语言大模型 / LLM - arXivDaily 专题

2501.12231 2025-01-22 cs.CV cs.AI cs.CL 88%

InsTALL: Context-aware Instructional Task Assistance with Multi-modal Large Language Models

Pha Nguyen, Sailik Sengupta, Girik Malik, Arshit Gupta, Bonan Min

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

2403.00894 2025-01-22 cs.SE cs.AI cs.CL cs.PL 88%

Comparing large language models and human programmers for generating programming code

Wenpin Hou, Zhicheng Ji

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

Journal ref Adv Sci (Weinh). 2024 Dec 30:e2412279. Epub ahead of print. PMID: 39736107

2501.08145 2025-01-15 cs.CL cs.AI 88%

Refusal Behavior in Large Language Models: A Nonlinear Perspective

Fabian Hildebrandt, Andreas Maier, Patrick Krauss, Achim Schilling

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

2412.00090 2025-01-15 cs.LG cs.CL cs.DC 88%

Energy-Efficient Split Learning for Fine-Tuning Large Language Models in Edge Networks

Zuguang Li, Shaohua Wu, Liang Li, Songge 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

Comments 5 pages, 6 figures

2410.05315 2025-01-10 cs.LG cs.AI 88%

PalmBench: A Comprehensive Benchmark of Compressed Large Language Models on Mobile Platforms

Yilong Li, Jingyu Liu, Hao Zhang, M Badri Narayanan, Utkarsh Sharma, Shuai Zhang, Pan Hu, Yijing Zeng, Jayaram Raghuram, Suman Banerjee

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 10 pages

2404.14795 2025-01-09 cs.CL cs.CR cs.LG 88%

Watch Out for Your Guidance on Generation! Exploring Conditional Backdoor Attacks against Large Language Models

Jiaming He, Wenbo Jiang, Guanyu Hou, Wenshu Fan, Rui Zhang, Hongwei Li

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 The paper has been accepted to AAAI 2025

2501.00999 2025-01-07 cs.CL cs.AI 88%

Exploring Information Processing in Large Language Models: Insights from Information Bottleneck Theory

Zhou Yang, Zhengyu Qi, Zhaochun Ren, Zhikai Jia, Haizhou Sun, Xiaofei Zhu, Xiangwen Liao

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 9 pages, 9 figures, 3 tables

2401.02974 2025-01-07 cs.CL cs.AI cs.IR 88%

Efficacy of Utilizing Large Language Models to Detect Public Threat Posted Online

Taeksoo Kwon, Connor Kim

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 10 pages, 4 figures (1 image figure saved in PNG)

2501.01830 2025-01-06 cs.CR cs.AI cs.CL 88%

Auto-RT: Automatic Jailbreak Strategy Exploration for Red-Teaming Large Language Models

Yanjiang Liu, Shuhen Zhou, Yaojie Lu, Huijia Zhu, Weiqiang Wang, Hongyu Lin, Ben He, Xianpei Han, Le Sun

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

2412.19821 2024-12-31 cs.AR cs.AI cs.DC cs.LG 88%

Nanoscaling Floating-Point (NxFP): NanoMantissa, Adaptive Microexponents, and Code Recycling for Direct-Cast Compression of Large Language Models

Yun-Chen Lo, Gu-Yeon Wei, David Brooks

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 12 pages, 12 figures

2412.16719 2024-12-31 cs.LG cs.AI 88%

Lillama: Large Language Models Compression via Low-Rank Feature Distillation

Yaya Sy, Christophe Cerisara, Irina Illina

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

Comments 20 pages, 8 figures

2410.19130 2024-12-24 cs.LG cs.AI cs.CR 88%

Research on Key Technologies for Cross-Cloud Federated Training of Large Language Models

Haowei Yang, Mingxiu Sui, Shaobo Liu, Xinyue Qian, Zhaoyang Zhang, Bingying Liu

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

2412.11919 2024-12-17 cs.CL cs.AI cs.IR 88%

RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within Generation

Xiaoxi Li, Jiajie Jin, Yujia Zhou, Yongkang Wu, Zhonghua Li, Qi Ye, Zhicheng Dou

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

2408.08470 2024-12-17 cs.LG cs.AI 88%

Context-Aware Assistant Selection for Improved Inference Acceleration with Large Language Models

