语言大模型 / LLM - arXivDaily 专题

2506.03510 2025-06-05 cs.CL 88%

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information

Seungcheol Park, Sojin Lee, Jongjin Kim, Jinsik Lee, Hyunjik Jo, U Kang

机构 * Seoul National University（首尔国立大学）； LG AI Research（LG AI研究院）

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

Comments IJCAI 2025 Main Track

2403.09073 2025-06-04 cs.CL 88%

Revealing the Parallel Multilingual Learning within Large Language Models

Yongyu Mu, Peinan Feng, Zhiquan Cao, Yuzhang Wu, Bei Li, Chenglong Wang, Tong Xiao, Kai Song, Tongran Liu, Chunliang Zhang, Jingbo Zhu

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

Comments Accepted to EMNLP 2024

2501.10639 2025-06-02 cs.CR cs.CL 88%

Latent-space adversarial training with post-aware calibration for defending large language models against jailbreak attacks

Xin Yi, Yue Li, Dongsheng Shi, Linlin Wang, Xiaoling Wang, Liang He

机构 * Lab of Artificial Intelligence for Education, East China Normal University, Shanghai 200062, China（教育人工智能实验室，东华大学，上海200062，中国）； Shanghai Institute of Artificial Intelligence for Education, East China Normal University, Shanghai 200062, China（教育人工智能研究所，东华大学，上海200062，中国）； School of Computer Science and Technology, East China Normal University, Shanghai 200062, China（计算机科学与技术学院，东华大学，上海200062，中国）

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

2505.23829 2025-06-02 cs.CL 88%

BiasFilter: An Inference-Time Debiasing Framework for Large Language Models

Xiaoqing Cheng, Ruizhe Chen, Hongying Zan, Yuxiang Jia, Min Peng

机构 * First Author Affiliation（第一作者单位）； Second Author Affiliation（第二作者单位）

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

2505.22689 2025-05-30 cs.LG 88%

SlimLLM: Accurate Structured Pruning for Large Language Models

Jialong Guo, Xinghao Chen, Yehui Tang, Yunhe Wang

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

Comments ICML 2025

2502.11501 2025-05-30 cs.CL cs.CV 88%

Token Pruning in Multimodal Large Language Models: Are We Solving the Right Problem?

Zichen Wen, Yifeng Gao, Weijia Li, Conghui He, Linfeng Zhang

机构 * Shanghai Jiao Tong University（上海交通大学）； EPIC Lab, SJTU（EPIC实验室，SJTu）； Shanghai AI Laboratory（上海人工智能实验室）； Sun Yat-sen University（中山大学）

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

Comments ACL 2025 Findings

2505.20100 2025-05-27 cs.CV cs.AI 88%

AdaTP: Attention-Debiased Token Pruning for Video Large Language Models

Fengyuan Sun, Leqi Shen, Hui Chen, Sicheng Zhao, Jungong Han, Guiguang Ding

机构 * School of Software, Tsinghua University（清华大学软件学院）； BNRist, Tsinghua University（清华大学BNRist）； Department of Automation, Tsinghua University（清华大学自动化系）

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

2505.19490 2025-05-27 cs.AI 88%

Automated CAD Modeling Sequence Generation from Text Descriptions via Transformer-Based Large Language Models

Jianxing Liao, Junyan Xu, Yatao Sun, Maowen Tang, Sicheng He, Jingxian Liao, Shui Yu, Yun Li, Hongguan Xiao

机构 * Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China（深圳先进研究院长江大学）； i4AI Ltd（i4AI公司）

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

Comments Accepted by ACL 2025 Main Conference

2505.19107 2025-05-27 cs.LG 88%

Optimization-Inspired Few-Shot Adaptation for Large Language Models

Boyan Gao, Xin Wang, Yibo Yang, David Clifton

机构 * University of Oxford（牛津大学）； KAUST（科威特大学）

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

2505.12216 2025-05-27 cs.CL 88%

One-for-All Pruning: A Universal Model for Customized Compression of Large Language Models

Rongguang Ye, Ming Tang

机构 * Department of Computer Science and Engineering and the Research Institute of Trustworthy Autonomous Systems（计算机科学与工程系和可信自主系统研究 institute）

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

Comments ACL Findings

2505.18149 2025-05-26 cs.CL 88%

First Finish Search: Efficient Test-Time Scaling in Large Language Models

Aradhye Agarwal, Ayan Sengupta, Tanmoy Chakraborty

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

2502.10743 2025-05-26 cs.CL 88%

1bit-Merging: Dynamic Quantized Merging for Large Language Models

Shuqi Liu, Yuxuan Yao, Bowei He, Zehua Liu, Xiongwei Han, Mingxuan Yuan, Han Wu, Linqi Song

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

2502.12464 2025-05-23 cs.CL 88%

SafeRoute: Adaptive Model Selection for Efficient and Accurate Safety Guardrails in Large Language Models

