语言大模型 / LLM

2510.25947 2025-10-31 cs.CL cs.AI cs.LG 90%

Revisiting Multilingual Data Mixtures in Language Model Pretraining

Negar Foroutan, Paul Teiletche, Ayush Kumar Tarun, Antoine Bosselut

机构 * EPFL（瑞士联邦理工学院）

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

Comments Under Review

2510.25804 2025-10-31 cs.CL 88%

Beyond Length: Quantifying Long-Range Information for Long-Context LLM Pretraining Data

Haoran Deng, Yingyu Lin, Zhenghao Lin, Xiao Liu, Yizhou Sun, Yi-An Ma, Yeyun Gong

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

2505.18125 2025-10-31 cs.LG cs.CL 86%

TabSTAR: A Tabular Foundation Model for Tabular Data with Text Fields

Alan Arazi, Eilam Shapira, Roi Reichart

机构 * Technion - IIT（技术学院-理工学院）

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

Comments Accepted to NeurIPS 2025

2502.01074 2025-10-31 cs.LG 84%

Omni-Mol: Multitask Molecular Model for Any-to-any Modalities

Chengxin Hu, Hao Li, Yihe Yuan, Zezheng Song, Chenyang Zhao, Haixin Wang

机构 * National University of Singapore（新加坡国立大学）； University of Maryland, College Park（马里兰大学 College Park 分校）； University of California, Los Angeles（加州大学洛杉矶分校）

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

Comments 44 pages, 9 figures, 13 tables, paper accepted by NeurIPS 2025

2510.26345 2025-10-31 cs.CL cs.AI cs.LG 80%

MisSynth: Improving MISSCI Logical Fallacies Classification with Synthetic Data

Mykhailo Poliakov, Nadiya Shvai

机构 * National University of Kyiv-Mohyla Academy（基辅-莫希拉学院国家大学）

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

2510.26336 2025-10-31 cs.CL cs.AI 79%

From Amateur to Master: Infusing Knowledge into LLMs via Automated Curriculum Learning

Nishit Neema, Srinjoy Mukherjee, Sapan Shah, Gokul Ramakrishnan, Ganesh Venkatesh

机构 * Cerebras Systems（Cerebras系统）

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

2410.16325 2025-10-31 cs.CL 77%

This Candidate is [MASK]. Prompt-based Sentiment Extraction and Reference Letters

Fabian Slonimczyk

机构 * International College of Economics and Finance, HSE（俄罗斯经济金融国际学院，俄罗斯）

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

2510.24817 2025-10-31 cs.CL cs.AI cs.LG 75%

Towards a Method for Synthetic Generation of Persons with Aphasia Transcripts

Jason M. Pittman, Anton Phillips, Yesenia Medina-Santos, Brielle C. Stark

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

Comments 19 pages, 1 figure, 7 tables

2510.16629 2025-10-31 cs.LG 70%

On the Impossibility of Retrain Equivalence in Machine Unlearning

Jiatong Yu, Yinghui He, Anirudh Goyal, Sanjeev Arora

机构 * Princeton Language and Intelligence（普林斯顿语言与智能）

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

Comments Code available at https://princeton-pli.github.io/impossibility-unlearning/

2504.12549 2025-10-31 cs.CL cs.AI cs.LG 67%

Memorization: A Close Look at Books

Iris Ma, Ian Domingo, Alberto Krone-Martins, Pierre Baldi, Cristina V. Lopes

机构 * School of Information and Computer Sciences University of California, Irvine（信息与计算机科学学院加州大学伊维奇分校）

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

Comments Accepted at ACL 2025 L2M2 Workshop

2510.25788 2025-10-31 cs.LG cond-mat.mtrl-sci 57%

SHA-256 Infused Embedding-Driven Generative Modeling of High-Energy Molecules in Low-Data Regimes

Siddharth Verma, Alankar Alankar

机构 * Department of Mechanical Engineering（机械工程系）； Center for Machine Intelligence and Data Science (CMInDS)（机器智能与数据科学中心）

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

2506.08188 2025-10-31 cs.CR cs.CL 57%

GradEscape: A Gradient-Based Evader Against AI-Generated Text Detectors

Wenlong Meng, Shuguo Fan, Chengkun Wei, Min Chen, Yuwei Li, Yuanchao Zhang, Zhikun Zhang, Wenzhi Chen

