语言大模型 / LLM - arXivDaily 专题

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

1. 预训练与数据 13 篇