{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T23:02:52Z","timestamp":1784242972121,"version":"3.55.0"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032250346","type":"print"},{"value":"9783032250353","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T00:00:00Z","timestamp":1782950400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T00:00:00Z","timestamp":1782950400000},"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":[[2027]]},"DOI":"10.1007\/978-3-032-25035-3_12","type":"book-chapter","created":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T22:02:57Z","timestamp":1784239377000},"page":"230-255","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Investigating User-Side Answer Errors and\u00a0Large Language Model Awareness in\u00a0Goal-Oriented Conversations"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-8541-2539","authenticated-orcid":false,"given":"Sara","family":"Mirabi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0579-8018","authenticated-orcid":false,"given":"Bahadorreza","family":"Ofoghi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7562-6767","authenticated-orcid":false,"given":"John","family":"Yearwood","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4973-0963","authenticated-orcid":false,"given":"Diego","family":"Molla-Aliod","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,2]]},"reference":[{"key":"12_CR1","unstructured":"Savi\u0107, D.A.: Single-objective vs. Multiobjective Optimisation for Integrated Decision Support (2002)"},{"key":"12_CR2","unstructured":"Ramamonjison, R., et al.: NL4Opt competition: Formulating optimization problems based on their natural language descriptions. arXiv preprint arXiv:2303.08233 (2023). https:\/\/doi.org\/10.48550\/arXiv.2303.08233"},{"key":"12_CR3","unstructured":"Hurst, A., Lerer, A., Goucher, A.P., Perelman, A., Ramesh, A., Clark, A., et al.: GPT-4o system card. arXiv preprint arXiv:2410.21276 (2024). https:\/\/arxiv.org\/abs\/2410.21276"},{"key":"12_CR4","unstructured":"Team, G., Georgiev, P., Lei, V.I., Burnell, R., Bai, L., Gulati, A., et al.: Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context. arXiv preprint arXiv:2403.05530 (2024)"},{"key":"12_CR5","unstructured":"Jiang, A.Q., Sablayrolles, A., Roux, A., Mensch, A., Savary, B., Bamford, C., et al.: Mixtral of experts. arXiv preprint arXiv:2401.04088 (2024). https:\/\/arxiv.org\/abs\/2401.04088"},{"key":"12_CR6","unstructured":"Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., Babaei, Y., et al.: LLaMA 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023). https:\/\/arxiv.org\/abs\/2307.09288"},{"key":"12_CR7","unstructured":"Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: BERT: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018). https:\/\/arxiv.org\/abs\/1810.04805"},{"key":"12_CR8","unstructured":"Sanh, V., Debut, L., Chaumond, J., Wolf, T.: DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108 (2019)."},{"key":"12_CR9","unstructured":"Liu, Y., et al.: RoBERTa: A robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692 (2019). https:\/\/arxiv.org\/abs\/1907.11692"},{"key":"12_CR10","unstructured":"Staudemeyer, R.C., Morris, E.R.: Understanding LSTM: A tutorial into long short-term memory recurrent neural networks. arXiv preprint arXiv:1909.09586 (2019). https:\/\/arxiv.org\/abs\/1909.09586"},{"key":"12_CR11","doi-asserted-by":"publisher","unstructured":"Mirabi, S., Ofoghi, B., Yearwood, J., Molla-Aliod, D., Mak-Hau, V.: Investigating answer validation using noise identification and classification in goal-oriented dialogues. In: Proceedings of the 17th International Conference on Agents and Artificial Intelligence \u2013 Volume 2: ICAART, pp. 658\u2013669. SciTePress (2025). https:\/\/doi.org\/10.5220\/0013304000003890","DOI":"10.5220\/0013304000003890"},{"key":"12_CR12","unstructured":"Abdullin, Y., Molla-Aliod, D., Ofoghi, B., Yearwood, J., Li, Q.: Synthetic dialogue dataset generation using LLM agents. arXiv preprint arXiv:2401.17461 (2024)."