语言大模型 / LLM

2510.09051 2025-10-13 cs.CL cs.AI cs.LG 90%

Alif: Advancing Urdu Large Language Models via Multilingual Synthetic Data Distillation

Muhammad Ali Shafique, Kanwal Mehreen, Muhammad Arham, Maaz Amjad, Sabur Butt, Hamza Farooq

机构 * University of British Columbia（不列颠哥伦比亚大学）； Texas Tech University（德克萨斯技术大学）； Institute for the Future of Education, Tecnológico de Monterrey（教育未来研究所，墨西哥蒙特雷技术学院）

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

Comments Accepted to the EMNLP 2025 Workshop on Multilingual Representation Learning (MRL)

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

2407.19638 2025-10-13 cs.CL 88%

On the Reliability of Large Language Models for Causal Discovery

Tao Feng, Lizhen Qu, Niket Tandon, Zhuang Li, Xiaoxi Kang, Gholamreza Haffari

机构 * Monash University（莫纳什大学）； Microsoft Research, India（微软研究院，印度）

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

Comments ACL 2025

2510.09423 2025-10-13 cs.LG 86%

Weight Initialization and Variance Dynamics in Deep Neural Networks and Large Language Models

Yankun Han

机构 * University of Florida（佛罗里达大学）

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

Comments 8 pages, 6 figures

2510.09471 2025-10-13 cs.CL 85%

Getting Your Indices in a Row: Full-Text Search for LLM Training Data for Real World

Ines Altemir Marinas, Anastasiia Kucherenko, Alexander Sternfeld, Andrei Kucharavy

机构 * IC, EPFL（EPFL）

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

2510.08920 2025-10-13 cs.LG 83%

Simple and Robust Forecasting of Spatiotemporally Correlated Small Earth Data with A Tabular Foundation Model

Yuting Yang, Gang Mei, Zhengjing Ma, Nengxiong Xu, Jianbing Peng

机构 * School of Engineering and Technology, China University of Geosciences (Beijing)（工程与技术学院，中国地质大学（北京））； School of Geological Engineering and Geomatics, Chang'an University（地质工程与测绘学院，长安大学）

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

2510.08664 2025-10-13 cs.SE cs.AI 83%

Faver: Boosting LLM-based RTL Generation with Function Abstracted Verifiable Middleware

Jianan Mu, Mingyu Shi, Yining Wang, Tianmeng Yang, Bin Sun, Xing Hu, Jing Ye, Huawei Li

机构 * Huawei（华为）

专题命中预训练与数据：LLM(title,abstract)；SFT(abstract)；分类 cs.AI

2506.09560 2025-10-13 cs.CL 83%

Towards Open Foundation Language Model and Corpus for Macedonian: A Low-Resource Language

Stefan Krsteski, Matea Tashkovska, Borjan Sazdov, Hristijan Gjoreski, Branislav Gerazov

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

Comments Camera-ready version accepted at SlavNLP-2025@ACL

2510.08744 2025-10-13 cs.LG cs.AI 79%

Graph Diffusion Transformers are In-Context Molecular Designers

Gang Liu, Jie Chen, Yihan Zhu, Michael Sun, Tengfei Luo, Nitesh V Chawla, Meng Jiang

机构 * University of Notre Dame（诺丁汉大学）； MIT-IBM Watson AI Lab, IBM Research（麻省理工-IBM Watson人工智能实验室，IBM研究）

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

Comments 29 pages, 16 figures, 17 tables. Model available at: https://huggingface.co/liuganghuggingface/DemoDiff-0.7B

2510.06250 2025-10-13 cs.CL cs.AI 79%

Scalable multilingual PII annotation for responsible AI in LLMs

Bharti Meena, Joanna Skubisz, Harshit Rajgarhia, Nand Dave, Kiran Ganesh, Shivali Dalmia, Abhishek Mukherji, Vasudevan Sundarababu

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

2510.09553 2025-10-13 cs.CL 77%

Hierarchical Indexing with Knowledge Enrichment for Multilingual Video Corpus Retrieval

Yu Wang, Tianhao Tan, Yifei Wang

机构 * School of Computing and Information, University of Pittsburgh, PA, USA（计算与信息学院，匹兹堡大学）； Wuhan University of Technology（武汉理工大学）； Hunan University（湖南大学）

