语言大模型 / LLM - arXivDaily 专题

2410.11331 2025-06-23 cs.CL cs.CV cs.LG 87%

SHAKTI: A 2.5 Billion Parameter Small Language Model Optimized for Edge AI and Low-Resource Environments

Syed Abdul Gaffar Shakhadri, Kruthika KR, Rakshit Aralimatti

机构 * SandLogic Technologies Pvt Ltd（沙逻辑技术私人有限公司）

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

Comments Paper in pdf format is 11 pages and contains 4 tables

2505.12268 2025-06-06 cs.CL cs.LG 87%

$K$-MSHC: Unmasking Minimally Sufficient Head Circuits in Large Language Models with Experiments on Syntactic Classification Tasks

Pratim Chowdhary, Peter Chin, Deepernab Chakrabarty

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

2502.04563 2025-06-02 cs.LG cs.AI cs.AR cs.DC cs.ET 87%

WaferLLM: Large Language Model Inference at Wafer Scale

Congjie He, Yeqi Huang, Pei Mu, Ziming Miao, Jilong Xue, Lingxiao Ma, Fan Yang, Luo Mai

机构 * University of Edinburgh（爱丁堡大学）； Microsoft Research（微软研究院）

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

2505.13547 2025-05-21 cs.LG cs.AI 87%

Exploring Federated Pruning for Large Language Models

Pengxin Guo, Yinong Wang, Wei Li, Mengting Liu, Ming Li, Jinkai Zheng, Liangqiong Qu

机构 * The University of Hong Kong（香港大学）； Southern University of Science and Technology（南方科技大学）； Sun Yat-sen University（中山大学）； Guangming Laboratory（光明实验室）； Hangzhou Dianzi University（杭州电子科技大学）

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

2505.07858 2025-05-14 cs.CL cs.AI 87%

Scaling Laws for Speculative Decoding

Siyuan Yan, Mo Zhu, Guo-qing Jiang, Jianfei Wang, Jiaxing Chen, Wentai Zhang, Xiang Liao, Xiao Cui, Chen Zhang, Zhuoran Song, Ran Zhu

机构 * Red Note Hi-Lab（红笔记高研实验室）； Shanghai Jiaotong University（上海交通大学）； Nanjing University（南京大学）； Zhejiang University（浙江大学）； Chinese University of Hong Kong（香港中文大学）

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

Comments 17 pages, 8 figures

2412.01129 2025-03-31 cs.LG cs.AI 87%

RILQ: Rank-Insensitive LoRA-based Quantization Error Compensation for Boosting 2-bit Large Language Model Accuracy

Geonho Lee, Janghwan Lee, Sukjin Hong, Minsoo Kim, Euijai Ahn, Du-Seong Chang, Jungwook Choi

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

Comments Accepted at AAAI 2025

2501.15405 2025-03-26 cs.CL cs.AI 87%

Semantic Layered Embedding Diffusion in Large Language Models for Multi-Contextual Consistency

Irin Kabakum, Thomas Montgomery, Daniel Ravenwood, Genevieve Harrington

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

Comments arXiv admin note: This paper has been withdrawn by arXiv due to disputed and unverifiable authorship

2501.18980 2025-02-03 cs.LG cs.AI 87%

Symmetric Pruning of Large Language Models

Kai Yi, Peter Richtárik

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

2412.01447 2024-12-03 cs.CL cs.AI 87%

PLD+: Accelerating LLM inference by leveraging Language Model Artifacts

Shwetha Somasundaram, Anirudh Phukan, Apoorv Saxena

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

2411.02359 2024-11-05 cs.RO cs.AI cs.LG 87%

DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution

Yang Yue, Yulin Wang, Bingyi Kang, Yizeng Han, Shenzhi Wang, Shiji Song, Jiashi Feng, Gao Huang

