{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,21]],"date-time":"2025-12-21T06:26:32Z","timestamp":1766298392497,"version":"3.41.0"},"publisher-location":"Singapore","reference-count":33,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819681853","type":"print"},{"value":"9789819681860","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-981-96-8186-0_3","type":"book-chapter","created":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T10:16:22Z","timestamp":1750155382000},"page":"28-39","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Practice of\u00a0Post-training on\u00a0Llama-3 70B with\u00a0Optimal Selection of\u00a0Additional Language Mixture Ratio"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-7529-4660","authenticated-orcid":false,"given":"Ningyuan","family":"Xi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3668-6414","authenticated-orcid":false,"given":"Yetao","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8394-9507","authenticated-orcid":false,"given":"Kun","family":"Fan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3604-5313","authenticated-orcid":false,"given":"Teng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6872-8910","authenticated-orcid":false,"given":"Qingqing","family":"Gu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2484-5345","authenticated-orcid":false,"given":"Luo","family":"Ji","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,18]]},"reference":[{"key":"3_CR1","doi-asserted-by":"crossref","unstructured":"Cai, H., et al.: Improving empathetic dialogue generation by dynamically infusing commonsense knowledge. In: Findings of ACL 2023 (2023)","DOI":"10.18653\/v1\/2023.findings-acl.498"},{"key":"3_CR2","unstructured":"Chen, J., et\u00a0al.: Towards effective and efficient continual pre-training of large language models (2024)"},{"key":"3_CR3","unstructured":"Chih Chieh\u00a0Shao, T.L., Lai, Y., Tseng, Y., Tsai, S.: Drcd: a Chinese machine reading comprehension dataset (2019). https:\/\/arxiv.org\/abs\/1806.00920"},{"key":"3_CR4","unstructured":"Cobbe, K., et al.: Training verifiers to solve math word problems (2021). https:\/\/arxiv.org\/abs\/2110.14168"},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Cui, Y., et\u00a0al.: A span-extraction dataset for Chinese machine reading comprehension. In: EMNLP-IJCNLP (2019)","DOI":"10.18653\/v1\/D19-1600"},{"key":"3_CR6","unstructured":"Dan\u00a0Hendrycks, Collin\u00a0Burns, S.B.A.Z.M.M.D.S.J.S.: Measuring massive multitask language understanding (2021). https:\/\/arxiv.org\/abs\/2009.03300"},{"key":"3_CR7","unstructured":"Duan, H., et al.: Botchat: Evaluating llms\u2019 capabilities of having multi-turn dialogues (2023). https:\/\/arxiv.org\/abs\/2310.13650"},{"key":"3_CR8","unstructured":"Grattafiori, A., et\u00a0al.: The llama 3 herd of models (2024)"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Gu, J., Yang, Z., Ding, C., Zhao, R., Tan, F.: Cmr scaling law: predicting critical mixture ratios for continual pre-training of language models (2024). https:\/\/arxiv.org\/abs\/2407.17467","DOI":"10.18653\/v1\/2024.emnlp-main.903"},{"key":"3_CR10","doi-asserted-by":"crossref","unstructured":"Gururangan, S., et al.: Don\u2019t stop pretraining: Adapt language models to domains and tasks (2020). https:\/\/arxiv.org\/abs\/2004.10964","DOI":"10.18653\/v1\/2020.acl-main.740"},{"key":"3_CR11","unstructured":"Hoffmann, J., et al.: Training compute-optimal large language models (2022). https:\/\/arxiv.org\/abs\/2203.15556"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Hu, B., Chen, Q., Zhu, F.: LCSTS: a large scale Chinese short text summarization dataset. In: M\u00e0rquez, L., Callison-Burch, C., Su, J. (eds.) Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, September 2015","DOI":"10.18653\/v1\/D15-1229"},{"key":"3_CR13","unstructured":"Jared\u00a0Kaplan, Sam\u00a0McCandlish, T.H.T.B.B.B.C.R.C.S.G.A.R.J.W.D.A.: Scaling laws for neural language models (2020). https:\/\/arxiv.org\/abs\/2001.08361"},{"key":"3_CR14","unstructured":"Liang, X., et al.: Task oriented in-domain data augmentation (2024). https:\/\/arxiv.org\/abs\/2406.16694"},{"key":"3_CR15","unstructured":"Xu, L., et al.: Fewclue: a Chinese few-shot learning evaluation benchmark (2021). https:\/\/arxiv.org\/abs\/2107.07498"},{"key":"3_CR16","unstructured":"Ma, S., et al.: Ecomgpt-ct: continual pre-training of e-commerce large language models with semi-structured data (2023). https:\/\/arxiv.org\/abs\/2312.15696"},{"key":"3_CR17","doi-asserted-by":"crossref","unstructured":"Joshi, M., Choi, E., Weld, D., Zettlemoyer, L.: Triviaqa: a large scale distantly supervised challenge dataset for reading comprehension (2017). https:\/\/arxiv.org\/abs\/1705.03551","DOI":"10.18653\/v1\/P17-1147"},{"key":"3_CR18","unstructured":"Chen, M., Tworek, J.: Evaluating large language models trained on code (2021). https:\/\/arxiv.org\/abs\/2107.03374"},{"key":"3_CR19","unstructured":"Ouyang, L., et\u00a0al.: Training language models to follow instructions with human feedback (2022). https:\/\/arxiv.org\/abs\/2203.02155"},{"key":"3_CR20","unstructured":"Que, H., et al.: D-cpt law: Domain-specific continual pre-training scaling law for large language models (2024). https:\/\/arxiv.org\/abs\/2406.01375"},{"key":"3_CR21","unstructured":"Rafailov, R., Sharma, A., Mitchell, E., Manning, C.D., Ermon, S., Finn, C.: Direct preference optimization: Your language model is secretly a reward model. In: Oh, A., Naumann, T., Globerson, A., Saenko, K., Hardt, M., Levine, S. (eds.) Advances in Neural Information Processing Systems, vol.\u00a036, pp. 53728\u201353741. Curran Associates, Inc. (2023)"},{"key":"3_CR22","unstructured":"Srivastava, A., Rastogi, A., et\u00a0al.: Beyond the imitation game: Quantifying and extrapolating the capabilities of language models (2023)"},{"key":"3_CR23","doi-asserted-by":"crossref","unstructured":"Wang, X., Li, X., Yin, Z., Wu, Y., Liu, J.: Emotional intelligence of large language models. Journal of Pacific Rim Psychology (2023)","DOI":"10.1177\/18344909231213958"},{"key":"3_CR24","doi-asserted-by":"crossref","unstructured":"Zhong, W., et al.: Agieval: A human-centric benchmark for evaluating foundation models (2023). https:\/\/arxiv.org\/abs\/2304.06364","DOI":"10.18653\/v1\/2024.findings-naacl.149"},{"key":"3_CR25","unstructured":"Wu, C., et al.: Llama pro: progressive llama with block expansion (2024). https:\/\/arxiv.org\/abs\/2401.02415"},{"key":"3_CR26","doi-asserted-by":"crossref","unstructured":"Xu, L., et\u00a0al.: Clue: A Chinese language understanding evaluation benchmark (2020)","DOI":"10.18653\/v1\/2020.coling-main.419"},{"key":"3_CR27","volume-title":"QWEN2 TECHNICAL REPORT","author":"A Yang","year":"2024","unstructured":"Yang, A., et al.: QWEN2 TECHNICAL REPORT. Technical report, Alibaba Group (2024)"},{"key":"3_CR28","unstructured":"Cui, Y., Yang, Z.: Efficient and effective text encoding for Chinese llama and alpaca, X.Y. (2023)"},{"key":"3_CR29","unstructured":"Ji, Y., et al.: Exploring the impact of instruction data scaling on large language models: An empirical study on real-world use cases (2023)"},{"key":"3_CR30","unstructured":"Huang, Y., et al.: C-eval: a multi-level multi-discipline Chinese evaluation suite for foundation models (2023). https:\/\/arxiv.org\/abs\/2305.08322"},{"key":"3_CR31","doi-asserted-by":"crossref","unstructured":"Zhang, T., Wang, S., Yan, S., Li, J., Liu, Q.: Generative table pre-training empowers models for tabular prediction (2023). https:\/\/arxiv.org\/abs\/2305.09696","DOI":"10.18653\/v1\/2023.emnlp-main.917"},{"key":"3_CR32","doi-asserted-by":"crossref","unstructured":"Zheng, Y., et\u00a0al.: Llamafactory: unified efficient fine-tuning of 100+ language models. In: ACL (2024)","DOI":"10.18653\/v1\/2024.acl-demos.38"},{"key":"3_CR33","unstructured":"Ke, Z., Liu, B.: Continual learning of natural language processing tasks: a survey (2023). https:\/\/arxiv.org\/abs\/2211.12701"}],"container-title":["Lecture Notes in Computer Science","Advances in Knowledge Discovery and Data Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-8186-0_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T10:16:35Z","timestamp":1750155395000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-8186-0_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819681853","9789819681860"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-8186-0_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"18 June 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PAKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sydney, NSW","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","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":"10 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 June 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pakdd2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/pakdd2025.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}