{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T05:03:49Z","timestamp":1743138229254,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":21,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819755745"},{"type":"electronic","value":"9789819755752"}],"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_29","type":"book-chapter","created":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T10:01:54Z","timestamp":1725184914000},"page":"390-401","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DEE: Dual-Stage Explainable Evaluation Method for\u00a0Text Generation"],"prefix":"10.1007","author":[{"given":"Shenyu","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiutian","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongrui","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenhao","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guilin","family":"Qi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,2]]},"reference":[{"key":"29_CR1","unstructured":"Bai, J., Bai, S., Chu, Y., Cui, Z., et\u00a0al.: Qwen technical report. arXiv (2023)"},{"key":"29_CR2","unstructured":"Banerjee, S., Lavie, A.: METEOR: an automatic metric for MT evaluation with improved correlation with human judgments. In: Goldstein, J., Lavie, A., Lin, C., Voss, C.R. (eds.) Proceedings of the Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization@ACL 2005, pp. 65\u201372 (2005)"},{"key":"29_CR3","unstructured":"Chung, H.W., Hou, L., Longpre, S., Zoph, B., et\u00a0al.: Scaling instruction-finetuned language models. arXiv (2022)"},{"key":"29_CR4","doi-asserted-by":"crossref","unstructured":"Deshpande, A., Murahari, V., Rajpurohit, T., Kalyan, A., Narasimhan, K.: Toxicity in chatGPT: analyzing persona-assigned language models. arXiv (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.88"},{"key":"29_CR5","doi-asserted-by":"crossref","unstructured":"Dziri, N., Kamalloo, E., Mathewson, K.W., Za\u00efane, O.R.: Evaluating coherence in dialogue systems using entailment. In: Burstein, J., Doran, C., Solorio, T. (eds.) NAACL-HLT, pp. 3806\u20133812 (2019)","DOI":"10.18653\/v1\/N19-1381"},{"key":"29_CR6","doi-asserted-by":"crossref","unstructured":"Fu, J., Ng, S., Jiang, Z., Liu, P.: GPTScore: evaluate as you desire. arXiv (2023)","DOI":"10.18653\/v1\/2024.naacl-long.365"},{"key":"29_CR7","unstructured":"Hu, E.J., Shen, Y., Wallis, P., Allen-Zhu, Z., et\u00a0al.: LoRA: low-rank adaptation of large language models. In: ICLR (2022)"},{"key":"29_CR8","doi-asserted-by":"crossref","unstructured":"Hu, J.E., Singh, A., Holzenberger, N., Post, M., Durme, B.V.: Large-scale, diverse, paraphrastic bitexts via sampling and clustering. In: Bansal, M., Villavicencio, A. (eds.) CoNLL, pp. 44\u201354 (2019)","DOI":"10.18653\/v1\/K19-1005"},{"issue":"12","key":"29_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3571730","volume":"55","author":"Z Ji","year":"2023","unstructured":"Ji, Z., Lee, N., Frieske, R., Yu, T., Su, D., et al.: Survey of hallucination in natural language generation. ACM Comput. Surv. 55(12), 1\u201338 (2023)","journal-title":"ACM Comput. Surv."},{"key":"29_CR10","unstructured":"Jiang, D., Li, Y., Zhang, G., Huang, W., Lin, B.Y., Chen, W.: TIGERScore: towards building explainable metric for all text generation tasks. arXiv (2023)"},{"key":"29_CR11","doi-asserted-by":"crossref","unstructured":"Kwon, W., Li, Z., Zhuang, S., Sheng, Y., et\u00a0al.: Efficient memory management for large language model serving with PagedAttention. In: Flinn, J., Seltzer, M.I., Druschel, P., Kaufmann, A., Mace, J. (eds.) SOSP, pp. 611\u2013626 (2023)","DOI":"10.1145\/3600006.3613165"},{"key":"29_CR12","doi-asserted-by":"crossref","unstructured":"Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., et\u00a0al.: BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: Jurafsky, D., Chai, J., Schluter, N., Tetreault, J.R. (eds.) ACL, pp. 7871\u20137880 (2020)","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"29_CR13","unstructured":"Lin, C.Y.: ROUGE: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381 (2004)"},{"key":"29_CR14","unstructured":"Liu, Y., Yao, Y., Ton, J.F., Zhang, X., et\u00a0al.: Trustworthy LLMs: a survey and guideline for evaluating large language models\u2019 alignment. arXiv (2023)"},{"key":"29_CR15","unstructured":"OpenAI: GPT-4 technical report. arXiv (2023)"},{"key":"29_CR16","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.: Bleu: a method for automatic evaluation of machine translation. In: ACL, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"29_CR17","unstructured":"Touvron, H., Lavril, T., Izacard, G., Martinet, X., et\u00a0al.: LLaMA: Open and efficient foundation language models. arXiv (2023)"},{"key":"29_CR18","doi-asserted-by":"crossref","unstructured":"Xu, W., et al.: INSTRUCTSCORE: towards explainable text generation evaluation with automatic feedback. In: Bouamor, H., Pino, J., Bali, K. (eds.) EMNLP, pp. 5967\u20135994 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.365"},{"key":"29_CR19","unstructured":"Yuan, W., Neubig, G., Liu, P.: BARTScore: evaluating generated text as text generation. In: Ranzato, M., Beygelzimer, A., Dauphin, Y.N., Liang, P., Vaughan, J.W. (eds.) NeurIPS, pp. 27263\u201327277 (2021)"},{"key":"29_CR20","unstructured":"Zeng, A., Liu, X., Du, Z., Wang, Z., et\u00a0al.: GLM-130B: an open bilingual pre-trained model. In: ICLR (2022)"},{"key":"29_CR21","unstructured":"Zhang, T., Kishore, V., Wu, F., Weinberger, K.Q., Artzi, Y.: BERTScore: evaluating text generation with BERT. In: 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_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T10:06:12Z","timestamp":1725185172000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-5575-2_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819755745","9789819755752"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-5575-2_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"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"}}]}}