语言大模型 / LLM - arXivDaily 专题

2506.02153 2025-09-17 cs.AI 91%

Small Language Models are the Future of Agentic AI

Peter Belcak, Greg Heinrich, Shizhe Diao, Yonggan Fu, Xin Dong, Saurav Muralidharan, Yingyan Celine Lin, Pavlo Molchanov

机构 * NVIDIA Research（NVIDIA研究）

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

2403.16393 2025-09-17 cs.AI cs.CL cs.LG 90%

Concurrent Linguistic Error Detection (CLED): a New Methodology for Error Detection in Large Language Models

Jinhua Zhu, Javier Conde, Zhen Gao, Pedro Reviriego, Shanshan Liu, Fabrizio Lombardi

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

Comments 11 pages, 6 figures, 30 references

Journal ref IEEE Transactions on Computers 2025

2405.20404 2025-09-17 cs.CL cs.LG 90%

JoPA:Explaining Large Language Model's Generation via Joint Prompt Attribution

Yurui Chang, Bochuan Cao, Yujia Wang, Jinghui Chen, Lu Lin

机构 * Pennsylvania State University（宾夕法尼亚州立大学）

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

Comments Accepted to ACL 2025 (Main)

2509.12754 2025-09-17 cs.RO cs.AI cs.HC cs.LG 90%

Toward Ownership Understanding of Objects: Active Question Generation with Large Language Model and Probabilistic Generative Model

Saki Hashimoto, Shoichi Hasegawa, Tomochika Ishikawa, Akira Taniguchi, Yoshinobu Hagiwara, Lotfi El Hafi, Tadahiro Taniguchi

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

Comments Submitted to AROB-ISBC 2026 (Journal Track option)

2412.03107 2025-09-17 cs.AI 89%

CredID: Credible Multi-Bit Watermark for Large Language Models Identification

Haoyu Jiang, Xuhong Wang, Ping Yi, Shanzhe Lei, Yilun Lin

机构 * School of Cyber Science and Engineering, Shanghai Jiao Tong University（上海交通大学计算机科学与工程学院）； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）

专题命中效率与部署：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.AI

Comments v2

2507.10178 2025-09-17 cs.AR cs.LG 89%

Pimba: A Processing-in-Memory Acceleration for Post-Transformer Large Language Model Serving

Wonung Kim, Yubin Lee, Yoonsung Kim, Jinwoo Hwang, Seongryong Oh, Jiyong Jung, Aziz Huseynov, Woong Gyu Park, Chang Hyun Park, Divya Mahajan, Jongse Park

机构 * Uppsala University（乌普萨拉大学）； Georgia Institute of Technology（佐治亚理工学院）

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

Journal ref MICRO 2025

2409.13745 2025-09-17 cs.CL cs.AI cs.CR cs.LG stat.ML 89%

Context-Aware Membership Inference Attacks against Pre-trained Large Language Models

Hongyan Chang, Ali Shahin Shamsabadi, Kleomenis Katevas, Hamed Haddadi, Reza Shokri

机构 * Mohamed bin Zayed University of Artificial Intelligence（莫扎伊德·本·扎耶德人工智能大学）； Brave Software（Brave软件公司）； Imperial College London（帝国理工学院）； National University of Singapore（新加坡国立大学）

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

2509.12221 2025-09-17 cs.LG cs.AI cs.CL cs.CR 89%

MEUV: Achieving Fine-Grained Capability Activation in Large Language Models via Mutually Exclusive Unlock Vectors

Xin Tong, Zhi Lin, Jingya Wang, Meng Han, Bo Jin

机构 * Xin Tong School of Information and Cyber Security People’s Public Security University of China（信息与网络安全学院中国人民公安大学）； Zhi Lin School of Safety Science Tsinghua University（安全科学学院清华大学）； Jingya Wang School of Information and Cyber Security People’s Public Security University of China（信息与网络安全学院中国人民公安大学）； Meng Han Intelligent Fusion Research Center Zhejiang University（智能融合研究中心浙江大学）； Bo Jin* The Third Research Institute of the Ministry of Public Security of China（中华人民共和国公安部第三研究所）

