语言大模型 / LLM - arXivDaily 专题

2504.11197 2025-04-17 cs.LG cs.AI cs.DC cs.IR 86%

Efficient Distributed Retrieval-Augmented Generation for Enhancing Language Model Performance

Shangyu Liu, Zhenzhe Zheng, Xiaoyao Huang, Fan Wu, Guihai Chen, Jie Wu

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

2504.07513 2025-04-11 cs.LG cs.AI cs.DC stat.ML 86%

GPT Carry-On: Training Foundation Model for Customization Could Be Simple, Scalable and Affordable

Jianqiao Wangni

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

2412.01380 2025-04-04 cs.LG cs.CL 86%

Efficient LLM Inference using Dynamic Input Pruning and Cache-Aware Masking

Marco Federici, Davide Belli, Mart van Baalen, Amir Jalalirad, Andrii Skliar, Bence Major, Markus Nagel, Paul Whatmough

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

Comments Main Text: 10 pages, 11 figures. Appendix: 6 pages, 3 figures

2503.22456 2025-04-01 cs.LG cs.AI 86%

Entropy-guided sequence weighting for efficient exploration in RL-based LLM fine-tuning

Abdullah Vanlioglu

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

2503.22562 2025-03-31 cs.LG cs.AI cs.DC 86%

Niyama : Breaking the Silos of LLM Inference Serving

Kanishk Goel, Jayashree Mohan, Nipun Kwatra, Ravi Shreyas Anupindi, Ramachandran Ramjee

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

2503.21807 2025-03-31 cs.LG cs.AI cs.MA 86%

LERO: LLM-driven Evolutionary framework with Hybrid Rewards and Enhanced Observation for Multi-Agent Reinforcement Learning

Yuan Wei, Xiaohan Shan, Jianmin Li

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

2410.10636 2025-03-25 cs.LG cs.AI 86%

Adapt-$\infty$: Scalable Continual Multimodal Instruction Tuning via Dynamic Data Selection

Adyasha Maharana, Jaehong Yoon, Tianlong Chen, Mohit Bansal

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

Comments First two authors contributed equally. Code: https://github.com/adymaharana/adapt-inf

2503.17500 2025-03-25 cs.LG cs.CL stat.ML 86%

Variance Control via Weight Rescaling in LLM Pre-training

Louis Owen, Abhay Kumar, Nilabhra Roy Chowdhury, Fabian Güra

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

2503.16530 2025-03-24 cs.CL cs.AI cs.IR 86%

Enhancing LLM Generation with Knowledge Hypergraph for Evidence-Based Medicine

Chengfeng Dou, Ying Zhang, Zhi Jin, Wenpin Jiao, Haiyan Zhao, Yongqiang Zhao, Zhengwei Tao

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

2502.08020 2025-03-20 cs.CL cs.AI 86%

Speculate, then Collaborate: Fusing Knowledge of Language Models during Decoding

Ziyao Wang, Muneeza Azmat, Ang Li, Raya Horesh, Mikhail Yurochkin

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

2410.11843 2025-03-20 cs.HC cs.AI cs.DB cs.LG 86%

From Commands to Prompts: LLM-based Semantic File System for AIOS

Zeru Shi, Kai Mei, Mingyu Jin, Yongye Su, Chaoji Zuo, Wenyue Hua, Wujiang Xu, Yujie Ren, Zirui Liu, Mengnan Du, Dong Deng, Yongfeng Zhang

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

Comments Accepted by International Conference on Learning Representations 2025(ICLR2025)

2503.10722 2025-03-17 cs.LG cs.AI 86%

TacticExpert: Spatial-Temporal Graph Language Model for Basketball Tactics

Xu Lingrui, Liu Mandi, Zhang Lei

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

2404.00242 2025-03-10 cs.CL cs.AI 86%

DeFT: Decoding with Flash Tree-attention for Efficient Tree-structured LLM Inference

Jinwei Yao, Kaiqi Chen, Kexun Zhang, Jiaxuan You, Binhang Yuan, Zeke Wang, Tao Lin

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

Comments Update DeFT-v4, accepted by ICLR'25 (https://openreview.net/forum?id=2c7pfOqu9k). Our code is available at https://github.com/LINs-lab/DeFT

2412.06860 2025-03-05 cs.LG cs.AI 86%

Balancing Efficiency and Effectiveness: An LLM-Infused Approach for Optimized CTR Prediction

