语言大模型 / LLM - arXivDaily 专题

2512.03047 2025-12-04 cs.CL cs.AI cs.LG 89%

Entropy-Based Measurement of Value Drift and Alignment Work in Large Language Models

基于熵的大型语言模型价值漂移与对齐工作的测量

Samih Fadli

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

AI总结本文提出基于熵的框架，用于测量大型语言模型中的价值漂移和对齐工作，通过五种行为分类法和熵动态分析，实现对模型伦理熵的实时监控与警报。

Comments 6 pages. Companion paper to "The Second Law of Intelligence: Controlling Ethical Entropy in Autonomous Systems". Code and tools: https://github.com/AerisSpace/EthicalEntropyKit

2512.00083 2025-12-02 cs.AR cs.DC 89%

LLaMCAT: Optimizing Large Language Model Inference with Cache Arbitration and Throttling

LLaMCAT：通过缓存仲裁和限流优化大语言模型推理

Zhongchun Zhou, Chengtao Lai, Wei Zhang

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

AI总结 LLaMCAT通过缓存仲裁和限流技术优化大语言模型推理，实现1.26-1.58倍速度提升，填补LLM解码特定MSHR竞争的空白。

Comments Accepted to ICPP 2025

Journal ref In Proceedings of 54th International Conference on Parallel Processing (ICPP 2025)

2408.04275 2025-12-01 cs.DC 89%

DistTrain: Addressing Model and Data Heterogeneity with Disaggregated Training for Multimodal Large Language Models

DistTrain: 通过解耦训练解决多模态大语言模型中的模型与数据异质性

Zili Zhang, Yinmin Zhong, Yimin Jiang, Hanpeng Hu, Jianjian Sun, Zheng Ge, Yibo Zhu, Daxin Jiang, Xin Jin

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

AI总结 DistTrain通过解耦模型编排和数据预处理，提升多模态大语言模型的训练效率和资源利用率。

Comments SIGCOMM 2025 (https://dl.acm.org/doi/10.1145/3718958.3750472)

Journal ref SIGCOMM'25: Proceedings of the ACM SIGCOMM 2025 Conference Pages 24-38

2511.21084 2025-11-27 cs.NI 89%

5G Network Automation Using Local Large Language Models and Retrieval-Augmented Generation

利用本地大语言模型和检索增强生成实现5G网络自动化

Ahmadreza Majlesara, Ali Majlesi, Ali Mamaghani, Alireza Shokrani, Babak Hossein Khalaj

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

AI总结本研究通过本地部署大语言模型与检索增强生成技术，实现5G网络自动化管理，提升隐私保护与配置效率。

Comments 4 pages, 1 figure, demonstrated on 6G Summit Abu Dhabi

2505.14454 2025-11-19 cs.CV 89%

Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language Models

Xuyang Liu, Yiyu Wang, Junpeng Ma, Linfeng Zhang

机构 * Shanghai Jiao Tong University（上海交通大学）； Sichuan University（四川大学）； Fudan University（复旦大学）

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

Comments EMNLP 2025 main

2511.11018 2025-11-17 cs.CL cs.AI cs.CR cs.LG cs.SE 89%

Automata-Based Steering of Large Language Models for Diverse Structured Generation

Xiaokun Luan, Zeming Wei, Yihao Zhang, Meng Sun

机构 * School of Mathematical Sciences, Peking University（北京大学数学科学学院）

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 ICFEM 2025 (Best Paper Award)

2409.16694 2025-11-13 cs.AI cs.CL cs.LG 89%

A Survey of Low-bit Large Language Models: Basics, Systems, and Algorithms

Ruihao Gong, Yifu Ding, Zining Wang, Chengtao Lv, Xingyu Zheng, Jinyang Du, Haotong Qin, Jinyang Guo, Michele Magno, Xianglong Liu

机构 * Beihang University（北京航空航天大学）； ETH Zurich（苏黎世联邦理工学院）； The Chinese University of Hong Kong（香港中文大学）

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

Comments Ruihao Gong leads the overall organization of the survey, with Yifu Ding and Jinyang Du contributing to Sections 2 and 3. Xingyu Zheng is responsible for authoring Section 4, while Chengtao Lv and Zining Wang collaborate on Section 5. Haotong Qin, Jinyang Guo, Michele Magno, and Xianglong Liu provide guidance during the whole process and assist in refining the final manuscript

2508.21432 2025-11-04 cs.CR cs.SE 89%

RepoMark: A Data-Usage Auditing Framework for Code Large Language Models

Wenjie Qu, Yuguang Zhou, Bo Wang, Yuexin Li, Lionel Z. Wang, Jinyuan Jia, Jiaheng Zhang

