语言大模型 / LLM - arXivDaily 专题

2602.04602 2026-02-05 cond-mat.mtrl-sci physics.data-an 89%

Automated Extraction of Multicomponent Alloy Data Using Large Language Models for Sustainable Design

利用大语言模型自动化提取多组分合金数据用于可持续设计

Aravindan Kamatchi Sundaram, Mohit Chakraborty, Sai Mani Kumar Devathi, B. Pabitramohan Prusty, Rohit Batra

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)

AI总结利用大语言模型自动化提取多组分合金数据，构建大规模数据库并用于可持续材料选择。

Comments 18 pages, 6 figures

2601.17492 2026-02-03 cs.IR 89%

Towards Fair Large Language Model-based Recommender Systems without Costly Retraining

迈向无需昂贵重训练的公平大型语言模型推荐系统

Jin Li, Huilin Gu, Shoujin Wang, Qi Zhang, Shui Yu, Chen Wang, Xiwei Xu, Fang Chen

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)

AI总结 FUDLR提出一种无需昂贵重训练的高效去偏方法，通过两阶段机器无学习提升LLM推荐系统的公平性，同时保持推荐准确性。

Comments Accepted by WWW 2026

2412.13126 2026-01-28 eess.IV cs.CV 89%

Knowledge-enhanced Pretraining for Vision-language Pathology Foundation Model on Cancer Diagnosis

基于知识增强的视觉语言病理基础模型用于癌症诊断

Xiao Zhou, Luoyi Sun, Dexuan He, Wenbin Guan, Ge Wang, Ruifen Wang, Lifeng Wang, Xiaojun Yuan, Xin Sun, Ya Zhang, Kun Sun, Yanfeng Wang, Weidi Xie

机构 * Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）； Shanghai Jiao Tong University（上海交通大学）； Xinhua Hospital Affiliated to Shanghai Jiao Tong University School of Medicine（上海交通大学医学院附属新华医院）； School of Artificial Intelligence（人工智能学院）； Department of Pathology（病理学部）； Department of Oral Pathology（口腔病理学部）； Department of Pediatric Hematology/Oncology（儿科血液肿瘤科）； Clinical Research and Innovation Unit（临床研究与创新单元）； Department of Pediatric Cardiology（儿童心脏病科）

专题命中预训练与数据：foundation model(title,abstract)；pretraining(title,abstract)；language model(abstract)

AI总结本文提出KEEP模型，通过整合疾病知识图谱提升癌症诊断的视觉语言基础模型性能，显著优于现有方法。

Comments V2: fixed typos, updated experimental results, added ablation

2601.15486 2026-01-23 cs.RO 89%

A Universal Large Language Model -- Drone Command and Control Interface

通用大型语言模型——无人机指挥与控制接口

Javier N. Ramos-Silva, Peter J. Burke

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)

AI总结本文提出了一种通用的无人机控制接口，通过MCP协议实现LLM与无人机的无缝集成，提供实时导航和飞行控制能力。

2508.08270 2025-12-30 cs.LG cs.AI cs.CL cs.MM 89%

Doctor Sun: A Bilingual Multimodal Large Language Model for Biomedical AI

Doctor Sun: 一种双语多模态大语言模型用于生物医学AI

Dong Xue, Ziyao Shao, Zhaoyang Duan, Fangzhou Liu, Bing Li, Zhongheng Zhang

机构 * Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education East China University of Science and Technology（能源化工过程智能制造重点实验室，东华大学）； Research Institute of Intelligent Control and Systems Harbin Institute of Technology（智能控制与系统研究室，哈尔滨工业大学）； Department of Emergency Medicine, Sir Run Run Shaw Hospital Zhejiang University School of Medicine（浙江大学医学院急诊医学科）； Provincial Key Laboratory of Precise Diagnosis Treatment of Abdominal Infection, Sir Run Run Shaw Hospital Zhejiang University School of Medicine（腹部感染精准诊断治疗省级重点实验室，浙江大学医学院）； School of Medicine Shaoxing University（绍兴大学医学院）

专题命中预训练与数据：large language model(title)；language model(title)；LLM(abstract)；instruction tuning(abstract)

AI总结 Doctor Sun是一种双语多模态大语言模型，通过整合预训练视觉编码器和医学LLM，提升生物医学多模态任务的性能，并提供SunMed-VL数据集支持研究进展。

2512.21107 2025-12-25 cs.CL cs.AI cs.LG 89%

Semi-Supervised Learning for Large Language Models Safety and Content Moderation

大型语言模型安全性和内容审核的半监督学习

Eduard Stefan Dinuta, Iustin Sirbu, Traian Rebedea

机构 * National University of Science and Technology Politehnica Bucharest（波兰技术大学科学与技术国家大学）

