语言大模型 / LLM

2510.14054 2025-10-17 cs.LG cs.DC 70%

FedHFT: Efficient Federated Finetuning with Heterogeneous Edge Clients

Fatih Ilhan, Selim Furkan Tekin, Tiansheng Huang, Gaowen Liu, Ramana Kompella, Greg Eisenhauer, Yingyan Celine Lin, Calton Pu, Ling Liu

机构 * School of Computer Science, Georgia Institute of Technology, USA（计算机科学系，佐治亚理工学院，美国）； CISCO Research, USA（思科研究，美国）

专题命中效率与部署：large language model(abstract)；language model(abstract)；分类 cs.LG

2510.14279 2025-10-17 cs.SE cs.PL 67%

Caruca: Effective and Efficient Specification Mining for Opaque Software Components

Evangelos Lamprou, Seong-Heon Jung, Mayank Keoliya, Lukas Lazarek, Konstantinos Kallas, Michael Greenberg, Nikos Vasilakis

专题命中效率与部署：large language model(abstract)；language model(abstract)

2509.12384 2025-10-17 cs.DC cs.DB 67%

Exploring Distributed Vector Databases Performance on HPC Platforms: A Study with Qdrant

Seth Ockerman, Amal Gueroudji, Song Young Oh, Robert Underwood, Nicholas Chia, Kyle Chard, Robert Ross, Shivaram Venkataraman

专题命中效率与部署：large language model(abstract)；language model(abstract)

Comments To appear in the SC'25 Workshop Frontiers in Generative AI for HPC Science and Engineering: Foundations, Challenges, and Opportunities

2510.12210 2025-10-17 eess.AS cs.CL cs.LG 62%

DiSTAR: Diffusion over a Scalable Token Autoregressive Representation for Speech Generation

Yakun Song, Xiaobin Zhuang, Jiawei Chen, Zhikang Niu, Guanrou Yang, Chenpeng Du, Dongya Jia, Zhuo Chen, Yuping Wang, Yuxuan Wang, Xie Chen

机构 * X-LANCE Lab, School of Computer Science, Shanghai Jiao Tong University（X-LANCE实验室，计算机科学学院，上海交通大学）； ByteDance Inc.（字节跳动公司）

专题命中效率与部署：language model(abstract)；分类 cs.CL、cs.LG

2509.24748 2025-10-17 cs.LG cs.AI 62%

Robust Policy Expansion for Offline-to-Online RL under Diverse Data Corruption

Longxiang He, Deheng Ye, Junbo Tan, Xueqian Wang, Li Shen

机构 * Tsinghua University（清华大学）； Tencent（腾讯）； Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区）

专题命中效率与部署：pretraining(abstract)；分类 cs.AI、cs.LG

Comments 39th Conference on Neural Information Processing Systems

2206.07023 2025-10-17 cs.CL cs.AI 62%

SBERT studies Meaning Representations: Decomposing Sentence Embeddings into Explainable Semantic Features

Juri Opitz, Anette Frank

专题命中效率与部署：language model(abstract)；分类 cs.CL、cs.AI

Comments to appear in AACL 2022 (main)

2510.14900 2025-10-17 cs.AI cs.CR 57%

Mapping Smarter, Not Harder: A Test-Time Reinforcement Learning Agent That Improves Without Labels or Model Updates

Wen-Kwang Tsao, Yao-Ching Yu, Chien-Ming Huang

机构 * AI Lab, TrendMicro（趋势科技人工智能实验室）

专题命中效率与部署：LLM(abstract)；分类 cs.AI

2510.14436 2025-10-17 cs.LG 57%

MergeMoE: Efficient Compression of MoE Models via Expert Output Merging

Ruijie Miao, Yilun Yao, Zihan Wang, Zhiming Wang, Bairen Yi, LingJun Liu, Yikai Zhao, Tong Yang

机构 * Peking University（北京大学）； ByteDance（字节跳动）

专题命中效率与部署：LLM(abstract)；分类 cs.LG

2510.14580 2025-10-17 cs.DC 50%

ScalePool: Hybrid XLink-CXL Fabric for Composable Resource Disaggregation in Unified Scale-up Domains