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

2508.06312 2025-10-22 cs.CE 89%

Chain-of-Alpha: Unleashing the Power of Large Language Models for Alpha Mining in Quantitative Trading

Lang Cao

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

Comments arXiv admin comment: This version has been removed by arXiv administrators as the submitter did not have the rights to agree to the license at the time of submission

2510.17147 2025-10-21 cs.NI 89%

Mamba4Net: Distilled Hybrid Mamba Large Language Models For Networking

Linhan Xia, Mingzhan Yang, Jingjing Wang, Ziwei Yan, Yakun Ren, Guo Yu, Kai Lei

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

2507.03308 2025-10-20 cs.AR 89%

Hummingbird: A Smaller and Faster Large Language Model Accelerator on Embedded FPGA

Jindong Li, Tenglong Li, Ruiqi Chen, Guobin Shen, Dongcheng Zhao, Qian Zhang, Yi Zeng

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

Comments Accepted by ICCAD2025

2510.13883 2025-10-17 q-bio.NC cs.MA 89%

Large Language Model Agents Enable Autonomous Design and Image Analysis of Microwell Microfluidics

Dinh-Nguyen Nguyen, Sadia Shakil, Raymond Kai-Yu Tong, Ngoc-Duy Dinh

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

2510.11211 2025-10-14 cs.DC 89%

An Explorative Study on Distributed Computing Techniques in Training and Inference of Large Language Models

Sheikh Azizul Hakim, Saem Hasan

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

2510.10561 2025-10-14 eess.SP 89%

Large Language Model-Empowered Channel Prediction and Predictive Beamforming for LEO Satellite Communications

Zhixiong Chen, Hyundong Shin, Arumugam Nallanathan, Jonathon Chambers

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

Comments 14 pages, 13 figures

2505.21334 2025-10-13 cs.CV 89%

HoliTom: Holistic Token Merging for Fast Video Large Language Models

Kele Shao, Keda Tao, Can Qin, Haoxuan You, Yang Sui, Huan Wang

机构 * Zhejiang University（浙江大学）； Shanghai Innovation Institute（上海创新研究院）； Westlake University（西湖大学）； Salesforce AI Research（Salesforce AI研究院）； Columbia University（哥伦比亚大学）； Rice University（Rice大学）

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

Comments code link: https://github.com/cokeshao/HoliTom

2510.00490 2025-10-02 cs.CR 89%

Has the Two-Decade-Old Prophecy Come True? Artificial Bad Intelligence Triggered by Merely a Single-Bit Flip in Large Language Models

Yu Yan, Siqi Lu, Yang Gao, Zhaoxuan Li, Ziming Zhao, Qingjun Yuan, Yongjuan Wang

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

Comments 19 pages

2509.26593 2025-10-01 cs.HC 89%

Exploring Large Language Model as an Interactive Sports Coach: Lessons from a Single-Subject Half Marathon Preparation

Kichang Lee

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

Comments 23 pages, 21 figures

2506.04203 2025-10-01 cs.DC 89%

Cascadia: An Efficient Cascade Serving System for Large Language Models

Youhe Jiang, Fangcheng Fu, Wanru Zhao, Stephan Rabanser, Jintao Zhang, Nicholas D. Lane, Binhang Yuan

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

2509.25100 2025-09-30 cs.LG cs.AI cs.CL 89%

ORPO-Distill: Mixed-Policy Preference Optimization for Cross-Architecture LLM Distillation

Aasheesh Singh, Vishal Vaddina, Dagnachew Birru

机构 * Phi Labs, Quantiphi（Phi Labs，Quantiphi）

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

Comments Accepted at NeurIPS 2025, Efficient Reasoning Workshop

2503.16980 2025-09-30 cs.CV cs.AI cs.CL cs.LG 89%

VQToken: Neural Discrete Token Representation Learning for Extreme Token Reduction in Video Large Language Models

Haichao Zhang, Yun Fu

机构 * Northeastern University（东北大学）

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

Comments Proceedings of the 38th Conference on Neural Information Processing Systems (NeurIPS 2025)

2509.17542 2025-09-30 cs.DC 89%

Disaggregated Prefill and Decoding Inference System for Large Language Model Serving on Multi-Vendor GPUs

Xing Chen, Rong Shi, Lu Zhao, Lingbin Wang, Xiao Jin, Yueqiang Chen, Hongfeng Sun

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

2507.13255 2025-09-24 cs.CL cs.AI cs.IR cs.LG cs.MM 89%

Automating Steering for Safe Multimodal Large Language Models

Lyucheng Wu, Mengru Wang, Ziwen Xu, Tri Cao, Nay Oo, Bryan Hooi, Shumin Deng

机构 * Zhejiang University（浙江大学）； Zhejiang University - Ant Group Joint Lab of Knowledge Graph（浙江大学-蚂蚁集团知识图谱联合实验室）； National University of Singapore, NUS-NCS Joint Lab（新加坡国立大学NUS-NCS联合实验室）

