语言大模型 / LLM - arXivDaily 专题

2511.17801 2025-11-25 cs.LG 92%

Layer-Wise High-Impact Parameter Ratio Optimization in Post-Training Quantization for Large Language Models

分层高影响参数比率优化在大语言模型后训练量化中的应用

Cuong Pham, Hoang Anh Dung, Cuong C. Nguyen, Trung Le, Gustavo Carneiro, Thanh-Toan Do

机构 * Department of Data Science and AI, Monash University, Australia（墨尔本大学数据科学与人工智能系）； Centre for Vision, Speech and Signal Processing, University of Surrey, UK（萨里大学视觉、语音与信号处理中心）

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

AI总结本文提出了一种分层高影响参数比率优化方法，通过二次优化框架确定各层的高影响参数比例，以提升大语言模型后训练量化的效率与精度。

2506.11044 2025-10-28 cs.LG 92%

Boost Post-Training Quantization via Null Space Optimization for Large Language Models

Jiaqi Zhao, Miao Zhang, Deng Xiang, Ming Li, Weili Guan, Liqiang Nie

机构 * Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））

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

Comments 17 pages, 4 figures

2510.12637 2025-10-15 cs.CL 92%

COSTAR-A: A prompting framework for enhancing Large Language Model performance on Point-of-View questions

Nzubechukwu C. Ohalete, Kevin B. Gittner, Lauren M. Matheny

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

Comments 20 pages, 2 figures

2509.15089 2025-09-19 cs.CL 92%

LLM-OREF: An Open Relation Extraction Framework Based on Large Language Models

Hongyao Tu, Liang Zhang, Yujie Lin, Xin Lin, Haibo Zhang, Long Zhang, Jinsong Su

机构 * School of Informatics, Xiamen University（厦门大学信息学院）； LLM Team, Shopee Pte. Ltd.（Shopee Pte. Ltd. 机器学习团队）； National Institute for Data Science in Health and Medicine, Xiamen University（厦门大学医学数据科学国家研究院）

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

2508.08300 2025-08-13 cs.AI 92%

LLM-BI: Towards Fully Automated Bayesian Inference with Large Language Models

Yongchao Huang

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

Comments 6 pages

2506.10443 2025-06-13 cs.LG 92%

MNN-LLM: A Generic Inference Engine for Fast Large Language Model Deployment on Mobile Devices

Zhaode Wang, Jingbang Yang, Xinyu Qian, Shiwen Xing, Xiaotang Jiang, Chengfei Lv, Shengyu Zhang

机构 * Alibaba Group（阿里巴巴集团）； Zhejiang University（浙江大学）

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

Comments 7 pages, 5 figures. Published in the Proceedings of the 6th ACM International Conference on Multimedia in Asia Workshops (MMAsia '24 Workshops). The final authenticated version is available at https://dl.acm.org/doi/10.1145/3700410.3702126

2501.15850 2025-06-10 cs.LG cs.CV cs.RO 92%

LLM-attacker: Enhancing Closed-loop Adversarial Scenario Generation for Autonomous Driving with Large Language Models

Yuewen Mei, Tong Nie, Jian Sun, Ye Tian

机构 * Department of Traffic Engineering and Key Laboratory of Road and Traffic Engineering, Ministry of Education, Tongji University（交通工程系和道路与交通工程重点实验室、教育部长江大学）； Department of Civil & Environmental Engineering, The Hong Kong Polytechnic University（土木及环境工程系、香港理工大学）

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

Comments Accepted as a regular paper at IEEE TITS 2025

Journal ref IEEE Transactions on Intelligent Transportation Systems 2025

2312.01797 2025-05-16 cs.RO cs.AI cs.HC 92%

LLM A: Human in the Loop Large Language Models Enabled A Search for Robotics

Hengjia Xiao, Peng Wang, Mingzhe Yu, Mattia Robbiani

机构 * Department of Computing and Mathematics, Manchester Metropolitan University（计算与数学系，曼彻斯特 Metropolitan 大学）； Manchester Metropolitan University（曼彻斯特 Metropolitan 大学）； Johnson Matthey Technology Centre, Johnson Matthey（Johnson Matthey 技术中心，Johnson Matthey）

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

Comments 7 figures, 8 pages

2406.18770 2025-04-04 cs.LG 92%

ADO-LLM: Analog Design Bayesian Optimization with In-Context Learning of Large Language Models

