{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T03:40:32Z","timestamp":1771990832794,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":28,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819794362","type":"print"},{"value":"9789819794379","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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":[[2025]]},"DOI":"10.1007\/978-981-97-9437-9_4","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T16:27:22Z","timestamp":1730392042000},"page":"42-54","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["LasQ: Largest Singular Components Fine-Tuning for\u00a0LLMs with\u00a0Quantization"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-0822-5060","authenticated-orcid":false,"given":"Xiang","family":"Zhao","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0236-859X","authenticated-orcid":false,"given":"Beining","family":"Lin","sequence":"additional","affiliation":[]},{"given":"You","family":"Song","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"4_CR1","unstructured":"Chee, J., Cai, Y., Kuleshov, V., Sa, C.D.: QuIP: 2-bit quantization of large language models with guarantees. In: Thirty-Seventh Conference on Neural Information Processing Systems (2023). https:\/\/openreview.net\/forum?id=xrk9g5vcXR"},{"key":"4_CR2","unstructured":"Chen, H., et al.: Understanding and mitigating the label noise in pre-training on downstream tasks. arXiv abs\/2309.17002 (2023). https:\/\/api.semanticscholar.org\/CorpusID:263310780"},{"key":"4_CR3","unstructured":"Cobbe, K., et al.: Training verifiers to solve math word problems. arXiv abs\/2110.14168 (2021). https:\/\/api.semanticscholar.org\/CorpusID:239998651"},{"key":"4_CR4","unstructured":"Dettmers, T., Lewis, M., Belkada, Y., Zettlemoyer, L.: Llm.int8(): 8-bit matrix multiplication for transformers at scale. arXiv abs\/2208.07339 (2022). https:\/\/api.semanticscholar.org\/CorpusID:251564521"},{"key":"4_CR5","unstructured":"Dettmers, T., Pagnoni, A., Holtzman, A., Zettlemoyer, L.: Qlora: efficient finetuning of quantized LLMs. arXiv abs\/2305.14314 (2023). https:\/\/api.semanticscholar.org\/CorpusID:258841328"},{"key":"4_CR6","unstructured":"Frantar, E., Ashkboos, S., Hoefler, T., Alistarh, D.: GPTQ: accurate post-training quantization for generative pre-trained transformers. arXiv abs\/2210.17323 (2022). https:\/\/api.semanticscholar.org\/CorpusID:253237200"},{"key":"4_CR7","doi-asserted-by":"publisher","unstructured":"Halko, N., Martinsson, P.G., Tropp, J.A.: Finding structure with randomness: probabilistic algorithms for constructing approximate matrix decompositions. SIAM Rev. 53(2), 217\u2013288 (2011). https:\/\/doi.org\/10.1137\/090771806","DOI":"10.1137\/090771806"},{"key":"4_CR8","unstructured":"Hayou, S., Ghosh, N., Yu, B.: Lora+: efficient low rank adaptation of large models. arXiv abs\/2402.12354 (2024). https:\/\/api.semanticscholar.org\/CorpusID:267750102"},{"key":"4_CR9","unstructured":"He, P., Liu, X., Gao, J., Chen, W.: Deberta: decoding-enhanced bert with disentangled attention. arXiv abs\/2006.03654 (2020). https:\/\/api.semanticscholar.org\/CorpusID:219531210"},{"key":"4_CR10","unstructured":"Hermann, K.M., et al.: Teaching machines to read and comprehend. arXiv abs\/1506.03340 (2015). https:\/\/api.semanticscholar.org\/CorpusID:6203757"},{"key":"4_CR11","unstructured":"Hu, J.E., et al.: Lora: low-rank adaptation of large language models. arXiv abs\/2106.09685 (2021). https:\/\/api.semanticscholar.org\/CorpusID:235458009"},{"key":"4_CR12","unstructured":"Kopiczko, D.J., Blankevoort, T., Asano, Y.M.: Vera: vector-based random matrix adaptation. arXiv abs\/2310.11454 (2023). https:\/\/api.semanticscholar.org\/CorpusID:264172315"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"Lewis, M., et al.: Bart: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: Annual Meeting of the Association for Computational Linguistics (2019). https:\/\/api.semanticscholar.org\/CorpusID:204960716","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"4_CR14","doi-asserted-by":"crossref","unstructured":"Li, X.L., Liang, P.: Prefix-tuning: optimizing continuous prompts for generation. