{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T12:28:07Z","timestamp":1742992087205,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":34,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819603473"},{"type":"electronic","value":"9789819603480"}],"license":[{"start":{"date-parts":[[2024,11,18]],"date-time":"2024-11-18T00:00:00Z","timestamp":1731888000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,18]],"date-time":"2024-11-18T00:00:00Z","timestamp":1731888000000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-0348-0_15","type":"book-chapter","created":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T18:38:24Z","timestamp":1732387104000},"page":"198-212","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Beyond Factualism: A Study of\u00a0LLM Calibration Through the\u00a0Lens of\u00a0Conversational Emotion Recognition"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4747-5452","authenticated-orcid":false,"given":"Samad","family":"Roohi","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2783-5257","authenticated-orcid":false,"given":"Richard","family":"Skarbez","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9958-432X","authenticated-orcid":false,"given":"Hien","family":"Nguyen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,18]]},"reference":[{"key":"15_CR1","doi-asserted-by":"crossref","unstructured":"Amayuelas, A., Pan, L., Chen, W., Wang, W.: Knowledge of knowledge: exploring known-unknowns uncertainty with large language models. arXiv:2305.13712 [cs] (2023)","DOI":"10.18653\/v1\/2024.findings-acl.383"},{"key":"15_CR2","unstructured":"Bloom, L., Lahey, M.: Language development and language disorders (1978). https:\/\/eric.ed.gov\/?id=ED150613, publisher: ERIC"},{"key":"15_CR3","doi-asserted-by":"publisher","unstructured":"Casas, J., et al.: Enhancing conversational agents with empathic abilities. In: Proceedings of the 21st ACM International Conference on Intelligent Virtual Agents. IVA \u201921, New York, NY, USA, pp. 41\u201347. Association for Computing Machinery (2021). https:\/\/doi.org\/10.1145\/3472306.3478344","DOI":"10.1145\/3472306.3478344"},{"key":"15_CR4","doi-asserted-by":"publisher","unstructured":"Chatterjee, A., Narahari, K.N., Joshi, M., Agrawal, P.: SemEval-2019 Task 3: EmoContext contextual emotion detection in text. In: May, J., Shutova, E., Herbelot, A., Zhu, X., Apidianaki, M., Mohammad, S.M. (eds.) Proceedings of the 13th International Workshop on Semantic Evaluation, Minneapolis, Minnesota, USA, pp. 39\u201348. Association for Computational Linguistics (2019). https:\/\/doi.org\/10.18653\/v1\/S19-2005, https:\/\/aclanthology.org\/S19-2005","DOI":"10.18653\/v1\/S19-2005"},{"key":"15_CR5","doi-asserted-by":"publisher","unstructured":"Chen, D., Zhengwei, H., Yiting, T., Jintao, M., Khanal, R.: Emotion and sentiment analysis for intelligent customer service conversation using a multi-task ensemble framework. Clust. Comput. (2023). https:\/\/doi.org\/10.1007\/s10586-023-04073-z","DOI":"10.1007\/s10586-023-04073-z"},{"key":"15_CR6","doi-asserted-by":"publisher","unstructured":"Chung, H.W., et al.: Scaling instruction-finetuned language models. arXiv:2210.11416 [cs] (2022). https:\/\/doi.org\/10.48550\/arXiv.2210.11416","DOI":"10.48550\/arXiv.2210.11416"},{"key":"15_CR7","doi-asserted-by":"publisher","unstructured":"Cosmides, L., Tooby, J.: Are humans good intuitive statisticians after all? Rethinking some conclusions from the literature on judgment under uncertainty. Cognition 58(1), 1\u201373 (1996). https:\/\/doi.org\/10.1016\/0010-0277(95)00664-8, https:\/\/www.sciencedirect.com\/science\/article\/pii\/0010027795006648","DOI":"10.1016\/0010-0277(95)00664-8"},{"key":"15_CR8","doi-asserted-by":"publisher","unstructured":"Feng, S., et al.: EmoWOZ: a large-scale corpus and labelling scheme for emotion recognition in task-oriented dialogue systems. arXiv:2109.04919 [cs] (2022). https:\/\/doi.org\/10.48550\/arXiv.2109.04919","DOI":"10.48550\/arXiv.2109.04919"},{"key":"15_CR9","doi-asserted-by":"publisher","unstructured":"Feng, S., Sun, G., Lubis, N., Zhang, C., Gas\u0306i\u0107, M.: Affect recognition in conversations using large language models. arXiv:2309.12881 [cs] (2023). https:\/\/doi.org\/10.48550\/arXiv.2309.12881","DOI":"10.48550\/arXiv.2309.12881"},{"key":"15_CR10","doi-asserted-by":"publisher","unstructured":"Ghosal, D., Majumder, N., Gelbukh, A., Mihalcea, R., Poria, S.: