语言大模型 / LLM - arXivDaily 专题

2410.21508 2025-09-23 cs.CL cs.AI 88%

Group-SAE: Efficient Training of Sparse Autoencoders for Large Language Models via Layer Groups

Davide Ghilardi, Federico Belotti, Marco Molinari, Tao Ma, Matteo Palmonari

机构 * University of Milan-Bicocca（米兰-比科卡大学）； London School of Economics（伦敦经济学院）

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 version at EMNLP'25

2509.15361 2025-09-22 cs.CL cs.AI cs.MM 88%

Beyond Spurious Signals: Debiasing Multimodal Large Language Models via Counterfactual Inference and Adaptive Expert Routing

Zichen Wu, Hsiu-Yuan Huang, Yunfang Wu

机构 * School of Computer Science, Peking University（北京大学计算机科学学院）； MOE Key Laboratory of Computational Linguistics, Peking University（北京大学教育部计算语言学重点实验室）； National Key Laboratory for Multimedia Information Processing, Peking University（北京大学国家多媒体信息处理重点实验室）

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

Comments Accepted by EMNLP 2025 Findings

2509.11868 2025-09-16 cs.CL cs.AI cs.HC cs.RO 88%

Growing Perspectives: Modelling Embodied Perspective Taking and Inner Narrative Development Using Large Language Models

Sabrina Patania, Luca Annese, Anna Lambiase, Anita Pellegrini, Tom Foulsham, Azzurra Ruggeri, Silvia Rossi, Silvia Serino, Dimitri Ognibene

机构 * Department of Psychology, University of Milan-Bicocca（心理学系，米兰-比科卡大学）； Department of Psychology, University of Essex（心理学系，埃塞克斯大学）； School of Social Sciences and Technology, Technical University of Munich（社会科学与技术学院，慕尼黑技术大学）； Department of Electrical Engineering and Information Technology, University of Naples Federico II（电气工程与信息技术系，那不勒斯费德里科二世大学）

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 ICDL https://icdl2025.fel.cvut.cz/

2408.11727 2025-09-03 cs.CR cs.AI cs.CL cs.SE 88%

Efficient Detection of Toxic Prompts in Large Language Models

Yi Liu, Junzhe Yu, Huijia Sun, Ling Shi, Gelei Deng, Yuqi Chen, Yang Liu

机构 * Nanyang Technological University（南洋理工大学）； ShanghaiTech University（上海科技大学）

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

Comments Accepted by the 39th IEEE/ACM International Conference on Automated Software Engineering (ASE 2024)

2508.16680 2025-08-27 cs.LG cs.AI 88%

CALR: Corrective Adaptive Low-Rank Decomposition for Efficient Large Language Model Layer Compression

Muchammad Daniyal Kautsar, Afra Majida Hariono, Widyawan, Syukron Abu Ishaq Alfarozi, Kuntpong Woraratpanya

机构 * Department of Electrical and Information Engineering, Universitas Gadjah Mada（电子与信息工程系，加雅马达大学）； School of Information Technology, King Mongkut’s Institute of Technology Ladkrabang（信息技术学院，拉差班科技学院）

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 Submitted to IEEE Transactions on Artificial Intelligence. This is the preprint version, not peer-reviewed. The final version may differ after peer review. (11 pages, 3 figures)

2508.18182 2025-08-26 cs.LG cs.AI math.OC 88%

AdLoCo: adaptive batching significantly improves communications efficiency and convergence for Large Language Models

Nikolay Kutuzov, Makar Baderko, Stepan Kulibaba, Artem Dzhalilov, Daniel Bobrov, Maxim Mashtaler, Alexander Gasnikov

机构 * Moscow Institute of Physics and Technology（莫斯科物理技术学院）； The School of the Center for Teacher Excellence（教师卓越中心学校）； Research Center of the Artificial Intelligence Institute（人工智能研究所研究部）； Innopolis University（因诺波利斯大学）； Sirius University of Science and Technology（西里乌斯科学技术大学）； Steklov Institute（斯捷克洛夫研究所）

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

2508.14025 2025-08-20 cs.CL cs.AI 88%

Ask Good Questions for Large Language Models

Qi Wu, Zhongqi Lu

机构 * College of Artificial Intelligence, China University of Petroleum-Beijing, China（人工智能学院，中国石油大学（北京））； Hainan Institute of China University of Petroleum (Beijing), Sanya, Hainan, China（海南中国石油大学（北京）研究院，三亚，海南）

