{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T06:57:18Z","timestamp":1781161038726,"version":"3.54.1"},"publisher-location":"Singapore","reference-count":14,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819200672","type":"print"},{"value":"9789819200689","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\/978-981-92-0068-9_9","type":"book-chapter","created":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T06:09:05Z","timestamp":1781158145000},"page":"121-135","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["End-to-End Chatbot Evaluation with\u00a0Adaptive Reasoning and\u00a0Uncertainty Filtering"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-0266-9246","authenticated-orcid":false,"given":"Nhi","family":"Dang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9900-7047","authenticated-orcid":false,"given":"Tung","family":"Le","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9948-1048","authenticated-orcid":false,"given":"Huy Tien","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,1]]},"reference":[{"key":"9_CR1","doi-asserted-by":"publisher","unstructured":"Chen, J., Yoon, J., Ebrahimi, S., Arik, S., Pfister, T., Jha, S.: Adaptation with self-evaluation to improve selective prediction in LLMs. In: Bouamor, H., Pino, J., Bali, K. (eds.) Findings of the Association for Computational Linguistics: EMNLP 2023, pp. 5190\u20135213. Association for Computational Linguistics, Singapore (2023). https:\/\/doi.org\/10.18653\/v1\/2023.findings-emnlp.345. https:\/\/aclanthology.org\/2023.findings-emnlp.345\/","DOI":"10.18653\/v1\/2023.findings-emnlp.345"},{"key":"9_CR2","doi-asserted-by":"publisher","unstructured":"Chiang, C.H., Lee, H.Y.: A closer look into using large language models for automatic evaluation. In: Bouamor, H., Pino, J., Bali, K. (eds.) Findings of the Association for Computational Linguistics: EMNLP 2023, pp. 8928\u20138942. Association for Computational Linguistics, Singapore (2023). https:\/\/doi.org\/10.18653\/v1\/2023.findings-emnlp.599. https:\/\/aclanthology.org\/2023.findings-emnlp.599\/","DOI":"10.18653\/v1\/2023.findings-emnlp.599"},{"key":"9_CR3","unstructured":"Confident-Ai: Confident-ai\/deepeval: The LLM evaluation framework. https:\/\/github.com\/confident-ai\/deepeval"},{"key":"9_CR4","doi-asserted-by":"publisher","unstructured":"Es, S., James, J., Espinosa\u00a0Anke, L., Schockaert, S.: RAGAs: automated evaluation of retrieval augmented generation. In: Aletras, N., De\u00a0Clercq, O. (eds.) Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations, pp. 150\u2013158. Association for Computational Linguistics, St. Julians, Malta (2024). https:\/\/doi.org\/10.18653\/v1\/2024.eacl-demo.16. https:\/\/aclanthology.org\/2024.eacl-demo.16\/","DOI":"10.18653\/v1\/2024.eacl-demo.16"},{"key":"9_CR5","doi-asserted-by":"publisher","unstructured":"Fan, W., et al.: A survey on rag meeting LLMs: towards retrieval-augmented large language models. In: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2024, pp. 6491\u20136501. Association for Computing Machinery, New York, NY, USA (2024). https:\/\/doi.org\/10.1145\/3637528.3671470","DOI":"10.1145\/3637528.3671470"},{"key":"9_CR6","doi-asserted-by":"publisher","unstructured":"Hwang, Y., Kim, Y., Bae, H., Lee, H., Bang, J., Jung, K.: Dialogizer: context-aware conversational-QA dataset generation from textual sources. In: Bouamor, H., Pino, J., Bali, K. (eds.) Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 8806\u20138828. Association for Computational Linguistics, Singapore (2023). https:\/\/doi.org\/10.18653\/v1\/2023.emnlp-main.545. https:\/\/aclanthology.org\/2023.emnlp-main.545\/","DOI":"10.18653\/v1\/2023.emnlp-main.545"},{"issue":"12","key":"9_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3571730","volume":"55","author":"Z Ji","year":"2023","unstructured":"Ji, Z., et al.: Survey of hallucination in natural language generation. ACM Comput. Surv. 55(12), 1\u201338 (2023)","journal-title":"ACM Comput. Surv."},{"key":"9_CR8","doi-asserted-by":"crossref","unstructured":"Liu, S., et al.: Can LLMs learn uncertainty on their own? expressing uncertainty effectively in a self-training manner. In: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp. 21635\u201321645 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.1205"},{"key":"9_CR9","doi-asserted-by":"publisher","unstructured":"Putri, R.A., Haznitrama, F.G., Adhista, D., Oh, A.: Can LLM generate culturally relevant commonsense QA data? Case study in Indonesian and Sundanese. In: Al-Onaizan, Y., Bansal, M., Chen, Y.N. (eds.) Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp. 20571\u201320590. Association for Computational Linguistics, Miami, Florida, USA (2024). https:\/\/doi.org\/10.18653\/v1\/2024.emnlp-main.1145. https:\/\/aclanthology.org\/2024.emnlp-main.1145\/","DOI":"10.18653\/v1\/2024.emnlp-main.1145"},{"issue":"1","key":"9_CR10","doi-asserted-by":"publisher","first-page":"13755","DOI":"10.1038\/s41598-025-98483-1","volume":"15","author":"M Raza","year":"2025","unstructured":"Raza, M., Jahangir, Z., Riaz, M.B., Saeed, M.J., Sattar, M.A.: Industrial applications of large language models. Sci. Rep. 15(1), 13755 (2025)","journal-title":"Sci. Rep."},{"key":"9_CR11","unstructured":"Ren, J., Zhao, Y., Vu, T., Liu, P.J., Lakshminarayanan, B.: Self-evaluation improves selective generation in large language models. In: Proceedings on, pp. 49\u201364. PMLR (2023)"},{"key":"9_CR12","doi-asserted-by":"publisher","unstructured":"Shen, C., Cheng, L., Nguyen, X.P., You, Y., Bing, L.: Large language models are not yet human-level evaluators for abstractive summarization. In: Bouamor, H., Pino, J., Bali, K. (eds.) Findings of the Association for Computational Linguistics: EMNLP 2023, pp. 4215\u20134233. Association for Computational Linguistics, Singapore (2023). https:\/\/doi.org\/10.18653\/v1\/2023.findings-emnlp.278. https:\/\/aclanthology.org\/2023.findings-emnlp.278\/","DOI":"10.18653\/v1\/2023.findings-emnlp.278"},{"key":"9_CR13","unstructured":"Wan, Y., et al.: Sciqag: a framework for auto-generated scientific question answering dataset with fine-grained evaluation. CoRR (2024)"},{"key":"9_CR14","first-page":"46595","volume":"36","author":"L Zheng","year":"2023","unstructured":"Zheng, L., et al.: Judging LLM-as-a-judge with mt-bench and chatbot arena. Adv. Neural. Inf. Process. Syst. 36, 46595\u201346623 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."}],"container-title":["Communications in Computer and Information Science","Recent Challenges in Intelligent information and Database Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-0068-9_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T06:09:08Z","timestamp":1781158148000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-0068-9_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819200672","9789819200689"],"references-count":14,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-0068-9_9","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"1 June 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACIIDS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Intelligent Information and Database Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kaohsiung","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Taiwan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 April 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 April 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aciids2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/aciids.pwr.edu.pl\/2026\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}