{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T16:21:09Z","timestamp":1783095669451,"version":"3.54.6"},"publisher-location":"Singapore","reference-count":24,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819617098","type":"print"},{"value":"9789819617104","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-981-96-1710-4_10","type":"book-chapter","created":{"date-parts":[[2025,1,31]],"date-time":"2025-01-31T09:56:47Z","timestamp":1738317407000},"page":"124-135","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Are Large Language Models More Honest in\u00a0Their Probabilistic or\u00a0Verbalized Confidence?"],"prefix":"10.1007","author":[{"given":"Shiyu","family":"Ni","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keping","family":"Bi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lulu","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiafeng","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,2,1]]},"reference":[{"key":"10_CR1","first-page":"508","volume":"2","author":"H Abdi","year":"2007","unstructured":"Abdi, H.: The kendall rank correlation coefficient. Encyclopedia Measurement Stat. 2, 508\u2013510 (2007)","journal-title":"Encyclopedia Measurement Stat."},{"key":"10_CR2","unstructured":"Berglund, L., et al.: The reversal curse: Llms trained on \u201ca is b\u201d fail to learn \u201cb is a\u201d. arXiv preprint arXiv:2309.12288 (2023)"},{"key":"10_CR3","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"10_CR4","doi-asserted-by":"crossref","unstructured":"Desai, S., Durrett, G.: Calibration of pre-trained transformers. arXiv preprint arXiv:2003.07892 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.21"},{"key":"10_CR5","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)"},{"key":"10_CR6","unstructured":"Fan, R.Z., et al.: Reformatted alignment. arXiv preprint arXiv:2402.12219 (2024)"},{"key":"10_CR7","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)"},{"issue":"2","key":"10_CR8","doi-asserted-by":"publisher","first-page":"87","DOI":"10.2478\/v10117-011-0021-1","volume":"30","author":"J Hauke","year":"2011","unstructured":"Hauke, J., Kossowski, T.: Comparison of values of pearson\u2019s and spearman\u2019s correlation coefficients on the same sets of data. Quaestiones Geographicae 30(2), 87\u201393 (2011)","journal-title":"Quaestiones Geographicae"},{"key":"10_CR9","doi-asserted-by":"publisher","first-page":"962","DOI":"10.1162\/tacl_a_00407","volume":"9","author":"Z Jiang","year":"2021","unstructured":"Jiang, Z., Araki, J., Ding, H., Neubig, G.: How can we know when language models know? on the calibration of language models for question answering. Trans. Assoc. Comput. Linguist. 9, 962\u2013977 (2021)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"10_CR10","unstructured":"Kadavath, S., et\u00a0al.: Language models (mostly) know what they know. arXiv preprint arXiv:2207.05221 (2022)"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Karpukhin, V., et al.: Dense passage retrieval for open-domain question answering. arXiv preprint arXiv:2004.04906 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"10_CR12","doi-asserted-by":"publisher","first-page":"453","DOI":"10.1162\/tacl_a_00276","volume":"7","author":"T Kwiatkowski","year":"2019","unstructured":"Kwiatkowski, T., et al.: Natural questions: a benchmark for question answering research. Trans. Assoc. Comput. Linguist. 7, 453\u2013466 (2019)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"10_CR13","unstructured":"Lewis, P., et al.: Retrieval-augmented generation for knowledge-intensive nlp tasks. Adv. Neural. Inf. Process. Syst. 33, 9459\u20139474 (2020)"},{"key":"10_CR14","unstructured":"Lin, S., Hilton, J., Evans, O.: Teaching models to express their uncertainty in words. arXiv preprint arXiv:2205.14334 (2022)"},{"key":"10_CR15","doi-asserted-by":"crossref","unstructured":"Mallen, A., Asai, A., Zhong, V., Das, R., Khashabi, D., Hajishirzi, H.: When not to trust language models: Investigating effectiveness of parametric and non-parametric memories. arXiv preprint arXiv:2212.10511 (2022)","DOI":"10.18653\/v1\/2023.acl-long.546"},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"Ni, S., Bi, K., Guo, J., Cheng, X.: A comparative study of training objectives for clarification facet generation. In: Proceedings of the Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region, pp. 1\u201310 (2023)","DOI":"10.1145\/3624918.3625332"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Ni, S., Bi, K., Guo, J., Cheng, X.: When do llms need retrieval augmentation? mitigating llms\u2019 overconfidence helps retrieval augmentation. arXiv preprint arXiv:2402.11457 (2024)","DOI":"10.18653\/v1\/2024.findings-acl.675"},{"key":"10_CR18","first-page":"27730","volume":"35","author":"L Ouyang","year":"2022","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. Adv. Neural. Inf. Process. Syst. 35, 27730\u201327744 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"10_CR19","unstructured":"Si, C., et al.: Prompting gpt-3 to be reliable. arXiv preprint arXiv:2210.09150 (2022)"},{"key":"10_CR20","doi-asserted-by":"crossref","unstructured":"Tian, K., et al.: Just ask for calibration: strategies for eliciting calibrated confidence scores from language models fine-tuned with human feedback. arXiv preprint arXiv:2305.14975 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.330"},{"key":"10_CR21","unstructured":"Xiong, M., et al.: Can llms express their uncertainty? An empirical evaluation of confidence elicitation in llms. arXiv preprint arXiv:2306.13063 (2023)"},{"key":"10_CR22","unstructured":"Yang, Y., Chern, E., Qiu, X., Neubig, G., Liu, P.: Alignment for honesty. arXiv preprint arXiv:2312.07000 (2023)"},{"key":"10_CR23","doi-asserted-by":"crossref","unstructured":"Yin, X., Zhang, X., Ruan, J., Wan, X.: Benchmarking knowledge boundary for large language model: a different perspective on model evaluation. arXiv preprint arXiv:2402.11493 (2024)","DOI":"10.18653\/v1\/2024.acl-long.124"},{"key":"10_CR24","doi-asserted-by":"crossref","unstructured":"Yin, Z., Sun, Q., Guo, Q., Wu, J., Qiu, X., Huang, X.: Do large language models know what they don\u2019t know? arXiv preprint arXiv:2305.18153 (2023)","DOI":"10.18653\/v1\/2023.findings-acl.551"}],"container-title":["Lecture Notes in Computer Science","Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-1710-4_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,31]],"date-time":"2025-01-31T09:56:55Z","timestamp":1738317415000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-1710-4_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819617098","9789819617104"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-1710-4_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"1 February 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CCIR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China Conference on Information Retrieval","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Wuhan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"18 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccir2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.cips-ir.org.cn\/CCIR2024\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}