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

Comments Under Review

2509.12521 2025-09-17 cs.LG 88%

Phi: Preference Hijacking in Multi-modal Large Language Models at Inference Time

Yifan Lan, Yuanpu Cao, Weitong Zhang, Lu Lin, Jinghui Chen

机构 * The Pennsylvania State University（宾夕法尼亚州立大学）； The University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）

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

2509.13265 2025-09-17 cs.CY 88%

Beyond Private or Public: Large Language Models as Quasi-Public Goods in the AI Economy

Yukun Zhang, TianYang Zhang

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

2509.13244 2025-09-17 cs.CL 87%

Evaluating LLM Alignment on Personality Inference from Real-World Interview Data

Jianfeng Zhu, Julina Maharjan, Xinyu Li, Karin G. Coifman, Ruoming Jin

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

Comments 8 pages, 3 figures

2509.12886 2025-09-17 cs.CL cs.AI 86%

The LLM Already Knows: Estimating LLM-Perceived Question Difficulty via Hidden Representations

Yubo Zhu, Dongrui Liu, Zecheng Lin, Wei Tong, Sheng Zhong, Jing Shao

机构 * State Key Laboratory for Novel Software Technology, Nanjing University（南京大学新型软件技术国家重点实验室）； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）； Xidian University（西安电子科技大学）

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

2509.13179 2025-09-17 cs.IR cs.LG 85%

Efficient Cold-Start Recommendation via BPE Token-Level Embedding Initialization with LLM

Yushang Zhao, Xinyue Han, Qian Leng, Qianyi Sun, Haotian Lyu, Chengrui Zhou

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

2509.12211 2025-09-17 cs.DC cs.AI 85%

TinyServe: Query-Aware Cache Selection for Efficient LLM Serving

Dong Liu, Yanxuan Yu

机构 * Yale University（耶鲁大学）； Columbia University（哥伦比亚大学）

专题命中效率与部署：LLM(title,abstract)；large language model(abstract)；language model(abstract)；分类 cs.AI

Comments Accepted to ACM MM as Oral Paper, also accepted to ICML MOSS workshop, publicly available as https://openreview.net/forum?id=sOdtl4jLci

2507.10259 2025-09-17 cs.DC cs.NI 85%

Temporal-Aware GPU Resource Allocation for Distributed LLM Inference via Reinforcement Learning

Chengze Du, Zhiwei Yu, Heng Xu, Haojie Wang, Bo liu, Jialong Li

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

Comments 17 pages, 12 figures

2507.08523 2025-09-17 cs.SE 85%

InferLog: Accelerating LLM Inference for Online Log Parsing via ICL-oriented Prefix Caching

Yilun Wang, Pengfei Chen, Haiyu Huang, Zilong He, Gou Tan, Chuanfu Zhang, Jingkai He, Zibin Zheng

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

Comments Accepted by ICSE '26 (The 48th IEEE/ACM International Conference on Software Engineering)

2509.12600 2025-09-17 cs.LG cs.AI q-bio.QM 81%

A Multimodal Foundation Model to Enhance Generalizability and Data Efficiency for Pan-cancer Prognosis Prediction

Huajun Zhou, Fengtao Zhou, Jiabo Ma, Yingxue Xu, Xi Wang, Xiuming Zhang, Li Liang, Zhenhui Li, Hao Chen

机构 * Department of Computer Science and Engineering（计算机科学与工程系）； Hong Kong University of Science and Technology（香港科学与技术大学）； Department of Pathology（病理学系）； School of Medicine（医学院）； Zhejiang University（浙江大学）； Nanfang Hospital and School of Basic Medical Sciences（南方医科大学基础医学系）； Southern Medical University（南方医学院）； Guangdong Provincial Key Laboratory of Molecular Tumor Pathology（广东省分子肿瘤病理重点实验室）； Jinfeng Laboratory（金凤实验室）； Department of Radiology（放射科）； Division of Life Science（生命科学系）； HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute（香港科技大学深圳-香港协同创新研究院）； State Key Laboratory of Nervous System Disorders（神经系统疾病国家重点实验室）