Guoxiao Zhang, Yi Wei, Yadong Zhang, Huajian Feng, Qiang Liu

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

Comments 5 pages, 4 figures,4 tables

Journal ref WWW2025

2503.00392 2025-03-04 cs.LG cs.AI 86%

Progressive Sparse Attention: Algorithm and System Co-design for Efficient Attention in LLM Serving

Qihui Zhou, Peiqi Yin, Pengfei Zuo, James Cheng

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

Comments 12 pages, 6 figures

2502.18934 2025-03-03 cs.CL cs.LG 86%

Kanana: Compute-efficient Bilingual Language Models

Kanana LLM Team, Yunju Bak, Hojin Lee, Minho Ryu, Jiyeon Ham, Seungjae Jung, Daniel Wontae Nam, Taegyeong Eo, Donghun Lee, Doohae Jung, Boseop Kim, Nayeon Kim, Jaesun Park, Hyunho Kim, Hyunwoong Ko, Changmin Lee, Kyoung-Woon On, Seulye Baeg, Junrae Cho, Sunghee Jung, Jieun Kang, EungGyun Kim, Eunhwa Kim, Byeongil Ko, Daniel Lee, Minchul Lee, Miok Lee, Shinbok Lee, Gaeun Seo

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

Comments 40 pages, 15 figures

2410.13461 2025-02-28 cs.LG cs.CL 86%

Progressive Mixed-Precision Decoding for Efficient LLM Inference

Hao Mark Chen, Fuwen Tan, Alexandros Kouris, Royson Lee, Hongxiang Fan, Stylianos I. Venieris

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

2406.00034 2025-02-27 cs.CL cs.AI 86%

Adaptive Activation Steering: A Tuning-Free LLM Truthfulness Improvement Method for Diverse Hallucinations Categories

Tianlong Wang, Xianfeng Jiao, Yinghao Zhu, Zhongzhi Chen, Yifan He, Xu Chu, Junyi Gao, Yasha Wang, Liantao Ma

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

Comments ACM TheWebConf 2025 Conference (WWW 2025) Research Track

2502.16696 2025-02-25 cs.LG cs.AI 86%

Dynamic LLM Routing and Selection based on User Preferences: Balancing Performance, Cost, and Ethics

Deepak Babu Piskala, Vijay Raajaa, Sachin Mishra, Bruno Bozza

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

Journal ref International Journal of Computer Applications, Vol. 186, No. 51, November 2024, pp. 1-7

2502.15700 2025-02-25 cs.IR cs.AI cs.CL 86%

Sustainable Digitalization of Business with Multi-Agent RAG and LLM

Muhammad Arslan, Saba Munawar, Christophe Cruz

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

2502.13965 2025-02-20 cs.LG cs.AI cs.DC 86%

Autellix: An Efficient Serving Engine for LLM Agents as General Programs

Michael Luo, Xiaoxiang Shi, Colin Cai, Tianjun Zhang, Justin Wong, Yichuan Wang, Chi Wang, Yanping Huang, Zhifeng Chen, Joseph E. Gonzalez, Ion Stoica

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

2502.12494 2025-02-19 cs.LG cs.AI 86%

EDGE: Efficient Data Selection for LLM Agents via Guideline Effectiveness

Yunxiao Zhang, Guanming Xiong, Haochen Li, Wen Zhao

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

2407.11686 2025-02-18 cs.CL cs.AI 86%

CCoE: A Compact and Efficient LLM Framework with Multi-Expert Collaboration for Resource-Limited Settings

Shaomang Huang, Jianfeng Pan, Min Peng, Hanzhong Zheng

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

2502.10308 2025-02-17 cs.AI cs.GT cs.LG 86%

LLM-Powered Preference Elicitation in Combinatorial Assignment

Ermis Soumalias, Yanchen Jiang, Kehang Zhu, Michael Curry, Sven Seuken, David C. Parkes

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

2502.09497 2025-02-14 cs.CL cs.AI 86%

Improve LLM-based Automatic Essay Scoring with Linguistic Features

Zhaoyi Joey Hou, Alejandro Ciuba, Xiang Lorraine Li

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

Comments To be published in the workshop Innovation and Responsibility in AI-Supported Education (iRaise) at the 2025 Conference on Artificial Intelligence (AAAI)