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL、cs.AI、cs.LG

AI总结本文提出利用半监督学习提升大型语言模型的安全性，通过结合标记和未标记数据以及任务特定增强技术，提高安全分类器的性能。

2512.15076 2025-12-18 cs.SE 89%

An Exploratory Study of Bayesian Prompt Optimization for Test-Driven Code Generation with Large Language Models

基于大语言模型的测试驱动代码生成中贝叶斯提示优化的探索性研究

Shlok Tomar, Aryan Deshwal, Ethan Villalovoz, Mattia Fazzini, Haipeng Cai, Janardhan Rao Doppa

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)

AI总结本文提出BODE-GEN方法，通过贝叶斯优化优化提示以提高大语言模型生成代码的准确性，实验表明其在代码生成准确性上优于固定提示和手动提示工程。

Comments 20 pages, 13 figures

2511.20799 2025-11-27 cs.CL cs.AI cs.CR cs.LG 89%

Memories Retrieved from Many Paths: A Multi-Prefix Framework for Robust Detection of Training Data Leakage in Large Language Models

从多路径中检索的记忆：一种多前缀框架，用于在大型语言模型中稳健检测训练数据泄露

Trung Cuong Dang, David Mohaisen

机构 * Department of Computer Science, University of Central Florida（计算机科学系，中央佛罗里达大学）

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL、cs.AI、cs.LG

AI总结本文提出多前缀框架，通过量化记忆的检索路径多样性，稳健检测大型语言模型中的训练数据泄露问题。

Comments 11 pages, 2 tables, 8 figures

2509.14926 2025-11-19 cs.CL cs.AI cs.LG 89%

Patent Language Model Pretraining with ModernBERT

Amirhossein Yousefiramandi, Ciaran Cooney

机构 * Clarivate

专题命中预训练与数据：language model(title,abstract)；pretraining(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 7 pages, 5 figures, 4 tables

2411.15821 2025-11-11 cs.CL cs.AI cs.LG 89%

Is Training Data Quality or Quantity More Impactful to Small Language Model Performance?

Aryan Sajith, Krishna Chaitanya Rao Kathala

专题命中预训练与数据：language model(title,abstract)；small language model(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 14 pages, 5 tables, 4 figures | Accepted at International Conference on Neural Computing for Advanced Applications 2025, Conference info: https://aaci.org.hk/ncaa2025

Journal ref Commun. Comput. Inf. Sci. 2665 (2025) 75-87

2506.07491 2025-11-06 cs.CV 89%

SpatialLM: Training Large Language Models for Structured Indoor Modeling

Yongsen Mao, Junhao Zhong, Chuan Fang, Jia Zheng, Rui Tang, Hao Zhu, Ping Tan, Zihan Zhou

机构 * Manycore Tech Inc.（Manycore科技公司）； Hong Kong University of Science and Technology（香港科技大学）

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)

2505.21375 2025-11-05 cs.CV 89%

GeoLLaVA-8K: Scaling Remote-Sensing Multimodal Large Language Models to 8K Resolution

Fengxiang Wang, Mingshuo Chen, Yueying Li, Di Wang, Haotian Wang, Zonghao Guo, Zefan Wang, Boqi Shan, Long Lan, Yulin Wang, Hongzhen Wang, Wenjing Yang, Bo Du, Jing Zhang

机构 * College of Computer Science and Technology, National University of Defense Technology, China（中国国防科技大学计算机科学与技术学院）； Beijing University of Posts and Telecommunications, China（北京邮电大学）； School of Computer Science, Wuhan University, China（武汉大学计算机学院）； Zhongguancun Academy, China（中关村学院）； Tsinghua University, China（清华大学）； Beihang University, China（北航大学）

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；foundation model(abstract)

Comments NeurlPS 2025 Spotlight

2510.13915 2025-10-17 cs.CL cs.AI cs.LG 89%

Readability $\ne$ Learnability: Rethinking the Role of Simplicity in Training Small Language Models

Ivan Lee, Taylor Berg-Kirkpatrick

机构 * UC San Diego（圣地亚哥大学）

专题命中预训练与数据：language model(title,abstract)；small language model(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted to COLM 2025 (Spotlight)

2501.05577 2025-10-14 physics.ed-ph 89%

Exploring Large Language Models (LLMs) through interactive Python activities

Eugenio Tufino

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)

Comments 13 pages, 6 figures

Journal ref Phys. Educ. 60 (2025) 055003

2510.09605 2025-10-13 cs.HC 89%

VisPile: A Visual Analytics System for Analyzing Multiple Text Documents With Large Language Models and Knowledge Graphs

Adam Coscia, Alex Endert

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)

Comments Accepted to HICSS 2026. 10 pages, 4 figures. For a demo video, see https://youtu.be/vY6SqkkNeMQ. For a live demo, visit https://adamcoscia.com/papers/vispile/demo/. The source code is available at https://github.com/AdamCoscia/VisPile

