语言大模型 / LLM - arXivDaily 专题

2409.13761 2024-10-22 cs.CL cs.AI 90%

Do Large Language Models Need a Content Delivery Network?

Yihua Cheng, Kuntai Du, Jiayi Yao, 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.CL、cs.AI

2410.10850 2024-10-18 cs.CL cs.AI cs.CY cs.HC 90%

On the Reliability of Large Language Models to Misinformed and Demographically-Informed Prompts

Toluwani Aremu, Oluwakemi Akinwehinmi, Chukwuemeka Nwagu, Syed Ishtiaque Ahmed, Rita Orji, Pedro Arnau Del Amo, Abdulmotaleb El Saddik

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 Study conducted between August and December 2023. Under review at AAAI-AI Magazine. Submitted for archival purposes only

2410.12153 2024-10-17 cs.CL cs.AI 90%

Layer-of-Thoughts Prompting (LoT): Leveraging LLM-Based Retrieval with Constraint Hierarchies

Wachara Fungwacharakorn, Nguyen Ha Thanh, May Myo Zin, Ken Satoh

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

Comments Presented at NeLaMKRR@KR, 2024 (arXiv:2410.05339)

2402.10052 2024-10-17 cs.CL cs.AI 90%

UNDIAL: Self-Distillation with Adjusted Logits for Robust Unlearning in Large Language Models

Yijiang River Dong, Hongzhou Lin, Mikhail Belkin, Ramon Huerta, Ivan Vulić

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

2402.11187 2024-10-16 cs.CL cs.AI 90%

LaCo: Large Language Model Pruning via Layer Collapse

Yifei Yang, Zouying Cao, Hai Zhao

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 Accepted as Findings of EMNLP2024

2410.09428 2024-10-15 cs.AI cs.CL 90%

Declarative Knowledge Distillation from Large Language Models for Visual Question Answering Datasets

Thomas Eiter, Jan Hadl, Nelson Higuera, Johannes Oetsch

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 Presented at NeLaMKRR@KR, 2024 (arXiv:2410.05339)

2405.10853 2024-10-15 cs.LG cs.AI cs.DC 90%

The Future of Large Language Model Pre-training is Federated

Lorenzo Sani, Alex Iacob, Zeyu Cao, Bill Marino, Yan Gao, Tomas Paulik, Wanru Zhao, William F. Shen, Preslav Aleksandrov, Xinchi Qiu, Nicholas D. Lane

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 24 pages, 15 figures, pre-print

2410.06392 2024-10-10 cs.CL cs.LG 90%

Counterfactual Causal Inference in Natural Language with Large Language Models

Gaël Gendron, Jože M. Rožanec, Michael Witbrock, Gillian Dobbie

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 22 pages, 10 pages for the main paper, 12 pages for the references and appendix, 5 figures

2405.08755 2024-10-10 cs.CR cs.AI cs.LG 90%

Distributed Threat Intelligence at the Edge Devices: A Large Language Model-Driven Approach

Syed Mhamudul Hasan, Alaa M. Alotaibi, Sajedul Talukder, Abdur R. Shahid

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

Journal ref 2024 IEEE 48th Annual Computers, Software, and Applications Conference (COMPSAC)

2410.01174 2024-10-03 cs.CL cs.AI 90%

Towards Inference-time Category-wise Safety Steering for Large Language Models

Amrita Bhattacharjee, Shaona Ghosh, Traian Rebedea, Christopher Parisien

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

2410.00387 2024-10-02 cs.CL cs.AI 90%

Boosting the Capabilities of Compact Models in Low-Data Contexts with Large Language Models and Retrieval-Augmented Generation

Bhargav Shandilya, Alexis Palmer

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 13 pages, 1 figure, 5 tables, submitted to COLING 2025

