语言大模型 / LLM

2509.03405 2025-09-04 cs.CL 88%

LMEnt: A Suite for Analyzing Knowledge in Language Models from Pretraining Data to Representations

Daniela Gottesman, Alon Gilae-Dotan, Ido Cohen, Yoav Gur-Arieh, Marius Mosbach, Ori Yoran, Mor Geva

机构 * Tel Aviv University（特拉维夫大学）； Mila – Quebec AI Institute & McGill University（蒙特利尔AI研究所 & 蒙特利尔大学）

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

Comments Submitted to TACL, August 2025

2509.03131 2025-09-04 cs.IR cs.LG 88%

RecBase: Generative Foundation Model Pretraining for Zero-Shot Recommendation

Sashuai Zhou, Weinan Gan, Qijiong Liu, Ke Lei, Jieming Zhu, Hai Huang, Yan Xia, Ruiming Tang, Zhenhua Dong, Zhou Zhao

机构 * Zhejiang University（浙江大学）； Huawei Noah’s Ark Lab（华为诺亚实验室）； Shanghai AI Lab（上海人工智能实验室）； The HK PolyU（香港理工大学）

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

Journal ref EMNLP 2025

2505.02273 2025-09-04 cs.CL 79%

Demystifying optimized prompts in language models

Rimon Melamed, Lucas H. McCabe, H. Howie Huang

机构 * The George Washington University（乔治·华盛顿大学）； LMI Consulting（LMI咨询公司）

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

Comments EMNLP 2025 Main

2509.02602 2025-09-04 eess.IV 78%

Masked Autoencoder Pretraining and BiXLSTM ResNet Architecture for PET/CT Tumor Segmentation

Moona Mazher, Steven A Niederer, Abdul Qayyum

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

2504.14212 2025-09-04 cs.CL 77%

Bias Analysis and Mitigation through Protected Attribute Detection and Regard Classification

Takuma Udagawa, Yang Zhao, Hiroshi Kanayama, Bishwaranjan Bhattacharjee

机构 * IBM Research - Tokyo（IBM东京研究实验室）； IBM T. J. Watson Research Center（IBM T.J. Watson研究中心）

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

Comments Accepted to EMNLP 2025 (Findings)

2411.19475 2025-09-04 cs.CV astro-ph.GA cs.AI cs.LG 73%

GalaxAlign: Mimicking Citizen Scientists' Multimodal Guidance for Galaxy Morphology Analysis

Ruoqi Wang, Haitao Wang, Qiong Luo

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州））； School of Computer Science and Engineering, Sun Yat-Sen University（中山大学计算机科学与工程学院）

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

Comments ACM MM 2025

2406.13748 2025-09-04 cs.CL cs.LG 73%

Learn and Unlearn: Addressing Misinformation in Multilingual LLMs

Taiming Lu, Philipp Koehn

机构 * Johns Hopkins University（约翰霍普金斯大学）

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

Comments EMNLP 2025 Main Conference

2508.01550 2025-09-04 cs.SE 71%

RepoForge: Training a SOTA Fast-thinking SWE Agent with an End-to-End Data Curation Pipeline Synergizing SFT and RL at Scale

Zhilong Chen, Chengzong Zhao, Boyuan Chen, Dayi Lin, Yihao Chen, Arthur Leung, Gopi Krishnan Rajbahadur, Gustavo A. Oliva, Haoxiang Zhang, Aaditya Bhatia, Chong Chun Yong, Ahmed E. Hassan

专题命中预训练与数据：SFT(title)

2509.02999 2025-09-04 cs.CL 70%

DiaCBT: A Long-Periodic Dialogue Corpus Guided by Cognitive Conceptualization Diagram for CBT-based Psychological Counseling

Yougen Zhou, Ningning Zhou, Qin Chen, Jie Zhou, Aimin Zhou, Liang He

机构 * Shanghai Institute of Artificial Intelligence for Education, East China Normal University（上海教育人工智能研究院，东华师范大学）； School of Computer Science and Technology, East China Normal University（计算机科学与技术学院，东华师范大学）； School of Psychology and Cognitive Science, East China Normal University（心理学与认知科学学院，东华师范大学）

