语言大模型 / LLM - arXivDaily 专题

2405.15007 2024-05-27 cs.CL cs.AI cs.LG 89%

RE-Adapt: Reverse Engineered Adaptation of Large Language Models

William Fleshman, Benjamin Van Durme

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

2402.13823 2024-05-16 cs.SE 89%

Using Large Language Models for Natural Language Processing Tasks in Requirements Engineering: A Systematic Guideline

Andreas Vogelsang, Jannik Fischbach

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

2310.11451 2024-05-09 cs.CL cs.AI cs.LG 89%

Seeking Neural Nuggets: Knowledge Transfer in Large Language Models from a Parametric Perspective

Ming Zhong, Chenxin An, Weizhu Chen, Jiawei Han, Pengcheng He

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

Comments ICLR 2024

2404.04522 2024-04-15 cs.CL cs.AI cs.IR cs.LG 89%

Q-PEFT: Query-dependent Parameter Efficient Fine-tuning for Text Reranking with Large Language Models

Zhiyuan Peng, Xuyang Wu, Qifan Wang, Sravanthi Rajanala, Yi Fang

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

2310.08825 2024-03-11 cs.CV 89%

From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models

Dongsheng Jiang, Yuchen Liu, Songlin Liu, Jin'e Zhao, Hao Zhang, Zhen Gao, Xiaopeng Zhang, Jin Li, Hongkai Xiong

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

2309.12307 2024-03-11 cs.CL cs.AI cs.LG 89%

LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models

Yukang Chen, Shengju Qian, Haotian Tang, Xin Lai, Zhijian Liu, Song Han, Jiaya Jia

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

Comments Code, models, dataset, and demo are available at https://github.com/dvlab-research/LongLoRA

2402.11417 2024-02-20 cs.CL cs.AI cs.LG 89%

LoRETTA: Low-Rank Economic Tensor-Train Adaptation for Ultra-Low-Parameter Fine-Tuning of Large Language Models

Yifan Yang, Jiajun Zhou, Ngai Wong, Zheng Zhang

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

2402.09260 2024-02-15 cs.HC 89%

Evaluating the Experience of LGBTQ+ People Using Large Language Model Based Chatbots for Mental Health Support

Zilin Ma, Yiyang Mei, Yinru Long, Zhaoyuan Su, Krzysztof Z. Gajos

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

2402.00070 2024-02-02 cs.NE cs.AI cs.CL cs.LG 89%

EvoMerge: Neuroevolution for Large Language Models

Yushu Jiang

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

Comments The current submission is the first draft, published for the sole purpose of sharing an idea and encouraging community effort. A more consolidated version may come later

2401.17862 2024-02-01 cs.CV 89%

Proximity QA: Unleashing the Power of Multi-Modal Large Language Models for Spatial Proximity Analysis

Jianing Li, Xi Nan, Ming Lu, Li Du, Shanghang Zhang

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

Comments 15 pages,version 1

2309.00904 2024-01-03 cs.RO 89%

Developmental Scaffolding with Large Language Models

Batuhan Celik, Alper Ahmetoglu, Emre Ugur, Erhan Oztop

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

Comments To appear in IEEE Transactions on Robotics ©IEEE2023

2309.10313 2023-12-06 cs.CL cs.AI cs.LG 89%

Investigating the Catastrophic Forgetting in Multimodal Large Language Models

Yuexiang Zhai, Shengbang Tong, Xiao Li, Mu Cai, Qing Qu, Yong Jae Lee, Yi Ma

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

2311.10697 2023-11-20 cs.CL cs.AI cs.IR cs.LG 89%

PEFT-MedAware: Large Language Model for Medical Awareness

Keivalya Pandya

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

Comments 7 pages, 1 figure, submitted to the Artificial Intelligence in Medicine Journal

