语言大模型 / LLM

DAM: Dynamic Attention Mask for Long-Context Large Language Model Inference Acceleration

Hanzhi Zhang, Heng Fan, Kewei Sha, Yan Huang, Yunhe Feng

机构 * LLaVi Lab, Department of Computer Science & Engineering（LLaVi实验室，计算机科学与工程系） ； Department of Data Science（数据科学系） 纠错

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

Persistent Topological Features in Large Language Models

Yuri Gardinazzi, Karthik Viswanathan, Giada Panerai, Alessio Ansuini, Alberto Cazzaniga, Matteo Biagetti

机构 * Area Science Park, Trieste, Italy（特雷斯特科学公园） ； University of Trieste, Trieste, Italy（特雷斯特大学） ； University of Amsterdam, Amsterdam, the Netherlands（阿姆斯特丹大学） 纠错

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 10+17 pages, 17 figures, 3 tables. Accepted as poster at ICML 2025

Prompt-based Depth Pruning of Large Language Models

Juyun Wee, Minjae Park, Jaeho Lee

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 Project: https://jwee01.github.io/PuDDing/ Code: https://github.com/tada0347/PuDDing

Deploying Open-Source Large Language Models: A performance Analysis

Yannis Bendi-Ouis, Dan Dutartre, Xavier Hinaut

机构 * Mnemosyne Inria Bordeaux, France（Mnemosyne 国家信息与自动化技术研究院波尔多分部） ； SED Inria Bordeaux, France（SED 国家信息与自动化技术研究院波尔多分部） 纠错

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

Securing Large Language Models: Threats, Vulnerabilities and Responsible Practices

Sara Abdali, Richard Anarfi, CJ Barberan, Jia He, Erfan Shayegani

机构 * Microsoft（微软） ； University of California, Riverside (UCR)（加州大学河滨分校） 纠错

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

Token Constraint Decoding Improves Robustness on Question Answering for Large Language Models

Jui-Ming Yao, Hao-Yuan Chen, Zi-Xian Tang, Bing-Jia Tan, Sheng-Wei Peng, Bing-Cheng Xie, Shun-Feng Su

机构 * Department of Computer Science and Information Engineering（计算机科学与信息工程系） ； National Taiwan University of Science and Technology（台湾科技大学） ； Bachelor’s Program in Computer Science（计算机科学学士班） ； University of London（伦敦大学） 纠错

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

Olica: Efficient Structured Pruning of Large Language Models without Retraining

Jiujun He, Huazhen Lin

机构 * Center of Statistical Research, School of Statistics（统计研究中心、统计学与数据科学学院） ； New Cornerstone Science Laboratory, Southwestern University of Finance（新基石科学实验室、西南财经大学） 纠错

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 to ICML 2025

High-Throughput Phenotyping of Clinical Text Using Large Language Models

Daniel B. Hier, S. Ilyas Munzir, Anne Stahlfeld, Tayo Obafemi-Ajayi, Michael D. Carrithers

机构 * Dept. of Neurology \& Rehabilitation University of Illinois at Chicago Chicago, IL USA ； Engineering Program Missouri State University Springfield, MO USA 纠错

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 Submitted to IEEE-EMBS International Conference on Biomedical and Health Informatics, Houston TX

Journal ref 2024 IEEE-EMBS International Conference on Biomedical and Health Informatics, Houston TX, USA pp. 1-8

Large Language Models Can Be a Viable Substitute for Expert Political Surveys When a Shock Disrupts Traditional Measurement Approaches

Patrick Y. Wu

机构 * Department of Computer Science（计算机科学系） ； American University（美国大学） 纠错

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 19 pages, 6 figures

Unified Game Moderation: Soft-Prompting and LLM-Assisted Label Transfer for Resource-Efficient Toxicity Detection

Zachary Yang, Domenico Tullo, Reihaneh Rabbany

机构 * Ubisoft La Forge（育碧La Forge） ； McGill University（麦吉尔大学） ； Mila ； CIFAR AI Chair（CIFAR人工智能主席） 纠错

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

Comments 11 pages, 1 figure, 9 Tables, KDD 2025 ADS Track

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models

Yifeng Gu, Zicong Jiang, Jianxiu Jin, Kailing Guo, Ziyang Zhang, Xiangmin Xu

机构 * South China University of Technology（南方科技大学） ； Pazhou Laboratory（琶洲实验室） 纠错

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 14 pages, 8 figures

Why Safeguarded Ships Run Aground? Aligned Large Language Models' Safety Mechanisms Tend to Be Anchored in The Template Region

Chak Tou Leong, Qingyu Yin, Jian Wang, Wenjie Li

机构 * Department of Computing, The Hong Kong Polytechnic University（计算系，香港理工大学） ； Zhejiang University（浙江大学） 纠错

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 ACL 2025 Main

Scalable Parameter and Memory Efficient Pretraining for LLM: Recent Algorithmic Advances and Benchmarking

Athanasios Glentis, Jiaxiang Li, Qiulin Shang, Andi Han, Ioannis Tsaknakis, Quan Wei, Mingyi Hong

机构 * Department of Electrical and Computer Engineering, University of Minnesota（明尼苏达大学电气与计算机工程系） ； Peking University（北京大学） ； School of Mathematics and Statistics, University of Sydney（悉尼大学数学与统计学学院） 纠错