Yuxuan Yin, Yu Wang, Boxun Xu, Peng Li

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

Comments 9 pages, 3 figures

Journal ref ICCAD: International Conference on Computer-Aided Design, 2024

2502.14189 2025-03-04 cs.CL 92%

QUAD-LLM-MLTC: Large Language Models Ensemble Learning for Healthcare Text Multi-Label Classification

Hajar Sakai, Sarah S. Lam

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

2404.01077 2024-12-03 cs.CL 92%

Efficient Prompting Methods for Large Language Models: A Survey

Kaiyan Chang, Songcheng Xu, Chenglong Wang, Yingfeng Luo, Xiaoqian Liu, Tong Xiao, Jingbo Zhu

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

2411.15664 2024-11-26 cs.DC cs.LG 92%

Enabling Efficient Serverless Inference Serving for LLM (Large Language Model) in the Cloud

Himel Ghosh

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

Comments 12 pages, 7 figures, TUM Cloud Computing Seminar

2411.00556 2024-11-04 cs.IR cs.AI 92%

LLM-KT: A Versatile Framework for Knowledge Transfer from Large Language Models to Collaborative Filtering

Nikita Severin, Aleksei Ziablitsev, Yulia Savelyeva, Valeriy Tashchilin, Ivan Bulychev, Mikhail Yushkov, Artem Kushneruk, Amaliya Zaryvnykh, Dmitrii Kiselev, Andrey Savchenko, Ilya Makarov

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

Comments accepted at ICDM 2024 (demo track)

2411.00136 2024-11-04 cs.LG 92%

LLM-Inference-Bench: Inference Benchmarking of Large Language Models on AI Accelerators

Krishna Teja Chitty-Venkata, Siddhisanket Raskar, Bharat Kale, Farah Ferdaus, Aditya Tanikanti, Ken Raffenetti, Valerie Taylor, Murali Emani, Venkatram Vishwanath

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

2408.13727 2024-08-27 cs.SE cs.AI 92%

LogParser-LLM: Advancing Efficient Log Parsing with Large Language Models

Aoxiao Zhong, Dengyao Mo, Guiyang Liu, Jinbu Liu, Qingda Lu, Qi Zhou, Jiesheng Wu, Quanzheng Li, Qingsong Wen

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

Comments Accepted by ACM KDD 2024

2407.11681 2024-07-17 cs.CL 92%

MINI-LLM: Memory-Efficient Structured Pruning for Large Language Models

Hongrong Cheng, Miao Zhang, Javen Qinfeng Shi

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

Comments 13 pages

2406.15758 2024-06-25 cs.LG cs.DC 92%

EDGE-LLM: Enabling Efficient Large Language Model Adaptation on Edge Devices via Layerwise Unified Compression and Adaptive Layer Tuning and Voting

Zhongzhi Yu, Zheng Wang, Yuhan Li, Haoran You, Ruijie Gao, Xiaoya Zhou, Sreenidhi Reedy Bommu, Yang Katie Zhao, Yingyan Celine Lin

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

2406.02267 2024-06-05 cs.CL 92%

Prompting Large Language Models with Human Error Markings for Self-Correcting Machine Translation

Nathaniel Berger, Stefan Riezler, Miriam Exel, Matthias Huck

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

Comments To appear at The 25th Annual Conference of the European Association for Machine Translation (EAMT 2024)

2404.11343 2024-06-04 cs.IR cs.AI 92%

Large Language Models meet Collaborative Filtering: An Efficient All-round LLM-based Recommender System

Sein Kim, Hongseok Kang, Seungyoon Choi, Donghyun Kim, Minchul Yang, Chanyoung Park

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

Comments KDD 2024

2405.11299 2024-05-28 cs.DB cs.LG 92%

The CAP Principle for LLM Serving: A Survey of Long-Context Large Language Model Serving

Pai Zeng, Zhenyu Ning, Jieru Zhao, Weihao Cui, Mengwei Xu, Liwei Guo, Xusheng Chen, Yizhou Shan

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

2404.13028 2024-04-22 cs.CE cs.AI 92%

When Life gives you LLMs, make LLM-ADE: Large Language Models with Adaptive Data Engineering

Stephen Choi, William Gazeley

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

Comments 6 pages, 3 tables and 3 figures

2404.12872 2024-04-22 cs.DB cs.CL 92%

LLM-R2: A Large Language Model Enhanced Rule-based Rewrite System for Boosting Query Efficiency

Zhaodonghui Li, Haitao Yuan, Huiming Wang, Gao Cong, Lidong Bing

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

Comments 12 pages

2310.12362 2024-04-09 cs.CR cs.CL 92%

REMARK-LLM: A Robust and Efficient Watermarking Framework for Generative Large Language Models