专题命中效率与部署：foundation model(title,abstract)；分类 cs.AI、cs.LG

Comments 27 pages, 7 figures

2509.13136 2025-09-17 cs.LG 79%

Discovering Mathematical Equations with Diffusion Language Model

Xiaoxu Han, Chengzhen Ning, Jinghui Zhong, Fubiao Yang, Yu Wang, Xin Mu

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

2506.03592 2025-09-17 cs.CL 79%

From Understanding to Generation: An Efficient Shortcut for Evaluating Language Models

Viktor Hangya, Fabian Küch, Darina Gold

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

Comments Accepted to EMNLP 2025 (Main Conference)

2507.10375 2025-09-17 cs.CV cs.LG 79%

Test-Time Canonicalization by Foundation Models for Robust Perception

Utkarsh Singhal, Ryan Feng, Stella X. Yu, Atul Prakash

机构 * University of Michigan（密歇根大学）

专题命中效率与部署：foundation model(title,abstract)；分类 cs.LG

Comments Published at ICML 2025

2411.15244 2025-09-17 cs.CV cs.AI 79%

Adversarial Prompt Distillation for Vision-Language Models

Lin Luo, Xin Wang, Bojia Zi, Shihao Zhao, Xingjun Ma, Yu-Gang Jiang

机构 * Shanghai Key Lab of Intell. Info. Processing, School of CS, Fudan University（上海智能信息处理实验室，计算机科学学院，复旦大学）； The Chinese University of Hong Kong, Shatin, Hong Kong（香港中文大学，沙田，香港）； The University of Hong Kong, Pokfulam, Hong Kong（香港大学，薄扶林，香港）

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

Comments This work has been submitted to the IEEE for possible publication

2509.13201 2025-09-17 cs.DC 78%

Scaling Up Throughput-oriented LLM Inference Applications on Heterogeneous Opportunistic GPU Clusters with Pervasive Context Management

Thanh Son Phung, Douglas Thain

专题命中效率与部署：LLM(title,abstract)

Comments 10 pages

2509.01957 2025-09-17 cs.NI 78%

Federated Foundation Models in Harsh Wireless Environments: Prospects, Challenges, and Future Directions

Evan Chen, Seyyedali Hosseinalipour, Christopher G. Brinton, David J. Love

专题命中效率与部署：foundation model(title,abstract)

Comments This paper is under review in IEEE Network Magazine Special Issue on Large AI Models for the Internet of Everything

2509.12867 2025-09-17 cs.LG cs.CV 77%

Tool-R1: Sample-Efficient Reinforcement Learning for Agentic Tool Use

Yabo Zhang, Yihan Zeng, Qingyun Li, Zhen Hu, Kavin Han, Wangmeng Zuo

机构 * Harbin Institute of Technology（哈尔滨工业大学）； Huawei Noah’s Ark Lab（华为诺亚实验室）

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

2509.11177 2025-09-17 cs.CL 77%

Optimal Brain Restoration for Joint Quantization and Sparsification of LLMs

Hang Guo, Yawei Li, Luca Benini

机构 * ETH Zürich（苏黎世联邦理工学院）

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

Comments Preprint

2507.08445 2025-09-17 cs.IR cs.AI 77%

Clue-RAG: Towards Accurate and Cost-Efficient Graph-based RAG via Multi-Partite Graph and Query-Driven Iterative Retrieval

Yaodong Su, Yixiang Fang, Yingli Zhou, Quanqing Xu, Chuanhui Yang

机构 * The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））

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

2405.08965 2025-09-17 cs.PL cs.AI 77%

MTP: A Meaning-Typed Language Abstraction for AI-Integrated Programming

Jayanaka L. Dantanarayana, Yiping Kang, Kugesan Sivasothynathan, Christopher Clarke, Baichuan Li, Savini Kashmira, Krisztian Flautner, Lingjia Tang, Jason Mars

