{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:29:43Z","timestamp":1774420183272,"version":"3.50.1"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888911","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["LEP: Leveraging Local Entropy Pruning for Sparsity in Large Language Models"],"prefix":"10.1109","author":[{"given":"Yuli","family":"Chen","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications,State Key Laboratory of Networking and Switching Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Cheng","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,State Key Laboratory of Networking and Switching Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingying","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,State Key Laboratory of Networking and Switching Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuhao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,State Key Laboratory of Networking and Switching Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhixuan","family":"Wu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,State Key Laboratory of Networking and Switching Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fanshen","family":"Meng","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,State Key Laboratory of Networking and Switching Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"issue":"5","key":"ref1","article-title":"Gpt-4 technical report. arxiv 2303.08774","volume":"2","author":"OpenAI","year":"2023","journal-title":"View in Article"},{"key":"ref2","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref3","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref4","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref5","article-title":"Opt: Open pre-trained transformer language models","author":"Zhang","year":"2022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11023-020-09548-1"},{"key":"ref7","article-title":"Llm-fp4: 4-bit floating-point quantized transformers","volume-title":"Conference on Empirical Methods in Natural Language Processing","author":"yang Liu","year":"2023"},{"key":"ref8","first-page":"30318","article-title":"Gpt3. int8 (): 8-bit matrix multiplication for transformers at scale","volume":"35","author":"Dettmers","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","article-title":"Optq: Accurate quantization for generative pre-trained transformers","volume-title":"The Eleventh International Conference on Learning Representations","author":"Frantar"},{"key":"ref10","article-title":"A survey on knowledge distillation of large language models","author":"Xu","year":"2024"},{"key":"ref11","article-title":"MiniLLM: Knowledge distillation of large language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Gu"},{"key":"ref12","article-title":"In-context learning distillation: Transferring few-shot learning ability of pre-trained language models","author":"Huang","year":"2022"},{"key":"ref13","first-page":"38087","article-title":"Smoothquant: Accurate and efficient post-training quantization for large language models","volume-title":"International Conference on Machine Learning","author":"Xiao"},{"key":"ref14","article-title":"The emergence of essential sparsity in large pre-trained models: The weights that matter","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"JAISWAL"},{"key":"ref15","article-title":"LLM-pruner: On the structural pruning of large language models","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Ma"},{"key":"ref16","first-page":"10323","article-title":"SparseGPT: Massive language models can be accurately pruned in one-shot","volume-title":"Proceedings of the 40th International Conference on Machine Learning, ser. Proceedings of Machine Learning Research","volume":"202","author":"Frantar"},{"key":"ref17","article-title":"A simple and effective pruning approach for large language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Sun"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.20944\/preprints202310.1487.v2","article-title":"Plug-and-play: An efficient post-training pruning method for large language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Zhang"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00704"},{"key":"ref20","article-title":"Lorashear: Efficient large language model structured pruning and knowledge recovery","volume-title":"ArXiv","author":"Chen","year":"2023"},{"key":"ref21","first-page":"15834","article-title":"The lottery ticket hypothesis for pre-trained bert networks","volume":"33","author":"Chen","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref22","article-title":"Dynamic network surgery for efficient dnns","volume":"29","author":"Guo","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00094"},{"key":"ref24","first-page":"1135","article-title":"Learning both weights and connections for efficient neural networks","volume-title":"Proceedings of the 28th International Conference on Neural Information Processing Systems Volume 1, ser. NIPS\u201915","author":"Han"},{"key":"ref25","article-title":"Beyond size: How gradients shape pruning decisions in large language models","author":"Das","year":"2024"},{"key":"ref26","article-title":"Second order derivatives for network pruning: Optimal brain surgeon","volume":"5","author":"Hassibi","year":"1992","journal-title":"Advances in neural information processing systems"},{"key":"ref27","first-page":"547","article-title":"On measures of entropy and information","volume-title":"Proceedings of the fourth Berkeley symposium on mathematical statistics and probability, volume 1: contributions to the theory of statistics","volume":"4","author":"Renyi"},{"key":"ref28","article-title":"Vicuna: An open-source chatbot impressing gpt4 with 90%* chatgpt quality","author":"Chiang","year":"2023"},{"key":"ref29","article-title":"Pointer sentinel mixture models","author":"Merity","year":"2016"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3115\/1075812.1075835"},{"issue":"140","key":"ref31","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of machine learning research"},{"key":"ref32","first-page":"353","article-title":"GLUE: A multi-task benchmark and analysis platform for natural language understanding","volume-title":"Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP","author":"Wang"},{"key":"ref33","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/P19-1472","article-title":"Hellaswag: Can a machine really finish your sentence?","volume-title":"Annual Meeting of the Association for Computational Linguistics","author":"Zellers"},{"key":"ref34","first-page":"1112","article-title":"A broad-coverage challenge corpus for sentence understanding through inference","volume-title":"Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)","author":"Williams"},{"key":"ref35","first-page":"2381","article-title":"Can a suit of armor conduct electricity? a new dataset for open book question answering","volume-title":"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing","author":"Mihaylov"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10888911.pdf?arnumber=10888911","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:51Z","timestamp":1774416411000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888911\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888911","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}