语言大模型 / LLM - arXivDaily 专题

2405.15877 2025-12-22 cs.LG cs.AR cs.CL 88%

Basis Selection: Low-Rank Decomposition of Pretrained Large Language Models for Target Applications

基底选择：为特定应用预训练大语言模型的低秩分解

Yang Li, Daniel Agyei Asante, Changsheng Zhao, Ernie Chang, Yangyang Shi, Vikas Chandra

机构 * Iowa State University（爱荷华州立大学）； Meta

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

AI总结本文提出了一种针对特定应用的LLM低秩分解方法，通过识别并去除冗余部分，有效压缩模型大小并保持性能。

Comments Transactions on Machine Learning Research (TMLR), 2025

2512.13194 2025-12-18 cs.CL cs.AI 88%

Efficient Adaptive Rejection Sampling for Accelerating Speculative Decoding in Large Language Models

高效自适应拒绝采样用于加速大语言模型中的推测解码

Chendong Sun, Ali Mao, Lei Xu, mingmin Chen

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

AI总结本文提出高效自适应拒绝采样方法，通过动态调整接受阈值减少随机拒绝，提升大语言模型推测解码效率。

2512.14481 2025-12-17 cs.CL cs.AI 88%

SASQ: Static Activation Scaling for Quantization-Aware Training in Large Language Models

SASQ：用于大语言模型量化感知训练的静态激活缩放

Shizhuo Mao, Song Chen, Yi Kang

机构 * University of Science and Technology of China（中国科学技术大学）

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

AI总结 SASQ通过优化激活量化因子，实现了大语言模型在量化感知训练中的高精度静态推理与高效部署。

2512.13705 2025-12-17 cs.LG cs.AI 88%

Scaling and Transferability of Annealing Strategies in Large Language Model Training

在大语言模型训练中退火策略的扩展性与可迁移性

Siqi Wang, Zhengyu Chen, Teng Xiao, Zheqi Lv, Jinluan Yang, Xunliang Cai, Jingang Wang, Xiaomeng Li

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

AI总结本研究提出了一种通用框架，用于优化大语言模型训练中的退火策略，通过实验表明退火策略可跨不同模型配置迁移，提高了学习率调度的效率和实用性。

Comments Accepted to AAAI 2026 (camera-ready version)

2511.21736 2025-12-01 cs.CL cs.AI 88%

R2Q: Towards Robust 2-Bit Large Language Models via Residual Refinement Quantization

R2Q: 向通过残差细化量化实现稳健的2位大语言模型

Jiayi Chen, Jieqi Shi, Jing Huo, Chen Wu

机构 * Nanjing University（南京大学）； Microsoft AI（微软人工智能）

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

AI总结 R2Q通过残差细化量化方法，在极端压缩下提升2位大语言模型的性能和稳定性。

2511.19495 2025-11-26 cs.LG cs.AI 88%

A Systematic Study of Compression Ordering for Large Language Models

大语言模型压缩顺序的系统研究

Shivansh Chhawri, Rahul Mahadik, Suparna Rooj

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

AI总结本研究系统探讨了大语言模型压缩技术的顺序对性能的影响，发现剪枝-知识蒸馏-量化顺序能实现3.68倍压缩并保持良好能力。

2505.01273 2025-11-19 cs.CL cs.AI 88%

Anti-adversarial Learning: Desensitizing Prompts for Large Language Models

Xuan Li, Zhe Yin, Xiaodong Gu, Beijun Shen

机构 * Beijun Shen（沈贝俊）

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

Comments Accepted to AAAI 2026

2501.15278 2025-11-18 cs.LG cs.CL 88%

PIP: Perturbation-based Iterative Pruning for Large Language Models

Yi Cao, Wei-Jie Xu, Yucheng Shen, Weijie Shi, Chi-Min Chan, Jianfeng Qu, Jiajie Xu

机构 * School of Computer Science and Technology, Soochow University（苏州大学计算机科学与技术学院）； School of Artificial Intelligence, Nanjing University（南京大学人工智能学院）； Department of Computer Science and Engineering, Hong Kong University of Science and Technology（香港科技大学计算机科学与工程系）