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

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models

Yongcan Yu, Yanbo Wang, Ran He, Jian Liang

机构 * NLPR & MAIS, Institute of Automation, Chinese Academy of Sciences（国家工程实验室与人工智能研究所，中国科学院） ； School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院） 纠错

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 Under Review

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models

Tzu-Tao Chang, Shivaram Venkataraman

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

AutoElicit: Using Large Language Models for Expert Prior Elicitation in Predictive Modelling

Alexander Capstick, Rahul G. Krishnan, Payam Barnaghi

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

What Changed? Detecting and Evaluating Instruction-Guided Image Edits with Multimodal Large Language Models

Lorenzo Baraldi, Davide Bucciarelli, Federico Betti, Marcella Cornia, Lorenzo Baraldi, Nicu Sebe, Rita Cucchiara

机构 * University of Modena and Reggio Emilia（摩德纳和雷吉奥艾米利亚大学） ； University of Pisa（比萨大学） ； University of Trento（特伦托大学） ； IIT-CNR 纠错

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

EPIC: Efficient Position-Independent Caching for Serving Large Language Models

Junhao Hu, Wenrui Huang, Weidong Wang, Haoyi Wang, Tiancheng Hu, Qin Zhang, Hao Feng, Xusheng Chen, Yizhou Shan, Tao Xie

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

FiLLM -- A Filipino-optimized Large Language Model based on Southeast Asia Large Language Model (SEALLM)

Carlos Jude G. Maminta, Isaiah Job Enriquez, Deandre Nigel Nunez, Michael B. Dela Fuente

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

Conformity in Large Language Models

Xiaochen Zhu, Caiqi Zhang, Tom Stafford, Nigel Collier, Andreas Vlachos

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 (main body), 9 figures (main body), ACL 2025 Main

Model-Distributed Inference for Large Language Models at the Edge

Davide Macario, Hulya Seferoglu, Erdem Koyuncu

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

FBQuant: FeedBack Quantization for Large Language Models

Yijiang Liu, Hengyu Fang, Liulu He, Rongyu Zhang, Yichuan Bai, Yuan Du, Li Du

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 to IJCAI 2025

Model Merging in Pre-training of Large Language Models

Yunshui Li, Yiyuan Ma, Shen Yan, Chaoyi Zhang, Jing Liu, Jianqiao Lu, Ziwen Xu, Mengzhao Chen, Minrui Wang, Shiyi Zhan, Jin Ma, Xunhao Lai, Deyi Liu, Yao Luo, Xingyan Bin, Hongbin Ren, Mingji Han, Wenhao Hao, Bairen Yi, LingJun Liu, Bole Ma, Xiaoying Jia, Xun Zhou, Siyuan Qiao, Liang Xiang, Yonghui Wu

机构 * ByteDance Seed（字节跳动种子） 纠错

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

Efficient Shapley Value-based Non-Uniform Pruning of Large Language Models

Chuan Sun, Han Yu, Lizhen Cui, Xiaoxiao Li

机构 * College of Computing and Data Science（计算与数据科学学院） ； Nanyang Technological University（南洋理工大学） ； School of Software（软件学院） ； Shandong University（山东大学） ； Department of Electrical and Computer Engineering（电气与计算机工程系） ； The University of British Columbia（不列颠哥伦比亚大学） 纠错

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

A Framework for Real-time Safeguarding the Text Generation of Large Language Model

Ximing Dong, Dayi Lin, Shaowei Wang, Ahmed E. Hassan

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

LAS: Loss-less ANN-SNN Conversion for Fully Spike-Driven Large Language Models

Long Chen, Xiaotian Song, Yanan Sun

机构 * Collage of Computer Science, Sichuan University（计算机科学学院，四川大学） 纠错

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

Efficient Fairness Testing in Large Language Models: Prioritizing Metamorphic Relations for Bias Detection

Suavis Giramata, Madhusudan Srinivasan, Venkat Naidu Gudivada, Upulee Kanewala

机构 * Computer Science Department East Carolina University（东卡罗来纳大学计算机科学系） ； Computer Science Department University of North Florida（北佛罗里达大学计算机科学系） 纠错

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

XG-NID: Dual-Modality Network Intrusion Detection using a Heterogeneous Graph Neural Network and Large Language Model

Yasir Ali Farrukh, Syed Wali, Irfan Khan, Nathaniel D. Bastian

机构 * Clean and Resilient Energy System Lab (CARES), Department of Electrical & Computer Engineering, Texas A&M University（清洁而坚韧的能量系统实验室（CARES），电气与计算机工程系，德克萨斯A&M大学） ； Army Cyber Institute, Department of Electrical Engineering & Computer Science, United States Military Academy（陆军网络学院，电气工程与计算机科学系，美国军事学院） 纠错

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 19 pages, 6 figures

Automatic Calibration for Membership Inference Attack on Large Language Models

Saleh Zare Zade, Yao Qiang, Xiangyu Zhou, Hui Zhu, Mohammad Amin Roshani, Prashant Khanduri, Dongxiao Zhu

机构 * Department of Computer Science, Wayne State University（韦恩州立大学计算机科学系） ； Department of Computer Science, Oakland University（奥克兰大学计算机科学系） 纠错

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

MoDeGPT: Modular Decomposition for Large Language Model Compression

Chi-Heng Lin, Shangqian Gao, James Seale Smith, Abhishek Patel, Shikhar Tuli, Yilin Shen, Hongxia Jin, Yen-Chang Hsu

机构 * Samsung Research America（三星美国研究实验室） 纠错

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 ICLR 2025 Oral