Jerry Huang, Prasanna Parthasarathi, Mehdi Rezagholizadeh, Sarath Chandar

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 Published as a long paper at the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP). Official version of paper within conference proceedings is available at http://aclanthology.org/2024.emnlp-main.332

2412.06512 2024-12-10 cs.AI cs.CL cs.SE 88%

The Fusion of Large Language Models and Formal Methods for Trustworthy AI Agents: A Roadmap

Yedi Zhang, Yufan Cai, Xinyue Zuo, Xiaokun Luan, Kailong Wang, Zhe Hou, Yifan Zhang, Zhiyuan Wei, Meng Sun, Jun Sun, Jing Sun, Jin Song Dong

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 24 pages, 4 figures

2412.03575 2024-12-06 cs.IR cs.AI cs.CL 88%

Leveraging Large Language Models for Generating Labeled Mineral Site Record Linkage Data

Jiyoon Pyo, Yao-Yi Chiang

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

Comments 11 pages, 10 figures

2412.02454 2024-12-04 cs.CL cs.AI cs.CR 88%

Gracefully Filtering Backdoor Samples for Generative Large Language Models without Retraining

Zongru Wu, Pengzhou Cheng, Lingyong Fang, Zhuosheng Zhang, Gongshen Liu

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 at COLING 2025

2411.18700 2024-12-02 cs.CL cs.AI 88%

On the Effectiveness of Incremental Training of Large Language Models

Miles Q. Li, Benjamin C. M. Fung, Shih-Chia Huang

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

2406.16838 2024-11-21 cs.CL cs.LG 88%

From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models

Sean Welleck, Amanda Bertsch, Matthew Finlayson, Hailey Schoelkopf, Alex Xie, Graham Neubig, Ilia Kulikov, Zaid Harchaoui

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

2411.10629 2024-11-19 cs.CL cs.AI 88%

Leveraging large language models for efficient representation learning for entity resolution

Xiaowei Xu, Bi T. Foua, Xingqiao Wang, Vivek Gunasekaran, John R. Talburt

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 22 pages and 12 figures

2405.06219 2024-11-13 cs.LG cs.CL 88%

SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models

Haojie Duanmu, Zhihang Yuan, Xiuhong Li, Jiangfei Duan, Xingcheng Zhang, Dahua Lin

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

2411.06171 2024-11-12 cs.CL cs.LG 88%

SEEKR: Selective Attention-Guided Knowledge Retention for Continual Learning of Large Language Models

Jinghan He, Haiyun Guo, Kuan Zhu, Zihan Zhao, Ming Tang, Jinqiao Wang

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 EMNLP2024

2407.07330 2024-11-08 cs.CL cs.AI 88%

Interpretable Differential Diagnosis with Dual-Inference Large Language Models

Shuang Zhou, Mingquan Lin, Sirui Ding, Jiashuo Wang, Genevieve B. Melton, James Zou, Rui Zhang

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 16 pages

2404.08763 2024-11-05 cs.LG cs.CL 88%

CATS: Contextually-Aware Thresholding for Sparsity in Large Language Models

Donghyun Lee, Je-Yong Lee, Genghan Zhang, Mo Tiwari, Azalia Mirhoseini

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

2408.05241 2024-11-01 cs.CL cs.AI cs.CY cs.ET cs.GT 88%

Large Model Strategic Thinking, Small Model Efficiency: Transferring Theory of Mind in Large Language Models

Nunzio Lore, Sepehr Ilami, Babak Heydari

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 18 pages, 6 figures

2311.09335 2024-10-28 cs.CL cs.AI 88%

Investigating Hallucinations in Pruned Large Language Models for Abstractive Summarization

George Chrysostomou, Zhixue Zhao, Miles Williams, Nikolaos Aletras

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 TACL 2024 (Presented at EMNLP 2024)