COSMIC: COmmonSense knowledge for eMotion identification in conversations. In: Findings of the Association for Computational Linguistics: EMNLP 2020, pp. 2470\u20132481. Association for Computational Linguistics (2020). https:\/\/doi.org\/10.18653\/v1\/2020.findings-emnlp.224, https:\/\/aclanthology.org\/2020.findings-emnlp.224","DOI":"10.18653\/v1\/2020.findings-emnlp.224"},{"key":"15_CR11","unstructured":"Guo, C., Pleiss, G., Sun, Y., Weinberger, K.Q.: On calibration of modern neural networks. In: International Conference on Machine Learning, pp. 1321\u20131330. PMLR (2017). http:\/\/proceedings.mlr.press\/v70\/guo17a.html"},{"key":"15_CR12","doi-asserted-by":"publisher","unstructured":"Huang, X., et al.: Emotion Detection for conversations based on reinforcement learning framework. IEEE Multimedia 28(2), 76\u201385 (2021). https:\/\/doi.org\/10.1109\/MMUL.2021.3065678, conference Name: IEEE MultiMedia","DOI":"10.1109\/MMUL.2021.3065678"},{"key":"15_CR13","unstructured":"Jiang, A.Q., et al.: Mistral 7B (2023). https:\/\/arxiv.org\/abs\/2310.06825v1"},{"key":"15_CR14","doi-asserted-by":"publisher","unstructured":"Kadavath, S., et al.: Language models (mostly) know what they know. arXiv:2207.05221 [cs] (2022). https:\/\/doi.org\/10.48550\/arXiv.2207.05221","DOI":"10.48550\/arXiv.2207.05221"},{"key":"15_CR15","doi-asserted-by":"publisher","unstructured":"Lei, S., Dong, G., Wang, X., Wang, K., Wang, S.: InstructERC: reforming emotion recognition in conversation with a retrieval multi-task LLMS framework. arXiv:2309.11911 [cs] (2023). https:\/\/doi.org\/10.48550\/arXiv.2309.11911","DOI":"10.48550\/arXiv.2309.11911"},{"key":"15_CR16","doi-asserted-by":"publisher","unstructured":"Lin, Z., Trivedi, S., Sun, J.: Generating with confidence: uncertainty quantification for black-box large language models. arXiv:2305.19187 [cs, stat] (2023). https:\/\/doi.org\/10.48550\/arXiv.2305.19187","DOI":"10.48550\/arXiv.2305.19187"},{"key":"15_CR17","doi-asserted-by":"publisher","unstructured":"Majumder, N., et al.: MIME: MIMicking emotions for empathetic response generation. arXiv:2010.01454 [cs] (2020). https:\/\/doi.org\/10.48550\/arXiv.2010.01454","DOI":"10.48550\/arXiv.2010.01454"},{"key":"15_CR18","doi-asserted-by":"crossref","unstructured":"Majumder, N., Poria, S., Hazarika, D., Mihalcea, R., Gelbukh, A., Cambria, E.: DialogueRNN: an attentive RNN for emotion detection in conversations. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a033, pp. 6818\u20136825 (2019). issue: 01","DOI":"10.1609\/aaai.v33i01.33016818"},{"key":"15_CR19","doi-asserted-by":"publisher","unstructured":"McKenna, N., Li, T., Cheng, L., Hosseini, M., Johnson, M., Steedman, M.: Sources of hallucination by large language models on inference tasks. In: Bouamor, H., Pino, J., Bali, K. (eds.) Findings of the Association for Computational Linguistics: EMNLP 2023, pp. 2758\u20132774. Association for Computational Linguistics, Singapore (2023). https:\/\/doi.org\/10.18653\/v1\/2023.findings-emnlp.182, https:\/\/aclanthology.org\/2023.findings-emnlp.182","DOI":"10.18653\/v1\/2023.findings-emnlp.182"},{"key":"15_CR20","doi-asserted-by":"publisher","unstructured":"Poria, S., Hazarika, D., Majumder, N., Naik, G., Cambria, E., Mihalcea, R.: MELD: a multimodal multi-party dataset for emotion recognition in conversations. arXiv:1810.02508 [cs] (2019). https:\/\/doi.org\/10.48550\/arXiv.1810.02508","DOI":"10.48550\/arXiv.1810.02508"},{"key":"15_CR21","doi-asserted-by":"publisher","unstructured":"Poria, S., Majumder, N., Mihalcea, R., Hovy, E.: Emotion recognition in conversation: research challenges, datasets, and recent advances. IEEE Access 7, 100943\u2013100953 (2019). https:\/\/doi.org\/10.1109\/ACCESS.2019.2929050, https:\/\/ieeexplore.ieee.org\/document\/8764449?signout=success, conference Name: IEEE Access","DOI":"10.1109\/ACCESS.2019.2929050"},{"key":"15_CR22","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners. OpenAI blog 1(8), 9 (2019). https:\/\/insightcivic.s3.us-east-1.amazonaws.com\/language-models.pdf"},{"key":"15_CR23","doi-asserted-by":"crossref","unstructured":"Rajani, N.F., McCann, B., Xiong, C., Socher, R.: Explain Yourself! leveraging language models for commonsense reasoning. arXiv:1906.02361 [cs] (2019)","DOI":"10.18653\/v1\/P19-1487"},{"key":"15_CR24","unstructured":"Shafer, G., Vovk, V.: A tutorial on conformal prediction. J. Mach. Learn. Res. 9(3) (2008)"},{"key":"15_CR25","doi-asserted-by":"publisher","unstructured":"Tian, K., et al.: Just ask for calibration: strategies for eliciting calibrated confidence scores from language models fine-tuned with human feedback. In: Bouamor, H., Pino, J., Bali, K. (eds.) Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 5433\u20135442. Association for Computational Linguistics, Singapore (2023). https:\/\/doi.org\/10.18653\/v1\/2023.emnlp-main.330, https:\/\/aclanthology.org\/2023.emnlp-main.330","DOI":"10.18653\/v1\/2023.emnlp-main.330"},{"key":"15_CR26","unstructured":"Touvron, H., et al.: LLaMA: open and efficient foundation language models (2023). https:\/\/arxiv.org\/abs\/2302.13971v1"},{"key":"15_CR27","doi-asserted-by":"publisher","unstructured":"Tu, G., Liang, B., Qin, B., Wong, K.F., Xu, R.: An empirical study on multiple knowledge from ChatGPT for emotion recognition in conversations. In: Bouamor, H., Pino, J., Bali, K. (eds.) Findings of the Association for Computational Linguistics: EMNLP 2023. pp. 12160\u201312173. Association for Computational Linguistics, Singapore (2023). https:\/\/doi.org\/10.18653\/v1\/2023.findings-emnlp.813, https:\/\/aclanthology.org\/2023.findings-emnlp.813","DOI":"10.18653\/v1\/2023.findings-emnlp.813"},{"key":"15_CR28","unstructured":"Tunstall, L., et al.: Zephyr: direct distillation of LM alignment (2023). arXiv:abs\/2310.16944v1"},{"key":"15_CR29","doi-asserted-by":"publisher","unstructured":"Xiao, Y., Wang, W.Y.: On hallucination and predictive uncertainty in conditional language generation. arXiv:2103.15025 [cs] (2021). https:\/\/doi.org\/10.48550\/arXiv.2103.15025","DOI":"10.48550\/arXiv.2103.15025"},{"key":"15_CR30","doi-asserted-by":"crossref","unstructured":"Xu, Y., Zeng, Z., Shen, Z.: Efficient cross-task prompt tuning for few-shot conversational emotion recognition. arXiv:2310.14614 [cs] (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.780"},{"key":"15_CR31","doi-asserted-by":"publisher","unstructured":"Yohanes, D., Putra, J.S., Filbert, K., Suryaningrum, K.M., Saputri, H.A.: Emotion detection in textual data using deep learning. Procedia Comput. Sci. 227, 464\u2013473 (2023). https:\/\/doi.org\/10.1016\/j.procs.2023.10.547, https:\/\/www.sciencedirect.com\/science\/article\/pii\/S1877050923017143","DOI":"10.1016\/j.procs.2023.10.547"},{"key":"15_CR32","unstructured":"Zhang, S., Chen, Z., Shen, Y., Ding, M., Tenenbaum, J.B., Gan, C.: Planning with large language models for code generation. arXiv:2303.05510 [cs] (2023)"},{"key":"15_CR33","doi-asserted-by":"publisher","unstructured":"Zhang, W., Deng, Y., Liu, B., Pan, S.J., Bing, L.: Sentiment analysis in the era of large language models: a reality check. arXiv:2305.15005 [cs] (2023). https:\/\/doi.org\/10.48550\/arXiv.2305.15005","DOI":"10.48550\/arXiv.2305.15005"},{"key":"15_CR34","doi-asserted-by":"publisher","unstructured":"Zhang, Y., Wang, M., Tiwari, P., Li, Q., Wang, B., Qin, J.: DialogueLLM: context and emotion knowledge-tuned LLaMA models for emotion recognition in conversations (2023). https:\/\/doi.org\/10.48550\/arXiv.2310.11374, http:\/\/arxiv.org\/abs\/2310.11374","DOI":"10.48550\/arXiv.2310.11374"}],"container-title":["Lecture Notes in Computer Science","AI 2024: Advances in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0348-0_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T19:03:56Z","timestamp":1732388636000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0348-0_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,18]]},"ISBN":["9789819603473","9789819603480"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0348-0_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,18]]},"assertion":[{"value":"18 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australasian Joint Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Melbourne, VIC","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","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":"25 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"37","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ausai2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ajcai2024.org\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}