{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T01:57:12Z","timestamp":1773194232502,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":18,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819755745","type":"print"},{"value":"9789819755752","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-981-97-5575-2_31","type":"book-chapter","created":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T10:01:54Z","timestamp":1725184914000},"page":"415-426","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["MATEval: A Multi-agent Discussion Framework for\u00a0Advancing Open-Ended Text Evaluation"],"prefix":"10.1007","author":[{"given":"Yu","family":"Li","sequence":"first","affiliation":[]},{"given":"Shenyu","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Rui","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Xiutian","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Yongrui","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Wenhao","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Guilin","family":"Qi","sequence":"additional","affiliation":[]},{"given":"Dehai","family":"Min","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,9,2]]},"reference":[{"key":"31_CR1","unstructured":"Banerjee, S., Lavie, A.: METEOR: an automatic metric for MT evaluation with improved correlation with human judgments. In: Proceedings of the Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization@ACL, pp. 65\u201372 (2005)"},{"key":"31_CR2","doi-asserted-by":"crossref","unstructured":"Callison-Burch, C.: Fast, cheap, and creative: evaluating translation quality using amazon\u2019s mechanical turk. In: Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, EMNLP 2009, pp. 286\u2013295 (2009)","DOI":"10.3115\/1699510.1699548"},{"key":"31_CR3","unstructured":"Chan, C.M., et\u00a0al: Chateval: Towards better llm-based evaluators through multi-agent debate. arXiv preprint arXiv:2308.07201 (2023)"},{"key":"31_CR4","doi-asserted-by":"crossref","unstructured":"Fu, J., et\u00a0al: Gptscore: Evaluate as you desire. arXiv preprint arXiv:2302.04166 (2023)","DOI":"10.18653\/v1\/2024.naacl-long.365"},{"key":"31_CR5","doi-asserted-by":"crossref","unstructured":"Ghazarian, S., et\u00a0al: Better automatic evaluation of open-domain dialogue systems with contextualized embeddings. arXiv preprint arXiv:1904.10635 (2019)","DOI":"10.18653\/v1\/W19-2310"},{"key":"31_CR6","doi-asserted-by":"crossref","unstructured":"Guan, J., et\u00a0al: Openmeva: a benchmark for evaluating open-ended story generation metrics. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL\/IJCNLP 2021, (Volume 1: Long Papers), pp. 6394\u20136407 (2021)","DOI":"10.18653\/v1\/2021.acl-long.500"},{"key":"31_CR7","doi-asserted-by":"crossref","unstructured":"Guan, J., et\u00a0al: LOT: a story-centric benchmark for evaluating Chinese long text understanding and generation. Trans. Assoc. Comput . Lingust. 10, 434\u2013451 (2022)","DOI":"10.1162\/tacl_a_00469"},{"key":"31_CR8","doi-asserted-by":"crossref","unstructured":"Guan, J., Huang, M.: UNION: an unreferenced metric for evaluating open-ended story generation. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, EMNLP, pp. 9157\u20139166 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.736"},{"key":"31_CR9","unstructured":"Li, G., et\u00a0al: Camel: Communicative agents for\u201c mind\" exploration of large scale language model society. arXiv preprint arXiv:2303.17760 (2023)"},{"key":"31_CR10","unstructured":"Lin, C.Y.: ROUGE: A package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381 (Jul 2004)"},{"key":"31_CR11","doi-asserted-by":"crossref","unstructured":"Liu, C., et\u00a0al: How to evaluate your dialogue system: An empirical study of unsupervised evaluation metrics for dialogue response generation. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, EMNLP, pp. 2122\u20132132 (2016)","DOI":"10.18653\/v1\/D16-1230"},{"key":"31_CR12","doi-asserted-by":"crossref","unstructured":"Liu, Y., et\u00a0al: G-eval: NLG evaluation using gpt-4 with better human alignment. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP. pp. 2511\u20132522 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.153"},{"key":"31_CR13","unstructured":"Madaan, A., et\u00a0al: Self-refine: Iterative refinement with self-feedback. arXiv preprint arXiv:2303.17651 (2023)"},{"key":"31_CR14","doi-asserted-by":"crossref","unstructured":"Papineni, K., et\u00a0al: Bleu: a method for automatic evaluation of machine translation. In: ACL, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"31_CR15","doi-asserted-by":"crossref","unstructured":"Wang, J., et\u00a0al: Is chatgpt a good nlg evaluator? a preliminary study. arXiv preprint arXiv:2303.04048 (2023)","DOI":"10.18653\/v1\/2023.newsum-1.1"},{"key":"31_CR16","unstructured":"Wang, P., et\u00a0al: Large language models are not fair evaluators. arXiv preprint arXiv:2305.17926 (2023)"},{"key":"31_CR17","first-page":"24824","volume":"35","author":"J Wei","year":"2022","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models. Adv. Neural. Inf. Process. Syst. 35, 24824\u201324837 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"31_CR18","unstructured":"Zhang, T., Kishore, V., Wu, F., Artzi, Y.: Bertscore: evaluating text generation with BERT. In: 8th International Conference on Learning Representations, ICLR (2020)"}],"container-title":["Lecture Notes in Computer Science","Database Systems for Advanced Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-5575-2_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T10:06:06Z","timestamp":1725185166000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-5575-2_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819755745","9789819755752"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-5575-2_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"2 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DASFAA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Database Systems for Advanced Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Gifu","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 July 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 July 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dasfaa2024a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.dasfaa2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}