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

2508.10552 2025-08-15 cs.CL cs.AI 88%

When Language Overrules: Revealing Text Dominance in Multimodal Large Language Models

Huyu Wu, Meng Tang, Xinhan Zheng, Haiyun Jiang

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

2508.09035 2025-08-13 cs.DC cs.CL cs.LG 88%

P/D-Device: Disaggregated Large Language Model between Cloud and Devices

Yibo Jin, Yixu Xu, Yue Chen, Chengbin Wang, Tao Wang, Jiaqi Huang, Rongfei Zhang, Yiming Dong, Yuting Yan, Ke Cheng, Yingjie Zhu, Shulan Wang, Qianqian Tang, Shuaishuai Meng, Guanxin Cheng, Ze Wang, Shuyan Miao, Ketao Wang, Wen Liu, Yifan Yang, Tong Zhang, Anran Wang, Chengzhou Lu, Tiantian Dong, Yongsheng Zhang, Zhe Wang, Hefei Guo, Hongjie Liu, Wei Lu, 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

2508.06135 2025-08-11 cs.CL cs.AI 88%

Less is More: Selective Reflection for Compatible and Efficient Knowledge Distillation in Large Language Models

Lingyuan Liu, Mengxiang Zhang

机构 * City University of Hong Kong（香港城市大学）； The University of Hong Kong（香港大学）

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

2402.10462 2025-08-11 cs.LG cs.CL 88%

QDyLoRA: Quantized Dynamic Low-Rank Adaptation for Efficient Large Language Model Tuning

Hossein Rajabzadeh, Mojtaba Valipour, Tianshu Zhu, Marzieh Tahaei, Hyock Ju Kwon, Ali Ghodsi, Boxing Chen, Mehdi Rezagholizadeh

机构 * University of Waterloo（滑铁卢大学）； 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、cs.LG

Comments Best Paper Award AAAI EIW Workshop

Journal ref https://aclanthology.org/2024.emnlp-industry.53.pdf

2503.10905 2025-08-07 cs.AI cs.CV cs.LG 88%

Learning to Inference Adaptively for Multimodal Large Language Models

Zhuoyan Xu, Khoi Duc Nguyen, Preeti Mukherjee, Saurabh Bagchi, Somali Chaterji, Yingyu Liang, Yin Li

机构 * University of Wisconsin-Madison（威斯康星大学麦迪逊分校）； Purdue University（普渡大学）； The University of Hong Kong（香港大学）

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 at ICCV 2025

2412.15441 2025-08-01 cs.SE cs.AI cs.LG 88%

Insights into resource utilization of code small language models serving with runtime engines and execution providers

Francisco Durán, Matias Martinez, Patricia Lago, Silverio Martínez-Fernández

机构 * Vrije Universiteit Amsterdam（阿姆斯特丹自由大学）

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

Comments Accepted in Journal of Systems and Software (JSS). For its published version refer to the Journal of JSS

2507.20984 2025-07-31 cs.LG cs.AI 88%

SmallThinker: A Family of Efficient Large Language Models Natively Trained for Local Deployment

Yixin Song, Zhenliang Xue, Dongliang Wei, Feiyang Chen, Jianxiang Gao, Junchen Liu, Hangyu Liang, Guangshuo Qin, Chengrong Tian, Bo Wen, Longyu Zhao, Xinrui Zheng, Zeyu Mi, Haibo Chen

机构 * Institute of Parallel and Distributed Systems, Shanghai Jiao Tong University（并行与分布式系统研究所，上海交通大学）； School of Artificial Intelligence, Shanghai Jiao Tong University（人工智能学院，上海交通大学）； Zenergize AI

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

2504.13932 2025-07-31 cs.LG cs.CL 88%

Enhancing Ultra-Low-Bit Quantization of Large Language Models Through Saliency-Aware Partial Retraining

Deyu Cao, Samin Aref

机构 * The University of Tokyo（东京大学）； Department of Mechanical and Industrial Engineering, University of Toronto（多伦多大学机械与工业工程系）

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 This is a post-peer-review accepted manuscript from the proceedings of the 22nd International Conference on Modeling Decisions for Artificial Intelligence (MDAI'25). The publisher authenticated version and full citation details are available on Springer's website (LNAI 15957). https://doi.org/10.1007/978-3-032-00891-6_28

2411.19628 2025-07-28 cs.CV cs.CL cs.LG cs.MM 88%

Accelerating Multimodal Large Language Models via Dynamic Visual-Token Exit and the Empirical Findings