机构 * Zhejiang University（浙江大学）； Vrije Universiteit Amsterdam（荷兰自由大学）； National University of Defense Technology（国防科技大学）； Mybank, Ant Group（蚂蚁集团Mybank）

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

Comments Accepted by USENIX Security'25; Update badges and Artifact Appendix

2504.11331 2025-10-31 cs.CL cs.MM 57%

Dependency Structure Augmented Contextual Scoping Framework for Multimodal Aspect-Based Sentiment Analysis

Hao Liu, Lijun He, Jiaxi Liang, Zhihan Ren, Haixia Bi, Fan Li

专题命中预训练与数据：pretraining(abstract)；分类 cs.CL

2502.00706 2025-10-31 cs.CR cs.CL cs.LG 90%

Model Provenance Testing for Large Language Models

Ivica Nikolic, Teodora Baluta, Prateek Saxena

机构 * National University of Singapore（新加坡国立大学）； Georgia Institute of Technology（佐治亚理工学院）

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

2505.17773 2025-10-31 cs.LG 89%

C-LoRA: Contextual Low-Rank Adaptation for Uncertainty Estimation in Large Language Models

Amir Hossein Rahmati, Sanket Jantre, Weifeng Zhang, Yucheng Wang, Byung-Jun Yoon, Nathan M. Urban, Xiaoning Qian

机构 * Texas A&M University（德克萨斯A&M大学）； Brookhaven National Laboratory（布鲁克海文国家实验室）

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

Comments Conference on Neural Information Processing Systems (NeurIPS 2025)

2506.14681 2025-10-31 cs.CL 88%

Massive Supervised Fine-tuning Experiments Reveal How Data, Layer, and Training Factors Shape LLM Alignment Quality

Yuto Harada, Yusuke Yamauchi, Yusuke Oda, Yohei Oseki, Yusuke Miyao, Yu Takagi

机构 * NII LLMC（日本信息处理学会大语言模型中心）； The University of Tokyo（东京大学）； NAIST（日本科学技术大学）； Nagoya Institute of Technology（名古屋技术大学）

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

Comments Accepted to EMNLP 2025 (Main Conference). Models and evaluation results available at: https://github.com/llm-jp/massive-sft

2510.26457 2025-10-31 cs.SE cs.AI cs.CL 87%

SecureReviewer: Enhancing Large Language Models for Secure Code Review through Secure-aware Fine-tuning

Fang Liu, Simiao Liu, Yinghao Zhu, Xiaoli Lian, Li Zhang

机构 * 1 State Key Laboratory of Complex \& Critical Software Environment, School of Computer Science ； Engineering, Beihang University, China

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

Comments Accepted by ICSE 2026. Code and data: https://github.com/SIMIAO515/SecureReviewer

2510.23595 2025-10-31 cs.AI 85%

Multi-Agent Evolve: LLM Self-Improve through Co-evolution

Yixing Chen, Yiding Wang, Siqi Zhu, Haofei Yu, Tao Feng, Muhan Zhang, Mostofa Patwary, Jiaxuan You

机构 * University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）； Peking University（北京大学）； NVIDIA（英伟达）

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

Comments 29 pages, 4 figures

2504.05747 2025-10-31 cs.CL 81%

SEA-LION: Southeast Asian Languages in One Network

Raymond Ng, Thanh Ngan Nguyen, Yuli Huang, Ngee Chia Tai, Wai Yi Leong, Wei Qi Leong, Xianbin Yong, Jian Gang Ngui, Yosephine Susanto, Nicholas Cheng, Hamsawardhini Rengarajan, Peerat Limkonchotiwat, Adithya Venkatadri Hulagadri, Kok Wai Teng, Yeo Yeow Tong, Bryan Siow, Wei Yi Teo, Wayne Lau, Choon Meng Tan, Brandon Ong, Zhi Hao Ong, Jann Railey Montalan, Adwin Chan, Sajeban Antonyrex, Ren Lee, Esther Choa, David Ong Tat-Wee, Bing Jie Darius Liu, William Chandra Tjhi, Erik Cambria, Leslie Teo

机构 * AI Singapore ； National University of Singapore（新加坡国立大学）； Nanyang Technological University（南洋理工大学）

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

Comments Accepted at IJCNLP-AACL 2025 (Main Track). We released our model at https://huggingface.co/collections/aisingapore/sea-lionv3-672589a39cdadd6a5b199581

