{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T13:14:52Z","timestamp":1783602892467,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":24,"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_26","type":"book-chapter","created":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T06:30:28Z","timestamp":1763793028000},"page":"335-348","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Multi-candidate Speculative Decoding"],"prefix":"10.1007","author":[{"given":"Sen","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shujian","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyu","family":"Dai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiajun","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,23]]},"reference":[{"key":"26_CR1","unstructured":"Achiam, J., et\u00a0al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"26_CR2","doi-asserted-by":"crossref","unstructured":"Bojar, O., et\u00a0al.: Findings of the 2014 workshop on statistical machine translation. In: Proceedings of the Ninth Workshop on Statistical Machine Translation, pp. 12\u201358 (2014)","DOI":"10.3115\/v1\/W14-3302"},{"key":"26_CR3","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"26_CR4","unstructured":"Cai, T., Li, Y., Geng, Z., Peng, H., Dao, T.: Medusa: Simple framework for accelerating LLM generation with multiple decoding heads. https:\/\/github.com\/FasterDecoding\/Medusa (2023)"},{"key":"26_CR5","unstructured":"Chen, C., Borgeaud, S., Irving, G., Lespiau, J.B., Sifre, L., Jumper, J.: Accelerating large language model decoding with speculative sampling. arXiv preprint arXiv:2302.01318 (2023)"},{"key":"26_CR6","unstructured":"Chiang, W.L., et al.: Vicuna: An open-source chatbot impressing GPT-4 with 90%* ChatGPT quality (2023). https:\/\/lmsys.org\/blog\/2023-03-30-vicuna\/"},{"key":"26_CR7","unstructured":"Chung, H.W., et\u00a0al.: Scaling instruction-finetuned language models. arXiv preprint arXiv:2210.11416 (2022)"},{"key":"26_CR8","doi-asserted-by":"crossref","unstructured":"Dettmers, T., Lewis, M., Belkada, Y., Zettlemoyer, L.: LLM. int8 (): 8-bit matrix multiplication for transformers at scale. arXiv preprint arXiv:2208.07339 (2022)","DOI":"10.52202\/068431-2198"},{"key":"26_CR9","first-page":"9895","volume":"34","author":"S Jaszczur","year":"2021","unstructured":"Jaszczur, S., et al.: Sparse is enough in scaling transformers. Adv. Neural. Inf. Process. Syst. 34, 9895\u20139907 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"26_CR10","doi-asserted-by":"crossref","unstructured":"Kwon, W., et al.: Efficient memory management for large language model serving with PagedAttention. In: Proceedings of the 29th Symposium on Operating Systems Principles, pp. 611\u2013626 (2023)","DOI":"10.1145\/3600006.3613165"},{"key":"26_CR11","unstructured":"Leviathan, Y., Kalman, M., Matias, Y.: Fast inference from transformers via speculative decoding. In: International Conference on Machine Learning, pp. 19274\u201319286. PMLR (2023)"},{"key":"26_CR12","unstructured":"Liu, X., et al.: Online speculative decoding. arXiv preprint arXiv:2310.07177 (2023)"},{"key":"26_CR13","unstructured":"Miao, X., et al.: SpecInfer: Accelerating generative LLM serving with speculative inference and token tree verification. arXiv preprint arXiv:2305.09781 (2023)"},{"key":"26_CR14","unstructured":"Peng, B., Li, C., He, P., Galley, M., Gao, J.: Instruction tuning with GPT-4. arXiv preprint arXiv:2304.03277 (2023)"},{"issue":"1","key":"26_CR15","first-page":"5485","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(1), 5485\u20135551 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"26_CR16","unstructured":"Shazeer, N.: Fast transformer decoding: One write-head is all you need. arXiv preprint arXiv:1911.02150 (2019)"},{"key":"26_CR17","unstructured":"So, D.R., Ma\u0144ke, W., Liu, H., Dai, Z., Shazeer, N., Le, Q.V.: Primer: Searching for efficient transformers for language modeling. arXiv preprint arXiv:2109.08668 (2021)"},{"key":"26_CR18","unstructured":"Stern, M., Shazeer, N., Uszkoreit, J.: Blockwise parallel decoding for deep autoregressive models. Adv. Neural Inf. Process. Syst. 31 (2018)"},{"key":"26_CR19","doi-asserted-by":"crossref","unstructured":"Sun, Z., Suresh, A.T., Ro, J.H., Beirami, A., Jain, H., Yu, F.: SpecTr: fast speculative decoding via optimal transport. In: Thirty-seventh Conference on Neural Information Processing Systems (2023)","DOI":"10.52202\/075280-1314"},{"key":"26_CR20","unstructured":"Taori, R., et al.: Stanford Alpaca: An instruction-following LLaMA model. https:\/\/github.com\/tatsu-lab\/stanford_alpaca (2023)"},{"key":"26_CR21","unstructured":"Touvron, H., et\u00a0al.: LLaMA: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"26_CR22","unstructured":"Touvron, H., et\u00a0al.: LLaMA 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"26_CR23","doi-asserted-by":"crossref","unstructured":"Xia, H., Ge, T., Wang, P., Chen, S.Q., Wei, F., Sui, Z.: Speculative decoding: Exploiting speculative execution for accelerating seq2seq generation. arXiv preprint arXiv:2203.16487 (2022)","DOI":"10.18653\/v1\/2023.findings-emnlp.257"},{"key":"26_CR24","unstructured":"Zhou, Y., et al.: distillspec: Improving speculative decoding via knowledge distillation. arXiv preprint arXiv:2310.08461 (2023)"}],"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_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T12:28:20Z","timestamp":1783600100000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-3343-5_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,23]]},"ISBN":["9789819533428","9789819533435"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-3343-5_26","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"}}]}}