Hyein Woo, Miryeong Kwon, Jiseon Kim, Eunjee Na, Hanjin Choi, Seonghyeon Jang, Myoungsoo Jung

专题命中效率与部署：LLM(abstract)

2510.14132 2025-10-17 physics.chem-ph math-ph math.MP 50%

Shadow Molecular Dynamics for Flexible Multipole Models

Rae A. Corrigan Grove, Robert Stanton, Michael E. Wall, Anders M. N. Niklasson

专题命中效率与部署：foundation model(abstract)

2510.13856 2025-10-17 cs.CL cs.AI cs.CV 90%

Multimodal Retrieval-Augmented Generation with Large Language Models for Medical VQA

A H M Rezaul Karim, Ozlem Uzuner

机构 * George Mason University（乔治·马歇尔大学）

专题命中领域大模型：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.AI

2510.08236 2025-10-17 cs.LG cs.AI 90%

The Hidden Bias: A Study on Explicit and Implicit Political Stereotypes in Large Language Models

Konrad Löhr, Shuzhou Yuan, Michael Färber

机构 * Technische Universität Dresden（德累斯顿技术大学）； Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI)（可扩展数据与人工智能研究中心（ScaDS.AI））

专题命中领域大模型：large language model(title,abstract)；language model(title,abstract)；prompting(abstract)；分类 cs.AI、cs.LG

2510.13985 2025-10-17 cs.AI 88%

Do Large Language Models Show Biases in Causal Learning? Insights from Contingency Judgment

María Victoria Carro, Denise Alejandra Mester, Francisca Gauna Selasco, Giovanni Franco Gabriel Marraffini, Mario Alejandro Leiva, Gerardo I. Simari, María Vanina Martinez

专题命中领域大模型：large language model(title,abstract)；language model(title,abstract)；分类 cs.AI

2506.21638 2025-10-17 cs.IR cs.AI cs.LG 88%

R1-Ranker: Teaching LLM Rankers to Reason

Tao Feng, Zhigang Hua, Zijie Lei, Yan Xie, Shuang Yang, Bo Long, Jiaxuan You

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）； Meta Monetization AI（Meta 资源 monetization AI）

专题命中领域大模型：LLM(title,abstract)；large language model(abstract)；language model(abstract)；foundation model(abstract)

2510.12217 2025-10-17 cs.CL cs.AI 86%

HALF: Harm-Aware LLM Fairness Evaluation Aligned with Deployment

Ali Mekky, Omar El Herraoui, Preslav Nakov, Yuxia Wang

机构 * Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）

专题命中领域大模型：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

2510.14348 2025-10-17 cs.NI 85%

Automated Extraction of Protocol State Machines from 3GPP Specifications with Domain-Informed Prompts and LLM Ensembles

Miao Zhang, Runhan Feng, Hongbo Tang, Yu Zhao, Jie Yang, Hang Qiu, Qi Liu

专题命中领域大模型：LLM(title)；large language model(abstract)；language model(abstract)；prompting(abstract)

2510.13931 2025-10-17 cs.CL 83%

Robust or Suggestible? Exploring Non-Clinical Induction in LLM Drug-Safety Decisions

Siying Liu, Shisheng Zhang, Indu Bala

专题命中领域大模型：LLM(title)；large language model(abstract)；language model(abstract)；分类 cs.CL

Comments Preprint of a paper accepted as a poster at the NeurIPS 2025 Workshop on Generative AI for Health (GenAI4Health). The final camera-ready workshop version may differ. Licensed under CC BY 4.0

2505.13541 2025-10-17 eess.AS cs.LG 83%

SPIRIT: Patching Speech Language Models against Jailbreak Attacks

Amirbek Djanibekov, Nurdaulet Mukhituly, Kentaro Inui, Hanan Aldarmaki, Nils Lukas