Seanie Lee, Dong Bok Lee, Dominik Wagner, Minki Kang, Haebin Seong, Tobias Bocklet, Juho Lee, Sung Ju Hwang

机构 * KAIST（韩国科学技术院）； Technische Hochschule Nürnberg Georg Simon Ohm（图林根工业大学诺伊堡分校）

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

Comments ACL 2025 findings

2406.10594 2025-05-23 cs.CL 88%

BlockPruner: Fine-grained Pruning for Large Language Models

Longguang Zhong, Fanqi Wan, Ruijun Chen, Xiaojun Quan, Liangzhi Li

机构 * School of Computer Science and Engineering, Sun Yat-sen University（中山大学计算机科学与工程学院）； Meetyou AI Lab（Meetyou人工智能实验室）

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

Comments ACL 2025 Findings

2505.14992 2025-05-22 cs.CL 88%

Effective and Efficient Schema-aware Information Extraction Using On-Device Large Language Models

Zhihao Wen, Sheng Liang, Yaxiong Wu, Yongyue Zhang, Yong Liu

机构 * Huawei Noah’s Ark Lab（华为诺亚实验室）

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

Comments 5 pages, 2 figures

2505.14260 2025-05-21 cs.CV cs.AI 88%

Speculative Decoding Reimagined for Multimodal Large Language Models

Luxi Lin, Zhihang Lin, Zhanpeng Zeng, Rongrong Ji

机构 * Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University（多媒体可信感知与高效计算重点实验室、中华人民共和国教育部、厦门大学）

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

Comments 12 pages

2402.00350 2025-05-20 cs.SE cs.AI 88%

On the Challenges of Fuzzing Techniques via Large Language Models

Linghan Huang, Peizhou Zhao, Huaming Chen, Lei Ma

机构 * School of Electrical and Computer Engineering, The University of Sydney（悉尼大学电气与计算机工程学院）； The University of Sydney（悉尼大学）； Department of Computer Science, The University of Tokyo（东京大学计算机科学系）； The University of Tokyo（东京大学）

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

2505.10732 2025-05-19 cs.CR cs.AI 88%

Automating Security Audit Using Large Language Model based Agent: An Exploration Experiment

Jia Hui Chin, Pu Zhang, Yu Xin Cheong, Jonathan Pan

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

2410.08604 2025-05-19 cs.CR cs.LG 88%

MergePrint: Merge-Resistant Fingerprints for Robust Black-box Ownership Verification of Large Language Models

Shojiro Yamabe, Futa Waseda, Tsubasa Takahashi, Koki Wataoka

机构 * Institute of Science Tokyo（东京科学研究所）； The University of Tokyo（东京大学）； SB Intuitions

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

Comments Accepted at ACL 2025 Main

2411.00646 2025-05-16 cs.CL 88%

Phase Diagram of Vision Large Language Models Inference: A Perspective from Interaction across Image and Instruction

Houjing Wei, Yuting Shi, Naoya Inoue

机构 * Japan Advanced Institute of Science and Technology（日本先进科学研究院）； RIKEN（日本资源技术研究所）

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

Comments 6 pages, 5 figures

2410.16314 2025-05-13 cs.NE cs.LG 88%

Steering Large Language Models using Conceptors: Improving Addition-Based Activation Engineering

Joris Postmus, Steven Abreu

机构 * University of Groningen（格罗宁根大学）

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

Comments Presented at the MINT workshop at NeurIPS 2024. v4: fix sign in equation 10

2504.21043 2025-05-08 cs.CR cs.AI 88%

CodeBC: A More Secure Large Language Model for Smart Contract Code Generation in Blockchain

Lingxiang Wang, Hainan Zhang, Qinnan Zhang, Ziwei Wang, Hongwei Zheng, Jin Dong, Zhiming Zheng

机构 * State Key Laboratory of Complex & Critical Software Environment, Beihang University（复杂与关键软件环境国家重点实验室，北京航空航天大学）； School of Artificial Intelligence, Beihang University（人工智能学院，北京航空航天大学）； Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing（未来区块链与隐私计算北京先进创新中心）； Beijing Academy of Blockchain and Edge Computing, BABEC（区块链与边缘计算北京研究院，BABEC）

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

2412.18135 2025-05-07 cs.CL 88%

LSAQ: Layer-Specific Adaptive Quantization for Large Language Model Deployment

Binrui Zeng, Bin Ji, Xiaodong Liu, Jie Yu, Shasha Li, Jun Ma, Xiaopeng Li, Shangwen Wang, Xinran Hong, Yongtao Tang

机构 * College of Computer Science and Technology, National University of Defense Technology（计算机科学与技术学院，国防科技大学）