Qiong Wu, Wenhao Lin, Yiyi Zhou, Weihao Ye, Zhanpeng Zen, Xiaoshuai Sun, Rongrong Ji

机构 * Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University（中国教育部多媒体可信感知与高效计算重点实验室，厦门大学）； Institute of Artificial Intelligence, Xiamen University（厦门大学人工智能研究院）

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

2507.09185 2025-07-15 cs.CL cs.LG 88%

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models

Ameen Ali, Shahar Katz, Lior Wolf, Ivan Titov

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

2507.07599 2025-07-11 cs.AI cs.CL 88%

Enhancing Vaccine Safety Surveillance: Extracting Vaccine Mentions from Emergency Department Triage Notes Using Fine-Tuned Large Language Models

Sedigh Khademi, Jim Black, Christopher Palmer, Muhammad Javed, Hazel Clothier, Jim Buttery, Gerardo Luis Dimaguila

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 5 pages

Journal ref Medinfo 2025

2507.07572 2025-07-11 cs.CL cs.AI cs.CV 88%

Single-to-mix Modality Alignment with Multimodal Large Language Model for Document Image Machine Translation

Yupu Liang, Yaping Zhang, Zhiyang Zhang, Yang Zhao, Lu Xiang, Chengqing Zong, Yu Zhou

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 ACL 2025 Main

2402.12993 2025-07-01 cs.IR cs.AI cs.LG q-bio.QM 88%

ChemMiner: A Large Language Model Agent System for Chemical Literature Data Mining

Kexin Chen, Yuyang Du, Junyou Li, Hanqun Cao, Menghao Guo, Xilin Dang, Lanqing Li, Jiezhong Qiu, Pheng Ann Heng, Guangyong Chen

机构 * The Chinese University of Hong Kong, New Territories, Hong Kong SAR（香港中文大学）； Zhejiang Lab, Zhejiang University, Hangzhou, China（浙江大学杭州实验室）； Hangzhou Institute of Medicine, Chinese Academy of Sciences, Hangzhou, China（中国科学院杭州医学研究所）

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

2506.22508 2025-07-01 cs.CL cs.AI 88%

AgentStealth: Reinforcing Large Language Model for Anonymizing User-generated Text

Chenyang Shao, Tianxing Li, Chenhao Pu, Fengli Xu, Yong Li

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 This work has been submitted to NeurIPS 2025. Under review

2506.21606 2025-06-30 cs.CL cs.AI cs.CY 88%

Large Language Models as symbolic DNA of cultural dynamics

Parham Pourdavood, Michael Jacob, Terrence Deacon

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 28 pages, 1 figure

2505.20888 2025-06-30 cs.CL cs.AI 88%

EasyDistill: A Comprehensive Toolkit for Effective Knowledge Distillation of Large Language Models

Chengyu Wang, Junbing Yan, Wenrui Cai, Yuanhao Yue, Jun Huang

机构 * Alibaba Cloud Computing（阿里云计算）； Shanghai Jiao Tong University（上海交通大学）

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

2506.05432 2025-06-27 cs.LG cs.AI 88%

PCDVQ: Enhancing Vector Quantization for Large Language Models via Polar Coordinate Decoupling

Yuxuan Yue, Zukang Xu, Zhihang Yuan, Dawei Yang, Jianlong Wu, Liqiang Nie

机构 * Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））； Houmo AI

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

2506.20251 2025-06-26 cs.LG cs.AI 88%

Q-resafe: Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language Models

Kejia Chen, Jiawen Zhang, Jiacong Hu, Yu Wang, Jian Lou, Zunlei Feng, Mingli Song

机构 * The State Key Laboratory of Blockchain and Data Security, Zhejiang University（区块链与数据安全国家重点实验室，浙江大学）； Sun Yat-sen University（中山大学）； Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security（杭州高新技术区（滨江）区块链与数据安全研究院）

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 ICML 2025

2406.18219 2025-06-24 cs.CL cs.LG 88%

A Closer Look into Mixture-of-Experts in Large Language Models

Ka Man Lo, Zeyu Huang, Zihan Qiu, Zili Wang, Jie Fu

机构 * University of Macau（澳门大学）； University of Edinburgh（爱丁堡大学）； Tsinghua University（清华大学）； INF Technology（INF技术）； Shanghai AI Lab（上海人工智能实验室）