机构 * MBZUAI ； Tohoku University（东北大学）； RIKEN（日本科学技术研究院）

专题命中领域大模型：language model(title,abstract)；SLM(abstract)；分类 cs.LG

2407.19941 2025-10-17 cs.LG 83%

Boosting Graph Foundation Model from Structural Perspective

Yao Cheng, Yige Zhao, Jianxiang Yu, Xiang Li

机构 * School of Data Science and Engineering, East China Normal University, Shanghai 200062, China（数据科学与工程学院，东华大学，上海200062，中国）

专题命中领域大模型：foundation model(title,abstract)；language model(abstract)；分类 cs.LG

Comments The article has been accepted by Frontiers of Computer Science (FCS), with the DOI: {10.1007/s11704-025-50736-y}

2510.13843 2025-10-17 cs.CL cs.AI 79%

Serialized EHR make for good text representations

Zhirong Chou, Quan Qin, Shi Li

机构 * Southern China University（南方中国大学）

专题命中领域大模型：language model(abstract)；foundation model(abstract)；pretraining(abstract)；分类 cs.CL、cs.AI

2510.14115 2025-10-17 cs.SE cs.LG 77%

David vs. Goliath: A comparative study of different-sized LLMs for code generation in the domain of automotive scenario generation

Philipp Bauerfeind, Amir Salarpour, David Fernandez, Pedram MohajerAnsari, Johannes Reschke, Mert D. Pesé

机构 * Clemson University（克莱姆森大学）

专题命中领域大模型：large language model(abstract)；language model(abstract)；prompting(abstract)；分类 cs.LG

2510.14257 2025-10-17 cs.IR 75%

Synergistic Integration and Discrepancy Resolution of Contextualized Knowledge for Personalized Recommendation

Lingyu Mu, Hao Deng, Haibo Xing, Kaican Lin, Zhitong Zhu, Yu Zhang, Xiaoyi Zeng, Zhengxiao Liu, Zheng Lin, Jinxin Hu

专题命中领域大模型：large language model(abstract)；language model(abstract)；prompting(abstract)

2510.13828 2025-10-17 cs.CL 70%

From Explainability to Action: A Generative Operational Framework for Integrating XAI in Clinical Mental Health Screening

Ratna Kandala, Akshata Kishore Moharir, Divya Arvinda Nayak

专题命中领域大模型：large language model(abstract)；language model(abstract)；分类 cs.CL

2510.10520 2025-10-17 cs.CY cs.RO 67%

AI-Agents for Culturally Diverse Online Higher Education Environments

Fuze Sun, Paul Craig, Lingyu Li, Shixiangyue Meng, Chuxi Nan

专题命中领域大模型：large language model(abstract)；language model(abstract)

2410.08397 2025-10-17 eess.IV cs.AI cs.CV 65%

VoxelPrompt: A Vision Agent for End-to-End Medical Image Analysis

Andrew Hoopes, Neel Dey, Victor Ion Butoi, John V. Guttag, Adrian V. Dalca

机构 * Massachusetts Institute of Technology（麻省理工学院）； Massachusetts General Hospital（麻省总医院）； Harvard Medical School（哈佛医学院）

专题命中领域大模型：language model(abstract)；分类 cs.AI；foundation model(comments)；language agent(comments)

Comments 22 pages, vision-language agent, medical image analysis, neuroimage foundation model

2510.13836 2025-10-17 cs.CL cs.AI 90%

SIMBA UQ: Similarity-Based Aggregation for Uncertainty Quantification in Large Language Models

Debarun Bhattacharjya, Balaji Ganesan, Junkyu Lee, Radu Marinescu, Katsiaryna Mirylenka, Michael Glass, Xiao Shou

机构 * IBM Research（IBM研究院）； Zalando ； Baylor University（贝勒大学）

专题命中知识编辑与模型理解：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.AI

Comments 15 pages including appendix, Findings of EMNLP 2025

2501.05643 2025-10-17 cs.CL cs.AI 90%

Iconicity in Large Language Models

Anna Marklová, Jiří Milička, Leonid Ryvkin, Ľudmila Lacková Bennet, Libuše Kormaníková

机构 * Department of Linguistics（语言学系）； Charles University（查尔斯大学）； Department（部门）； Claude Bernard University Lyon（克莱尔·伯纳德大学里昂）； Department of General Linguistics（一般语言学系）； Palacký University Olomouc（帕拉茨基大学奥洛穆克）

