{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T02:28:29Z","timestamp":1777861709270,"version":"3.51.4"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031971402","type":"print"},{"value":"9783031971419","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"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\/978-3-031-97141-9_2","type":"book-chapter","created":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T08:57:21Z","timestamp":1751273841000},"page":"19-33","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Memory Efficient LM Compression Using Fisher Information from\u00a0Low-Rank Representations"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-7943-4259","authenticated-orcid":false,"given":"Daniil","family":"Moskovskiy","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2325-4268","authenticated-orcid":false,"given":"Sergey","family":"Pletenev","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9684-5240","authenticated-orcid":false,"given":"Sergey","family":"Zagoruyko","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6097-6118","authenticated-orcid":false,"given":"Alexander","family":"Panchenko","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,7,1]]},"reference":[{"issue":"2","key":"2_CR1","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1162\/089976698300017746","volume":"10","author":"S Amari","year":"1998","unstructured":"Amari, S.: Natural gradient works efficiently in learning. Neural Comput. 10(2), 251\u2013276 (1998)","journal-title":"Neural Comput."},{"key":"2_CR2","unstructured":"Casella, G.C.: Theory of Point Estimation. Springer, Heidelberg (2001)"},{"key":"2_CR3","unstructured":"Dao, T.: Flashattention-2: faster attention with better parallelism and work partitioning. In: The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, 7\u201311 May 2024. OpenReview.net (2024)"},{"key":"2_CR4","unstructured":"Dettmers, T., Lewis, M., Belkada, Y., Zettlemoyer, L.: Gpt3.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: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, 28 November\u20139 December 2022 (2022)"},{"key":"2_CR5","doi-asserted-by":"crossref","unstructured":"Dettmers, T., Pagnoni, A., Holtzman, A., Zettlemoyer, L.: Qlora: efficient finetuning of quantized llms. In: Oh, A., Naumann, T., Globerson, A., Saenko, K., Hardt, M., Levine, S. (eds.) Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, 10\u201316 December 2023 (2023)","DOI":"10.52202\/075280-0441"},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Fan, C., et al.: Layer-wise model pruning based on mutual information. In: Moens, M., Huang, X., Specia, L., Yih, S.W. (eds.) Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021, Virtual Event\/Punta Cana, Dominican Republic, 7\u201311 November, 2021, pp. 3079\u20133090. Association for Computational Linguistics (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.246"},{"key":"2_CR7","unstructured":"Hendrycks, D., et al.: Measuring massive multitask language understanding. In: 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, 3\u20137 May 2021. OpenReview.net (2021)"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Hrinchuk, O., Khrulkov, V., Mirvakhabova, L., Orlova, E., Oseledets, I.V.: Tensorized embedding layers. In: Cohn, T., He, Y., Liu, Y. (eds.) Findings of the Association for Computational Linguistics: EMNLP 2020, Online Event, 16\u201320 November 2020. Findings of ACL, vol. EMNLP 2020, pp. 4847\u20134860. Association for Computational Linguistics (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.436"},{"key":"2_CR9","unstructured":"Hsu, Y., Hua, T., Chang, S., Lou, Q., Shen, Y., Jin, H.: Language model compression with weighted low-rank factorization (2022)"},{"key":"2_CR10","unstructured":"Hu, E.J., et al.: Lora: Low-rank adaptation of large language models. In: The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, 25\u201329 April 2022. OpenReview.net (2022)"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Hua, T., Hsu, Y., Wang, F., Lou, Q., Shen, Y., Jin, H.: Numerical optimizations for weighted low-rank estimation on language models. In: Goldberg, Y., Kozareva, Z., Zhang, Y. (eds.) Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022, Abu Dhabi, United Arab Emirates, 7\u201311 December 2022, pp. 1404\u20131416. Association for Computational Linguistics (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.91"},{"key":"2_CR12","unstructured":"Jiang, A.Q., et al.: Mistral 7b. CoRR arxiv:2310.06825 (2023)"},{"key":"2_CR13","unstructured":"Konovalov, V., Tumunbayarova, Z.: Learning word embeddings for low resourse languages: the case of buryat. In: Komp\u2019juternaja Lingvistika i Intellektual\u2019nye Tehnologiithis, pp. 331\u2013341 (2018). http:\/\/www.dialog-21.ru\/media\/4528\/konovalovvp_tumunbayarovazb.pdf"},{"key":"2_CR14","unstructured":"Kunstner, F., Hennig, P., Balles, L.: Limitations of the empirical fisher approximation for natural gradient descent. In: Wallach, H.M., Larochelle, H., Beygelzimer, A., d\u2019Alch\u00e9-Buc, F., Fox, E.B., Garnett, R. (eds.) Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, Vancouver, BC, Canada, 8\u201314 December 2019, pp. 4158\u20134169 (2019)"},{"key":"2_CR15","unstructured":"Kurtic, E., Frantar, E., Alistarh, D.: Ziplm: Inference-aware structured pruning of language models. In: Oh, A., Naumann, T., Globerson, A., Saenko, K., Hardt, M., Levine, S. (eds.) Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, 10\u201316 December 2023 (2023)"},{"key":"2_CR16","unstructured":"Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., Soricut, R.: ALBERT: a lite BERT for self-supervised learning of language representations. In: 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, 26\u201330 April 2020. OpenReview.net (2020)"},{"key":"2_CR17","unstructured":"Liu, Y., et al.: Roberta: a robustly optimized BERT pretraining approach. CoRR arxiv:1907.11692 (2019)"},{"key":"2_CR18","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, 6\u20139 May 2019. OpenReview.net (2019)"},{"issue":"7","key":"2_CR19","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-024-40663-9","volume":"19","author":"Y Mao","year":"2024","unstructured":"Mao, Y., et al.: A survey on lora of large language models. Front. Comput. Sci. 19(7), 197605 (2024)","journal-title":"Front. Comput. Sci."},{"key":"2_CR20","unstructured":"Michel, P., Levy, O., Neubig, G.: Are sixteen heads really better than one? In: Wallach, H.M., Larochelle, H., Beygelzimer, A., d\u2019Alch\u00e9-Buc, F., Fox, E.B., Garnett, R. (eds.) Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, Vancouver, BC, Canada, 8\u201314 December 2019, pp. 14014\u201314024 (2019)"},{"key":"2_CR21","series-title":"Adaptive computation and machine learning series","volume-title":"Machine learning - a probabilistic perspective","author":"KP Murphy","year":"2012","unstructured":"Murphy, K.P.: Machine learning - a probabilistic perspective. Adaptive computation and machine learning series, MIT Press, Cambridge (2012)"},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Narayan, S., Cohen, S.B., Lapata, M.: Don\u2019t give me the details, just the summary! topic-aware convolutional neural networks for extreme summarization. In: Riloff, E., Chiang, D., Hockenmaier, J., Tsujii, J. (eds.) Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium, 31 October\u20134 November 2018, pp. 1797\u20131807. Association for Computational Linguistics (2018)","DOI":"10.18653\/v1\/D18-1206"},{"key":"2_CR23","doi-asserted-by":"publisher","first-page":"2295","DOI":"10.1137\/090752286","volume":"33","author":"I Oseledets","year":"2011","unstructured":"Oseledets, I.: Tensor-train decomposition. SIAM J. Sci. Comput. 33, 2295\u20132317 (2011)","journal-title":"SIAM J. Sci. Comput."},{"key":"2_CR24","unstructured":"Pletenev, S., Chekalina, V., Moskovskiy, D., Seleznev, M., Zagoruyko, S., Panchenko, A.: A computational study of matrix decomposition methods for compression of pre-trained transformers. In: Huang, C.R., et al. (eds.) Proceedings of the 37th Pacific Asia Conference on Language, Information and Computation, pp. 723\u2013742. Association for Computational Linguistics, Hong Kong (2023)"},{"key":"2_CR25","doi-asserted-by":"crossref","unstructured":"Pletenev, S., et al.: How much knowledge can you pack into a LoRA adapter without harming LLM? In: Chiruzzo, L., Ritter, A., Wang, L. (eds.) Findings of the Association for Computational Linguistics: NAACL 2025, pp. 4309\u20134322. Association for Computational Linguistics, Albuquerque (2025). https:\/\/aclanthology.org\/2025.findings-naacl.243\/","DOI":"10.18653\/v1\/2025.findings-naacl.243"},{"key":"2_CR26","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21, 140:1\u2013140:67 (2020)"},{"key":"2_CR27","doi-asserted-by":"crossref","unstructured":"Rajpurkar, P., Jia, R., Liang, P.: Know what you don\u2019t know: unanswerable questions for SQuAD. In: Gurevych, I., Miyao, Y. (eds.) Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, vol. 2: Short Papers, pp. 784\u2013789. Association for Computational Linguistics, Melbourne (2018)","DOI":"10.18653\/v1\/P18-2124"},{"key":"2_CR28","unstructured":"Ren, J., et al.: Zero-offload: democratizing billion-scale model training. In: Calciu, I., Kuenning, G. (eds.) Proceedings of the 2021 USENIX Annual Technical Conference, USENIX ATC 2021, 14\u201316 July 2021, pp. 551\u2013564. USENIX Association (2021)"},{"key":"2_CR29","doi-asserted-by":"crossref","unstructured":"Sang, E.F.T.K., Meulder, F.D.: Introduction to the conll-2003 shared task: language-independent named entity recognition. In: Daelemans, W., Osborne, M. (eds.) Proceedings of the Seventh Conference on Natural Language Learning, CoNLL 2003, Held in cooperation with HLT-NAACL 2003, Edmonton, Canada, 31 May\u20131 June 2003, pp. 142\u2013147. ACL (2003)","DOI":"10.3115\/1119176.1119195"},{"key":"2_CR30","unstructured":"Srebro, N., Jaakkola, T.S.: Weighted low-rank approximations. In: Fawcett, T., Mishra, N. (eds.) Machine Learning, Proceedings of the Twentieth International Conference (ICML 2003), Washington, DC, USA, 21\u201324 August 2003, pp. 720\u2013727. AAAI Press (2003)"},{"issue":"4","key":"2_CR31","doi-asserted-by":"publisher","first-page":"798","DOI":"10.2307\/2373246","volume":"87","author":"PA Tucker","year":"1965","unstructured":"Tucker, P.A.: On the reduction of induced indecomposable representations. Am. J. Math. 87(4), 798\u2013806 (1965)","journal-title":"Am. J. Math."},{"key":"2_CR32","unstructured":"Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., Bowman, S.R.: GLUE: a multi-task benchmark and analysis platform for natural language understanding. In: 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, 6\u20139 May 2019. OpenReview.net (2019)"},{"key":"2_CR33","unstructured":"Wang, B., Ren, Y., Shang, L., Jiang, X., Liu, Q.: Exploring extreme parameter compression for pre-trained language models. In: The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, 25\u201329 April 2022. OpenReview.net (2022)"},{"key":"2_CR34","doi-asserted-by":"crossref","unstructured":"Zanella, M., Ayed, I.B.: Low-rank few-shot adaptation of vision-language models. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2024 - Workshops, Seattle, WA, USA, 17\u201318 June 2024, pp. 1593\u20131603. IEEE (2024)","DOI":"10.1109\/CVPRW63382.2024.00166"},{"key":"2_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, M., et al.: Loraprune: structured pruning meets low-rank parameter-efficient fine-tuning. In: Ku, L., Martins, A., Srikumar, V. (eds.) Findings of the Association for Computational Linguistics, ACL 2024, Bangkok, Thailand and Virtual Meeting, 11\u201316 August 2024, pp. 3013\u20133026. Association for Computational Linguistics (2024)","DOI":"10.18653\/v1\/2024.findings-acl.178"},{"key":"2_CR36","doi-asserted-by":"publisher","first-page":"1556","DOI":"10.1162\/tacl_a_00704","volume":"12","author":"X Zhu","year":"2024","unstructured":"Zhu, X., Li, J., Liu, Y., Ma, C., Wang, W.: A survey on model compression for large language models. Trans. Assoc. Comput. Linguist. 12, 1556\u20131577 (2024)","journal-title":"Trans. Assoc. Comput. Linguist."}],"container-title":["Lecture Notes in Computer Science","Natural Language Processing and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-97141-9_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T05:00:06Z","timestamp":1777525206000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-97141-9_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,1]]},"ISBN":["9783031971402","9783031971419"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-97141-9_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,1]]},"assertion":[{"value":"1 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NLDB","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Applications of Natural Language to Information Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kanazawa","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","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":"4 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nldb2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/nldb2025.github.io\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}