2509.25494 2025-10-01 cs.IR 89%

On-Premise AI for the Newsroom: Evaluating Small Language Models for Investigative Document Search

Nick Hagar, Nicholas Diakopoulos, Jeremy Gilbert

专题命中预训练与数据：language model(title,abstract)；small language model(title)；LLM(abstract)；large language model(abstract)

Comments Accepted to Computation + Journalism Symposium 2025

2509.07909 2025-09-10 cs.LG cs.AI cs.CL 89%

Uncovering Scaling Laws for Large Language Models via Inverse Problems

Arun Verma, Zhaoxuan Wu, Zijian Zhou, Xiaoqiang Lin, Zhiliang Chen, Rachael Hwee Ling Sim, Rui Qiao, Jingtan Wang, Nhung Bui, Xinyuan Niu, Wenyang Hu, Gregory Kang Ruey Lau, Zi-Yu Khoo, Zitong Zhao, Xinyi Xu, Apivich Hemachandra, See-Kiong Ng, Bryan Kian Hsiang Low

机构 * Singapore-MIT Alliance for Research and Technology（新加坡-麻省理工联盟研究技术中心）； Dept. of Computer Science, National University of Singapore（新加坡国立大学计算机科学系）； Agency for Science, Technology and Research（科技研究局）； Institute of Data Science, National University of Singapore（新加坡国立大学数据科学研究院）； SAP（SAP公司）； AI Singapore（AI新加坡）

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted at EMNLP Findings 2025

2508.01242 2025-08-06 cs.GR cs.CV 89%

MeshLLM: Empowering Large Language Models to Progressively Understand and Generate 3D Mesh

Shuangkang Fang, I-Chao Shen, Yufeng Wang, Yi-Hsuan Tsai, Yi Yang, Shuchang Zhou, Wenrui Ding, Takeo Igarashi, Ming-Hsuan Yang

机构 * Beihang University（北航大学）； The University of Tokyo（东京大学）； Atmanity Inc.（Atmanity公司）； StepFun Inc.（StepFun公司）； UC Merced（加州大学默塞德分校）

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)

Comments Accepted by ICCV. Project Website: https://sk-fun.fun/MeshLLM

2404.14445 2025-07-25 cs.LG cs.AI cs.CL 89%

A Multi-Faceted Evaluation Framework for Assessing Synthetic Data Generated by Large Language Models

Yefeng Yuan, Yuhong Liu, Liang Cheng

机构 * Santa Clara University（圣克拉拉大学）； eBay Inc.（eBay公司）

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 10 pages, 1 figure, 4 tables

2507.16969 2025-07-24 cs.IR 89%

LLM4MEA: Data-free Model Extraction Attacks on Sequential Recommenders via Large Language Models

Shilong Zhao, Fei Sun, Kaike Zhang, Shaoling Jing, Du Su, Zhichao Shi, Zhiyi Yin, Huawei Shen, Xueqi Cheng

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)

2507.09965 2025-07-15 cs.MA cs.AR 89%

AnalogTester: A Large Language Model-Based Framework for Automatic Testbench Generation in Analog Circuit Design

Weiyu Chen, Chengjie Liu, Wenhao Huang, Jinyang Lyu, Mingqian Yang, Yuan Du, Li Du, Jun Yang

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)

Comments accepted by ISEDA 2025

2506.21898 2025-07-09 cs.HC 89%

Bias, Accuracy, and Trust: Gender-Diverse Perspectives on Large Language Models

Aimen Gaba, Emily Wall, Tejas Ramkumar Babu, Yuriy Brun, Kyle Hall, Cindy Xiong Bearfield

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)

2503.17690 2025-07-01 cs.CV 89%

CountLLM: Towards Generalizable Repetitive Action Counting via Large Language Model

Ziyu Yao, Xuxin Cheng, Zhiqi Huang, Lei Li

机构 * Peking University（北京大学）； University of Washington（华盛顿大学）； University of Copenhagen（哥本哈根大学）

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)

Comments Accepted by CVPR 2025

2506.12699 2025-06-23 cs.CR cs.HC 89%

SoK: The Privacy Paradox of Large Language Models: Advancements, Privacy Risks, and Mitigation

Yashothara Shanmugarasa, Ming Ding, M. A. P Chamikara, Thierry Rakotoarivelo

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)

2506.02012 2025-06-04 cs.CV cs.SD eess.AS 89%

Leveraging Large Language Models in Visual Speech Recognition: Model Scaling, Context-Aware Decoding, and Iterative Polishing

Zehua Liu, Xiaolou Li, Li Guo, Lantian Li, Dong Wang

机构 * Beijing University of Posts and TelecommunicationsChina（北京邮电大学中国）； Tsinghua UniversityChina（清华大学中国）

