语言大模型 / LLM - arXivDaily 专题

2505.23807 2025-06-04 cs.CL cs.AI 90%

DLP: Dynamic Layerwise Pruning in Large Language Models

Yuli Chen, Bo Cheng, Jiale Han, Yingying Zhang, Yingting Li, Shuhao Zhang

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

Comments Accepted by ICML 2025

2502.20727 2025-06-03 cs.DC cs.AI cs.LG 90%

SPD: Sync-Point Drop for Efficient Tensor Parallelism of Large Language Models

Han-Byul Kim, Duc Hoang, Arnav Kundu, Mohammad Samragh, Minsik Cho

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 International Conference on Machine Learning (ICML) 2025

2502.19726 2025-06-03 cs.LG cs.CL 90%

Tokens for Learning, Tokens for Unlearning: Mitigating Membership Inference Attacks in Large Language Models via Dual-Purpose Training

Toan Tran, Ruixuan Liu, Li Xiong

机构 * Emory University（埃默里大学）

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 ACL'25 (Findings)

2502.11256 2025-05-30 cs.LG cs.AR cs.CL 90%

Unveiling Environmental Impacts of Large Language Model Serving: A Functional Unit View

Yanran Wu, Inez Hua, Yi Ding

机构 * Purdue University（普渡大学）

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 17 pages, 38 figures, Proceedings of the The 63rd Annual Meeting of the Association for Computational Linguistics, Vienna, Austria, July 27-August 1st, 2025

2505.21670 2025-05-29 cs.CL cs.AI 90%

Rethinking the Outlier Distribution in Large Language Models: An In-depth Study

Rahul Raman, Khushi Sharma, Sai Qian Zhang

机构 * New York University（纽约大学）

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.AI

2505.19893 2025-05-27 cs.LG cs.CL 90%

ESLM: Risk-Averse Selective Language Modeling for Efficient Pretraining

Melis Ilayda Bal, Volkan Cevher, Michael Muehlebach

机构 * Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）； LIONS, EPFL（EPFL 系统研究所）； AGI Foundations, Amazon（人工智能基础，亚马逊）

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

2505.19128 2025-05-27 cs.CL cs.AI 90%

RetrieveAll: A Multilingual Named Entity Recognition Framework with Large Language Models

Jin Zhang, Fan Gao, Linyu Li, Yongbin Yu, Xiangxiang Wang, Nyima Tashi, Gadeng Luosang

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

2501.02009 2025-05-21 cs.CL cs.AI 90%

Cross-model Transferability among Large Language Models on the Platonic Representations of Concepts

Youcheng Huang, Chen Huang, Duanyu Feng, Wenqiang Lei, Jiancheng Lv

机构 * Sichuan University, China（四川大学）； Engineering Research Center of Machine Learning and Industry Intelligence, Ministry of Education, China（教育部机器学习与工业智能工程研究中心）

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

Comments ACL 2025 Main Camera Ready

2505.07903 2025-05-14 cs.CL cs.AI 90%

SEM: Reinforcement Learning for Search-Efficient Large Language Models

Zeyang Sha, Shiwen Cui, Weiqiang Wang

机构 * Ant Group（蚂蚁集团）

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

2505.07437 2025-05-13 cs.LG cs.AI cs.DB 90%

LEAD: Iterative Data Selection for Efficient LLM Instruction Tuning

Xiaotian Lin, Yanlin Qi, Yizhang Zhu, Themis Palpanas, Chengliang Chai, Nan Tang, Yuyu Luo

机构 * HKUST (GZ)（香港科技大学（广州））； Université Paris Cité（巴黎Cité大学）； BIT（北京理工大学）

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

2411.15100 2025-05-13 cs.CL cs.AI cs.PL 90%

XGrammar: Flexible and Efficient Structured Generation Engine for Large Language Models

Yixin Dong, Charlie F. Ruan, Yaxing Cai, Ruihang Lai, Ziyi Xu, Yilong Zhao, Tianqi Chen

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

Comments MLSys '25

2505.06297 2025-05-13 cs.LG cs.CL 90%

Lossless Compression of Large Language Model-Generated Text via Next-Token Prediction

Yu Mao, Holger Pirk, Chun Jason Xue

机构 * MBZUAI（穆扎布伊人工智能研究院）； Imperial College London（伦敦帝国理工学院）

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

2505.06267 2025-05-13 cs.SE cs.AI cs.LG 90%

AKD : Adversarial Knowledge Distillation For Large Language Models Alignment on Coding tasks