Ruisi Zhang, Shehzeen Samarah Hussain, Paarth Neekhara, Farinaz Koushanfar

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

Comments accept to usenix security 2024

2408.00214 2025-06-17 eess.SY cs.SY 91%

Large Language Model (LLM)-enabled In-context Learning for Wireless Network Optimization: A Case Study of Power Control

Hao Zhou, Chengming Hu, Dun Yuan, Ye Yuan, Di Wu, Xue Liu, Charlie Zhang

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

Comments The latest version of this work has been accepted by ICML 2025 Workshop on ML4Wireless, and the revised title is "Prompting Wireless Networks: Reinforced In-Context Learning for Power Control"

2506.22666 2026-06-02 cs.CR cs.CL cs.LG stat.ML 91%

VERA: Variational Inference Framework for Jailbreaking Large Language Models

VERA：用于越狱大型语言模型的变分推理框架

Anamika Lochab, Lu Yan, Patrick Pynadath, Xiangyu Zhang, Ruqi Zhang

机构 * Department of Computer Science, Purdue University（计算机科学系，普渡大学）

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

AI总结提出VERA框架，将黑盒越狱提示生成视为变分推理问题，训练小型攻击者LLM近似目标LLM的对抗提示后验，无需重新优化即可生成多样且流畅的越狱提示。

Comments Accepted by NeurIPS 2025

2603.19262 2026-06-01 cs.CL cs.AI 91%

Empirical Characterization of Inference-Time Elicited Probability Transformations in Large Language Models

大型语言模型中推理时引发的概率变换的经验表征

Mike Farmer, Abhinav Kochar, Yugyung Lee

机构 * Bloch School of Management, Regnier Institute for Entrepreneurship & Innovation, University of Missouri–Kansas City（布洛赫管理学院、雷尼创业与创新研究所、密苏里大学堪萨斯城分校）； Department of Computer Science, School of Science and Engineering, University of Missouri–Kansas City（计算机科学系、科学与工程学院、密苏里大学堪萨斯城分校）

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

AI总结本研究通过经验观察发现，在多种推理时流程（如思维链、自我细化、检索增强和验证器引导修订）下，候选答案的概率变换遵循近似的对数比率关系，并分析了其系数变化和鲁棒性。

Comments 22 pages, 11 figures, 5 tables

2605.23158 2026-05-25 cs.CR cs.CL cs.LG 91%

What Does the Server See? Understanding Privacy Leakage from Large Language Models in Split Inference

服务器看到了什么？理解大语言模型在分割推理中的隐私泄露

Mingyuan Fan, Yu Liu, Fuyi Wang, Cen Chen

机构 * East China Normal University（华东师范大学）； RMIT University（皇家墨尔本理工大学）

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

AI总结提出ActInv方法解决中间激活匹配问题以重建客户端输入，并引入扰动放大因子（PAF）量化层固有抗重建能力，揭示隐私脆弱性在层间不均匀分布，进而设计PriPert防御策略。

Comments Accepted to ACM CCS'26

2604.19790 2026-04-23 cs.AI cs.LG 91%

Hidden Reliability Risks in Large Language Models: Systematic Identification of Precision-Induced Output Disagreements

大语言模型中的隐藏可靠性风险：系统性识别精度诱导的输出分歧

Yifei Wang, Tianlin Li, Xiaohan Zhang, Xiaoyu Zhang, Wei Ma, Mingfei Cheng, Li Pan

机构 * Shanghai Jiao Tong University（上海交通大学）； Beihang University（北航）； Nanyang Technological University（南洋理工大学）； Singapore Management University（新加坡管理学院）

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

AI总结本文提出PrecisionDiff框架，用于系统检测大语言模型在不同精度下的行为分歧，通过生成精度敏感测试输入并进行跨精度比较分析，揭示传统方法难以发现的细微差异，实验表明此类分歧在多个开源对齐LLM中普遍存在，PrecisionDiff在检测此类问题上表现优异。

Comments 12 pages, 5 figures

2510.19410 2026-04-21 cs.CL cs.AI 91%

ToMMeR -- Efficient Entity Mention Detection from Large Language Models

ToMMeR -- 从大语言模型中高效实体提及检测

Victor Morand, Nadi Tomeh, Josiane Mothe, Benjamin Piwowarski

机构 * Institut des Systèmes Intelligents et de Robotique (ISIR), Sorbonne Université, CNRS（智能系统与机器人研究所（ISIR），索邦大学，法国国家科学研究中心）； LIPN, Université Sorbonne Paris Nord, UMR7030 CNRS（LIPN，巴黎-索邦大学，法国国家科学研究中心）； INSPE, UT2J, Univ. Toulouse, IRIT, CLLE UMR5505 UMR5263 CNRS（INSPE，图卢兹大学，IRIT，CLLE法国国家科学研究中心）

