语言大模型 / LLM - arXivDaily 专题

2505.07239 2025-05-13 cs.CR cs.AI 89%

Comet: Accelerating Private Inference for Large Language Model by Predicting Activation Sparsity

Guang Yan, Yuhui Zhang, Zimu Guo, Lutan Zhao, Xiaojun Chen, Chen Wang, Wenhao Wang, Dan Meng, Rui Hou

机构 * State Key Laboratory of Cyberspace Security Defense, Institute of Information Engineering, CAS and University of Chinese Academy of Sciences（国家密码安全防御重点实验室，信息工程研究所，中国科学院及中国科学院大学）； EIRI, NELBDRC, Tsinghua University（EIRI，NELBDRC，清华大学）

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

Comments Accepted to SP 2025

2505.07105 2025-05-13 cs.IR cs.LG 89%

Knowledge Distillation for Enhancing Walmart E-commerce Search Relevance Using Large Language Models

Hongwei Shang, Nguyen Vo, Nitin Yadav, Tian Zhang, Ajit Puthenputhussery, Xunfan Cai, Shuyi Chen, Prijith Chandran, Changsung Kang

机构 * Walmart Global Tech（沃尔玛全球技术）

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

Comments 9 pages, published at WWWW'25

Journal ref The Web Conference 2025

2505.06803 2025-05-13 cs.SD cs.CL cs.CV cs.MM eess.AS 89%

Bridging Ears and Eyes: Analyzing Audio and Visual Large Language Models to Humans in Visible Sound Recognition and Reducing Their Sensory Gap via Cross-Modal Distillation

Xilin Jiang, Junkai Wu, Vishal Choudhari, Nima Mesgarani

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

2412.15247 2025-05-13 cs.CL cs.IR 89%

Streamlining Systematic Reviews: A Novel Application of Large Language Models

Fouad Trad, Ryan Yammine, Jana Charafeddine, Marlene Chakhtoura, Maya Rahme, Ghada El-Hajj Fuleihan, Ali Chehab

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

Journal ref BMC Medical Research Methodology, 2025

2505.04655 2025-05-09 cs.CL 89%

Integration of Large Language Models and Traditional Deep Learning for Social Determinants of Health Prediction

Paul Landes, Jimeng Sun, Adam Cross

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

2505.02489 2025-05-06 cs.AI cs.ET cs.MA cs.SE 89%

Beyond the model: Key differentiators in large language models and multi-agent services

Muskaan Goyal, Pranav Bhasin

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

Comments 4 pages

Journal ref World Journal of Advanced Research and Reviews, 2025, 26(01), 2703-2706

2505.01693 2025-05-06 cs.CL 89%

High-Fidelity Pseudo-label Generation by Large Language Models for Training Robust Radiology Report Classifiers

Brian Wong, Kaito Tanaka

机构 * SANNO University（SANNO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

2504.20348 2025-05-06 cs.PF cs.AI cs.SY eess.SY 89%

CarbonCall: Sustainability-Aware Function Calling for Large Language Models on Edge Devices

Varatheepan Paramanayakam, Andreas Karatzas, Iraklis Anagnostopoulos, Dimitrios Stamoulis

机构 * School of Electrical, Computer and Biomedical Engineering, Southern Illinois University, Carbondale, IL, U.S.A.（南方伊利诺伊大学电气、计算机与生物医学工程学院）； Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, TX, U.S.A.（德克萨斯大学奥斯汀分校电气与计算机工程系）

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

2504.19277 2025-04-29 cs.AI cs.SE 89%

Small Models, Big Tasks: An Exploratory Empirical Study on Small Language Models for Function Calling

Ishan Kavathekar, Raghav Donakanti, Ponnurangam Kumaraguru, Karthik Vaidhyanathan

机构 * IIIT-Hyderabad（IIIT- Hyderabad）

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

Comments Accepted at EASE 2025 AI Models and Data Evaluation track

2411.06251 2025-04-29 cs.AI 89%

Quasi-random Multi-Sample Inference for Large Language Models

Aditya Parashar, Aditya Vikram Singh, Avinash Amballa, Jinlin Lai, Benjamin Rozonoyer

机构 * College of Information & Computer Sciences, University of Massachusetts Amherst（信息与计算机科学学院，马萨诸塞大学阿默斯特分校）

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

2412.15921 2025-04-25 cs.SE cs.AI 89%

Less is More: Towards Green Code Large Language Models via Unified Structural Pruning

Guang Yang, Yu Zhou, Xiangyu Zhang, Wei Cheng, Ke Liu, Xiang Chen, Terry Yue Zhuo, Taolue Chen