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

Comments NAACL 2025 Findings

2502.01208 2025-06-23 cs.LG cs.CL 88%

On Almost Surely Safe Alignment of Large Language Models at Inference-Time

Xiaotong Ji, Shyam Sundhar Ramesh, Matthieu Zimmer, Ilija Bogunovic, Jun Wang, Haitham Bou Ammar

机构 * Huawei Noah’s Ark Lab（华为诺亚实验室）； Imperial College London（帝国理工学院伦敦分校）； University College London（伦敦大学学院）； UCL Centre for Artificial Intelligence（UCL人工智能中心）

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

2506.14158 2025-06-18 cs.CL cs.AI 88%

S$^4$C: Speculative Sampling with Syntactic and Semantic Coherence for Efficient Inference of Large Language Models

Tao He, Guang Huang, Yu Yang, Tianshi Xu, Sicheng Zhao, Guiguang Ding, Pengyang Wang, Feng Tian

机构 * GRG Banking Equipment Co., Ltd（GRG银行设备有限公司）； South China University of Technology（华南理工大学）； University of Macau（澳门大学）； Tsinghua University（清华大学）

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

2506.13472 2025-06-18 cs.CL cs.AI 88%

ROSAQ: Rotation-based Saliency-Aware Weight Quantization for Efficiently Compressing Large Language Models

Junho Yoon, Geom Lee, Donghyeon Jeon, Inho Kang, Seung-Hoon Na

机构 * Jeonbuk National University（全州国立大学）； Naver ； UNIST（全南国立科学技术大学）

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, 2 figures

2506.09342 2025-06-17 cs.CL cs.AI 88%

Latent Multi-Head Attention for Small Language Models

Sushant Mehta, Raj Dandekar, Rajat Dandekar, Sreedath Panat

机构 * Vizuara AI Labs（Vizuara AI实验室）

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

Comments 6 pages, 1 figure. 5 tables

1. 效率与部署 22368 篇

Group-SAE: Efficient Training of Sparse Autoencoders for Large Language Models via Layer Groups

Beyond Spurious Signals: Debiasing Multimodal Large Language Models via Counterfactual Inference and Adaptive Expert Routing

Growing Perspectives: Modelling Embodied Perspective Taking and Inner Narrative Development Using Large Language Models

Efficient Detection of Toxic Prompts in Large Language Models

CALR: Corrective Adaptive Low-Rank Decomposition for Efficient Large Language Model Layer Compression

AdLoCo: adaptive batching significantly improves communications efficiency and convergence for Large Language Models

Ask Good Questions for Large Language Models

When Language Overrules: Revealing Text Dominance in Multimodal Large Language Models

P/D-Device: Disaggregated Large Language Model between Cloud and Devices

Less is More: Selective Reflection for Compatible and Efficient Knowledge Distillation in Large Language Models

QDyLoRA: Quantized Dynamic Low-Rank Adaptation for Efficient Large Language Model Tuning

Learning to Inference Adaptively for Multimodal Large Language Models

Insights into resource utilization of code small language models serving with runtime engines and execution providers

SmallThinker: A Family of Efficient Large Language Models Natively Trained for Local Deployment

Enhancing Ultra-Low-Bit Quantization of Large Language Models Through Saliency-Aware Partial Retraining

Accelerating Multimodal Large Language Models via Dynamic Visual-Token Exit and the Empirical Findings

Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models

Enhancing Vaccine Safety Surveillance: Extracting Vaccine Mentions from Emergency Department Triage Notes Using Fine-Tuned Large Language Models

Single-to-mix Modality Alignment with Multimodal Large Language Model for Document Image Machine Translation

ChemMiner: A Large Language Model Agent System for Chemical Literature Data Mining

AgentStealth: Reinforcing Large Language Model for Anonymizing User-generated Text

Large Language Models as symbolic DNA of cultural dynamics

EasyDistill: A Comprehensive Toolkit for Effective Knowledge Distillation of Large Language Models

PCDVQ: Enhancing Vector Quantization for Large Language Models via Polar Coordinate Decoupling

Q-resafe: Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language Models

A Closer Look into Mixture-of-Experts in Large Language Models

On Almost Surely Safe Alignment of Large Language Models at Inference-Time

S$^4$C: Speculative Sampling with Syntactic and Semantic Coherence for Efficient Inference of Large Language Models

ROSAQ: Rotation-based Saliency-Aware Weight Quantization for Efficiently Compressing Large Language Models

Latent Multi-Head Attention for Small Language Models