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

AI总结 ToMMeR通过轻量模型验证早期LLM层的提及检测能力，在13个NER基准中实现93%零样本召回率，证明实体提及自然从语言建模中产生。

Comments Accepted at ACL2026 - Code: https://github.com/VictorMorand/llm2ner

2603.21389 2026-03-24 cs.CL cs.LG 91%

Task-Specific Efficiency Analysis: When Small Language Models Outperform Large Language Models

任务特定效率分析：当小型语言模型超越大型语言模型

Jinghan Cao, Yu Ma, Xinjin Li, Qingyang Ren, Xiangyun Chen

机构 * San Francisco State University - Department of Computer Science（旧金山州立大学-计算机科学系）； Carnegie Mellon University - Department of Computer Science（卡内基梅隆大学-计算机科学系）； Columbia University - Department of Computer Science（哥伦比亚大学-计算机科学系）； Cornell University - Department of Computer Science（康奈尔大学-计算机科学系）； Pennsylvania State University - Department of Biochemistry and Molecular Biology（宾夕法尼亚州立大学-生物化学与分子生物学系）

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

AI总结本文通过对比16个模型在五个NLP任务上的效率，提出PER指标，发现小型模型在效率上表现更优，为高效推理场景提供依据。

Comments Accepted for publication at ESANN 2025. This is a task-specific efficiency analysis comparing small language models

1. 效率与部署 22280 篇

Layer-Wise High-Impact Parameter Ratio Optimization in Post-Training Quantization for Large Language Models

Boost Post-Training Quantization via Null Space Optimization for Large Language Models

COSTAR-A: A prompting framework for enhancing Large Language Model performance on Point-of-View questions

LLM-OREF: An Open Relation Extraction Framework Based on Large Language Models

LLM-BI: Towards Fully Automated Bayesian Inference with Large Language Models

MNN-LLM: A Generic Inference Engine for Fast Large Language Model Deployment on Mobile Devices

LLM-attacker: Enhancing Closed-loop Adversarial Scenario Generation for Autonomous Driving with Large Language Models

LLM A*: Human in the Loop Large Language Models Enabled A* Search for Robotics

ADO-LLM: Analog Design Bayesian Optimization with In-Context Learning of Large Language Models

QUAD-LLM-MLTC: Large Language Models Ensemble Learning for Healthcare Text Multi-Label Classification

Efficient Prompting Methods for Large Language Models: A Survey

Enabling Efficient Serverless Inference Serving for LLM (Large Language Model) in the Cloud

LLM-KT: A Versatile Framework for Knowledge Transfer from Large Language Models to Collaborative Filtering

LLM-Inference-Bench: Inference Benchmarking of Large Language Models on AI Accelerators

LogParser-LLM: Advancing Efficient Log Parsing with Large Language Models

MINI-LLM: Memory-Efficient Structured Pruning for Large Language Models

EDGE-LLM: Enabling Efficient Large Language Model Adaptation on Edge Devices via Layerwise Unified Compression and Adaptive Layer Tuning and Voting

Prompting Large Language Models with Human Error Markings for Self-Correcting Machine Translation

Large Language Models meet Collaborative Filtering: An Efficient All-round LLM-based Recommender System

The CAP Principle for LLM Serving: A Survey of Long-Context Large Language Model Serving

When Life gives you LLMs, make LLM-ADE: Large Language Models with Adaptive Data Engineering

LLM-R2: A Large Language Model Enhanced Rule-based Rewrite System for Boosting Query Efficiency

REMARK-LLM: A Robust and Efficient Watermarking Framework for Generative Large Language Models

Large Language Model (LLM)-enabled In-context Learning for Wireless Network Optimization: A Case Study of Power Control

VERA: Variational Inference Framework for Jailbreaking Large Language Models

Empirical Characterization of Inference-Time Elicited Probability Transformations in Large Language Models

What Does the Server See? Understanding Privacy Leakage from Large Language Models in Split Inference

Hidden Reliability Risks in Large Language Models: Systematic Identification of Precision-Induced Output Disagreements

ToMMeR -- Efficient Entity Mention Detection from Large Language Models

Task-Specific Efficiency Analysis: When Small Language Models Outperform Large Language Models

LLM A: Human in the Loop Large Language Models Enabled A Search for Robotics