Ilyas Oulkadda, Julien Perez

机构 * Laboratoire de Recherche de l'EPITA (LRE)（EPITA研究实验室）； Department of XXX, University of YYY（YYY大学XXX系）； School of ZZZ, Institute of WWW（WWW研究所ZZZ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.AI、cs.LG

2410.09982 2025-05-13 cs.LG cs.CL 90%

Self-Data Distillation for Recovering Quality in Pruned Large Language Models

Vithursan Thangarasa, Ganesh Venkatesh, Mike Lasby, Nish Sinnadurai, Sean Lie

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

Comments Accepted to MLSys 2025. Main paper: 14 pp., 4 figs., 6 tabs.; Supplementary: 5 pp

2505.03804 2025-05-08 cs.LG cs.AI 90%

MoEQuant: Enhancing Quantization for Mixture-of-Experts Large Language Models via Expert-Balanced Sampling and Affinity Guidance

Xing Hu, Zhixuan Chen, Dawei Yang, Zukang Xu, Chen Xu, Zhihang Yuan, Sifan Zhou, Jiangyong Yu

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

2505.03756 2025-05-08 cs.AR cs.AI cs.LG cs.PF 90%

Improving the Serving Performance of Multi-LoRA Large Language Models via Efficient LoRA and KV Cache Management

Hang Zhang, Jiuchen Shi, Yixiao Wang, Quan Chen, Yizhou Shan, Minyi Guo

机构 * Shanghai Jiao Tong University（上海交通大学）

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

2504.20500 2025-04-30 cs.CL cs.LG 90%

UniDetox: Universal Detoxification of Large Language Models via Dataset Distillation

Huimin Lu, Masaru Isonuma, Junichiro Mori, Ichiro Sakata

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 at ICLR 2025 (poster)

2408.16073 2025-04-28 cs.CL cs.AI 90%

Using Large Language Models to Create AI Personas for Replication, Generalization and Prediction of Media Effects: An Empirical Test of 133 Published Experimental Research Findings

Leo Yeykelis, Kaavya Pichai, James J. Cummings, Byron Reeves

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

Comments 40 pages, 13 figures, 3 tables

2310.13561 2025-04-28 cs.CL cs.LG 90%

Cache & Distil: Optimising API Calls to Large Language Models

Guillem Ramírez, Matthias Lindemann, Alexandra Birch, Ivan Titov

机构 * ILCC, University of Edinburgh（ILCC、爱丁堡大学）； ILLC, University of Amsterdam（ILLC、阿姆斯特丹大学）

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

Journal ref Findings of the Association for Computational Linguistics: ACL 2024

2504.17674 2025-04-25 cs.CL cs.LG 90%

Energy Considerations of Large Language Model Inference and Efficiency Optimizations

Jared Fernandez, Clara Na, Vashisth Tiwari, Yonatan Bisk, Sasha Luccioni, Emma Strubell

机构 * Carnegie Mellon University（卡内基梅隆大学）； Hugging Face

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 16 pages

2504.09223 2025-04-15 cs.CV cs.AI cs.LG 90%

DL-QAT: Weight-Decomposed Low-Rank Quantization-Aware Training for Large Language Models

Wenjin Ke, Zhe Li, Dong Li, Lu Tian, Emad Barsoum

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

Journal ref https://aclanthology.org/2024.emnlp-industry.10/

2502.17189 2025-04-15 cs.LG cs.AI 90%

IGDA: Interactive Graph Discovery through Large Language Model Agents

Alex Havrilla, David Alvarez-Melis, Nicolo Fusi

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

2504.07624 2025-04-11 cs.CL cs.AI cs.IR 90%

ConceptFormer: Towards Efficient Use of Knowledge-Graph Embeddings in Large Language Models

Joel Barmettler, Abraham Bernstein, Luca Rossetto

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

2407.04752 2025-04-11 cs.LG cs.CL cs.NE 90%

SpikeLLM: Scaling up Spiking Neural Network to Large Language Models via Saliency-based Spiking

Xingrun Xing, Boyan Gao, Zheng Zhang, David A. Clifton, Shitao Xiao, Li Du, Guoqi Li, Jiajun Zhang