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

Comments 8 pages, 4 figures, accepted to IJCNN 2025

2505.02533 2025-05-06 cs.DC cs.AI 88%

Large Language Model Partitioning for Low-Latency Inference at the Edge

Dimitrios Kafetzis, Ramin Khalili, Iordanis Koutsopoulos

机构 * Athens University of Economics and Business（雅典经济与商业大学）； Huawei European Research Center（华为欧洲研究中心）

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

2505.02087 2025-05-06 cs.AI 88%

Retrieval-augmented in-context learning for multimodal large language models in disease classification

Zaifu Zhan, Shuang Zhou, Xiaoshan Zhou, Yongkang Xiao, Jun Wang, Jiawen Deng, He Zhu, Yu Hou, Rui Zhang

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

Comments 17 Pages, 1 figure, 7 tables

2412.05547 2025-05-06 cs.IR cs.AI 88%

KG-Retriever: Efficient Knowledge Indexing for Retrieval-Augmented Large Language Models

Weijie Chen, Ting Bai, Jinbo Su, Jian Luan, Wei Liu, Chuan Shi

机构 * Beijing University of Posts and Telecommunications（北京邮电大学）； University of Science and Technology Beijing（北京科技大学）； Xiaomi Corporation（小米公司）

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

2504.17365 2025-04-30 cs.CV cs.CL 88%

TimeSoccer: An End-to-End Multimodal Large Language Model for Soccer Commentary Generation

Ling You, Wenxuan Huang, Xinni Xie, Xiangyi Wei, Bangyan Li, Shaohui Lin, Yang Li, Changbo Wang

机构 * East China Normal University（东华大学）

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

2410.02102 2025-04-30 cs.CL 88%

Racing Thoughts: Explaining Contextualization Errors in Large Language Models

Michael A. Lepori, Michael C. Mozer, Asma Ghandeharioun

机构 * Google DeepMind（谷歌DeepMind）； Brown University（布朗大学）

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

2504.08907 2025-04-28 cs.SD cs.CL eess.AS 88%

Spatial Audio Processing with Large Language Model on Wearable Devices

Ayushi Mishra, Yang Bai, Priyadarshan Narayanasamy, Nakul Garg, Nirupam Roy

机构 * SING: Spatial Context in Large Language Model for Next-Gen Wearables（SING: 空间上下文在大语言模型中的应用）

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

2504.16134 2025-04-24 cs.CV cs.CL 88%

Multimodal Large Language Models for Enhanced Traffic Safety: A Comprehensive Review and Future Trends

Mohammad Abu Tami, Mohammed Elhenawy, Huthaifa I. Ashqar

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

1. 效率与部署 22313 篇

Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information

Revealing the Parallel Multilingual Learning within Large Language Models

Latent-space adversarial training with post-aware calibration for defending large language models against jailbreak attacks

BiasFilter: An Inference-Time Debiasing Framework for Large Language Models

SlimLLM: Accurate Structured Pruning for Large Language Models

Token Pruning in Multimodal Large Language Models: Are We Solving the Right Problem?

AdaTP: Attention-Debiased Token Pruning for Video Large Language Models

Automated CAD Modeling Sequence Generation from Text Descriptions via Transformer-Based Large Language Models

Optimization-Inspired Few-Shot Adaptation for Large Language Models

One-for-All Pruning: A Universal Model for Customized Compression of Large Language Models

First Finish Search: Efficient Test-Time Scaling in Large Language Models

1bit-Merging: Dynamic Quantized Merging for Large Language Models

SafeRoute: Adaptive Model Selection for Efficient and Accurate Safety Guardrails in Large Language Models

BlockPruner: Fine-grained Pruning for Large Language Models

Effective and Efficient Schema-aware Information Extraction Using On-Device Large Language Models

Speculative Decoding Reimagined for Multimodal Large Language Models

On the Challenges of Fuzzing Techniques via Large Language Models

Automating Security Audit Using Large Language Model based Agent: An Exploration Experiment

MergePrint: Merge-Resistant Fingerprints for Robust Black-box Ownership Verification of Large Language Models

Phase Diagram of Vision Large Language Models Inference: A Perspective from Interaction across Image and Instruction

Steering Large Language Models using Conceptors: Improving Addition-Based Activation Engineering

CodeBC: A More Secure Large Language Model for Smart Contract Code Generation in Blockchain

LSAQ: Layer-Specific Adaptive Quantization for Large Language Model Deployment

Large Language Model Partitioning for Low-Latency Inference at the Edge

Retrieval-augmented in-context learning for multimodal large language models in disease classification

KG-Retriever: Efficient Knowledge Indexing for Retrieval-Augmented Large Language Models

TimeSoccer: An End-to-End Multimodal Large Language Model for Soccer Commentary Generation

Racing Thoughts: Explaining Contextualization Errors in Large Language Models

Spatial Audio Processing with Large Language Model on Wearable Devices

Multimodal Large Language Models for Enhanced Traffic Safety: A Comprehensive Review and Future Trends