专题命中预训练与数据：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

Comments Accepted to NLPCC 2025 (Springer), to appear November 2025

2510.08850 2025-10-13 cs.SE cs.AI 77%

Repository-Aware File Path Retrieval via Fine-Tuned LLMs

Vasudha Yanuganti, Ishaan Puri, Swapnil Chhatre, Mantinder Singh, Ashok Jallepalli, Hritvik Shrivastava, Pradeep Kumar Sharma

专题命中预训练与数据：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

2510.08054 2025-10-13 cs.CV 71%

RetouchLLM: Training-free Code-based Image Retouching with Vision Language Models

Moon Ye-Bin, Roy Miles, Tae-Hyun Oh, Ismail Elezi, Jiankang Deng

机构 * POSTECH ； Huawei London Research Center（华为伦敦研究中心）； KAIST（韩国科学技术院）； Imperial College London（伦敦帝国理工学院）

专题命中预训练与数据：language model(title)

2502.11411 2025-10-13 cs.LG 70%

Detecting and Filtering Unsafe Training Data via Data Attribution with Denoised Representation

Yijun Pan, Taiwei Shi, Jieyu Zhao, Jiaqi W. Ma

机构 * University of Michigan（密歇根大学）； University of Southern California（南加州大学）； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）

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

Comments 14 pages

2510.09031 2025-10-13 cs.SI 67%

Web Crawler Restrictions, AI Training Datasets \& Political Biases

Paul Bouchaud, Pedro Ramaciotti

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

2510.09596 2025-10-13 cs.LG cs.AI 62%

BaNEL: Exploration Posteriors for Generative Modeling Using Only Negative Rewards

Sangyun Lee, Brandon Amos, Giulia Fanti

机构 * Carnegie Mellon University（卡内基梅隆大学）

专题命中预训练与数据：post-training(abstract)；分类 cs.AI、cs.LG

2510.09422 2025-10-13 stat.CO 50%

Solving Fokker-Planck-Kolmogorov Equation by Distribution Self-adaptation Normalized Physics-informed Neural Networks

Yi Zhang, Yiting Duan, Xiangjun Wang, Zhikun Zhang

专题命中预训练与数据：pretraining(abstract)

2510.08625 2025-10-13 cs.CV 50%

Adjusting Initial Noise to Mitigate Memorization in Text-to-Image Diffusion Models

Hyeonggeun Han, Sehwan Kim, Hyungjun Joo, Sangwoo Hong, Jungwoo Lee

机构 * Seoul National University（首尔国立大学）； CSE, Konkuk University（计算机科学与工程系，konkuk大学）； Hodoo AI Labs（Hodoo AI实验室）

专题命中预训练与数据：prompting(abstract)

2510.09400 2025-10-13 cs.SE 91%

TIT: A Tree-Structured Instruction Tuning Approach for LLM-Based Code Translation

He Jiang, Yufu Wang, Hao Lin, Peiyu Zou, Zhide Zhou, Ang Jia, Xiaochen Li, Zhilei Ren

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

2510.08620 2025-10-13 cs.CL 89%

JAI-1: A Thai-Centric Large Language Model

Attapol T. Rutherford, Jullajak Karnjanaekarin, Narongkorn Panitsrisit, Pontakorn Trakuekul, Sumana Sumanakul, Natchanon Pollertlam

机构 * Jasmine Technology Solution, Thailand ； Department of Linguistics, Chulalongkorn University, Thailand（语言学系，朱拉隆功大学）

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

2305.06212 2025-10-13 cs.CL cs.CR 89%

Privacy-Preserving Parameter-Efficient Fine-Tuning for Large Language Model Services

Yansong Li, Zhixing Tan, Paula Branco, Yang Liu

机构 * University of Ottawa（渥太华大学）； Zhongguancun Laboratory（中关村实验室）； School of Electrical Engineering and Computer Science（电气工程与计算机科学学院）； Department of Computer Science and Technology（计算机科学与技术系）； Institute for AI Industry Research (AIR)（人工智能产业研究院）

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

Journal ref IEEE Transactions on Audio, Speech, and Language Processing 33 (2025) 4085-4097