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

2504.04514 2025-04-10 cs.CL cs.AI 90%

Saliency-driven Dynamic Token Pruning for Large Language Models

Yao Tao, Yehui Tang, Yun Wang, Mingjian Zhu, Hailin Hu, Yunhe Wang

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

2504.02858 2025-04-07 cs.CL cs.LG 90%

Optimizing Humor Generation in Large Language Models: Temperature Configurations and Architectural Trade-offs

Evgenii Evstafev

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 10 pages, 4 figures

2503.24377 2025-04-01 cs.CL cs.AI 90%

Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models

Rui Wang, Hongru Wang, Boyang Xue, Jianhui Pang, Shudong Liu, Yi Chen, Jiahao Qiu, Derek Fai Wong, Heng Ji, Kam-Fai Wong

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

Comments In Progress; Paper list Repo: https://github.com/DevoAllen/Awesome-Reasoning-Economy-Papers

2503.24000 2025-04-01 cs.LG cs.AI 90%

Rethinking Key-Value Cache Compression Techniques for Large Language Model Serving

Wei Gao, Xinyu Zhou, Peng Sun, Tianwei Zhang, Yonggang Wen

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 21 pages, 18 figures, published to MLSys2025

2503.23924 2025-04-01 cs.CL cs.LG 90%

Model Hemorrhage and the Robustness Limits of Large Language Models

Ziyang Ma, Zuchao Li, Lefei Zhang, Gui-Song Xia, Bo Du, Liangpei Zhang, Dacheng Tao

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 33 pages, 18 figures

2503.19455 2025-03-26 cs.LG cs.AI 90%

Data-centric Federated Graph Learning with Large Language Models

Bo Yan, Zhongjian Zhang, Huabin Sun, Mengmei Zhang, Yang Cao, Chuan Shi

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 ongoing work

1. 效率与部署 22188 篇

DLP: Dynamic Layerwise Pruning in Large Language Models

SPD: Sync-Point Drop for Efficient Tensor Parallelism of Large Language Models

Tokens for Learning, Tokens for Unlearning: Mitigating Membership Inference Attacks in Large Language Models via Dual-Purpose Training

Unveiling Environmental Impacts of Large Language Model Serving: A Functional Unit View

Rethinking the Outlier Distribution in Large Language Models: An In-depth Study

ESLM: Risk-Averse Selective Language Modeling for Efficient Pretraining

RetrieveAll: A Multilingual Named Entity Recognition Framework with Large Language Models

Cross-model Transferability among Large Language Models on the Platonic Representations of Concepts

SEM: Reinforcement Learning for Search-Efficient Large Language Models

LEAD: Iterative Data Selection for Efficient LLM Instruction Tuning

XGrammar: Flexible and Efficient Structured Generation Engine for Large Language Models

Lossless Compression of Large Language Model-Generated Text via Next-Token Prediction

AKD : Adversarial Knowledge Distillation For Large Language Models Alignment on Coding tasks

Self-Data Distillation for Recovering Quality in Pruned Large Language Models

MoEQuant: Enhancing Quantization for Mixture-of-Experts Large Language Models via Expert-Balanced Sampling and Affinity Guidance

Improving the Serving Performance of Multi-LoRA Large Language Models via Efficient LoRA and KV Cache Management

UniDetox: Universal Detoxification of Large Language Models via Dataset Distillation

Using Large Language Models to Create AI Personas for Replication, Generalization and Prediction of Media Effects: An Empirical Test of 133 Published Experimental Research Findings

Cache & Distil: Optimising API Calls to Large Language Models

Energy Considerations of Large Language Model Inference and Efficiency Optimizations

DL-QAT: Weight-Decomposed Low-Rank Quantization-Aware Training for Large Language Models

IGDA: Interactive Graph Discovery through Large Language Model Agents

ConceptFormer: Towards Efficient Use of Knowledge-Graph Embeddings in Large Language Models

SpikeLLM: Scaling up Spiking Neural Network to Large Language Models via Saliency-based Spiking

Saliency-driven Dynamic Token Pruning for Large Language Models

Optimizing Humor Generation in Large Language Models: Temperature Configurations and Architectural Trade-offs

Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models

Rethinking Key-Value Cache Compression Techniques for Large Language Model Serving

Model Hemorrhage and the Robustness Limits of Large Language Models

Data-centric Federated Graph Learning with Large Language Models