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) abs\/2101.00190 (2021). https:\/\/api.semanticscholar.org\/CorpusID:230433941","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"4_CR15","unstructured":"Li, Y., et al.: LoftQ: LoRA-fine-tuning-aware quantization for large language models. arXiv abs\/2310.08659 (2023). https:\/\/api.semanticscholar.org\/CorpusID:264128197"},{"key":"4_CR16","unstructured":"Lin, J., et al.: AWQ: activation-aware weight quantization for LLM compression and acceleration. In: MLSys (2024)"},{"key":"4_CR17","unstructured":"yang Liu, S., et al.: Dora: weight-decomposed low-rank adaptation. arXiv abs\/2402.09353 (2024). https:\/\/api.semanticscholar.org\/CorpusID:267657886"},{"key":"4_CR18","unstructured":"Liu, X., et al.: GPT understands, too. arXiv abs\/2103.10385 (2021). https:\/\/api.semanticscholar.org\/CorpusID:232269696"},{"key":"4_CR19","unstructured":"Meng, F., Wang, Z., Zhang, M.: PISSA: principal singular values and singular vectors adaptation of large language models (2024). https:\/\/api.semanticscholar.org\/CorpusID:268889493"},{"key":"4_CR20","unstructured":"Merity, S., Xiong, C., Bradbury, J., Socher, R.: Pointer sentinel mixture models. arXiv abs\/1609.07843 (2016). https:\/\/api.semanticscholar.org\/CorpusID:16299141"},{"key":"4_CR21","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. arXiv abs\/1808.08745 (2018). https:\/\/api.semanticscholar.org\/CorpusID:215768182","DOI":"10.18653\/v1\/D18-1206"},{"key":"4_CR22","doi-asserted-by":"crossref","unstructured":"Rajpurkar, P., Zhang, J., Lopyrev, K., Liang, P.: Squad: 100,000+ questions for machine comprehension of text. In: Conference on Empirical Methods in Natural Language Processing (2016). https:\/\/api.semanticscholar.org\/CorpusID:11816014","DOI":"10.18653\/v1\/D16-1264"},{"key":"4_CR23","unstructured":"Saha, R., Srivastava, V., Pilanci, M.: Matrix compression via randomized low rank and low precision factorization. arXiv abs\/2310.11028 (2023). https:\/\/api.semanticscholar.org\/CorpusID:262233736"},{"key":"4_CR24","unstructured":"Sharma, P., Ash, J.T., Misra, D.: The truth is in there: improving reasoning in language models with layer-selective rank reduction. arXiv abs\/2312.13558 (2023). https:\/\/api.semanticscholar.org\/CorpusID:266435969"},{"key":"4_CR25","unstructured":"Touvron, H., et al.: Llama 2: open foundation and fine-tuned chat models. arXiv abs\/2307.09288 (2023). https:\/\/api.semanticscholar.org\/CorpusID:259950998"},{"key":"4_CR26","doi-asserted-by":"crossref","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: BlackboxNLP@EMNLP (2018). https:\/\/api.semanticscholar.org\/CorpusID:5034059","DOI":"10.18653\/v1\/W18-5446"},{"key":"4_CR27","unstructured":"Xiao, G., Lin, J., Seznec, M., Wu, H., Demouth, J., Han, S.: SmoothQuant: accurate and efficient post-training quantization for large language models. In: Proceedings of the 40th International Conference on Machine Learning (2023)"},{"key":"4_CR28","unstructured":"Zhang, Q., et al.: Adalora: adaptive budget allocation for parameter-efficient fine-tuning (2023). https:\/\/api.semanticscholar.org\/CorpusID:266435293"}],"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\/978-981-97-9437-9_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T16:27:51Z","timestamp":1730392071000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-9437-9_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9789819794362","9789819794379"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-9437-9_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 November 2024","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":"Hangzhou","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2024\/index.php","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}