2510.08902 2025-10-13 cs.CL cs.AI 88%

A Unified Biomedical Named Entity Recognition Framework with Large Language Models

Tengxiao Lv, Ling Luo, Juntao Li, Yanhua Wang, Yuchen Pan, Chao Liu, Yanan Wang, Yan Jiang, Huiyi Lv, Yuanyuan Sun, Jian Wang, Hongfei Lin

机构 * College of Computer Science and Technology, Dalian University of Technology（大连理工大学计算机科学与技术学院）； Air Force Communications NCO Academy（空军通信NCO学院）； Department of Pharmacy, Second Affiliated Hospital of Dalian Medical University（大连医科大学第二附属医院药学部）

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

Comments Accepted as a short paper at BIBM2025

2508.06944 2025-10-13 cs.LG cs.AI cs.CL cs.CV 88%

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

2510.03683 2025-10-13 cs.CL 88%

Fine-Tuning Large Language Models with QLoRA for Offensive Language Detection in Roman Urdu-English Code-Mixed Text

Nisar Hussain, Amna Qasim, Gull Mehak, Muhammad Zain, Momina Hafeez, Grigori Sidorov

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

Comments 25 pages, 22 figures

2508.19078 2025-10-13 cs.DC cs.AI 88%

Federated Fine-Tuning of Sparsely-Activated Large Language Models on Resource-Constrained Devices

Fahao Chen, Jie Wan, Peng Li, Zhou Su, Dongxiao Yu

机构 * Shandong University（山东大学）； Xi’an Jiaotong University（西安交通大学）

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

Comments Accepted by EuroSys 2026

2510.09347 2025-10-13 cs.CL 87%

LLP: LLM-based Product Pricing in E-commerce

Hairu Wang, Sheng You, Qiheng Zhang, Xike Xie, Shuguang Han, Yuchen Wu, Fei Huang, Jufeng Chen

机构 * University of Science and Technology of China（中国科学技术大学）； Xianyu of Alibaba（阿里巴巴闲鱼）

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

2510.09030 2025-10-13 cs.CL 85%

Automated Refinement of Essay Scoring Rubrics for Language Models via Reflect-and-Revise

Keno Harada, Lui Yoshida, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo

机构 * The University of Tokyo（东京大学）

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

2510.09586 2025-10-13 cs.CV 85%

Vision Language Models: A Survey of 26K Papers

Fengming Lin

机构 * School of Computer Science, The University of Manchester, Manchester, UK（曼彻斯特大学计算机科学学院）

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

Comments VLM/LLM Learning Notes

2508.20582 2025-10-13 cs.IR 83%

SUMMA: A Multimodal Large Language Model for Advertisement Summarization

Weitao Jia, Shuo Yin, Zhoufutu Wen, Han Wang, Zehui Dai, Kun Zhang, Zhenyu Li, Tao Zeng, Xiaohui Lv

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

2507.17131 2025-10-13 cs.LG cs.AI 82%

Enabling Self-Improving Agents to Learn at Test Time With Human-In-The-Loop Guidance

Yufei He, Ruoyu Li, Alex Chen, Yue Liu, Yulin Chen, Yuan Sui, Cheng Chen, Yi Zhu, Luca Luo, Frank Yang, Bryan Hooi

机构 * National University of Singapore（新加坡国立大学）； ByteDance Inc.（字节跳动公司）

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

Comments EMNLP 2025

1. 预训练与数据 18 篇

Alif: Advancing Urdu Large Language Models via Multilingual Synthetic Data Distillation

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

On the Reliability of Large Language Models for Causal Discovery

Weight Initialization and Variance Dynamics in Deep Neural Networks and Large Language Models

Getting Your Indices in a Row: Full-Text Search for LLM Training Data for Real World

Simple and Robust Forecasting of Spatiotemporally Correlated Small Earth Data with A Tabular Foundation Model

Faver: Boosting LLM-based RTL Generation with Function Abstracted Verifiable Middleware

Towards Open Foundation Language Model and Corpus for Macedonian: A Low-Resource Language