2311.06495 2023-11-14 cs.CV 89%

LayoutPrompter: Awaken the Design Ability of Large Language Models

Jiawei Lin, Jiaqi Guo, Shizhao Sun, Zijiang James Yang, Jian-Guang Lou, Dongmei Zhang

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

Comments NeurIPS 2023

2310.20487 2023-11-01 cs.IR 89%

Large Language Model Can Interpret Latent Space of Sequential Recommender

Zhengyi Yang, Jiancan Wu, Yanchen Luo, Jizhi Zhang, Yancheng Yuan, An Zhang, Xiang Wang, Xiangnan He

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

2310.15793 2023-10-25 cs.LG cs.AI cs.CL 89%

Improving generalization in large language models by learning prefix subspaces

Louis Falissard, Vincent Guigue, Laure Soulier

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

2310.10449 2023-10-19 cs.CL cs.AI cs.LG 89%

Text Summarization Using Large Language Models: A Comparative Study of MPT-7b-instruct, Falcon-7b-instruct, and OpenAI Chat-GPT Models

Lochan Basyal, Mihir Sanghvi

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

Comments 4 pages, 2 tables

2308.07074 2023-08-16 cs.CL cs.AI cs.LG 89%

#InsTag: Instruction Tagging for Analyzing Supervised Fine-tuning of Large Language Models

Keming Lu, Hongyi Yuan, Zheng Yuan, Runji Lin, Junyang Lin, Chuanqi Tan, Chang Zhou, Jingren Zhou

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

2305.13292 2023-05-24 cs.CV 89%

VideoLLM: Modeling Video Sequence with Large Language Models

Guo Chen, Yin-Dong Zheng, Jiahao Wang, Jilan Xu, Yifei Huang, Junting Pan, Yi Wang, Yali Wang, Yu Qiao, Tong Lu, Limin Wang

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

Comments Technical Report

2602.11715 2026-06-17 cs.LG cs.CL 版本更新 89%

DICE: Diffusion Large Language Models Excel at Generating CUDA Kernels

DICE：扩散大语言模型在生成CUDA内核方面表现出色

Haolei Bai, Lingcheng Kong, Xueyi Chen, Jianmian Wang, Zhiqiang Tao, Huan Wang

机构 * Westlake University（西湖大学）； Hong Kong University of Science and Technology（香港科技大学）； Rochester Institute of Technology（罗切斯特理工学院）

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

AI总结提出CuKe数据集和BiC-RL训练框架，构建DICE系列扩散大语言模型（1.7B/4B/8B），在KernelBench上显著优于同类自回归和扩散模型，实现CUDA内核生成新SOTA。

Comments v2: Expanded with dLLM vs. autoregressive LLM comparisons, ablation studies, and qualitative case studies

2412.03665 2024-12-06 cs.CV cs.AI cs.CL cs.MM 89%

Personalizing Multimodal Large Language Models for Image Captioning: An Experimental Analysis

Davide Bucciarelli, Nicholas Moratelli, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara

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

Comments ECCV 2024 Workshop on Green Foundation Models

2411.03495 2024-11-07 cs.CL cs.AI 89%

Automatic Generation of Question Hints for Mathematics Problems using Large Language Models in Educational Technology

Junior Cedric Tonga, Benjamin Clement, Pierre-Yves Oudeyer

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

Comments Accepted at NeurIPS 2024 Workshop on Large Foundation Models for Educational Assessment (FM-Assess)

2508.08636 2026-08-12 cs.CL 版本更新 89%

InternAgentHarness: A Scalable Synthetic Environment for Enhancing LLM Agentic Abilities

InternBootcamp 技术报告：通过可验证的任务扩展提升大语言模型推理能力

Xiaozhe Li, Yongkang Chen, Shujian Deng, Peiji Li, Yichuan Ma, Huaxi Huang, Qiye Cai, Tianyi Lyu, Le Ma, Linyang Li, Qipeng Guo, Dahua Lin, Kai Chen