2403.19181 2024-09-30 cs.IR cs.CL cs.LG 90%

Make Large Language Model a Better Ranker

Wen-Shuo Chao, Zhi Zheng, Hengshu Zhu, Hao Liu

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 12 pages, 5 figures

2409.05902 2024-09-25 cs.LG cs.AR cs.CL 90%

OPAL: Outlier-Preserved Microscaling Quantization Accelerator for Generative Large Language Models

Jahyun Koo, Dahoon Park, Sangwoo Jung, Jaeha Kung

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 7 pages, 8 figures, DAC2024 accepted

2409.14381 2024-09-24 cs.CL cs.LG 90%

Investigating Layer Importance in Large Language Models

Yang Zhang, Yanfei Dong, Kenji Kawaguchi

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

2409.13693 2024-09-24 cs.FL cs.AI cs.CL cs.ET cs.HC 90%

Declarative Integration and Management of Large Language Models through Finite Automata: Application to Automation, Communication, and Ethics

Thierry Petit, Arnault Pachot, Claire Conan-Vrinat, Alexandre Dubarry

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 Submitted to IAAI-2025, Philadelphia, PA

2409.09040 2024-09-17 cs.HC cs.AI cs.CL 90%

ChatSUMO: Large Language Model for Automating Traffic Scenario Generation in Simulation of Urban MObility

Shuyang Li, Talha Azfar, Ruimin Ke

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

2401.03426 2024-09-13 cs.CL cs.AI 90%

On Leveraging Large Language Models for Enhancing Entity Resolution: A Cost-efficient Approach

Huahang Li, Longyu Feng, Shuangyin Li, Fei Hao, Chen Jason Zhang, Yuanfeng Song

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 9 pages, preprint under review

2401.06118 2024-09-12 cs.LG cs.CL 90%

Extreme Compression of Large Language Models via Additive Quantization

Vage Egiazarian, Andrei Panferov, Denis Kuznedelev, Elias Frantar, Artem Babenko, Dan Alistarh

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 ICML, 2024

2312.12391 2024-09-11 cs.LG cs.AI cs.AR 90%

vTrain: A Simulation Framework for Evaluating Cost-effective and Compute-optimal Large Language Model Training

Jehyeon Bang, Yujeong Choi, Myeongwoo Kim, Yongdeok Kim, Minsoo Rhu

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

2409.04833 2024-09-10 cs.CL cs.AI 90%

Achieving Peak Performance for Large Language Models: A Systematic Review

Zhyar Rzgar K Rostam, Sándor Szénási, Gábor Kertész

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 34 pages, 7 figures, 8 tables. Journal Article: IEEE Access

Journal ref IEEE Access (2024) 96017-96050;

2409.04073 2024-09-10 cs.CL cs.AI cs.DB 90%

AnyMatch -- Efficient Zero-Shot Entity Matching with a Small Language Model

Zeyu Zhang, Paul Groth, Iacer Calixto, Sebastian Schelter

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.CL、cs.AI

Comments 12 pages excluding references, 3 figures, and 5 tables

2402.19465 2024-09-04 cs.CL cs.AI 90%

Towards Tracing Trustworthiness Dynamics: Revisiting Pre-training Period of Large Language Models

Chen Qian, Jie Zhang, Wei Yao, Dongrui Liu, Zhenfei Yin, Yu Qiao, Yong Liu, Jing Shao

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 at ACL 2024

2406.10260 2024-08-29 cs.CL cs.LG 90%

Flextron: Many-in-One Flexible Large Language Model

Ruisi Cai, Saurav Muralidharan, Greg Heinrich, Hongxu Yin, Zhangyang Wang, Jan Kautz, Pavlo Molchanov

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

2408.11393 2024-08-22 cs.CL cs.LG 90%

First Activations Matter: Training-Free Methods for Dynamic Activation in Large Language Models

Chi Ma, Mincong Huang, Ying Zhang, Chao Wang, Yujie Wang, Lei Yu, Chuan Liu, Wei Lin