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

2509.03336 2025-09-04 q-bio.MN cs.IR q-bio.QM 67%

AI-Driven Drug Repurposing through miRNA-mRNA Relation

Sharanya Manoharan, Balu Bhasuran, Oviya Ramalakshmi Iyyappan, Mohamed Saleem Abdul Shukkoor, Malathi Sellapan, Kalpana Raja

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

2509.03353 2025-09-04 cs.LG cs.AI 62%

Fair Resource Allocation for Fleet Intelligence

Oguzhan Baser, Kaan Kale, Po-han Li, Sandeep Chinchali

机构 * Wireless Networking Communications Group (WNCG) Department of Electrical ； Computer Engineering The University of Texas at Austin Email

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

Comments This paper has been accepted for presentation at the 2025 IEEE Global Communications Conference (GLOBECOM 2025)

2509.02856 2025-09-04 cs.CR cs.LG 57%

Managing Correlations in Data and Privacy Demand

Syomantak Chaudhuri, Thomas A. Courtade

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

专题命中预训练与数据：LLM(abstract)；分类 cs.LG

Comments To appeat at ACM CCS, 2025

2509.02612 2025-09-04 eess.IV cs.AI cs.CV 57%

Is Synthetic Image Augmentation Useful for Imbalanced Classification Problems? Case-Study on the MIDOG2025 Atypical Cell Detection Competition

Leire Benito-Del-Valle, Pedro A. Moreno-Sánchez, Itziar Egusquiza, Itsaso Vitoria, Artzai Picón, Cristina López-Saratxaga, Adrian Galdran

机构 * TECNALIA ； Basque Research and Technology Alliance (BRTA)（巴斯克研究与技术联盟）； University of the Basque Country（巴斯克大学）

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

Comments version 0, to be updated; submitted to midog 2025

2505.17879 2025-09-04 eess.SP 89%

LLM4SG: Adapting Large Language Model for Scatterer Generation via Synesthesia of Machines

Zengrui Han, Lu Bai, Ziwei Huang, Xiang Cheng

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

2406.09701 2025-09-04 cs.SE 89%

Towards Explainable Vulnerability Detection with Large Language Models

Qiheng Mao, Zhenhao Li, Xing Hu, Kui Liu, Xin Xia, Jianling Sun

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

2509.03057 2025-09-04 cs.CL 88%

Structure-Learnable Adapter Fine-Tuning for Parameter-Efficient Large Language Models

Ming Gong, Yingnan Deng, Nia Qi, Yujun Zou, Zhihao Xue, Yun Zi

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

2410.16822 2025-09-04 cs.AI 86%

Can Large Language Models Act as Ensembler for Multi-GNNs?

Hanqi Duan, Yao Cheng, Jianxiang Yu, Yao Liu, Xiang Li

机构 * East China Normal University（东华师范大学）

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

2509.02915 2025-09-04 cs.CL 83%

English Pronunciation Evaluation without Complex Joint Training: LoRA Fine-tuned Speech Multimodal LLM

Taekyung Ahn, Hosung Nam

机构 * Enuma, Inc.（Enuma公司）； Korea University（韩国大学）

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

2509.02830 2025-09-04 cs.CL eess.AS 57%

SSVD: Structured SVD for Parameter-Efficient Fine-Tuning and Benchmarking under Domain Shift in ASR

Pu Wang, Shinji Watanabe, Hugo Van hamme

机构 * Department of Electrical Engineering KU Leuven Leuven, Belgium（电气工程系卡尔·冯·特里尔大学布鲁塞尔，比利时）； Language Technologies Institute Carnegie Mellon University Pittsburgh, PA, USA（语言技术研究所哈佛大学贝尔蒙特，美国）

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

Comments Accepted by IEEE ASRU 2025

2509.01028 2025-09-04 cs.CV 50%

CompSlider: Compositional Slider for Disentangled Multiple-Attribute Image Generation

