语言大模型 / LLM - arXivDaily 专题

2410.03765 2024-10-08 cs.CL cs.LG 88%

Basis Sharing: Cross-Layer Parameter Sharing for Large Language Model Compression

Jingcun Wang, Yu-Guang Chen, Ing-Chao Lin, Bing Li, Grace Li Zhang

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

2407.01614 2024-10-08 cs.LG cs.AI 88%

Enhancing Stability for Large Language Models Training in Constrained Bandwidth Networks

Yun Dai, Tejas Dharamsi, Byron Hsu, Tao Song, Hamed Firooz

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

2406.16069 2024-10-08 cs.CL cs.AI 88%

FastMem: Fast Memorization of Prompt Improves Context Awareness of Large Language Models

Junyi Zhu, Shuochen Liu, Yu Yu, Bo Tang, Yibo Yan, Zhiyu Li, Feiyu Xiong, Tong Xu, Matthew B. Blaschko

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

2307.00526 2024-10-07 cs.CL cs.LG cs.NA cs.NE math.NA 88%

TensorGPT: Efficient Compression of Large Language Models based on Tensor-Train Decomposition

Mingxue Xu, Yao Lei Xu, Danilo P. Mandic

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

2410.02202 2024-10-04 cs.CL cs.AI 88%

Can Language Models Take A Hint? Prompting for Controllable Contextualized Commonsense Inference

Pedro Colon-Hernandez, Nanxi Liu, Chelsea Joe, Peter Chin, Claire Yin, Henry Lieberman, Yida Xin, Cynthia Breazeal

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

Comments Submitted to ACL Rolling Review. arXiv admin note: text overlap with arXiv:2302.05406

2410.00362 2024-10-02 cs.CL cs.AI 88%

FedPT: Federated Proxy-Tuning of Large Language Models on Resource-Constrained Edge Devices

Zhidong Gao, Yu Zhang, Zhenxiao Zhang, Yanmin Gong, Yuanxiong Guo

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

Comments 29 pages, 19 figures

2406.17328 2024-10-02 cs.CL cs.AI 88%

Dual-Space Knowledge Distillation for Large Language Models

Songming Zhang, Xue Zhang, Zengkui Sun, Yufeng Chen, Jinan Xu

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

Comments The camera-ready version for EMNLP 2024 main conference. 17 pages, 11 figures, code available at: https://github.com/songmzhang/DSKD

2408.04905 2024-09-24 cs.CL cs.AI 88%

GlitchProber: Advancing Effective Detection and Mitigation of Glitch Tokens in Large Language Models

Zhibo Zhang, Wuxia Bai, Yuxi Li, Mark Huasong Meng, Kailong Wang, Ling Shi, Li Li, Jun Wang, Haoyu Wang

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

2409.13747 2024-09-24 cs.CL cs.ET cs.LG 88%

Machine Translation with Large Language Models: Decoder Only vs. Encoder-Decoder

Abhinav P. M., SujayKumar Reddy M, Oswald Christopher

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

2409.12500 2024-09-20 cs.CL cs.AI 88%

LLMR: Knowledge Distillation with a Large Language Model-Induced Reward

Dongheng Li, Yongchang Hao, Lili Mou

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

Comments Accepted by LERC COLING 2024

2405.13014 2024-09-20 cs.CL cs.AI 88%

QCRD: Quality-guided Contrastive Rationale Distillation for Large Language Models

Wei Wang, Zhaowei Li, Qi Xu, Yiqing Cai, Hang Song, Qi Qi, Ran Zhou, Zhida Huang, Tao Wang, Li Xiao

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

2409.09086 2024-09-17 cs.LG cs.AI cs.CV cs.DC cs.PF 88%

Inf-MLLM: Efficient Streaming Inference of Multimodal Large Language Models on a Single GPU

Zhenyu Ning, Jieru Zhao, Qihao Jin, Wenchao Ding, Minyi Guo

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

2407.09050 2024-09-09 cs.CR cs.AI cs.CV cs.LG 88%

Refusing Safe Prompts for Multi-modal Large Language Models

Zedian Shao, Hongbin Liu, Yuepeng Hu, Neil Zhenqiang Gong

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

2405.07626 2024-08-29 cs.LG cs.AI 88%

AnomalyLLM: Few-shot Anomaly Edge Detection for Dynamic Graphs using Large Language Models