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)

2505.11121 2025-05-19 cs.CV 89%

Redundancy-Aware Pretraining of Vision-Language Foundation Models in Remote Sensing

Mathis Jürgen Adler, Leonard Hackel, Gencer Sumbul, Begüm Demir

机构 * TU Berlin（柏林技术大学）； BIFOLD（BIFOLD机构）； EPFL（苏黎世联邦理工学院）

专题命中预训练与数据：foundation model(title,abstract)；pretraining(title,abstract)；language model(abstract)

Comments Accepted at IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2025. Our code is available at https://git.tu-berlin.de/rsim/redundacy-aware-rs-vlm

2407.12665 2025-05-16 cs.CL cs.AI cs.LG 89%

Beyond Next Token Prediction: Patch-Level Training for Large Language Models

Chenze Shao, Fandong Meng, Jie Zhou

机构 * Pattern Recognition Center, WeChat AI, Tencent Inc（模式识别中心、微信AI、腾讯公司）

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments ICLR 2025 Spotlight

2408.10613 2025-05-14 cs.IR 89%

Task-level Distributionally Robust Optimization for Large Language Model-based Dense Retrieval

Guangyuan Ma, Yongliang Ma, Xing Wu, Zhenpeng Su, Ming Zhou, Songlin Hu

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)

Comments Accepted by AAAI25. Source code is available at https://github.com/ma787639046/tdro

2504.09776 2025-04-15 cs.CR 89%

An Investigation of Large Language Models and Their Vulnerabilities in Spam Detection

Qiyao Tang, Xiangyang Li

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)

Comments 10 pages; presented at HotSoS'2025 as a work in progress paper

2502.20779 2025-04-01 cs.CL cs.AI cs.LG q-bio.NC 89%

Triple Phase Transitions: Understanding the Learning Dynamics of Large Language Models from a Neuroscience Perspective

Yuko Nakagi, Keigo Tada, Sota Yoshino, Shinji Nishimoto, Yu Takagi

专题命中预训练与数据：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 46 pages

1. 预训练与数据 12403 篇

Automated Extraction of Multicomponent Alloy Data Using Large Language Models for Sustainable Design

Towards Fair Large Language Model-based Recommender Systems without Costly Retraining

Knowledge-enhanced Pretraining for Vision-language Pathology Foundation Model on Cancer Diagnosis

A Universal Large Language Model -- Drone Command and Control Interface

Doctor Sun: A Bilingual Multimodal Large Language Model for Biomedical AI

Semi-Supervised Learning for Large Language Models Safety and Content Moderation

An Exploratory Study of Bayesian Prompt Optimization for Test-Driven Code Generation with Large Language Models

Memories Retrieved from Many Paths: A Multi-Prefix Framework for Robust Detection of Training Data Leakage in Large Language Models

Patent Language Model Pretraining with ModernBERT

Is Training Data Quality or Quantity More Impactful to Small Language Model Performance?

SpatialLM: Training Large Language Models for Structured Indoor Modeling

GeoLLaVA-8K: Scaling Remote-Sensing Multimodal Large Language Models to 8K Resolution

Readability $\ne$ Learnability: Rethinking the Role of Simplicity in Training Small Language Models

Exploring Large Language Models (LLMs) through interactive Python activities

VisPile: A Visual Analytics System for Analyzing Multiple Text Documents With Large Language Models and Knowledge Graphs

On-Premise AI for the Newsroom: Evaluating Small Language Models for Investigative Document Search

Uncovering Scaling Laws for Large Language Models via Inverse Problems

MeshLLM: Empowering Large Language Models to Progressively Understand and Generate 3D Mesh

A Multi-Faceted Evaluation Framework for Assessing Synthetic Data Generated by Large Language Models

LLM4MEA: Data-free Model Extraction Attacks on Sequential Recommenders via Large Language Models

AnalogTester: A Large Language Model-Based Framework for Automatic Testbench Generation in Analog Circuit Design

Bias, Accuracy, and Trust: Gender-Diverse Perspectives on Large Language Models

CountLLM: Towards Generalizable Repetitive Action Counting via Large Language Model

SoK: The Privacy Paradox of Large Language Models: Advancements, Privacy Risks, and Mitigation

Leveraging Large Language Models in Visual Speech Recognition: Model Scaling, Context-Aware Decoding, and Iterative Polishing

Redundancy-Aware Pretraining of Vision-Language Foundation Models in Remote Sensing

Beyond Next Token Prediction: Patch-Level Training for Large Language Models

Task-level Distributionally Robust Optimization for Large Language Model-based Dense Retrieval

An Investigation of Large Language Models and Their Vulnerabilities in Spam Detection

Triple Phase Transitions: Understanding the Learning Dynamics of Large Language Models from a Neuroscience Perspective