{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T22:22:53Z","timestamp":1775082173471,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":21,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819584192","type":"print"},{"value":"9789819584208","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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\/978-981-95-8420-8_21","type":"book-chapter","created":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T20:13:54Z","timestamp":1775074434000},"page":"265-275","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Human-Aligned Data Quality Assessment via\u00a0Prompt and\u00a0Scorer Co-optimization"],"prefix":"10.1007","author":[{"given":"Quanzeng","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Conglei","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zijian","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiancheng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,4,2]]},"reference":[{"key":"21_CR1","doi-asserted-by":"crossref","unstructured":"Kim, Y., Ha, H., Lee, S., Kim, J., Yang, S., Park, C.: Rethinking KenLM: good and bad model ensembles for efficient text quality filtering in large web corpora. arXiv preprint arXiv:2409.09613 (2024)","DOI":"10.18653\/v1\/2025.acl-short.4"},{"key":"21_CR2","unstructured":"Henriksson, E., Tarkka, O., Ginter, F.: FinerWeb-10BT: refining web data with LLM-based line-level filtering. arXiv preprint arXiv:2501.07314 (2025)"},{"key":"21_CR3","unstructured":"Penedo, G., et al.: The RefinedWeb dataset for Falcon LLM: outperforming curated corpora with web data, and web data only. arXiv preprint arXiv:2306.01116 (2023)"},{"key":"21_CR4","unstructured":"Chen, J., et al.: ChineseWebText: large-scale high-quality Chinese web text extracted with effective evaluation model. arXiv preprint arXiv:2311.01149 (2023)"},{"key":"21_CR5","first-page":"116462","volume":"37","author":"M Weber","year":"2024","unstructured":"Weber, M., et al.: RedPajama: an open dataset for training large language models. Adv. Neural. Inf. Process. Syst. 37, 116462\u2013116492 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"21_CR6","unstructured":"Wang, L., et al.: CCI3. 0-HQ: a large-scale Chinese dataset of high quality designed for pre-training large language models. arXiv preprint arXiv:2410.18505 (2024)"},{"key":"21_CR7","unstructured":"Wettig, A., Gupta, A., Malik, S., Chen, D.: Qurating: Selecting high-quality data for training language models. arXiv preprint arXiv:2402.09739 (2024)"},{"key":"21_CR8","first-page":"30811","volume":"37","author":"G Penedo","year":"2024","unstructured":"Penedo, G., et al.: The fineweb datasets: decanting the web for the finest text data at scale. Adv. Neural. Inf. Process. Syst. 37, 30811\u201330849 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"21_CR9","unstructured":"Wenzek, G., et al.: CCNet: extracting high quality monolingual datasets from web crawl data. arXiv preprint arXiv:1911.00359 (2019)"},{"key":"21_CR10","unstructured":"Zhang, J., Luo, Z., Liu, J., Shroff, N., Nowak, R.: GPT-4o as the gold standard: a scalable and general purpose approach to filter language model pretraining data. arXiv preprint arXiv:2410.02755 (2024)"},{"key":"21_CR11","unstructured":"Qiu, J., et al.: Wanjuan-CC: a safe and high-quality open-sourced English webtext dataset. arXiv preprint arXiv:2402.19282 (2024)"},{"key":"21_CR12","unstructured":"Messmer, B., Sabol\u010dec, V., Jaggi, M.: Enhancing multilingual LLM pretraining with model-based data selection. arXiv preprint arXiv:2502.10361 (2025)"},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"Ali, M., et al.: Judging quality across languages: a multilingual approach to pretraining data filtering with language models. arXiv preprint arXiv:2505.22232 (2025)","DOI":"10.18653\/v1\/2025.emnlp-main.449"},{"key":"21_CR14","unstructured":"Penedo, G., et al.: FineWeb2: one pipeline to scale them all\u2013adapting pre-training data processing to every language. arXiv preprint arXiv:2506.20920 (2025)"},{"key":"21_CR15","unstructured":"Touvron, H., et al.: LLaMA: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"21_CR16","unstructured":"Hurst, A., et al.: GPT-4o system card. arXiv preprint arXiv:2410.21276 (2024)"},{"key":"21_CR17","unstructured":"Liu, A., et al.: Deepseek-v3 technical report. arXiv preprint arXiv:2412.19437 (2024)"},{"key":"21_CR18","unstructured":"Leaderboard. https:\/\/huggingface.co\/spaces\/mteb\/leaderboard. Accessed 29 July 2025"},{"key":"21_CR19","doi-asserted-by":"crossref","unstructured":"Zhang, X., et al.: mGTE: generalized long-context text representation and reranking models for multilingual text retrieval. arXiv preprint arXiv:2407.19669 (2024)","DOI":"10.18653\/v1\/2024.emnlp-industry.103"},{"key":"21_CR20","unstructured":"Li, Z., Zhang, X., Zhang, Y., Long, D., Xie, P., Zhang, M.: Towards general text embeddings with multi-stage contrastive learning. arXiv preprint arXiv:2308.03281 (2023)"},{"key":"21_CR21","unstructured":"Team, Qwen. Qwen2 technical report. arXiv preprint arXiv:2407.10671 (2024)"}],"container-title":["Lecture Notes in Computer Science","Algorithms and Architectures for Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-8420-8_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T20:13:56Z","timestamp":1775074436000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-8420-8_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819584192","9789819584208"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-8420-8_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"2 April 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ICA3PP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Algorithms and Architectures for Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Zhengzhou","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":"30 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ica3pp2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ieee-cybermatics.org\/2025\/ica3pp\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}