2502.09175 2025-02-14 cs.CR cs.AI cs.CL 86%

FLAME: Flexible LLM-Assisted Moderation Engine

Ivan Bakulin, Ilia Kopanichuk, Iaroslav Bespalov, Nikita Radchenko, Vladimir Shaposhnikov, Dmitry Dylov, Ivan Oseledets

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

2502.06111 2025-02-13 cs.SE cs.AI cs.LG 86%

CSR-Bench: Benchmarking LLM Agents in Deployment of Computer Science Research Repositories

Yijia Xiao, Runhui Wang, Luyang Kong, Davor Golac, Wei Wang

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

2411.13045 2025-02-11 cs.IR cs.AI cs.CL 86%

Explainable LLM-driven Multi-dimensional Distillation for E-Commerce Relevance Learning

Gang Zhao, Ximing Zhang, Chenji Lu, Hui Zhao, Tianshu Wu, Pengjie Wang, Jian Xu, Bo Zheng

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

Comments Accepted by WWW 2025 oral

2501.16368 2025-02-06 cs.LG cs.AI cs.SY eess.SY 86%

Foundation Models for CPS-IoT: Opportunities and Challenges

Ozan Baris, Yizhuo Chen, Gaofeng Dong, Liying Han, Tomoyoshi Kimura, Pengrui Quan, Ruijie Wang, Tianchen Wang, Tarek Abdelzaher, Mario Bergés, Paul Pu Liang, Mani Srivastava

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

2502.02199 2025-02-05 cs.CL cs.CE cs.LG q-fin.CP 86%

When Dimensionality Hurts: The Role of LLM Embedding Compression for Noisy Regression Tasks

Felix Drinkall, Janet B. Pierrehumbert, Stefan Zohren

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

1. 效率与部署 22280 篇

Efficient Distributed Retrieval-Augmented Generation for Enhancing Language Model Performance

GPT Carry-On: Training Foundation Model for Customization Could Be Simple, Scalable and Affordable

Efficient LLM Inference using Dynamic Input Pruning and Cache-Aware Masking

Entropy-guided sequence weighting for efficient exploration in RL-based LLM fine-tuning

Niyama : Breaking the Silos of LLM Inference Serving

LERO: LLM-driven Evolutionary framework with Hybrid Rewards and Enhanced Observation for Multi-Agent Reinforcement Learning

Adapt-$\infty$: Scalable Continual Multimodal Instruction Tuning via Dynamic Data Selection

Variance Control via Weight Rescaling in LLM Pre-training

Enhancing LLM Generation with Knowledge Hypergraph for Evidence-Based Medicine

Speculate, then Collaborate: Fusing Knowledge of Language Models during Decoding

From Commands to Prompts: LLM-based Semantic File System for AIOS

TacticExpert: Spatial-Temporal Graph Language Model for Basketball Tactics

DeFT: Decoding with Flash Tree-attention for Efficient Tree-structured LLM Inference

Balancing Efficiency and Effectiveness: An LLM-Infused Approach for Optimized CTR Prediction

Progressive Sparse Attention: Algorithm and System Co-design for Efficient Attention in LLM Serving

Kanana: Compute-efficient Bilingual Language Models

Progressive Mixed-Precision Decoding for Efficient LLM Inference

Adaptive Activation Steering: A Tuning-Free LLM Truthfulness Improvement Method for Diverse Hallucinations Categories

Dynamic LLM Routing and Selection based on User Preferences: Balancing Performance, Cost, and Ethics

Sustainable Digitalization of Business with Multi-Agent RAG and LLM

Autellix: An Efficient Serving Engine for LLM Agents as General Programs

EDGE: Efficient Data Selection for LLM Agents via Guideline Effectiveness

CCoE: A Compact and Efficient LLM Framework with Multi-Expert Collaboration for Resource-Limited Settings

LLM-Powered Preference Elicitation in Combinatorial Assignment

Improve LLM-based Automatic Essay Scoring with Linguistic Features

FLAME: Flexible LLM-Assisted Moderation Engine

CSR-Bench: Benchmarking LLM Agents in Deployment of Computer Science Research Repositories

Explainable LLM-driven Multi-dimensional Distillation for E-Commerce Relevance Learning

Foundation Models for CPS-IoT: Opportunities and Challenges

When Dimensionality Hurts: The Role of LLM Embedding Compression for Noisy Regression Tasks