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

Comments EMNLP 2025 Findings, 17 pages, 5 figures, 15 tables

2405.13746 2025-11-18 cs.LG cs.AI cs.DC 88%

CG-FedLLM: How to Compress Gradients in Federated Fune-tuning for Large Language Models

Huiwen Wu, Xiaogang Xu, Deyi Zhang, Xiaohan Li, Jiafei Wu, Zhe Liu

机构 * Zhejiang Laboratory（浙江实验室）

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

2511.11821 2025-11-18 cs.CL cs.AI 88%

Scaling Open-Weight Large Language Models for Hydropower Regulatory Information Extraction: A Systematic Analysis

Hong-Jun Yoon, Faisal Ashraf, Thomas A. Ruggles, Debjani Singh

机构 * Oak Ridge National Laboratory（奥克伍德国家实验室）

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

Comments 18 pages, zero figures, Preprint submitted to Environmental Modeling and Software

2511.10676 2025-11-17 cs.CL cs.AI 88%

Pre-Attention Expert Prediction and Prefetching for Mixture-of-Experts Large Language Models

Shien Zhu, Samuel Bohl, Robin Oester, Gustavo Alonso

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

2511.08082 2025-11-12 cs.AI cs.LG econ.GN q-fin.EC 88%

Prudential Reliability of Large Language Models in Reinsurance: Governance, Assurance, and Capital Efficiency

Stella C. Dong

机构 * Reinsurance Analytics（再保险分析）

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

Comments 48 pages, 9 figures, 5 tables. Submitted to the Journal of Risk and Insurance (JRI), November 2025

2510.08576 2025-11-12 cs.SE cs.AI cs.CL cs.HC 88%

Comparative Analysis of Large Language Models for the Machine-Assisted Resolution of User Intentions

Justus Flerlage, Alexander Acker, Odej Kao

机构 * logsight.ai GmbH（logsight.ai公司）

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

Comments Accepted at First International Workshop on Human-AI Collaborative Systems (HAIC), published in CEUR-WS.org Vol-4072 (2025). URN: urn:nbn:de:0074-4072-x

2511.06086 2025-11-11 cs.CL cs.LG 88%

MuonAll: Muon Variant for Efficient Finetuning of Large Language Models

Saurabh Page, Advait Joshi, S. S. Sonawane

机构 * Computer Engineering（计算机工程）； Pune Institute of Computer Technology（普那计算机技术学院）

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

2511.05085 2025-11-10 cs.CL cs.LG 88%

Iterative Layer-wise Distillation for Efficient Compression of Large Language Models

Grigory Kovalev, Mikhail Tikhomirov

机构 * Lomonosov Moscow State University, Russia（莫斯科罗蒙诺夫国立大学）

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

2502.02421 2025-11-10 cs.CL cs.AI 88%

Activation-Informed Merging of Large Language Models

Amin Heyrani Nobari, Kaveh Alim, Ali ArjomandBigdeli, Akash Srivastava, Faez Ahmed, Navid Azizan

机构 * Massachusetts Institute of Technology（麻省理工学院）； Stony Brook University（石溪大学）； MIT-IBM Watson AI Lab & Red Hat AI Innovation（MIT-IBM Watson AI实验室及Red Hat AI创新）

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

2511.04499 2025-11-07 cs.CL cs.AI 88%

Decoding Emergent Big Five Traits in Large Language Models: Temperature-Dependent Expression and Architectural Clustering

Christos-Nikolaos Zacharopoulos, Revekka Kyriakoglou

机构 * Université Paris 8 Vincennes – Saint-Denis（巴黎第八大学）

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

Comments Accepted at IJCNLP-AACL 2025

2510.23652 2025-10-29 cs.LG cs.AI 88%

The Structural Scalpel: Automated Contiguous Layer Pruning for Large Language Models

Yao Lu, Yuqi Li, Wenbin Xie, Shanqing Yu, Qi Xuan, Zhaowei Zhu, Shiping Wen

机构 * Institute of Cyberspace Security, College of Information Engineering, Zhejiang University of Technology（浙江工业大学信息工程学院网络安全研究所）； Binjiang Institute of Artificial Intelligence, Zhejiang University of Technology（浙江工业大学滨江人工智能研究院）； City College of New York, City University of New York（纽约市立大学城市学院）； Australian AI Institute, Faculty of Engineering and Information Technology, University of Technology（澳大利亚人工智能研究院，技术大学工程与信息学院）

