Itzhak, Gabriel Stanovsky, Nir Rosenfeld, Yonatan Belinkov

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

Comments TACL 2024. Presented at ACL 2024. 12 pages

Building Accurate Translation-Tailored LLMs with Language Aware Instruction Tuning

Changtong Zan, Liang Ding, Li Shen, Yibing Zhen, Weifeng Liu, Dacheng Tao

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

RAD-PHI2: Instruction Tuning PHI-2 for Radiology

Mercy Ranjit, Gopinath Ganapathy, Shaury Srivastav, Tanuja Ganu, Srujana Oruganti

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

Arabic Mini-ClimateGPT : A Climate Change and Sustainability Tailored Arabic LLM

Sahal Shaji Mullappilly, Abdelrahman Shaker, Omkar Thawakar, Hisham Cholakkal, Rao Muhammad Anwer, Salman Khan, Fahad Shahbaz Khan

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

Comments Accepted to EMNLP 2023 (Findings)

Journal ref Findings of the Association for Computational Linguistics: EMNLP 2023, pages 14126-14136

Qilin-Med-VL: Towards Chinese Large Vision-Language Model for General Healthcare

Junling Liu, Ziming Wang, Qichen Ye, Dading Chong, Peilin Zhou, Yining Hua

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

On the Exploitability of Instruction Tuning

Manli Shu, Jiongxiao Wang, Chen Zhu, Jonas Geiping, Chaowei Xiao, Tom Goldstein

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

Comments NeurIPS 2023 camera-ready (21 pages, 10 figures)

Maybe Only 0.5% Data is Needed: A Preliminary Exploration of Low Training Data Instruction Tuning

Hao Chen, Yiming Zhang, Qi Zhang, Hantao Yang, Xiaomeng Hu, Xuetao Ma, Yifan Yanggong, Junbo Zhao

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

Comments 9 pages, 2 tables, 2 figures

SED-SFT: Selectively Encouraging Diversity in Supervised Fine-Tuning

SED-SFT: 在监督微调中选择性鼓励多样性

Yijie Chen, Yijin Liu, Fandong Meng

机构 * Tencent Inc（腾讯公司） 纠错

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

AI总结 SED-SFT通过引入选择性熵正则化和掩码机制，在监督微调中提升生成多样性，从而提高后续强化学习的性能。

Comments The code is publicly available at https://github.com/pppa2019/SED-SFT

Omni-Persona: Systematic Benchmarking and Improving Omnimodal Personalization

Omni-Persona：系统性基准测试与改进多模态个性化

Yeongtak Oh, Dongwook Lee, Sangkwon Park, Heeseung Kim, Sungroh Yoon

机构 * Department of Electrical and Computer Engineering, Seoul National University（首尔国立大学电气与计算机工程系） ； Interdisciplinary Program in Artificial Intelligence, Seoul National University（首尔国立大学人工智能跨学科项目） ； Department of Artificial Intelligence, University of Seoul（首尔大学人工智能系） 纠错

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

AI总结 Omni-Persona提出首个多模态个性化基准，通过Persona Modality Graph任务组和细粒度任务，系统分析多模态个性化中的接地行为，提出Calibrated Accuracy评估方法，揭示开源模型在音频与视觉接地上的差距及SFT与RLVR的局限性。

Comments Project Page: https://github.com/oyt9306/Omni-Persona

Quokka: Accelerating Program Verification with LLMs via Invariant Synthesis

Quokka：通过不变式合成加速程序验证

Anjiang Wei, Tianran Sun, Tarun Suresh, Haoze Wu, Ke Wang, Alex Aiken

机构 * Stanford University（斯坦福大学） ； Shanghai Jiao Tong University（上海交通大学） ； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） ； Amherst College（阿默斯特学院） ； Nanjing University（南京大学） 纠错

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

AI总结 Quokka通过利用大语言模型生成有用的循环不变式，提升程序验证效率，其评价导向框架在多个模型家族中表现出色，优于现有基于LLM的验证器。

Separating Clicks from Baits: Using Large Language Models to Detect Misleading YouTube Thumbnails