2502.04380 2025-10-31 cs.CL cs.AI cs.LG 80%

Diversity as a Reward: Fine-Tuning LLMs on a Mixture of Domain-Undetermined Data

Zhenqing Ling, Daoyuan Chen, Liuyi Yao, Qianli Shen, Yaliang Li, Ying Shen

机构 * Sun Yat-sen University（中山大学）； Alibaba Group（阿里巴巴集团）； FSIETP

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

Comments Accepted by NeurIPS'25 main track. 47 pages, 21 figures, 32 tables

2508.11607 2025-10-31 cs.CL 79%

TinyTim: A Family of Language Models for Divergent Generation

Christopher J. Agostino

机构 * NPC Worldwide（NPC全球）

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

Comments 7 pages, 3 figures, accepted to NeurIPS Creative AI track, models available at https://hf.co/npc-worldwide/

2510.26183 2025-10-31 cs.CL 79%

Similarity-Distance-Magnitude Language Models

Allen Schmaltz

机构 * Reexpress AI

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

Comments 8 pages, 5 tables

2510.26516 2025-10-31 cs.SE 67%

Envisioning Future Interactive Web Development: Editing Webpage with Natural Language

Truong Hai Dang, Jingyu Xiao, Yintong Huo

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

Comments accepted by AIWare'25

2510.26474 2025-10-31 cs.CV cs.AI cs.CL cs.LG 67%

Counteracting Matthew Effect in Self-Improvement of LVLMs through Head-Tail Re-balancing

Xin Guo, Zhiheng Xi, Yiwen Ding, Yitao Zhai, Xiaowei Shi, Xunliang Cai, Tao Gui, Qi Zhang, Xuanjing Huang

机构 * Fudan University（复旦大学）； Meituan（美团）； Shanghai Innovation Institute（上海创新研究院）

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

Comments Preprint

2502.09969 2025-10-31 cs.LG cs.AI cs.CL 67%

Neural Networks for Learnable and Scalable Influence Estimation of Instruction Fine-Tuning Data

Ishika Agarwal, Dilek Hakkani-Tür

机构 * Department of Computer Science UIUC（计算机科学系 UIUC）

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

2503.09499 2025-10-31 cs.CV cs.AI cs.CL 62%

MindGYM: What Matters in Question Synthesis for Thinking-Centric Fine-Tuning?

Zhe Xu, Daoyuan Chen, Zhenqing Ling, Yaliang Li, Ying Shen

机构 * Sun Yat-sen University（中山大学）； Alibaba Group（阿里巴巴集团）； FSIETP

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

Comments Accepted by NeurIPS'25. 30 pages, 2 figures, 13 tables

2510.25990 2025-10-31 cs.CV 50%

Fine-tuning Segment Anything for Real-Time Tumor Tracking in Cine-MRI

Valentin Boussot, Cédric Hémon, Jean-Claude Nunes, Jean-Louis Dillenseger

机构 * Univ Rennes 1（里昂大学）

专题命中指令微调：foundation model(abstract)

Comments Paper for the Trackrad2025 challenge, Team BreizhTrack

2509.04448 2025-10-31 cs.CV cs.MM 50%

TRUST-VL: An Explainable News Assistant for General Multimodal Misinformation Detection

Zehong Yan, Peng Qi, Wynne Hsu, Mong Li Lee

专题命中指令微调：language model(abstract)

Comments EMNLP 2025 Oral; Project Homepage: https://yanzehong.github.io/trust-vl/

2305.17608 2025-10-31 cs.LG cs.AI cs.CL math.OC stat.ML 89%

Reward Collapse in Aligning Large Language Models

Ziang Song, Tianle Cai, Jason D. Lee, Weijie J. Su

专题命中后训练与偏好优化：large language model(title,abstract)；language model(title,abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted for publication in the Journal of Data Science (JDS), reference JDS1201

2503.03710 2025-10-31 cs.CL cs.CR cs.LG 88%

Improving LLM Safety Alignment with Dual-Objective Optimization

Xuandong Zhao, Will Cai, Tianneng Shi, David Huang, Licong Lin, Song Mei, Dawn Song

机构 * University of California, Berkeley（加州大学伯克利分校）

专题命中后训练与偏好优化：LLM(title,abstract)；large language model(abstract)；language model(abstract)；preference optimization(abstract)

Comments ICML 2025

1. 预训练与数据 13 篇