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

2407.11654 2025-10-28 cs.LG cs.AI eess.SP 88%

R-SFLLM: Jamming Resilient Framework for Split Federated Learning with Large Language Models

Aladin Djuhera, Vlad C. Andrei, Xinyang Li, Ullrich J. Mönich, Holger Boche, Walid Saad

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

Journal ref IEEE Transactions on Information Forensics and Security (Volume: 20), 2025

2409.14595 2025-10-28 cs.CL cs.LG 88%

EchoAtt: Attend, Copy, then Adjust for More Efficient Large Language Models

Hossein Rajabzadeh, Aref Jafari, Aman Sharma, Benyamin Jami, Hyock Ju Kwon, Ali Ghodsi, Boxing Chen, Mehdi Rezagholizadeh

机构 * University of Waterloo（滑铁卢大学）； Huawei Noah’s Ark Lab（华为诺亚实验室）

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

2506.02720 2025-10-27 cs.AI cs.CL 88%

LocalGPT: Benchmarking and Advancing Large Language Models for Local Life Services in Meituan

Xiaochong Lan, Jie Feng, Jiahuan Lei, Xinlei Shi, Yong Li

机构 * Department of Electronic\ , BNRist,\ University Beijing, China ； Department of Electronic\ , BNRist,\ University

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

Comments KDD 2025

2502.01472 2025-10-22 cs.CL cs.AI 88%

FALCON: Fine-grained Activation Manipulation by Contrastive Orthogonal Unalignment for Large Language Model

Jinwei Hu, Zhenglin Huang, Xiangyu Yin, Wenjie Ruan, Guangliang Cheng, Yi Dong, Xiaowei Huang

机构 * School of Computer Science and Informatics, University of Liverpool, UK（计算机科学与信息学学院，利物浦大学）

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

Comments Accepted at NeurIPS 2025 with minor revisions

2403.00046 2025-10-22 cs.SE cs.AI cs.CL 88%

Exploring Data-Efficient Adaptation of Large Language Models for Code Generation

Xue Jiang, Yihong Dong, Zhiyuan Fan, Zhi Jin, Wenpin Jiao, Ge Li

机构 * Key Laboratory of High Confidence Software Technologies (Peking University), Ministry of Education（高可信软件技术重点实验室（北京大学））； School of Computer Science, Peking University, Beijing（计算机学院（北京大学））

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

Comments Accepted by TOSEM

2510.17705 2025-10-21 cs.AI cs.CL 88%

Contextual Attention Modulation: Towards Efficient Multi-Task Adaptation in Large Language Models

Dayan Pan, Zhaoyang Fu, Jingyuan Wang, Xiao Han, Yue Zhu, Xiangyu Zhao

机构 * SCSE, Beihang University（北京航空航天大学系统工程学院）； ERC of ACAT, MOE（教育部人工智能教育联合体）； City University of Hong Kong（香港城市大学）； Huawei Technologies Ltd.（华为技术有限公司）； Key Lab of DIM, MIIT（信息通信技术重点实验室）； SEM, Beihang University（北京航空航天大学电子机械学院）； Zhejiang University of Technology（浙江工业大学）

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

Comments Accepted by CIKM' 25

2509.23809 2025-10-20 cs.LG cs.AI 88%

Tequila: Trapping-free Ternary Quantization for Large Language Models

Hong Huang, Decheng Wu, Rui Cen, Guanghua Yu, Zonghang Li, Kai Liu, Jianchen Zhu, Peng Chen, Xue Liu, Dapeng Wu

机构 * City University of Hong Kong（香港城市大学）； Tencent（腾讯）； MBZUAI ； McGill University（麦吉尔大学）

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

2503.01933 2025-10-20 cs.LG cs.AR cs.CL cs.CV 88%

Fine-Tuning Small Language Models for Domain-Specific AI: An Edge AI Perspective

Rakshit Aralimatti, Syed Abdul Gaffar Shakhadri, Kruthika KR, Kartik Basavaraj Angadi