Zixin Zhu, Kevin Duarte, Mamshad Nayeem Rizve, Chengyuan Xu, Ratheesh Kalarot, Junsong Yuan

机构 * University at Buffalo（布法罗大学）； Adobe Inc. (ASML)（Adobe公司）

专题命中指令微调：foundation model(abstract)

Comments Accepted by ICCV 2025

2406.17642 2025-09-04 cs.CL cs.AI 86%

Banishing LLM Hallucinations Requires Rethinking Generalization

Johnny Li, Saksham Consul, Eda Zhou, James Wong, Naila Farooqui, Yuxin Ye, Nithyashree Manohar, Zhuxiaona Wei, Tian Wu, Ben Echols, Sharon Zhou, Gregory Diamos

专题命中长上下文与记忆：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments I want to revisit some of the experiments in this paper, specifically figure 5

2508.18721 2025-09-04 cs.SE 78%

LLM as an Execution Estimator: Recovering Missing Dependency for Practical Time-travelling Debugging

Yunrui Pei, Hongshu Wang, Wenjie Zhang, Yun Lin, Weiyu Kong, Jin song Dong

专题命中长上下文与记忆：LLM(title,abstract)

2509.02864 2025-09-04 cs.CL cs.AI 62%

A-SEA3L-QA: A Fully Automated Self-Evolving, Adversarial Workflow for Arabic Long-Context Question-Answer Generation

Kesen Wang, Daulet Toibazar, Pedro J. Moreno

机构 * Humain

专题命中长上下文与记忆：language model(abstract)；分类 cs.CL、cs.AI

2509.01947 2025-09-04 cs.SE 90%

Automated Repair of C Programs Using Large Language Models

Mahdi Farzandway, Fatemeh Ghassemi

专题命中推理与问题求解：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；prompting(abstract)

2505.16022 2025-09-04 cs.CL cs.AI cs.LG 85%

NOVER: Incentive Training for Language Models via Verifier-Free Reinforcement Learning

Wei Liu, Siya Qi, Xinyu Wang, Chen Qian, Yali Du, Yulan He

机构 * King’s College London（伦敦国王学院）； The Alan Turing Institute（艾伦·图灵研究所）； Shanghai Jiao Tong University（上海交通大学）

专题命中推理与问题求解：language model(title,abstract)；large language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 20 pages, 5 tables, 12 figures. accepted to EMNLP 2025

2507.17695 2025-09-04 cs.AI cs.NI 81%

Symbiotic Agents: A Novel Paradigm for Trustworthy AGI-driven Networks

Ilias Chatzistefanidis, Navid Nikaein

机构 * Eurecom（埃鲁埃康）

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；SLM(abstract)

Comments Submitted to Computer Networks AI for 6G

2505.05755 2025-09-04 cs.CL cs.LG 81%

Insertion Language Models: Sequence Generation with Arbitrary-Position Insertions

Dhruvesh Patel, Aishwarya Sahoo, Avinash Amballa, Tahira Naseem, Tim G. J. Rudner, Andrew McCallum

专题命中推理与问题求解：language model(title,abstract)；分类 cs.CL、cs.LG

Comments Additional related work. Code available at: https://dhruveshp.com/projects/ilm

2508.11133 2025-09-04 cs.CL cs.AI cs.DB 79%

MoNaCo: More Natural and Complex Questions for Reasoning Across Dozens of Documents

Tomer Wolfson, Harsh Trivedi, Mor Geva, Yoav Goldberg, Dan Roth, Tushar Khot, Ashish Sabharwal, Reut Tsarfaty

机构 * University of Pennsylvania（宾夕法尼亚大学）； Allen Institute for AI（人工智能研究院）； Tel Aviv University（特拉维夫大学）； Bar-Ilan University（巴伊兰大学）； Oracle AI（Oracle人工智能）

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments Accepted for publication in Transactions of the Association for Computational Linguistics (TACL), 2025. Authors pre-print