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

Comments 25 pages, 6 figures, NeurIPS 2024

2410.11905 2024-10-17 cs.AI cs.LG 87%

A Scalable Communication Protocol for Networks of Large Language Models

Samuele Marro, Emanuele La Malfa, Jesse Wright, Guohao Li, Nigel Shadbolt, Michael Wooldridge, Philip Torr

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

2408.14866 2024-10-08 cs.CL cs.CR cs.LG 87%

Advancing Adversarial Suffix Transfer Learning on Aligned Large Language Models

Hongfu Liu, Yuxi Xie, Ye Wang, Michael Shieh

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

Comments Accepted to the EMNLP 2024

2406.12016 2024-10-07 cs.LG cs.CL 87%

Prefixing Attention Sinks can Mitigate Activation Outliers for Large Language Model Quantization

Seungwoo Son, Wonpyo Park, Woohyun Han, Kyuyeun Kim, Jaeho Lee

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

Comments EMNLP 2024 Main (Long)

2409.20149 2024-10-01 cs.CL cs.AI 87%

1 Trillion Token (1TT) Platform: A Novel Framework for Efficient Data Sharing and Compensation in Large Language Models

Chanjun Park, Hyunsoo Ha, Jihoo Kim, Yungi Kim, Dahyun Kim, Sukyung Lee, Seonghoon Yang

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

2407.03582 2024-07-08 cs.CL cs.AI 87%

Integrating Randomness in Large Language Models: A Linear Congruential Generator Approach for Generating Clinically Relevant Content

Andrew Bouras

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

2402.19361 2024-06-25 cs.LG cs.AI cs.CR 87%

Watermark Stealing in Large Language Models

Nikola Jovanović, Robin Staab, Martin Vechev

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

Comments ICML 2024

2403.00835 2024-06-14 cs.CL cs.AI 87%

CLLMs: Consistency Large Language Models

Siqi Kou, Lanxiang Hu, Zhezhi He, Zhijie Deng, Hao Zhang

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

Comments In the proceedings of the 41st International Conference on Machine Learning (ICML) 2024

2404.01306 2024-06-06 cs.LG cs.CL 87%

NeuroPrune: A Neuro-inspired Topological Sparse Training Algorithm for Large Language Models

Amit Dhurandhar, Tejaswini Pedapati, Ronny Luss, Soham Dan, Aurelie Lozano, Payel Das, Georgios Kollias

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

Comments Accepted at ACL 2024

2401.00588 2024-06-06 cs.AI cs.LG cs.PF 87%

Fairness in Serving Large Language Models

Ying Sheng, Shiyi Cao, Dacheng Li, Banghua Zhu, Zhuohan Li, Danyang Zhuo, Joseph E. Gonzalez, Ion Stoica

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

2404.08801 2024-04-17 cs.LG cs.CL 87%

Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length

Xuezhe Ma, Xiaomeng Yang, Wenhan Xiong, Beidi Chen, Lili Yu, Hao Zhang, Jonathan May, Luke Zettlemoyer, Omer Levy, Chunting Zhou

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

Comments 9 pages, 6 figures and 8 tables

2401.06829 2024-04-10 cs.CL cs.AI 87%

Cross-Attention Watermarking of Large Language Models

Folco Bertini Baldassini, Huy H. Nguyen, Ching-Chung Chang, Isao Echizen

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

Comments 5 pages, 3 figures. Accepted to ICASSP 2024

2311.07311 2023-11-14 cs.CL cs.AI 87%

Do large language models and humans have similar behaviors in causal inference with script knowledge?