专题命中知识编辑与模型理解：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.AI

Comments Supplementary information: https://osf.io/ywjrk/

2510.13750 2025-10-17 cs.CL 85%

Confidence-Based Response Abstinence: Improving LLM Trustworthiness via Activation-Based Uncertainty Estimation

Zhiqi Huang, Vivek Datla, Chenyang Zhu, Alfy Samuel, Daben Liu, Anoop Kumar, Ritesh Soni

机构 * Capital One

专题命中知识编辑与模型理解：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.CL

Comments UncertaiNLP at EMNLP 2025

2510.04384 2025-10-17 cs.AI 85%

LLM Based Bayesian Optimization for Prompt Search

Adam Ballew, Jingbo Wang, Shaogang Ren

机构 * Department of Computer Science and Engineering（计算机科学与工程系）； University of Tennessee at Chattanooga（田纳西大学查塔努加分校）

专题命中知识编辑与模型理解：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

2510.14825 2025-10-17 cs.LG 83%

Programmatic Representation Learning with Language Models

Gabriel Poesia, Georgia Gabriela Sampaio

机构 * Kempner Institute at Harvard University（哈佛大学凯普纳研究所）； Stanford University（斯坦福大学）

专题命中知识编辑与模型理解：language model(title,abstract)；large language model(abstract)；分类 cs.LG

Comments Code available at https://github.com/gpoesia/leapr/

1. 效率与部署 34 篇

FedHFT: Efficient Federated Finetuning with Heterogeneous Edge Clients

Caruca: Effective and Efficient Specification Mining for Opaque Software Components

Exploring Distributed Vector Databases Performance on HPC Platforms: A Study with Qdrant

DiSTAR: Diffusion over a Scalable Token Autoregressive Representation for Speech Generation

Robust Policy Expansion for Offline-to-Online RL under Diverse Data Corruption

SBERT studies Meaning Representations: Decomposing Sentence Embeddings into Explainable Semantic Features

Mapping Smarter, Not Harder: A Test-Time Reinforcement Learning Agent That Improves Without Labels or Model Updates

MergeMoE: Efficient Compression of MoE Models via Expert Output Merging

ScalePool: Hybrid XLink-CXL Fabric for Composable Resource Disaggregation in Unified Scale-up Domains

Shadow Molecular Dynamics for Flexible Multipole Models

2. 领域大模型 15 篇

Multimodal Retrieval-Augmented Generation with Large Language Models for Medical VQA

The Hidden Bias: A Study on Explicit and Implicit Political Stereotypes in Large Language Models

Do Large Language Models Show Biases in Causal Learning? Insights from Contingency Judgment

R1-Ranker: Teaching LLM Rankers to Reason

HALF: Harm-Aware LLM Fairness Evaluation Aligned with Deployment

Automated Extraction of Protocol State Machines from 3GPP Specifications with Domain-Informed Prompts and LLM Ensembles

Robust or Suggestible? Exploring Non-Clinical Induction in LLM Drug-Safety Decisions

SPIRIT: Patching Speech Language Models against Jailbreak Attacks

Boosting Graph Foundation Model from Structural Perspective

Serialized EHR make for good text representations

David vs. Goliath: A comparative study of different-sized LLMs for code generation in the domain of automotive scenario generation

Synergistic Integration and Discrepancy Resolution of Contextualized Knowledge for Personalized Recommendation

From Explainability to Action: A Generative Operational Framework for Integrating XAI in Clinical Mental Health Screening

AI-Agents for Culturally Diverse Online Higher Education Environments

VoxelPrompt: A Vision Agent for End-to-End Medical Image Analysis

3. 知识编辑与模型理解 9 篇

SIMBA UQ: Similarity-Based Aggregation for Uncertainty Quantification in Large Language Models

Iconicity in Large Language Models

Confidence-Based Response Abstinence: Improving LLM Trustworthiness via Activation-Based Uncertainty Estimation

LLM Based Bayesian Optimization for Prompt Search

Programmatic Representation Learning with Language Models