},{"key":"12_CR13","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhang, D.: Enabling answer validation by logic form reasoning in Chinese question answering. In: Proceedings of the International Conference on Natural Language Processing and Knowledge Engineering, pp. 275\u2013280 (2003)","DOI":"10.1109\/NLPKE.2003.1275912"},{"key":"12_CR14","doi-asserted-by":"crossref","unstructured":"Harabagiu, S.M., Hickl, A.: Methods for using textual entailment in open-domain question answering. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL) (2006)","DOI":"10.3115\/1220175.1220289"},{"key":"12_CR15","unstructured":"Bouma, G., Fahmi, I., Mur, J., van Noord, G., van der Plas, M., Tiedemann, J.: Evaluation of multilingual and multi-modal information retrieval. In: Peters, C. et al. (eds.) CLEF 2006, LNCS, vol. 4730, pp. xxx\u2013xxx. Springer, Berlin, Heidelberg (2007)"},{"key":"12_CR16","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1002\/asi.20989","volume":"60","author":"B Ofoghi","year":"2009","unstructured":"Ofoghi, B., Yearwood, J., Ma, L.: The impact of frame semantic annotation levels, frame-alignment techniques, and fusion methods on factoid answer processing. J. Assoc. Inf. Sci. Technol. 60, 247\u2013263 (2009)","journal-title":"J. Assoc. Inf. Sci. Technol."},{"key":"12_CR17","unstructured":"Pakray, P., Bhaskar, P., Banerjee, S., Pal, B.C., Bandyopadhyay, S., Gelbukh, A.: A hybrid question answering system based on information retrieval and answer validation. In: Forner, P., Karlgren, J., Womser-Hacker, C. (eds.) CLEF 2011, LNCS, vol. 7182, pp. xxx\u2013xxx. Springer, Berlin, Heidelberg (2012)"},{"key":"12_CR18","doi-asserted-by":"crossref","unstructured":"Xiang, Y., Zhang, Y., Zhou, X., Wang, X., Qin, Y.: Problematic situation analysis and automatic recognition for chinese online conversational system. In: Proceedings of the Third CIPS-SIGHAN Joint Conference on Chinese Language Processing, pp. 43\u201351. Association for Computational Linguistics, Wuhan, China (2014). https:\/\/aclanthology.org\/W14-6808","DOI":"10.3115\/v1\/W14-6808"},{"key":"12_CR19","doi-asserted-by":"crossref","unstructured":"Lowe, R., Noseworthy, M., Serban, I., Angelard-Gontier, N., Bengio, Y., Pineau, J.: Towards an automatic turing test: learning to evaluate dialogue responses. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1116\u20131126. Association for Computational Linguistics, Vancouver, Canada (2017). https:\/\/doi.org\/10.18653\/v1\/P17-1103","DOI":"10.18653\/v1\/P17-1103"},{"key":"12_CR20","doi-asserted-by":"crossref","unstructured":"Welleck, S., Weston, J., Szlam, A., Cho, K.: Dialogue natural language inference. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 3731\u20133741. Association for Computational Linguistics, Florence, Italy (2019). https:\/\/doi.org\/10.18653\/v1\/P19-1363","DOI":"10.18653\/v1\/P19-1363"},{"key":"12_CR21","doi-asserted-by":"crossref","unstructured":"Chen, Q., Zhu, X., Ling, Z.-H., Wei, S., Jiang, H., Inkpen, D.: Enhanced LSTM for Natural Language Inference. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1657\u20131668. Association for Computational Linguistics, Vancouver, Canada (2017). https:\/\/doi.org\/10.18653\/v1\/P17-1152","DOI":"10.18653\/v1\/P17-1152"},{"key":"12_CR22","doi-asserted-by":"crossref","unstructured":"Conneau, A., Kiela, D., Schwenk, H., Barrault, L., Bordes, A.: Supervised learning of universal sentence representations from natural language inference data. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 670\u2013680. Association for Computational Linguistics, Copenhagen, Denmark (2017). https:\/\/doi.org\/10.18653\/v1\/D17-1070","DOI":"10.18653\/v1\/D17-1070"},{"key":"12_CR23","doi-asserted-by":"crossref","unstructured":"Durmus, E., He, H., Diab, M.T.: FEQA: A question answering evaluation framework for faithfulness assessment in abstractive summarization. arXiv preprint arXiv:2005.03754 (2020). https:\/\/arxiv.org\/abs\/2005.03754","DOI":"10.18653\/v1\/2020.acl-main.454"},{"key":"12_CR24","doi-asserted-by":"crossref","unstructured":"Dziri, N., Madotto, A., Zaiane, O.R., Bose, A.: Neural Path Hunter: Reducing hallucination in dialogue systems via path grounding. arXiv preprint arXiv:2104.08455 (2021). https:\/\/arxiv.org\/abs\/2104.08455","DOI":"10.18653\/v1\/2021.emnlp-main.168"},{"key":"12_CR25","doi-asserted-by":"crossref","unstructured":"Konigari, R., Ramola, S., Alluri, V.V., Shrivastava, M.: Topic shift detection for mixed initiative response. In: Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL), pp. 161\u2013166 (2021)","DOI":"10.18653\/v1\/2021.sigdial-1.17"},{"key":"12_CR26","unstructured":"Pan, L., Chen, W., Kan, M., Wang, W.Y.: ContraQA: Question answering under contradicting contexts. arXiv preprint arXiv:2110.07803 (2021). https:\/\/arxiv.org\/abs\/2110.07803"},{"key":"12_CR27","doi-asserted-by":"crossref","unstructured":"Yu, D., Sagae, K.: Automatically exposing problems with neural dialog models. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 456\u2013470. Association for Computational Linguistics, Online and Punta Cana, Dominican Republic (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.37"},{"key":"12_CR28","doi-asserted-by":"crossref","unstructured":"Jiang, Z., Peng, H., Feng, S., Li, F., Li, D.: LLMs can find mathematical reasoning mistakes by pedagogical chain-of-thought. In: Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence (IJCAI-24), pp. 3439\u20133447. International Joint Conferences on Artificial Intelligence, Jeju, Korea (2024). https:\/\/doi.org\/10.24963\/ijcai.2024\/381","DOI":"10.24963\/ijcai.2024\/381"},{"key":"12_CR29","doi-asserted-by":"crossref","unstructured":"Gao, Y., et al.: Dr3: Ask Large Language Models Not to Give Off-Topic Answers in Open Domain Multi-Hop Question Answering. arXiv preprint arXiv:2403.12393 (2024). https:\/\/doi.org\/10.48550\/arXiv.2403.12393","DOI":"10.63317\/2p9wpa9uw35c"},{"key":"12_CR30","doi-asserted-by":"crossref","unstructured":"Chen, G.H., Chen, S., Liu, Z., Jiang, F., Wang, B.: Humans or LLMs as the Judge? a study on judgement bias. In: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 8301\u20138327. Association for Computational Linguistics, Miami, Florida, USA (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.474"},{"key":"12_CR31","unstructured":"Daniel, W.W., Cross, C.L.: Biostatistics: A Foundation for Analysis in the Health Sciences (10th ed.). John Wiley & Sons (2018)"},{"issue":"1","key":"12_CR32","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1177\/001316446002000104","volume":"20","author":"J Cohen","year":"1960","unstructured":"Cohen, J.: A coefficient of agreement for nominal scales. Educ. Psychol. Measur. 20(1), 37\u201346 (1960)","journal-title":"Educ. Psychol. Measur."},{"key":"12_CR33","doi-asserted-by":"crossref","first-page":"24824","DOI":"10.52202\/068431-1800","volume-title":"Advances in Neural Information Processing Systems, 35","author":"J Wei","year":"2022","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models. In: Koyejo, S., Mohamed, S., Agarwal, A., Belgrave, D., Cho, K., Oh, A. (eds.) Advances in Neural Information Processing Systems, 35, pp. 24824\u201324837. Curran Associates Inc (2022)"},{"key":"12_CR34","doi-asserted-by":"publisher","first-page":"1058","DOI":"10.1162\/opmi_a_00160","volume":"8","author":"C Cuskley","year":"2024","unstructured":"Cuskley, C., Woods, R., Flaherty, M.: The limitations of large language models for understanding human language and cognition. Open Mind 8, 1058\u20131083 (2024)","journal-title":"Open Mind"}],"container-title":["Lecture Notes in Computer Science","Agents and Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-25035-3_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T22:03:00Z","timestamp":1784239380000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-25035-3_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,2]]},"ISBN":["9783032250346","9783032250353"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-25035-3_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,2]]},"assertion":[{"value":"2 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICAART","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Agents and Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Porto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","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":"23 February 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 February 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icaart2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icaart.scitevents.org\/?y=2025","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}