Graph Diffusion Transformers are In-Context Molecular Designers

Scalable multilingual PII annotation for responsible AI in LLMs

Hierarchical Indexing with Knowledge Enrichment for Multilingual Video Corpus Retrieval

Repository-Aware File Path Retrieval via Fine-Tuned LLMs

RetouchLLM: Training-free Code-based Image Retouching with Vision Language Models

Detecting and Filtering Unsafe Training Data via Data Attribution with Denoised Representation

Web Crawler Restrictions, AI Training Datasets \& Political Biases

BaNEL: Exploration Posteriors for Generative Modeling Using Only Negative Rewards

Solving Fokker-Planck-Kolmogorov Equation by Distribution Self-adaptation Normalized Physics-informed Neural Networks

Adjusting Initial Noise to Mitigate Memorization in Text-to-Image Diffusion Models

2. 指令微调 19 篇

TIT: A Tree-Structured Instruction Tuning Approach for LLM-Based Code Translation

JAI-1: A Thai-Centric Large Language Model

Privacy-Preserving Parameter-Efficient Fine-Tuning for Large Language Model Services

A Unified Biomedical Named Entity Recognition Framework with Large Language Models

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

Fine-Tuning Large Language Models with QLoRA for Offensive Language Detection in Roman Urdu-English Code-Mixed Text

Federated Fine-Tuning of Sparsely-Activated Large Language Models on Resource-Constrained Devices

LLP: LLM-based Product Pricing in E-commerce

Automated Refinement of Essay Scoring Rubrics for Language Models via Reflect-and-Revise

Vision Language Models: A Survey of 26K Papers

SUMMA: A Multimodal Large Language Model for Advertisement Summarization

Enabling Self-Improving Agents to Learn at Test Time With Human-In-The-Loop Guidance

1. 预训练与数据 18 篇

Alif: Advancing Urdu Large Language Models via Multilingual Synthetic Data Distillation

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

On the Reliability of Large Language Models for Causal Discovery

Weight Initialization and Variance Dynamics in Deep Neural Networks and Large Language Models

Getting Your Indices in a Row: Full-Text Search for LLM Training Data for Real World

Simple and Robust Forecasting of Spatiotemporally Correlated Small Earth Data with A Tabular Foundation Model

Faver: Boosting LLM-based RTL Generation with Function Abstracted Verifiable Middleware

Towards Open Foundation Language Model and Corpus for Macedonian: A Low-Resource Language

Graph Diffusion Transformers are In-Context Molecular Designers

Scalable multilingual PII annotation for responsible AI in LLMs

Hierarchical Indexing with Knowledge Enrichment for Multilingual Video Corpus Retrieval

Repository-Aware File Path Retrieval via Fine-Tuned LLMs

RetouchLLM: Training-free Code-based Image Retouching with Vision Language Models

Detecting and Filtering Unsafe Training Data via Data Attribution with Denoised Representation

Web Crawler Restrictions, AI Training Datasets \&amp; Political Biases

BaNEL: Exploration Posteriors for Generative Modeling Using Only Negative Rewards

Solving Fokker-Planck-Kolmogorov Equation by Distribution Self-adaptation Normalized Physics-informed Neural Networks

Adjusting Initial Noise to Mitigate Memorization in Text-to-Image Diffusion Models

2. 指令微调 19 篇

TIT: A Tree-Structured Instruction Tuning Approach for LLM-Based Code Translation

JAI-1: A Thai-Centric Large Language Model

Privacy-Preserving Parameter-Efficient Fine-Tuning for Large Language Model Services

A Unified Biomedical Named Entity Recognition Framework with Large Language Models

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

Fine-Tuning Large Language Models with QLoRA for Offensive Language Detection in Roman Urdu-English Code-Mixed Text

Federated Fine-Tuning of Sparsely-Activated Large Language Models on Resource-Constrained Devices

LLP: LLM-based Product Pricing in E-commerce

Automated Refinement of Essay Scoring Rubrics for Language Models via Reflect-and-Revise

Vision Language Models: A Survey of 26K Papers

SUMMA: A Multimodal Large Language Model for Advertisement Summarization

Enabling Self-Improving Agents to Learn at Test Time With Human-In-The-Loop Guidance

Web Crawler Restrictions, AI Training Datasets \& Political Biases