Shuo Liu, Di Yao, Lanting Fang, Zhetao Li, Wenbin Li, Kaiyu Feng, XiaoWen Ji, Jingping Bi

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

Comments 13pages

2408.12480 2024-08-26 cs.LG cs.CL 88%

Vintern-1B: An Efficient Multimodal Large Language Model for Vietnamese

Khang T. Doan, Bao G. Huynh, Dung T. Hoang, Thuc D. Pham, Nhat H. Pham, Quan T. M. Nguyen, Bang Q. Vo, Suong N. Hoang

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

2407.19832 2024-08-22 cs.CV cs.AI cs.CL 88%

ML-Mamba: Efficient Multi-Modal Large Language Model Utilizing Mamba-2

Wenjun Huang, Jiakai Pan, Jiahao Tang, Yanyu Ding, Yifei Xing, Yuhe Wang, Zhengzhuo Wang, Jianguo Hu

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

2408.10210 2024-08-21 cs.CL cs.LG 88%

A Survey on Symbolic Knowledge Distillation of Large Language Models

Kamal Acharya, Alvaro Velasquez, Houbing Herbert Song

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

Comments 21 pages, 7 figures

2311.09433 2024-08-19 cs.CR cs.AI cs.CL 88%

Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment

Haoran Wang, Kai Shu

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

Comments ACM International Conference on Information and Knowledge Management (CIKM'24)

2408.08147 2024-08-16 cs.DC cs.CL cs.LG 88%

P/D-Serve: Serving Disaggregated Large Language Model at Scale

Yibo Jin, Tao Wang, Huimin Lin, Mingyang Song, Peiyang Li, Yipeng Ma, Yicheng Shan, Zhengfan Yuan, Cailong Li, Yajing Sun, Tiandeng Wu, Xing Chu, Ruizhi Huan, Li Ma, Xiao You, Wenting Zhou, Yunpeng Ye, Wen Liu, Xiangkun Xu, Yongsheng Zhang, Tiantian Dong, Jiawei Zhu, Zhe Wang, Xijian Ju, Jianxun Song, Haoliang Cheng, Xiaojing Li, Jiandong Ding, Hefei Guo, Zhengyong Zhang

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

2408.02651 2024-08-06 cs.CL cs.AI cs.CR 88%

Can Reinforcement Learning Unlock the Hidden Dangers in Aligned Large Language Models?

Mohammad Bahrami Karkevandi, Nishant Vishwamitra, Peyman Najafirad

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

Comments Accepted to AI4CYBER - KDD 2024

2308.07633 2024-07-31 cs.CL cs.AI 88%

A Survey on Model Compression for Large Language Models

Xunyu Zhu, Jian Li, Yong Liu, Can Ma, Weiping Wang

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

Comments Accepted for publication in TACL; a pre-MIT Press publication version

2407.10969 2024-07-25 cs.CL cs.LG 88%

Q-Sparse: All Large Language Models can be Fully Sparsely-Activated

Hongyu Wang, Shuming Ma, Ruiping Wang, Furu Wei

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

Comments Work in progress

2401.02938 2024-07-23 cs.CL cs.LG 88%

Fast and Effective Weight Update for Pruned Large Language Models

Vladimír Boža

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

2407.14269 2024-07-22 cs.CL cs.AI 88%

Predictive Simultaneous Interpretation: Harnessing Large Language Models for Democratizing Real-Time Multilingual Communication

Kurando Iida, Kenjiro Mimura, Nobuo Ito

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

Comments 7 pages

2407.06085 2024-07-09 cs.LG cs.AI cs.NI 88%

LLMcap: Large Language Model for Unsupervised PCAP Failure Detection

Lukasz Tulczyjew, Kinan Jarrah, Charles Abondo, Dina Bennett, Nathanael Weill

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

Comments Copyright 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works

2407.03964 2024-07-08 cs.CL cs.LG 88%

Improving Sample Efficiency of Reinforcement Learning with Background Knowledge from Large Language Models

