语言大模型 / LLM - arXivDaily 专题

2410.20299 2025-02-17 cs.DC 87%

EACO-RAG: Towards Distributed Tiered LLM Deployment using Edge-Assisted and Collaborative RAG with Adaptive Knowledge Update

Jiaxing Li, Chi Xu, Lianchen Jia, Feng Wang, Cong Zhang, Jiangchuan Liu

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

2502.02671 2025-02-06 cs.LG cs.AI cs.CL stat.ML 87%

On Teacher Hacking in Language Model Distillation

Daniil Tiapkin, Daniele Calandriello, Johan Ferret, Sarah Perrin, Nino Vieillard, Alexandre Ramé, Mathieu Blondel

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

2501.13941 2025-01-27 cs.CR cs.AI cs.CL cs.LG 87%

GaussMark: A Practical Approach for Structural Watermarking of Language Models

Adam Block, Ayush Sekhari, Alexander Rakhlin

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、cs.LG

2410.10989 2025-01-27 cs.LG cs.AI cs.CL cs.DC 87%

Liger Kernel: Efficient Triton Kernels for LLM Training

Pin-Lun Hsu, Yun Dai, Vignesh Kothapalli, Qingquan Song, Shao Tang, Siyu Zhu, Steven Shimizu, Shivam Sahni, Haowen Ning, Yanning Chen

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、cs.LG

Comments 17 pages, 12 figures

2501.00032 2025-01-03 cs.LG cs.AI cs.AR cs.CL 87%

Highly Optimized Kernels and Fine-Grained Codebooks for LLM Inference on Arm CPUs

Dibakar Gope, David Mansell, Danny Loh, Ian Bratt

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、cs.LG

2409.01366 2024-12-30 cs.CL cs.AI cs.LG 87%

CHESS: Optimizing LLM Inference via Channel-Wise Thresholding and Selective Sparsification

Junhui He, Shangyu Wu, Weidong Wen, Chun Jason Xue, Qingan 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、cs.LG

2412.13435 2024-12-19 cs.CL cs.AI cs.LG 87%

Lightweight Safety Classification Using Pruned Language Models

Mason Sawtell, Tula Masterman, Sandi Besen, Jim Brown

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、cs.LG

2412.12154 2024-12-18 cs.LG cs.AI cs.CL 87%

PyOD 2: A Python Library for Outlier Detection with LLM-powered Model Selection

Sihan Chen, Zhuangzhuang Qian, Wingchun Siu, Xingcan Hu, Jiaqi Li, Shawn Li, Yuehan Qin, Tiankai Yang, Zhuo Xiao, Wanghao Ye, Yichi Zhang, Yushun Dong, Yue Zhao

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、cs.LG

2412.03537 2024-12-05 cs.CL cs.AI cs.LG 87%

Evaluating Gender Bias Transfer between Pre-trained and Prompt-Adapted Language Models

Natalie Mackraz, Nivedha Sivakumar, Samira Khorshidi, Krishna Patel, Barry-John Theobald, Luca Zappella, Nicholas Apostoloff

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

2412.00061 2024-12-03 cs.LG cs.AI cs.CL 87%

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration

Zhuofan Wen, Shangtong Gui, Yang Feng

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、cs.LG

2412.00053 2024-12-03 cs.LG cs.AI cs.CL 87%

LeMoLE: LLM-Enhanced Mixture of Linear Experts for Time Series Forecasting

Lingzheng Zhang, Lifeng Shen, Yimin Zheng, Shiyuan Piao, Ziyue Li, Fugee Tsung

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、cs.LG

2407.14679 2024-11-05 cs.CL cs.AI cs.LG 87%

Compact Language Models via Pruning and Knowledge Distillation

Saurav Muralidharan, Sharath Turuvekere Sreenivas, Raviraj Joshi, Marcin Chochowski, Mostofa Patwary, Mohammad Shoeybi, Bryan Catanzaro, Jan Kautz, Pavlo Molchanov

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、cs.LG

2406.00024 2024-10-29 cs.CL cs.AI cs.ET cs.LG 87%

Embedding-Aligned Language Models

Guy Tennenholtz, Yinlam Chow, Chih-Wei Hsu, Lior Shani, Ethan Liang, Craig Boutilier