2208.13266 2025-09-04 cs.AI cs.CL cs.CV cs.RO 79%

JARVIS: A Neuro-Symbolic Commonsense Reasoning Framework for Conversational Embodied Agents

Kaizhi Zheng, Kaiwen Zhou, Jing Gu, Yue Fan, Jialu Wang, Zonglin Di, Xuehai He, Xin Eric Wang

机构 * University of California（加州大学）

专题命中推理与问题求解：large language model(abstract)；language model(abstract)；prompting(abstract)；分类 cs.CL、cs.AI

Comments 19th International Conference on Neurosymbolic Learning and Reasoning

2508.19855 2025-09-04 cs.IR 75%

Youtu-GraphRAG: Vertically Unified Agents for Graph Retrieval-Augmented Complex Reasoning

Junnan Dong, Siyu An, Yifei Yu, Qian-Wen Zhang, Linhao Luo, Xiao Huang, Yunsheng Wu, Di Yin, Xing Sun

专题命中推理与问题求解：LLM(abstract)；large language model(abstract)；language model(abstract)

Comments 19 pages, 7 figures, 6 tables

1. 预训练与数据 13 篇

LMEnt: A Suite for Analyzing Knowledge in Language Models from Pretraining Data to Representations

RecBase: Generative Foundation Model Pretraining for Zero-Shot Recommendation

Demystifying optimized prompts in language models

Masked Autoencoder Pretraining and BiXLSTM ResNet Architecture for PET/CT Tumor Segmentation

Bias Analysis and Mitigation through Protected Attribute Detection and Regard Classification

GalaxAlign: Mimicking Citizen Scientists' Multimodal Guidance for Galaxy Morphology Analysis

Learn and Unlearn: Addressing Misinformation in Multilingual LLMs

RepoForge: Training a SOTA Fast-thinking SWE Agent with an End-to-End Data Curation Pipeline Synergizing SFT and RL at Scale

DiaCBT: A Long-Periodic Dialogue Corpus Guided by Cognitive Conceptualization Diagram for CBT-based Psychological Counseling

AI-Driven Drug Repurposing through miRNA-mRNA Relation

Fair Resource Allocation for Fleet Intelligence

Managing Correlations in Data and Privacy Demand

Is Synthetic Image Augmentation Useful for Imbalanced Classification Problems? Case-Study on the MIDOG2025 Atypical Cell Detection Competition

2. 指令微调 7 篇

LLM4SG: Adapting Large Language Model for Scatterer Generation via Synesthesia of Machines

Towards Explainable Vulnerability Detection with Large Language Models

Structure-Learnable Adapter Fine-Tuning for Parameter-Efficient Large Language Models

Can Large Language Models Act as Ensembler for Multi-GNNs?

English Pronunciation Evaluation without Complex Joint Training: LoRA Fine-tuned Speech Multimodal LLM

SSVD: Structured SVD for Parameter-Efficient Fine-Tuning and Benchmarking under Domain Shift in ASR

CompSlider: Compositional Slider for Disentangled Multiple-Attribute Image Generation

3. 长上下文与记忆 3 篇

Banishing LLM Hallucinations Requires Rethinking Generalization

LLM as an Execution Estimator: Recovering Missing Dependency for Practical Time-travelling Debugging

A-SEA3L-QA: A Fully Automated Self-Evolving, Adversarial Workflow for Arabic Long-Context Question-Answer Generation

4. 推理与问题求解 16 篇

Automated Repair of C Programs Using Large Language Models

NOVER: Incentive Training for Language Models via Verifier-Free Reinforcement Learning

Symbiotic Agents: A Novel Paradigm for Trustworthy AGI-driven Networks

Insertion Language Models: Sequence Generation with Arbitrary-Position Insertions

MoNaCo: More Natural and Complex Questions for Reasoning Across Dozens of Documents

JARVIS: A Neuro-Symbolic Commonsense Reasoning Framework for Conversational Embodied Agents

Youtu-GraphRAG: Vertically Unified Agents for Graph Retrieval-Augmented Complex Reasoning