Journal ref Transactions of the Association for Computational Linguistics (2024) 12: 1163-1181

2410.18311 2024-10-25 cs.LG cs.CL 88%

CoreInfer: Accelerating Large Language Model Inference with Semantics-Inspired Adaptive Sparse Activation

Qinsi Wang, Saeed Vahidian, Hancheng Ye, Jianyang Gu, Jianyi Zhang, Yiran 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

Comments Project page: https://wangqinsi1.github.io/coreinfer_page/

2410.12686 2024-10-18 cs.CV cs.AI cs.LG 88%

Automatic Mapping of Anatomical Landmarks from Free-Text Using Large Language Models: Insights from Llama-2

Mohamad Abdi, Gerardo Hermosillo Valadez, Halid Ziya Yerebakan

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 6 pages, 2 figures, 1 table

2406.15524 2024-10-14 cs.CL cs.LG 88%

Rethinking Pruning Large Language Models: Benefits and Pitfalls of Reconstruction Error Minimization

Sungbin Shin, Wonpyo Park, Jaeho Lee, Namhoon Lee

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 EMNLP 2024 main

2401.17244 2024-10-11 cs.CL cond-mat.mtrl-sci cs.AI 88%

LLaMP: Large Language Model Made Powerful for High-fidelity Materials Knowledge Retrieval and Distillation

Yuan Chiang, Elvis Hsieh, Chia-Hong Chou, Janosh Riebesell

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 32 pages, 5 figures

1. 效率与部署 22368 篇

InsTALL: Context-aware Instructional Task Assistance with Multi-modal Large Language Models

Comparing large language models and human programmers for generating programming code

Refusal Behavior in Large Language Models: A Nonlinear Perspective

Energy-Efficient Split Learning for Fine-Tuning Large Language Models in Edge Networks

PalmBench: A Comprehensive Benchmark of Compressed Large Language Models on Mobile Platforms

Watch Out for Your Guidance on Generation! Exploring Conditional Backdoor Attacks against Large Language Models

Exploring Information Processing in Large Language Models: Insights from Information Bottleneck Theory

Efficacy of Utilizing Large Language Models to Detect Public Threat Posted Online

Auto-RT: Automatic Jailbreak Strategy Exploration for Red-Teaming Large Language Models

Nanoscaling Floating-Point (NxFP): NanoMantissa, Adaptive Microexponents, and Code Recycling for Direct-Cast Compression of Large Language Models

Lillama: Large Language Models Compression via Low-Rank Feature Distillation

Research on Key Technologies for Cross-Cloud Federated Training of Large Language Models

RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within Generation

Context-Aware Assistant Selection for Improved Inference Acceleration with Large Language Models

The Fusion of Large Language Models and Formal Methods for Trustworthy AI Agents: A Roadmap

Leveraging Large Language Models for Generating Labeled Mineral Site Record Linkage Data

Gracefully Filtering Backdoor Samples for Generative Large Language Models without Retraining

On the Effectiveness of Incremental Training of Large Language Models

From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models

Leveraging large language models for efficient representation learning for entity resolution

SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models

SEEKR: Selective Attention-Guided Knowledge Retention for Continual Learning of Large Language Models

Interpretable Differential Diagnosis with Dual-Inference Large Language Models

CATS: Contextually-Aware Thresholding for Sparsity in Large Language Models

Large Model Strategic Thinking, Small Model Efficiency: Transferring Theory of Mind in Large Language Models

Investigating Hallucinations in Pruned Large Language Models for Abstractive Summarization

CoreInfer: Accelerating Large Language Model Inference with Semantics-Inspired Adaptive Sparse Activation

Automatic Mapping of Anatomical Landmarks from Free-Text Using Large Language Models: Insights from Llama-2

Rethinking Pruning Large Language Models: Benefits and Pitfalls of Reconstruction Error Minimization

LLaMP: Large Language Model Made Powerful for High-fidelity Materials Knowledge Retrieval and Distillation