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、cs.LG

Comments Accepted Neurips 2024

2406.17542 2024-10-24 cs.LG cs.AI cs.CL 87%

CDQuant: Greedy Coordinate Descent for Accurate LLM Quantization

Pranav Ajit Nair, Arun Sai Suggala

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

2410.15667 2024-10-22 cs.CL cs.AI cs.LG 87%

RAC: Efficient LLM Factuality Correction with Retrieval Augmentation

Changmao Li, Jeffrey Flanigan

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、cs.LG

2312.11511 2024-10-16 cs.CL cs.AI cs.LG 87%

ComplexityNet: Increasing LLM Inference Efficiency by Learning Task Complexity

Henry Bae, Aghyad Deeb, Alex Fleury, Kehang Zhu

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、cs.LG

2410.07513 2024-10-11 cs.LG cs.AI cs.CL 87%

Evolutionary Contrastive Distillation for Language Model Alignment

Julian Katz-Samuels, Zheng Li, Hyokun Yun, Priyanka Nigam, Yi Xu, Vaclav Petricek, Bing Yin, Trishul Chilimbi

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

2410.04380 2024-10-11 eess.AS cs.SD 87%

HALL-E: Hierarchical Neural Codec Language Model for Minute-Long Zero-Shot Text-to-Speech Synthesis

Yuto Nishimura, Takumi Hirose, Masanari Ohi, Hideki Nakayama, Nakamasa Inoue

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

2410.02950 2024-10-07 cs.LG cs.AI cs.CL cs.CY 87%

LLMCO2: Advancing Accurate Carbon Footprint Prediction for LLM Inferences

Zhenxiao Fu, Fan Chen, Shan Zhou, Haitong Li, Lei Jiang

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、cs.LG

Comments 9 pages, 11 figures

2410.00037 2024-10-03 eess.AS cs.AI cs.CL cs.LG cs.SD 87%

Moshi: a speech-text foundation model for real-time dialogue

Alexandre Défossez, Laurent Mazaré, Manu Orsini, Amélie Royer, Patrick Pérez, Hervé Jégou, Edouard Grave, Neil Zeghidour

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

2403.05527 2024-10-02 cs.LG cs.AI cs.CL 87%

GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Hao Kang, Qingru Zhang, Souvik Kundu, Geonhwa Jeong, Zaoxing Liu, Tushar Krishna, Tuo Zhao

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、cs.LG

2409.15281 2024-09-25 cs.AR cs.ET 87%

LAAG-RV: LLM Assisted Assertion Generation for RTL Design Verification

Karthik Maddala, Bhabesh Mali, Chandan Karfa

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

Comments 3 Figures, 1 Table

2402.13598 2024-09-11 cs.CL cs.AI cs.LG 87%

User-LLM: Efficient LLM Contextualization with User Embeddings

Lin Ning, Luyang Liu, Jiaxing Wu, Neo Wu, Devora Berlowitz, Sushant Prakash, Bradley Green, Shawn O'Banion, Jun Xie

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、cs.LG

2409.02877 2024-09-05 cs.AI cs.CL cs.LG 87%

Configurable Foundation Models: Building LLMs from a Modular Perspective

Chaojun Xiao, Zhengyan Zhang, Chenyang Song, Dazhi Jiang, Feng Yao, Xu Han, Xiaozhi Wang, Shuo Wang, Yufei Huang, Guanyu Lin, Yingfa Chen, Weilin Zhao, Yuge Tu, Zexuan Zhong, Ao Zhang, Chenglei Si, Khai Hao Moo, Chenyang Zhao, Huimin Chen, Yankai Lin, Zhiyuan Liu, Jingbo Shang, Maosong Sun

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

2407.07000 2024-09-02 cs.LG cs.AI cs.CL cs.DC 87%

Etalon: Holistic Performance Evaluation Framework for LLM Inference Systems

Amey Agrawal, Anmol Agarwal, Nitin Kedia, Jayashree Mohan, Souvik Kundu, Nipun Kwatra, Ramachandran Ramjee, Alexey Tumanov