机构 * Shanghai AI Laboratory（上海人工智能实验室）； Fudan University（复旦大学）

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

AI总结本文提出InternBootcamp框架，通过可验证的任务扩展方法提升大语言模型的推理能力，为基于强化学习的模型优化、合成数据生成和模型评估提供了基础设施。

Comments InternAgentHarness tech report

2605.27752 2026-08-10 cs.AI 版本更新 89%

Same Answer, Different Confidence: Protocol Sensitivity in LLM Confidence Calibration

询问是不够的：LLM 置信度校准中的协议敏感性

Hankyeol Kim, Pilsung Kang

机构 * Seoul National University（首尔国立大学）

专题命中指令微调：LLM(title,title_cn)；分类 cs.AI

AI总结研究通过改变测量协议（如条件上下文、令牌读取方式）发现，LLM 的令牌概率置信度与口头置信度之间的比较高度敏感，且口头置信度不仅反映正确性还反映答案的合理性和来源。

2607.26023 2026-07-29 cs.AI 新提交 89%

CHARM: A Multimodal Graph Foundation Model with Hierarchical Context Modeling for Zero-Shot Transfer

CHARM：一种用于零样本迁移的具有分层上下文建模的多模态图基础模型

Ankang Yang, Jitao Zhao, Di Jin, Yuxiao Huang, Dongxiao He

机构 * School of Computer Science and Technology, College of Intelligence and Computing, Tianjin University（天津大学智能与计算学部计算机科学与技术学院）； Data Science Program, Columbian College of Arts and Sciences, The George Washington University（乔治华盛顿大学文理学院哥伦比亚艺术与科学学院数据科学项目）

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

AI总结研究多模态图零样本迁移问题，提出CHARM模型，通过分层上下文建模，用图上下文替换原始节点，减少对目标域监督或适配的依赖，经实验验证该模型在零样本多模态图任务上有改进。

2607.22205 2026-07-29 cs.CV cs.AI 版本更新 89%

Filling Before Advancing: Capability-Gap-Driven Post-Training for Scenario-Specialized Remote Sensing MLLMs

推进前填充：能力差距驱动的场景专用遥感多模态大语言模型的训练后处理

Yuheng Zong, Minghua Wang, Xin Zhao, Zhi-Hui Zhan, Antonio Plaza, Jon Atli Benediktsson

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

AI总结针对地球观测应用中遥感多模态大语言模型因高质量数据稀缺和能力覆盖不完整难以实现细粒度场景专业化的问题，提出能力差距驱动的推进前填充（FBA）方法，经实验验证其效果优于其他方法，提升了模型在相关基准上的表现。

2407.10887 2026-07-02 cs.CR cs.AI 版本更新 89%

Hey, That's My Model! Introducing Chain & Hash, An LLM Fingerprinting Technique

嘿，那是我的模型！引入链与哈希，一种大语言模型指纹识别技术

Mark Russinovich, Yanan Cai, Ahmed Salem

机构 * Microsoft（微软）

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

AI总结提出一种基于链与哈希的LLM指纹识别框架，通过加密绑定提示与响应防止碰撞，并利用随机填充和元提示配置增强鲁棒性，实现可验证的所有权证明。

Comments Published at ICLR 2026

2606.30140 2026-06-30 q-bio.GN cs.CL 89%

DNA Language Models: An Assessment of Pre-Training for Fine-Tuning Tasks

DNA语言模型：面向微调任务的预训练评估

Romain Karpinsky, Julien Mozziconacci, Mickaël Delcey

机构 * CNRS（法国国家科学研究中心）； LORIA（洛林大学）

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

AI总结本研究系统比较了基于Transformer和卷积的DNA语言模型在微调任务上的表现，评估了预训练的实际贡献以及BPE分词对基因组学任务的影响。

Comments 12 pages, 2 figures, 14 tables

2606.24064 2026-06-24 cs.AI 新提交 89%

Beyond Trajectory Imitation: Strategy-Guided Policy Optimization for LLM Reasoning