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 EMNLP 2025 Main Conference. 23 pages (8+ for main); 25 figures; 1 table

2509.07485 2025-09-22 cs.IR 89%

Multi-view-guided Passage Reranking with Large Language Models

Jeongwoo Na, Jun Kwon, Eunseong Choi, Jongwuk Lee

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

2505.13452 2025-09-22 cs.PL 89%

Large Language Model Powered Symbolic Execution

Yihe Li, Ruijie Meng, Gregory J. Duck

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

Comments 29 pages, 6 figures, 7 tables, published in "Object-Oriented Programming, Systems, Languages & Applications" (OOPSLA), 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

2509.12019 2025-09-16 cs.LG cs.AI cs.CL 89%

AMQ: Enabling AutoML for Mixed-precision Weight-Only Quantization of Large Language Models

Sangjun Lee, Seung-taek Woo, Jungyu Jin, Changhun Lee, Eunhyeok Park

机构 * Graduate School of Artificial Intelligence（人工智能研究生院）； Department of Convergence IT Engineering（融合IT工程系）； Pohang University of Science and Technology (POSTECH)（釜山科学技术大学）

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

Comments EMNLP 2025 Main Conference, Long Paper (Oral)

2509.08853 2025-09-12 cs.CY 89%

POW: Political Overton Windows of Large Language Models

Leif Azzopardi, Yashar Moshfeghi

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

Comments Accepted in EMNLP 2025

2509.07594 2025-09-10 cs.IR 89%

ELEC: Efficient Large Language Model-Empowered Click-Through Rate Prediction

Rui Dong, Wentao Ouyang, Xiangzheng Liu

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

Comments SIGIR 2025

2505.04416 2025-09-10 cs.CL cs.AI cs.CR cs.LG 89%

OBLIVIATE: Robust and Practical Machine Unlearning for Large Language Models

Xiaoyu Xu, Minxin Du, Qingqing Ye, Haibo Hu

机构 * The Hong Kong Polytechnic University（香港理工大学）； The State Key Laboratory of Blockchain and Data Security, Zhejiang University（浙江大学区块链与数据安全国家重点实验室）

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 To appear at EMNLP 25 main conference

1. 效率与部署 22405 篇

Entropy-Based Measurement of Value Drift and Alignment Work in Large Language Models

LLaMCAT: Optimizing Large Language Model Inference with Cache Arbitration and Throttling

DistTrain: Addressing Model and Data Heterogeneity with Disaggregated Training for Multimodal Large Language Models

5G Network Automation Using Local Large Language Models and Retrieval-Augmented Generation

Video Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language Models

Automata-Based Steering of Large Language Models for Diverse Structured Generation

A Survey of Low-bit Large Language Models: Basics, Systems, and Algorithms

RepoMark: A Data-Usage Auditing Framework for Code Large Language Models

Chain-of-Alpha: Unleashing the Power of Large Language Models for Alpha Mining in Quantitative Trading

Mamba4Net: Distilled Hybrid Mamba Large Language Models For Networking

Hummingbird: A Smaller and Faster Large Language Model Accelerator on Embedded FPGA

Large Language Model Agents Enable Autonomous Design and Image Analysis of Microwell Microfluidics

An Explorative Study on Distributed Computing Techniques in Training and Inference of Large Language Models

Large Language Model-Empowered Channel Prediction and Predictive Beamforming for LEO Satellite Communications

HoliTom: Holistic Token Merging for Fast Video Large Language Models

Has the Two-Decade-Old Prophecy Come True? Artificial Bad Intelligence Triggered by Merely a Single-Bit Flip in Large Language Models

Exploring Large Language Model as an Interactive Sports Coach: Lessons from a Single-Subject Half Marathon Preparation

Cascadia: An Efficient Cascade Serving System for Large Language Models

ORPO-Distill: Mixed-Policy Preference Optimization for Cross-Architecture LLM Distillation

VQToken: Neural Discrete Token Representation Learning for Extreme Token Reduction in Video Large Language Models

Disaggregated Prefill and Decoding Inference System for Large Language Model Serving on Multi-Vendor GPUs

Automating Steering for Safe Multimodal Large Language Models

Multi-view-guided Passage Reranking with Large Language Models

Large Language Model Powered Symbolic Execution

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

AMQ: Enabling AutoML for Mixed-precision Weight-Only Quantization of Large Language Models

POW: Political Overton Windows of Large Language Models

ELEC: Efficient Large Language Model-Empowered Click-Through Rate Prediction

OBLIVIATE: Robust and Practical Machine Unlearning for Large Language Models