机构 * SandLogic Technologies Pvt Ltd（SandLogic技术有限公司）

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

2508.11711 2025-10-09 cs.CR cs.AI cs.LG 88%

Enhancing GraphQL Security by Detecting Malicious Queries Using Large Language Models, Sentence Transformers, and Convolutional Neural Networks

Irash Perera, Hiranya Abeyrathne, Sanjeewa Malalgoda, Arshardh Ifthikar

机构 * Department. of CSE University of Moratuwa Colombo, Sri Lanka（计算机科学与工程系，穆塔瓦拉大学，科伦坡，斯里兰卡）

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

2510.03662 2025-10-07 cs.LG cs.AI 88%

Operationalizing Data Minimization for Privacy-Preserving LLM Prompting

Jijie Zhou, Niloofar Mireshghallah, Tianshi Li

机构 * Northeastern University（东北大学）； Carnegie Mellon University（卡内基梅隆大学）

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

2510.01240 2025-10-03 cs.LG cs.CL 88%

RSAVQ: Riemannian Sensitivity-Aware Vector Quantization for Large Language Models

Zukang Xu, Xing Hu, Qiang Wu, Dawei Yang

机构 * Houmo AI

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

2509.11662 2025-10-01 cs.CV cs.AI cs.CL eess.IV 88%

MindVL: Towards Efficient and Effective Training of Multimodal Large Language Models on Ascend NPUs

Feilong Chen, Yijiang Liu, Yi Huang, Hao Wang, Miren Tian, Ya-Qi Yu, Minghui Liao, Jihao Wu

机构 * Huawei Technologies Co., Ltd.（华为技术有限公司）

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

1. 效率与部署 22368 篇

Basis Selection: Low-Rank Decomposition of Pretrained Large Language Models for Target Applications

Efficient Adaptive Rejection Sampling for Accelerating Speculative Decoding in Large Language Models

SASQ: Static Activation Scaling for Quantization-Aware Training in Large Language Models

Scaling and Transferability of Annealing Strategies in Large Language Model Training

R2Q: Towards Robust 2-Bit Large Language Models via Residual Refinement Quantization

A Systematic Study of Compression Ordering for Large Language Models

Anti-adversarial Learning: Desensitizing Prompts for Large Language Models

PIP: Perturbation-based Iterative Pruning for Large Language Models

CG-FedLLM: How to Compress Gradients in Federated Fune-tuning for Large Language Models

Scaling Open-Weight Large Language Models for Hydropower Regulatory Information Extraction: A Systematic Analysis

Pre-Attention Expert Prediction and Prefetching for Mixture-of-Experts Large Language Models

Prudential Reliability of Large Language Models in Reinsurance: Governance, Assurance, and Capital Efficiency

Comparative Analysis of Large Language Models for the Machine-Assisted Resolution of User Intentions

MuonAll: Muon Variant for Efficient Finetuning of Large Language Models

Iterative Layer-wise Distillation for Efficient Compression of Large Language Models

Activation-Informed Merging of Large Language Models

Decoding Emergent Big Five Traits in Large Language Models: Temperature-Dependent Expression and Architectural Clustering

The Structural Scalpel: Automated Contiguous Layer Pruning for Large Language Models

R-SFLLM: Jamming Resilient Framework for Split Federated Learning with Large Language Models

EchoAtt: Attend, Copy, then Adjust for More Efficient Large Language Models

LocalGPT: Benchmarking and Advancing Large Language Models for Local Life Services in Meituan

FALCON: Fine-grained Activation Manipulation by Contrastive Orthogonal Unalignment for Large Language Model

Exploring Data-Efficient Adaptation of Large Language Models for Code Generation

Contextual Attention Modulation: Towards Efficient Multi-Task Adaptation in Large Language Models

Tequila: Trapping-free Ternary Quantization for Large Language Models

Fine-Tuning Small Language Models for Domain-Specific AI: An Edge AI Perspective

Enhancing GraphQL Security by Detecting Malicious Queries Using Large Language Models, Sentence Transformers, and Convolutional Neural Networks

Operationalizing Data Minimization for Privacy-Preserving LLM Prompting

RSAVQ: Riemannian Sensitivity-Aware Vector Quantization for Large Language Models

MindVL: Towards Efficient and Effective Training of Multimodal Large Language Models on Ascend NPUs