Xudong Hong, Margarita Ryzhova, Daniel Adrian Biondi, Vera Demberg

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

Comments 15 pages, 3 figures

2310.15594 2023-10-25 cs.CL cs.AI 87%

Retrieval-based Knowledge Transfer: An Effective Approach for Extreme Large Language Model Compression

Jiduan Liu, Jiahao Liu, Qifan Wang, Jingang Wang, Xunliang Cai, Dongyan Zhao, Ran Lucien Wang, Rui Yan

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

Comments EMNLP 2023 Findings

2307.09702 2023-08-22 cs.CL cs.LG 87%

Efficient Guided Generation for Large Language Models

Brandon T. Willard, Rémi Louf

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

2306.06662 2023-06-14 cs.CL cs.AI 87%

EaSyGuide : ESG Issue Identification Framework leveraging Abilities of Generative Large Language Models

Hanwool Lee, Jonghyun Choi, Sohyeon Kwon, Sungbum Jung

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

Comments Accepted at The IJCAI-2023 Workshop On Financial Technology and Natural Language Processing (FinNLP)

2305.18679 2023-06-05 cs.CL cs.LG 87%

KEYword based Sampling (KEYS) for Large Language Models

Jyothir S, Zuhaib Akhtar

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

2304.04616 2023-04-11 cs.CL cs.AI 87%

Automated Reading Passage Generation with OpenAI's Large Language Model

Ummugul Bezirhan, Matthias von Davier

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

2203.07259 2022-10-19 cs.CL cs.LG 87%

The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models

Eldar Kurtic, Daniel Campos, Tuan Nguyen, Elias Frantar, Mark Kurtz, Benjamin Fineran, Michael Goin, Dan Alistarh

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

Comments Accepted to EMNLP 2022

2202.04728 2022-02-11 cs.LG cs.CL 87%

Predicting Human Similarity Judgments Using Large Language Models

Raja Marjieh, Ilia Sucholutsky, Theodore R. Sumers, Nori Jacoby, Thomas L. Griffiths

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

Comments 7 pages, 6 figures

2101.08890 2021-01-25 cs.CL cs.AI 87%

Distilling Large Language Models into Tiny and Effective Students using pQRNN

Prabhu Kaliamoorthi, Aditya Siddhant, Edward Li, Melvin Johnson

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

1. 效率与部署 22280 篇

SHAKTI: A 2.5 Billion Parameter Small Language Model Optimized for Edge AI and Low-Resource Environments

$K$-MSHC: Unmasking Minimally Sufficient Head Circuits in Large Language Models with Experiments on Syntactic Classification Tasks

WaferLLM: Large Language Model Inference at Wafer Scale

Exploring Federated Pruning for Large Language Models

Scaling Laws for Speculative Decoding

RILQ: Rank-Insensitive LoRA-based Quantization Error Compensation for Boosting 2-bit Large Language Model Accuracy

Semantic Layered Embedding Diffusion in Large Language Models for Multi-Contextual Consistency

Symmetric Pruning of Large Language Models

PLD+: Accelerating LLM inference by leveraging Language Model Artifacts

DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution

A Scalable Communication Protocol for Networks of Large Language Models

Advancing Adversarial Suffix Transfer Learning on Aligned Large Language Models

Prefixing Attention Sinks can Mitigate Activation Outliers for Large Language Model Quantization

1 Trillion Token (1TT) Platform: A Novel Framework for Efficient Data Sharing and Compensation in Large Language Models

Integrating Randomness in Large Language Models: A Linear Congruential Generator Approach for Generating Clinically Relevant Content

Watermark Stealing in Large Language Models

CLLMs: Consistency Large Language Models

NeuroPrune: A Neuro-inspired Topological Sparse Training Algorithm for Large Language Models

Fairness in Serving Large Language Models

Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length

Cross-Attention Watermarking of Large Language Models

Do large language models and humans have similar behaviors in causal inference with script knowledge?

Retrieval-based Knowledge Transfer: An Effective Approach for Extreme Large Language Model Compression

Efficient Guided Generation for Large Language Models

EaSyGuide : ESG Issue Identification Framework leveraging Abilities of Generative Large Language Models

KEYword based Sampling (KEYS) for Large Language Models

Automated Reading Passage Generation with OpenAI's Large Language Model

The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models

Predicting Human Similarity Judgments Using Large Language Models

Distilling Large Language Models into Tiny and Effective Students using pQRNN