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

2407.12021 2024-08-20 cs.CL cs.AI 90%

Adaptive Draft-Verification for Efficient Large Language Model Decoding

Xukun Liu, Bowen Lei, Ruqi Zhang, Dongkuan Xu

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 Under review of Neurips 2024

2408.04140 2024-08-09 cs.CL cs.AI 90%

UNLEARN Efficient Removal of Knowledge in Large Language Models

Tyler Lizzo, Larry Heck

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 11 pages, 2 Figures

2311.08640 2024-08-06 cs.CL cs.LG 90%

Multistage Collaborative Knowledge Distillation from a Large Language Model for Semi-Supervised Sequence Generation

Jiachen Zhao, Wenlong Zhao, Andrew Drozdov, Benjamin Rozonoyer, Md Arafat Sultan, Jay-Yoon Lee, Mohit Iyyer, Andrew McCallum

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 2024

2408.01050 2024-08-05 cs.SE cs.CL cs.LG 90%

The Impact of Hyperparameters on Large Language Model Inference Performance: An Evaluation of vLLM and HuggingFace Pipelines

Matias Martinez

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

2407.20503 2024-07-31 cs.LG cs.AI 90%

A federated large language model for long-term time series forecasting

Raed Abdel-Sater, A. Ben Hamza

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

2407.19947 2024-07-30 cs.CL cs.LG 90%

Inference acceleration for large language models using "stairs" assisted greedy generation

Domas Grigaliūnas, Mantas Lukoševičius

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 the 29th International Conference on Information Society and University Studies (IVUS 2024)

1. 效率与部署 22368 篇

Do Large Language Models Need a Content Delivery Network?

On the Reliability of Large Language Models to Misinformed and Demographically-Informed Prompts

Layer-of-Thoughts Prompting (LoT): Leveraging LLM-Based Retrieval with Constraint Hierarchies

UNDIAL: Self-Distillation with Adjusted Logits for Robust Unlearning in Large Language Models

LaCo: Large Language Model Pruning via Layer Collapse

Declarative Knowledge Distillation from Large Language Models for Visual Question Answering Datasets

The Future of Large Language Model Pre-training is Federated

Counterfactual Causal Inference in Natural Language with Large Language Models

Distributed Threat Intelligence at the Edge Devices: A Large Language Model-Driven Approach

Towards Inference-time Category-wise Safety Steering for Large Language Models

Boosting the Capabilities of Compact Models in Low-Data Contexts with Large Language Models and Retrieval-Augmented Generation

Make Large Language Model a Better Ranker

OPAL: Outlier-Preserved Microscaling Quantization Accelerator for Generative Large Language Models

Investigating Layer Importance in Large Language Models

Declarative Integration and Management of Large Language Models through Finite Automata: Application to Automation, Communication, and Ethics

ChatSUMO: Large Language Model for Automating Traffic Scenario Generation in Simulation of Urban MObility

On Leveraging Large Language Models for Enhancing Entity Resolution: A Cost-efficient Approach

Extreme Compression of Large Language Models via Additive Quantization

vTrain: A Simulation Framework for Evaluating Cost-effective and Compute-optimal Large Language Model Training

Achieving Peak Performance for Large Language Models: A Systematic Review

AnyMatch -- Efficient Zero-Shot Entity Matching with a Small Language Model

Towards Tracing Trustworthiness Dynamics: Revisiting Pre-training Period of Large Language Models

Flextron: Many-in-One Flexible Large Language Model

First Activations Matter: Training-Free Methods for Dynamic Activation in Large Language Models

Adaptive Draft-Verification for Efficient Large Language Model Decoding

UNLEARN Efficient Removal of Knowledge in Large Language Models

Multistage Collaborative Knowledge Distillation from a Large Language Model for Semi-Supervised Sequence Generation

The Impact of Hyperparameters on Large Language Model Inference Performance: An Evaluation of vLLM and HuggingFace Pipelines

A federated large language model for long-term time series forecasting

Inference acceleration for large language models using "stairs" assisted greedy generation