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、cs.LG

2402.16823 2024-08-23 cs.AI cs.CL cs.LG cs.MA 87%

Language Agents as Optimizable Graphs

Mingchen Zhuge, Wenyi Wang, Louis Kirsch, Francesco Faccio, Dmitrii Khizbullin, Jürgen Schmidhuber

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

Comments Project Website: https://gptswarm.org ; Github Repo: https://github.com/metauto-ai/gptswarm . In Forty-first International Conference on Machine Learning (2024)

2404.00725 2024-07-26 cs.SE cs.AI cs.CL cs.LG 87%

The Larger the Better? Improved LLM Code-Generation via Budget Reallocation

Michael Hassid, Tal Remez, Jonas Gehring, Roy Schwartz, Yossi Adi

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、cs.LG

Comments COLM 2024

2407.09979 2024-07-16 cs.CV 87%

PFPs: Prompt-guided Flexible Pathological Segmentation for Diverse Potential Outcomes Using Large Vision and Language Models

Can Cui, Ruining Deng, Junlin Guo, Quan Liu, Tianyuan Yao, Haichun Yang, Yuankai Huo

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

2306.03341 2024-06-27 cs.LG cs.AI cs.CL 87%

Inference-Time Intervention: Eliciting Truthful Answers from a Language Model

Kenneth Li, Oam Patel, Fernanda Viégas, Hanspeter Pfister, Martin Wattenberg

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

Comments NeurIPS 2023 spotlight; code: https://github.com/likenneth/honest_llama

2312.03668 2024-06-07 eess.AS cs.AI cs.CL cs.LG 87%

Integrating Pre-Trained Speech and Language Models for End-to-End Speech Recognition

Yukiya Hono, Koh Mitsuda, Tianyu Zhao, Kentaro Mitsui, Toshiaki Wakatsuki, Kei Sawada

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、cs.LG

Comments 17 pages, 4 figures, 9 tables, accepted for Findings of ACL 2024. The model is available at https://huggingface.co/rinna/nue-asr

1. 效率与部署 22280 篇

EACO-RAG: Towards Distributed Tiered LLM Deployment using Edge-Assisted and Collaborative RAG with Adaptive Knowledge Update

On Teacher Hacking in Language Model Distillation

GaussMark: A Practical Approach for Structural Watermarking of Language Models

Liger Kernel: Efficient Triton Kernels for LLM Training

Highly Optimized Kernels and Fine-Grained Codebooks for LLM Inference on Arm CPUs

CHESS: Optimizing LLM Inference via Channel-Wise Thresholding and Selective Sparsification

Lightweight Safety Classification Using Pruned Language Models

PyOD 2: A Python Library for Outlier Detection with LLM-powered Model Selection

Evaluating Gender Bias Transfer between Pre-trained and Prompt-Adapted Language Models

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration

LeMoLE: LLM-Enhanced Mixture of Linear Experts for Time Series Forecasting

Compact Language Models via Pruning and Knowledge Distillation

Embedding-Aligned Language Models

CDQuant: Greedy Coordinate Descent for Accurate LLM Quantization

RAC: Efficient LLM Factuality Correction with Retrieval Augmentation

ComplexityNet: Increasing LLM Inference Efficiency by Learning Task Complexity

Evolutionary Contrastive Distillation for Language Model Alignment

HALL-E: Hierarchical Neural Codec Language Model for Minute-Long Zero-Shot Text-to-Speech Synthesis

LLMCO2: Advancing Accurate Carbon Footprint Prediction for LLM Inferences

Moshi: a speech-text foundation model for real-time dialogue

GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

LAAG-RV: LLM Assisted Assertion Generation for RTL Design Verification

User-LLM: Efficient LLM Contextualization with User Embeddings

Configurable Foundation Models: Building LLMs from a Modular Perspective

Etalon: Holistic Performance Evaluation Framework for LLM Inference Systems

Language Agents as Optimizable Graphs

The Larger the Better? Improved LLM Code-Generation via Budget Reallocation

PFPs: Prompt-guided Flexible Pathological Segmentation for Diverse Potential Outcomes Using Large Vision and Language Models

Inference-Time Intervention: Eliciting Truthful Answers from a Language Model

Integrating Pre-Trained Speech and Language Models for End-to-End Speech Recognition