超越轨迹模仿：策略引导的策略优化用于大语言模型推理

Tianyuan Shi, Canbin Huang, Bei Li, Xin Chen, Xiaojun Quan, Jingang Wang, Qifan Wang

机构 * School of Computer Science and Engineering, Sun Yat-sen University, China（中山大学计算机科学与工程学院）； Meituan, Inc., China（美团）； Shenzhen Loop Area Institute, China（深圳环区研究所）； Meta AI, USA（Meta AI）

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

AI总结提出策略引导的策略优化（SGPO），通过可重用策略蒸馏替代实例级轨迹模仿，利用前向KL散度和自适应加权提升LLM推理泛化能力，在数学基准上平均提升2.2分。

2606.12882 2026-06-12 cs.AI 新提交 89%

HarnessBridge: Learnable Bidirectional Controller for LLM Agent Harness

HarnessBridge: 用于LLM智能体框架的可学习双向控制器

Xiaoxuan Wang, Haixin Wang, Alexander Taylor, Jason Cong, Yizhou Sun, Wei Wang

机构 * University of California, Los Angeles（加州大学洛杉矶分校）

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

AI总结提出HarnessBridge，一种轻量级可学习框架控制器，通过双向投影参数化智能体-环境接口，减少令牌使用和轨迹长度，并泛化到更大模型。

1. 指令微调 11653 篇

RE-Adapt: Reverse Engineered Adaptation of Large Language Models

Using Large Language Models for Natural Language Processing Tasks in Requirements Engineering: A Systematic Guideline

Seeking Neural Nuggets: Knowledge Transfer in Large Language Models from a Parametric Perspective

Q-PEFT: Query-dependent Parameter Efficient Fine-tuning for Text Reranking with Large Language Models

From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models

LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models

LoRETTA: Low-Rank Economic Tensor-Train Adaptation for Ultra-Low-Parameter Fine-Tuning of Large Language Models

Evaluating the Experience of LGBTQ+ People Using Large Language Model Based Chatbots for Mental Health Support

EvoMerge: Neuroevolution for Large Language Models

Proximity QA: Unleashing the Power of Multi-Modal Large Language Models for Spatial Proximity Analysis

Developmental Scaffolding with Large Language Models

Investigating the Catastrophic Forgetting in Multimodal Large Language Models

PEFT-MedAware: Large Language Model for Medical Awareness

LayoutPrompter: Awaken the Design Ability of Large Language Models

Large Language Model Can Interpret Latent Space of Sequential Recommender

Improving generalization in large language models by learning prefix subspaces

Text Summarization Using Large Language Models: A Comparative Study of MPT-7b-instruct, Falcon-7b-instruct, and OpenAI Chat-GPT Models

#InsTag: Instruction Tagging for Analyzing Supervised Fine-tuning of Large Language Models

VideoLLM: Modeling Video Sequence with Large Language Models

DICE: Diffusion Large Language Models Excel at Generating CUDA Kernels

Personalizing Multimodal Large Language Models for Image Captioning: An Experimental Analysis

Automatic Generation of Question Hints for Mathematics Problems using Large Language Models in Educational Technology

InternAgentHarness: A Scalable Synthetic Environment for Enhancing LLM Agentic Abilities

Same Answer, Different Confidence: Protocol Sensitivity in LLM Confidence Calibration

CHARM: A Multimodal Graph Foundation Model with Hierarchical Context Modeling for Zero-Shot Transfer

Filling Before Advancing: Capability-Gap-Driven Post-Training for Scenario-Specialized Remote Sensing MLLMs

Hey, That's My Model! Introducing Chain & Hash, An LLM Fingerprinting Technique

DNA Language Models: An Assessment of Pre-Training for Fine-Tuning Tasks

Beyond Trajectory Imitation: Strategy-Guided Policy Optimization for LLM Reasoning

HarnessBridge: Learnable Bidirectional Controller for LLM Agent Harness