机构 * Nanjing University of Aeronautics and Astronautics（南京航空航天大学）； Singapore Management University（新加坡国立管理学院）； National University of Defense Technology（国防科技大学）； Nantong University（南通大学）； Monash University and CSIRO’s Data61（莫纳什大学和CSIRO Data61）； Birkbeck, University of London（伦敦大学伯贝克学院）

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

Comments UNDER REVIEW

2504.15472 2025-04-23 cs.RO cs.LG cs.SY eess.SY 89%

LAPP: Large Language Model Feedback for Preference-Driven Reinforcement Learning

Pingcheng Jian, Xiao Wei, Yanbaihui Liu, Samuel A. Moore, Michael M. Zavlanos, Boyuan Chen

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

2504.13700 2025-04-21 cs.HC cs.AI 89%

Exploring Multimodal Prompt for Visualization Authoring with Large Language Models

Zhen Wen, Luoxuan Weng, Yinghao Tang, Runjin Zhang, Yuxin Liu, Bo Pan, Minfeng Zhu, Wei Chen

机构 * State Key Lab of CAD&CG, Zhejiang University（CAD与CG国家重点实验室，浙江大学）

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

Comments 11 pages, 8 figures

2406.10690 2025-04-18 cs.AI cs.DB 89%

Automating Pharmacovigilance Evidence Generation: Using Large Language Models to Produce Context-Aware SQL

Jeffery L. Painter, Venkateswara Rao Chalamalasetti, Raymond Kassekert, Andrew Bate

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 15 pages, 3 tables, 5 figures

2501.00750 2025-04-17 cs.AI 89%

Beyond Text: Implementing Multimodal Large Language Model-Powered Multi-Agent Systems Using a No-Code Platform

Cheonsu Jeong

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 22 pages, 27 figures

Journal ref 2025 Journal of Intelligence and Information Systems

2504.11514 2025-04-17 cs.AI cs.RO 89%

Enhancing Autonomous Driving Systems with On-Board Deployed Large Language Models

Nicolas Baumann, Cheng Hu, Paviththiren Sivasothilingam, Haotong Qin, Lei Xie, Michele Magno, Luca Benini

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

2309.15531 2025-04-15 cs.LG 89%

Rethinking Channel Dimensions to Isolate Outliers for Low-bit Weight Quantization of Large Language Models

Jung Hwan Heo, Jeonghoon Kim, Beomseok Kwon, Byeongwook Kim, Se Jung Kwon, Dongsoo Lee

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

Comments ICLR 2024

2504.08850 2025-04-15 cs.DC cs.AI 89%

SpecEE: Accelerating Large Language Model Inference with Speculative Early Exiting

Jiaming Xu, Jiayi Pan, Yongkang Zhou, Siming Chen, Jinhao Li, Yaoxiu Lian, Junyi Wu, Guohao Dai

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 Accepted by ISCA 2025

2409.20052 2025-04-14 cs.IR cs.AI 89%

Mitigating Propensity Bias of Large Language Models for Recommender Systems

Guixian Zhang, Guan Yuan, Debo Cheng, Lin Liu, Jiuyong Li, Shichao Zhang

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

2405.01814 2025-04-11 cs.LG cs.DC 89%

Efficient Heterogeneous Large Language Model Decoding with Model-Attention Disaggregation

Shaoyuan Chen, Wencong Xiao, Yutong Lin, Mingxing Zhang, Yingdi Shan, Jinlei Jiang, Kang Chen, Yongwei Wu

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

2504.04151 2025-04-08 cs.CL 89%

STEP: Staged Parameter-Efficient Pre-training for Large Language Models

Kazuki Yano, Takumi Ito, Jun Suzuki

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

Comments Accepted to NAACL 2025 Main

2406.19774 2025-04-08 cs.CL 89%

Direct Preference Knowledge Distillation for Large Language Models

Yixing Li, Yuxian Gu, Li Dong, Dequan Wang, Yu Cheng, Furu Wei

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

2504.03045 2025-04-07 cs.CL 89%

Extending CREAMT: Leveraging Large Language Models for Literary Translation Post-Editing

Antonio Castaldo, Sheila Castilho, Joss Moorkens, Johanna Monti

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

Comments to be published in the Proceedings of the 20th Machine Translation Summit (MT Summit 2025)

2501.08598 2025-04-07 cs.SE cs.AI 89%

LlamaRestTest: Effective REST API Testing with Small Language Models

Myeongsoo Kim, Saurabh Sinha, Alessandro Orso

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

Comments To be published in the ACM International Conference on the Foundations of Software Engineering (FSE 2025)

