{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T23:03:18Z","timestamp":1784329398260,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":20,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819233939","type":"print"},{"value":"9789819233946","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T00:00:00Z","timestamp":1784332800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T00:00:00Z","timestamp":1784332800000},"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":[[2027]]},"DOI":"10.1007\/978-981-92-3394-6_5","type":"book-chapter","created":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T22:21:00Z","timestamp":1784326860000},"page":"50-63","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Lightweight Debiased Pruning: Stabilizing Highly Sparse LLMs with Minimal Overhead"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-3286-4567","authenticated-orcid":false,"given":"Yang","family":"Xiao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiqing","family":"Gu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tiejun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,18]]},"reference":[{"key":"5_CR1","doi-asserted-by":"publisher","unstructured":"Park, S., Choi, J., Lee, S., Kang, U.: A comprehensive survey of compression algorithms for language models. CoRR abs\/2401.15347 (2024). doi:https:\/\/doi.org\/10.48550\/arXiv.2401.15347","DOI":"10.48550\/arXiv.2401.15347"},{"key":"5_CR2","first-page":"1877","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","author":"TB Brown","year":"2020","unstructured":"Brown, T.B., et al.: Language models are few-shot learners. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M.F., Lin, H. (eds.) Advances in Neural Information Processing Systems 33: Proceedings of the 34th International Conference on Neural Information Processing Systems, pp. 1877\u20131901. Curran Associates Inc., Red Hook, NY, USA (2020)"},{"key":"5_CR3","unstructured":"Touvron, H., et al.: LLaMA: Open and efficient foundation language models. CoRR abs\/2302.13971 (2023). doi:10.48550\/arXiv.2302.13971."},{"key":"5_CR4","doi-asserted-by":"publisher","first-page":"12868","DOI":"10.18653\/v1\/2025.findings-emnlp.690","volume-title":"Findings of the Association for Computational Linguistics: EMNLP 2025","author":"Y Kang","year":"2025","unstructured":"Kang, Y., et al.: SwiftPrune: Hessian-free weight pruning for large language models. In: Findings of the Association for Computational Linguistics: EMNLP 2025, pp. 12868\u201312879. Association for Computational Linguistics, Suzhou, China (2025)"},{"key":"5_CR5","first-page":"38887","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","author":"A Jaiswal","year":"2023","unstructured":"Jaiswal, A., Liu, S., Chen, T., Wang, Z.: The emergence of essential sparsity in large pre-trained models: the weights that matter. In: Oh, A., Naumann, T., Globerson, A., Saenko, K., Hardt, M., Levine, S. (eds.) Advances in Neural Information Processing Systems 36, pp. 38887\u201338901. Curran Associates, Inc., Red Hook, NY, USA (2023)"},{"key":"5_CR6","first-page":"1960","volume-title":"In: Proc. 31st ACM SIGKDD Conf. Knowledge Discovery and Data Mining (KDD 2025)","author":"S Zhang","year":"2025","unstructured":"Zhang, S., Zhang, L., Zhou, J., Zheng, Z., Xiong, H.: LLM-Eraser: optimizing large language model unlearning through selective pruning. In: Sun, Y., Chierichetti, F., Lauw, H.W., Perlich, C., Tok, W.H., Tomkins, A. (eds.) Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, V.1, pp. 1960\u20131971. ACM, New York, NY, USA (2025)"},{"key":"5_CR7","first-page":"10323","volume-title":"Proc. 40th Int. Conf. Machine Learning (ICML 2023)","author":"E Frantar","year":"2023","unstructured":"Frantar, E., Alistarh, D.: SparseGPT: massive language models can be accurately pruned in one-shot. In: Krause, A., Brunskill, E., Cho, K., Engelhardt, B., Sabato, S., Scarlett, J. (eds.) Proceedings of the 40th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 202, pp. 10323\u201310337. PMLR, Honolulu, HI, USA (2023)"},{"key":"5_CR8","unstructured":"Sun, M., Liu, Z., Bair, A., Kolter, J.Z.: A simple and effective pruning approach for large language models. In: Proc. 12th Int. Conf. Learning Representations (ICLR) (2024)"},{"key":"5_CR9","unstructured":"Dettmers, T., et al.: SpQR: A sparse-quantized representation for near-lossless LLM weight compression. In: Proc. 12th Int. Conf. Learning Representations (ICLR) (2024)."},{"key":"5_CR10","first-page":"30318","volume-title":"Proc. 36th Conf. Neural Information Processing Systems (NeurIPS 2022)","author":"T Dettmers","year":"2022","unstructured":"Dettmers, T., Lewis, M., Belkada, Y., Zettlemoyer, L.: LLM.int8(): 8-bit matrix multiplication for transformers at scale. In: Koyejo, S., Mohamed, S., Agarwal, A., Belgrave, D., Cho, K., Oh, A. (eds.) Advances in Neural Information Processing Systems 35, pp. 30318\u201330332. Curran Associates, Inc., Red Hook, NY, USA (2022)"},{"key":"5_CR11","doi-asserted-by":"publisher","first-page":"1648","DOI":"10.18653\/v1\/2023.emnlp-main.102","volume-title":"Proc. Conf. Empirical Methods in Natural Language Processing (EMNLP 2023)","author":"X Wei","year":"2023","unstructured":"Wei, X., Zhang, Y., Li, Y., Zhang, X., Gong, R., Guo, J., Liu, X.: Outlier Suppression+: accurate quantization of large language models by equivalent and effective shifting and scaling. In: Bouamor, H., Pino, J., Bali, K. (eds.) Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 1648\u20131665. Association for Computational Linguistics, Singapore (2023)"},{"key":"5_CR12","first-page":"57101","volume-title":"Proc. 41st Int. Conf. Machine Learning (ICML 2024)","author":"L Yin","year":"2024","unstructured":"Yin, L., et al.: Outlier weighed layerwise sparsity (OWL): a missing secret sauce for pruning LLMs to high sparsity. In: Salakhutdinov, R., et al., (eds.) Proceedings of the 41st International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 235, pp. 57101\u201357115. PMLR, Vienna, Austria (2024)"},{"key":"5_CR13","first-page":"7934","volume-title":"Proc. 42nd Int. Conf. Machine Learning (ICML 2025)","author":"Y Chen","year":"2025","unstructured":"Chen, Y., Cheng, B., Han, J., Zhang, Y., Li, Y., Zhang, S.: DLP: dynamic layerwise pruning in large language models. In: Singh, A., et al. (eds.) Proceedings of the 42nd International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 267, pp. 7934\u20137956. PMLR, Vancouver, Canada (2025)"},{"key":"5_CR14","first-page":"5298","volume-title":"Proc. 41st Int. Conf. Machine Learning (ICML 2024)","author":"R Cai","year":"2024","unstructured":"Cai, R., Muralidharan, S., Heinrich, G., Yin, H., Wang, Z., Kautz, J., Molchanov, P.: FLEXTRON: many-in-one flexible large language model. In: Salakhutdinov, R., et al., (eds.) Proceedings of the 41st International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 235, pp. 5298\u20135311. PMLR, Vienna, Austria (2024)"},{"key":"5_CR15","first-page":"141292","volume-title":"Proc. 38th Conf. Neural Information Processing Systems (NeurIPS 2024)","author":"L Li","year":"2024","unstructured":"Li, L., et al.: Discovering sparsity allocation for layer-wise pruning of large language models. In: Globerson, A., Mackey, L., Belgrave, D., Fan, A., Paquet, U., Tomczak, J., Zhang, C. (eds.) Advances in Neural Information Processing Systems 37, pp. 141292\u2013141317. Curran Associates, Inc., Red Hook, NY, USA (2024)"},{"key":"5_CR16","first-page":"21702","volume-title":"Proc. 37th Int. Conf. Neural Information Processing Systems (NeurIPS 2023)","author":"X Ma","year":"2023","unstructured":"Ma, X., Fang, G., Wang, X.: LLM-Pruner: on the structural pruning of large language models. In: Oh, A., Naumann, T., Globerson, A., Saenko, K., Hardt, M., Levine, S. (eds.) Advances in Neural Information Processing Systems 36, pp. 21702\u201321720. Curran Associates, Inc., Red Hook, NY, USA (2023)"},{"key":"5_CR17","doi-asserted-by":"crossref","unstructured":"Ling, G., Wang, Z., Yan, Y., Liu, Q.: SlimGPT: layer-wise structured pruning for large language models. In: Globerson, A., Mackey, L., Belgrave, D., Fan, A., Paquet, U., Tomczak, J., Zhang, C. (eds.) Advances in Neural Information Processing Systems 37, pp. 107112\u2013107137. Curran Associates, Inc., Red Hook, NY, USA (2024)","DOI":"10.52202\/079017-3401"},{"key":"5_CR18","doi-asserted-by":"publisher","first-page":"3013","DOI":"10.18653\/v1\/2024.findings-acl.178","volume-title":"Findings of the Association for Computational Linguistics: ACL 2024","author":"M Zhang","year":"2024","unstructured":"Zhang, M., Chen, H., Shen, C., Yang, Z., Ou, L., Yu, X., Zhuang, B.: LoRAPrune: structured pruning meets low-rank parameter-efficient fine-tuning. In: Ku, L.-W., Martins, A., Srikumar, V. (eds.) Findings of the Association for Computational Linguistics: ACL 2024, pp. 3013\u20133026. Association for Computational Linguistics, Bangkok, Thailand (2024)"},{"key":"5_CR19","doi-asserted-by":"publisher","first-page":"6401","DOI":"10.18653\/v1\/2024.findings-emnlp.372","volume-title":"Findings of the Association for Computational Linguistics: EMNLP 2024","author":"Y Yang","year":"2024","unstructured":"Yang, Y., Cao, Z., Zhao, H.: LaCo: large language model pruning via layer collapse. In: Al-Onaizan, Y., Bansal, M., Chen, Y.-N. (eds.) Findings of the Association for Computational Linguistics: EMNLP 2024, pp. 6401\u20136417. Association for Computational Linguistics, Miami, FL, USA (2024)"},{"key":"5_CR20","unstructured":"Chen, X., Hu, Y., Zhang, J., Wang, Y.: Streamlining redundant layers to compress large language models. In: Proc. 13th Int. Conf. Learning Representations (ICLR) (2025)."}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-3394-6_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T22:21:03Z","timestamp":1784326863000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3394-6_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,18]]},"ISBN":["9789819233939","9789819233946"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3394-6_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,18]]},"assertion":[{"value":"18 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Toronto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2026a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2026\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}