从诱饵中分离点击：使用大语言模型检测误导性的YouTube缩略图

Wajiha Naveed, Muhammad Muneeb Pervez, Zaeem Mohtashim Khan, Zafar Ayyub Qazi, Zartash Afzal Uzmi

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

AI总结 研究针对YouTube等平台误导性缩略图问题，提出用大语言模型的多模态检测管道，构建数据集并评估多个模型，发现Claude 3.5 Sonnet性能突出，通过失败分析为视频平台发展提供方向。

Comments Accepted to the 21st International AAAI Conference on Web and Social Media (ICWSM 2027)

Journal ref Proceedings of the International AAAI Conference on Web and Social Media, 2027

daVinci-kernel: Co-Evolving Skill Selection, Summarization, and Utilization via RL for GPU Kernel Optimization

daVinci-kernel：通过强化学习协同进化技能选择、总结与利用的GPU内核优化

Dayuan Fu, Mohan Jiang, Tongyu Wang, Dian Yang, Jiarui Hu, Liming Liu, Jinlong Hou, Pengfei Liu

机构 * University of Science and Technology of China（中国科学技术大学） 纠错

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

AI总结 提出daVinci-kernel框架，通过强化学习联合训练技能选择、策略生成和技能总结三个智能体，共享LLM骨干，实现GPU内核优化，在KernelBench上超越先前最优模型。

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models

GAP-MLLM：几何对齐预训练以激活多模态大语言模型中的3D空间感知

Jiaxin Zhang, Junjun Jiang, Haijie Li, Youyu Chen, Kui Jiang, Dave Zhenyu Chen

机构 * Harbin Institute of Technology（哈尔滨工业大学） ； School of Electronic and Computer Engineering, Peking University（北京大学电子与计算机工程学院） ； Huawei（华为） 纠错

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

AI总结 本文提出GAP-MLLM，通过几何对齐预训练激活多模态大语言模型中的3D空间感知，改进了传统方法在3D空间感知上的不足。

Comments Accepted by ECCV 2026. Project page: https://gapmllm.github.io/

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously

视频流思考：VideoLLMs可以同时观看和思考

Yiran Guan, Liang Yin, Dingkang Liang, Jianzhong Ju, Zhenbo Luo, Jian Luan, Yuliang Liu, Xiang Bai

机构 * Huazhong University of Science and Technology（华中科技大学） ； MiLM Plus Xiaomi Inc.（小米公司） 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 VST提出了一种视频流理解的新范式，通过在流式过程中激活推理，提高实时响应和理解能力，同时在多个基准测试中表现出更高的效率和泛化能力。

Comments Accepted by ECCV 2026, project page https://1ranguan.github.io/VST/

From Geometric Labels to Semantic Understanding of Indoor Building Components Using Multimodal Large Language Models

使用多模态大语言模型从几何标签到室内建筑组件的语义理解

Shuju Jing, Chao Yin

机构 * School of Qilu Transportation, Shandong University（山东大学齐鲁交通学院） ； Guangzhou Institute of Geography, Guangdong Academy of Sciences（广东省地理研究所） 纠错

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

AI总结 研究针对室内建筑组件，提出以点云为中心的多模态大语言模型Building-MLLM，通过特定机制解决语义集中问题，开发引擎编译数据集，实验表明其在多任务上表现优异，提升室内组件语言理解。

Comments 46 pages, 13 figures, accepted by Automation in Construction journal

FDLoRA: Personalized Federated Learning of Large Language Model via Dual LoRA Tuning

FDLoRA：通过双LoRA调整实现大语言模型的个性化联邦学习

Yao Lu, Jiaxing QI, Zhongzhi Luan, Shaohan Huang, Carol Fung, Hailong Yang, Depei Qian

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

AI总结 针对单个用户训练大语言模型资源需求高的挑战，提出FDLoRA框架，采用双LoRA调整，在客户端分别捕捉个性化和全局知识，仅全局模块上传参数，经自适应融合提升性能，降低通信和计算成本。