2405.16444 2025-04-07 cs.LG 89%

CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion

Jiayi Yao, Hanchen Li, Yuhan Liu, Siddhant Ray, Yihua Cheng, Qizheng Zhang, Kuntai Du, Shan Lu, Junchen Jiang

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

2407.09025 2025-04-03 cs.AI 89%

SpreadsheetLLM: Encoding Spreadsheets for Large Language Models

Haoyu Dong, Jianbo Zhao, Yuzhang Tian, Junyu Xiong, Shiyu Xia, Mengyu Zhou, Yun Lin, José Cambronero, Yeye He, Shi Han, Dongmei Zhang

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

2404.03275 2025-04-02 cs.RO cs.AI 89%

DELTA: Decomposed Efficient Long-Term Robot Task Planning using Large Language Models

Yuchen Liu, Luigi Palmieri, Sebastian Koch, Ilche Georgievski, Marco Aiello

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 Accepted at ICRA 2025

2406.12257 2025-03-28 cs.AI cs.CR 89%

CleanGen: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models

Yuetai Li, Zhangchen Xu, Fengqing Jiang, Luyao Niu, Dinuka Sahabandu, Bhaskar Ramasubramanian, Radha Poovendran

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 This paper is presented at EMNLP 2024

2503.21115 2025-03-28 cs.CL 89%

Leveraging Large Language Models for Risk Assessment in Hyperconnected Logistic Hub Network Deployment

Yinzhu Quan, Yujia Xu, Guanlin Chen, Frederick Benaben, Benoit Montreuil

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

2503.20103 2025-03-27 cs.CL 89%

Bigger But Not Better: Small Neural Language Models Outperform Large Language Models in Detection of Thought Disorder

Changye Li, Weizhe Xu, Serguei Pakhomov, Ellen Bradley, Dror Ben-Zeev, Trevor Cohen

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

Comments Accepted to CL Psych 2025 workshop, co-located with NAACL 2025

1. 效率与部署 22405 篇

Comet: Accelerating Private Inference for Large Language Model by Predicting Activation Sparsity

Knowledge Distillation for Enhancing Walmart E-commerce Search Relevance Using Large Language Models

Bridging Ears and Eyes: Analyzing Audio and Visual Large Language Models to Humans in Visible Sound Recognition and Reducing Their Sensory Gap via Cross-Modal Distillation

Streamlining Systematic Reviews: A Novel Application of Large Language Models

Integration of Large Language Models and Traditional Deep Learning for Social Determinants of Health Prediction

Beyond the model: Key differentiators in large language models and multi-agent services

High-Fidelity Pseudo-label Generation by Large Language Models for Training Robust Radiology Report Classifiers

CarbonCall: Sustainability-Aware Function Calling for Large Language Models on Edge Devices

Small Models, Big Tasks: An Exploratory Empirical Study on Small Language Models for Function Calling

Quasi-random Multi-Sample Inference for Large Language Models

Less is More: Towards Green Code Large Language Models via Unified Structural Pruning

LAPP: Large Language Model Feedback for Preference-Driven Reinforcement Learning

Exploring Multimodal Prompt for Visualization Authoring with Large Language Models

Automating Pharmacovigilance Evidence Generation: Using Large Language Models to Produce Context-Aware SQL

Beyond Text: Implementing Multimodal Large Language Model-Powered Multi-Agent Systems Using a No-Code Platform

Enhancing Autonomous Driving Systems with On-Board Deployed Large Language Models

Rethinking Channel Dimensions to Isolate Outliers for Low-bit Weight Quantization of Large Language Models

SpecEE: Accelerating Large Language Model Inference with Speculative Early Exiting

Mitigating Propensity Bias of Large Language Models for Recommender Systems

Efficient Heterogeneous Large Language Model Decoding with Model-Attention Disaggregation

STEP: Staged Parameter-Efficient Pre-training for Large Language Models

Direct Preference Knowledge Distillation for Large Language Models

Extending CREAMT: Leveraging Large Language Models for Literary Translation Post-Editing

LlamaRestTest: Effective REST API Testing with Small Language Models

CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion

SpreadsheetLLM: Encoding Spreadsheets for Large Language Models

DELTA: Decomposed Efficient Long-Term Robot Task Planning using Large Language Models

CleanGen: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models

Leveraging Large Language Models for Risk Assessment in Hyperconnected Logistic Hub Network Deployment

Bigger But Not Better: Small Neural Language Models Outperform Large Language Models in Detection of Thought Disorder