机构 * University of Michigan（密歇根大学）； Jaseci Labs（Jaseci实验室）

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

Comments OOPSLA 2025

2508.16044 2025-09-17 cs.DB 75%

AMAZe: A Multi-Agent Zero-shot Index Advisor for Relational Databases

Zhaodonghui Li, Haitao Yuan, Jiachen Shi, Hao Zhang, Yu Rong, Gao Cong

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

2509.12423 2025-09-17 cs.AI cs.CL 73%

Small Models, Big Results: Achieving Superior Intent Extraction through Decomposition

Danielle Cohen, Yoni Halpern, Noam Kahlon, Joel Oren, Omri Berkovitch, Sapir Caduri, Ido Dagan, Anatoly Efros

机构 * Google（谷歌）； Bar-Ilan University（巴伊兰大学）

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

2509.12951 2025-09-17 cs.AI 70%

Black-box Model Merging for Language-Model-as-a-Service with Massive Model Repositories

Shilian Chen, Jie Zhou, Tianyu Huai, Yujiang Lu, Junsong Li, Bihao Zhan, Qianjun Pan, Yutao Yang, Xin Li, Qin Chen, Hang Yan, Liang He

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

1. 效率与部署 37 篇

Small Language Models are the Future of Agentic AI

Concurrent Linguistic Error Detection (CLED): a New Methodology for Error Detection in Large Language Models

JoPA:Explaining Large Language Model's Generation via Joint Prompt Attribution

Toward Ownership Understanding of Objects: Active Question Generation with Large Language Model and Probabilistic Generative Model

CredID: Credible Multi-Bit Watermark for Large Language Models Identification

Pimba: A Processing-in-Memory Acceleration for Post-Transformer Large Language Model Serving

Context-Aware Membership Inference Attacks against Pre-trained Large Language Models

MEUV: Achieving Fine-Grained Capability Activation in Large Language Models via Mutually Exclusive Unlock Vectors

Phi: Preference Hijacking in Multi-modal Large Language Models at Inference Time

Beyond Private or Public: Large Language Models as Quasi-Public Goods in the AI Economy

Evaluating LLM Alignment on Personality Inference from Real-World Interview Data

The LLM Already Knows: Estimating LLM-Perceived Question Difficulty via Hidden Representations

Efficient Cold-Start Recommendation via BPE Token-Level Embedding Initialization with LLM

TinyServe: Query-Aware Cache Selection for Efficient LLM Serving

Temporal-Aware GPU Resource Allocation for Distributed LLM Inference via Reinforcement Learning

InferLog: Accelerating LLM Inference for Online Log Parsing via ICL-oriented Prefix Caching

A Multimodal Foundation Model to Enhance Generalizability and Data Efficiency for Pan-cancer Prognosis Prediction

Discovering Mathematical Equations with Diffusion Language Model

From Understanding to Generation: An Efficient Shortcut for Evaluating Language Models

Test-Time Canonicalization by Foundation Models for Robust Perception

Adversarial Prompt Distillation for Vision-Language Models

Scaling Up Throughput-oriented LLM Inference Applications on Heterogeneous Opportunistic GPU Clusters with Pervasive Context Management

Federated Foundation Models in Harsh Wireless Environments: Prospects, Challenges, and Future Directions

Tool-R1: Sample-Efficient Reinforcement Learning for Agentic Tool Use

Optimal Brain Restoration for Joint Quantization and Sparsification of LLMs

Clue-RAG: Towards Accurate and Cost-Efficient Graph-based RAG via Multi-Partite Graph and Query-Driven Iterative Retrieval

MTP: A Meaning-Typed Language Abstraction for AI-Integrated Programming

AMAZe: A Multi-Agent Zero-shot Index Advisor for Relational Databases

Small Models, Big Results: Achieving Superior Intent Extraction through Decomposition

Black-box Model Merging for Language-Model-as-a-Service with Massive Model Repositories