Fuxiang Zhang, Junyou Li, Yi-Chen Li, Zongzhang Zhang, Yang Yu, Deheng Ye

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

2407.00928 2024-07-02 cs.LG cs.CL 88%

FoldGPT: Simple and Effective Large Language Model Compression Scheme

Songwei Liu, Chao Zeng, Lianqiang Li, Chenqian Yan, Lean Fu, Xing Mei, Fangmin Chen

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

2406.14711 2024-06-27 cs.CL cs.AI cs.MA 88%

MultiAgent Collaboration Attack: Investigating Adversarial Attacks in Large Language Model Collaborations via Debate

Alfonso Amayuelas, Xianjun Yang, Antonis Antoniades, Wenyue Hua, Liangming Pan, William Wang

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

2406.11097 2024-06-21 cs.CL cs.AI 88%

InstructCMP: Length Control in Sentence Compression through Instruction-based Large Language Models

Juseon-Do, Jingun Kwon, Hidetaka Kamigaito, Manabu Okumura

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

Comments 8 pages, 3 figures, accepted to ACL 2024 Findings (Long Paper)

2402.05926 2024-06-18 cs.LG cs.CL 88%

On the Convergence of Zeroth-Order Federated Tuning for Large Language Models

Zhenqing Ling, Daoyuan Chen, Liuyi Yao, Yaliang Li, Ying Shen

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

Comments accepted by KDD'24 research track. 21 pages, 10 figures, 8 tables

1. 效率与部署 22368 篇

Basis Sharing: Cross-Layer Parameter Sharing for Large Language Model Compression

Enhancing Stability for Large Language Models Training in Constrained Bandwidth Networks

FastMem: Fast Memorization of Prompt Improves Context Awareness of Large Language Models

TensorGPT: Efficient Compression of Large Language Models based on Tensor-Train Decomposition

Can Language Models Take A Hint? Prompting for Controllable Contextualized Commonsense Inference

FedPT: Federated Proxy-Tuning of Large Language Models on Resource-Constrained Edge Devices

Dual-Space Knowledge Distillation for Large Language Models

GlitchProber: Advancing Effective Detection and Mitigation of Glitch Tokens in Large Language Models

Machine Translation with Large Language Models: Decoder Only vs. Encoder-Decoder

LLMR: Knowledge Distillation with a Large Language Model-Induced Reward

QCRD: Quality-guided Contrastive Rationale Distillation for Large Language Models

Inf-MLLM: Efficient Streaming Inference of Multimodal Large Language Models on a Single GPU

Refusing Safe Prompts for Multi-modal Large Language Models

AnomalyLLM: Few-shot Anomaly Edge Detection for Dynamic Graphs using Large Language Models

Vintern-1B: An Efficient Multimodal Large Language Model for Vietnamese

ML-Mamba: Efficient Multi-Modal Large Language Model Utilizing Mamba-2

A Survey on Symbolic Knowledge Distillation of Large Language Models

Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment

P/D-Serve: Serving Disaggregated Large Language Model at Scale

Can Reinforcement Learning Unlock the Hidden Dangers in Aligned Large Language Models?

A Survey on Model Compression for Large Language Models

Q-Sparse: All Large Language Models can be Fully Sparsely-Activated

Fast and Effective Weight Update for Pruned Large Language Models

Predictive Simultaneous Interpretation: Harnessing Large Language Models for Democratizing Real-Time Multilingual Communication

LLMcap: Large Language Model for Unsupervised PCAP Failure Detection

Improving Sample Efficiency of Reinforcement Learning with Background Knowledge from Large Language Models

FoldGPT: Simple and Effective Large Language Model Compression Scheme

MultiAgent Collaboration Attack: Investigating Adversarial Attacks in Large Language Model Collaborations via Debate

InstructCMP: Length Control in Sentence Compression through Instruction-based Large Language Models

On the Convergence of Zeroth-Order Federated Tuning for Large Language Models