{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:32:25Z","timestamp":1767339145345,"version":"3.45.0"},"publisher-location":"Singapore","reference-count":26,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819533428","type":"print"},{"value":"9789819533435","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T00:00:00Z","timestamp":1763856000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T00:00:00Z","timestamp":1763856000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-95-3343-5_36","type":"book-chapter","created":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T06:29:47Z","timestamp":1763792987000},"page":"466-478","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["EvoP: Robust LLM Inference via\u00a0Evolutionary Pruning"],"prefix":"10.1007","author":[{"given":"Shangyu","family":"Wu","sequence":"first","affiliation":[]},{"given":"Hongchao","family":"Du","sequence":"additional","affiliation":[]},{"given":"Ying","family":"Xiong","sequence":"additional","affiliation":[]},{"given":"Shuai","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Tei-Wei","family":"Kuo","sequence":"additional","affiliation":[]},{"given":"Nan","family":"Guan","sequence":"additional","affiliation":[]},{"given":"Chun Jason","family":"Xue","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,23]]},"reference":[{"key":"36_CR1","unstructured":"Ashkboos, S., et\u00a0al.: Slicegpt: compress large language models by deleting rows and columns. In: Proceedings of ICLR (2024)"},{"key":"36_CR2","unstructured":"Chowdhery, A., et\u00a0al.: Palm: scaling language modeling with pathways. J. Mach. Learn. Res. 24, 240:1\u2013240:113 (2023)"},{"key":"36_CR3","unstructured":"Devlin, J., et\u00a0al.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL-HLT, pp. 4171\u20134186 (2019)"},{"key":"36_CR4","unstructured":"Frantar, E., Alistarh, D.: Sparsegpt: massive language models can be accurately pruned in one-shot. In: Proceedings of ICML (2023)"},{"key":"36_CR5","unstructured":"Gao, L., et\u00a0al.: A framework for few-shot language model evaluation (2024)"},{"key":"36_CR6","unstructured":"Huang, L., et\u00a0al.: RAEE: a training-free retrieval-augmented early exiting framework for efficient inference. CoRR (2024)"},{"key":"36_CR7","doi-asserted-by":"crossref","unstructured":"Jiang, C., et\u00a0al.: Efficient DNN neuron pruning by minimizing layer-wise nonlinear reconstruction error. In: Proceedings of IJCAI, pp. 2298\u20132304 (2018)","DOI":"10.24963\/ijcai.2018\/318"},{"key":"36_CR8","unstructured":"LeCun, Y., Denker, J.S., Solla, S.A.: Optimal brain damage. In: Proceedings of NeurIPS, pp. 598\u2013605 (1989)"},{"key":"36_CR9","unstructured":"Ma, X., Fang, G., Wang, X.: LLM-pruner: on the structural pruning of large language models. In: Proceedings of NeurIPS (2023)"},{"key":"36_CR10","unstructured":"Merity, S., et\u00a0al.: Pointer sentinel mixture models. In: Proceedings of ICLR (2017)"},{"key":"36_CR11","unstructured":"Raffel, C., et\u00a0al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21, 140:1\u2013140:67 (2020)"},{"key":"36_CR12","unstructured":"Scao, T.L., et\u00a0al.: BLOOM: A 176b-parameter open-access multilingual language model. CoRR (2022)"},{"key":"36_CR13","unstructured":"Song, J., et\u00a0al.: SLEB: streamlining LLMs through redundancy verification and elimination of transformer blocks. In: Proceedings of ICML (2024)"},{"key":"36_CR14","unstructured":"Sun, M., et\u00a0al.: A simple and effective pruning approach for large language models. In: Proceedings of ICLR (2024)"},{"key":"36_CR15","unstructured":"Thoppilan, R., et\u00a0al.: Lamda: language models for dialog applications. CoRR (2022)"},{"key":"36_CR16","unstructured":"Touvron, H., et\u00a0al.: Llama 2: open foundation and fine-tuned chat models. CoRR (2023)"},{"key":"36_CR17","unstructured":"Touvron, H., et\u00a0al.: Llama: open and efficient foundation language models. CoRR (2023)"},{"key":"36_CR18","doi-asserted-by":"crossref","unstructured":"Voita, E., et\u00a0al.: Analyzing multi-head self-attention: specialized heads do the heavy lifting, the rest can be pruned. In: Proceedings of ACL, pp. 5797\u20135808 (2019)","DOI":"10.18653\/v1\/P19-1580"},{"key":"36_CR19","doi-asserted-by":"crossref","unstructured":"Wang, Z.: Sparsert: accelerating unstructured sparsity on GPUs for deep learning inference. In: Proceedings of PACT, pp. 31\u201342 (2020)","DOI":"10.1145\/3410463.3414654"},{"key":"36_CR20","doi-asserted-by":"crossref","unstructured":"Xin, J., et\u00a0al.: Deebert: dynamic early exiting for accelerating BERT inference. In: Proceedings of ACL, pp. 2246\u20132251 (2020)","DOI":"10.18653\/v1\/2020.acl-main.204"},{"key":"36_CR21","unstructured":"Zeng, A., et\u00a0al.: GLM-130B: an open bilingual pre-trained model. In: Proceedings of ICLR (2023)"},{"key":"36_CR22","unstructured":"Zhang, P., et\u00a0al.: Tinyllama: an open-source small language model. CoRR (2024)"},{"key":"36_CR23","unstructured":"Zhang, S., et\u00a0al.: OPT: open pre-trained transformer language models. CoRR (2022)"},{"key":"36_CR24","unstructured":"Zhang, Y., et\u00a0al.: Learning best combination for efficient N: M sparsity. In: Proceedings of NeurIPS (2022)"},{"key":"36_CR25","unstructured":"Zhang, Y., et\u00a0al.: Dynamic sparse no training: training-free fine-tuning for sparse llms. In: Proceedings of ICLR (2024)"},{"key":"36_CR26","unstructured":"Zhou, A., et\u00a0al.: Learning N: M fine-grained structured sparse neural networks from scratch. In: Proceedings of ICLR (2021)"}],"container-title":["Lecture Notes in Computer Science","Natural Language Processing and Chinese Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-3343-5_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T06:30:09Z","timestamp":1763793009000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-3343-5_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,23]]},"ISBN":["9789819533428","9789819533435"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-3343-5_36","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,23]]},"assertion":[{"value":"23 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NLPCC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CCF International Conference on Natural Language Processing and Chinese Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Urumqi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 August 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 August 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2025\/index.php","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}