{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T08:03:49Z","timestamp":1784189029267,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":33,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819234165","type":"print"},{"value":"9789819234172","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T00:00:00Z","timestamp":1784246400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T00:00:00Z","timestamp":1784246400000},"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\/978-981-92-3417-2_50","type":"book-chapter","created":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T07:11:22Z","timestamp":1784185882000},"page":"587-598","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Unsupervised Hallucination Detection via Generalized Semantic Entropy"],"prefix":"10.1007","author":[{"given":"Jun","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyu","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangming","family":"Dai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,17]]},"reference":[{"key":"50_CR1","unstructured":"Almazrouei, E. et al.., et al.: The falcon series of open language models. arXiv preprint https:\/\/arxiv.org\/abs\/2311.16867 (2023)"},{"key":"50_CR2","doi-asserted-by":"publisher","first-page":"967","DOI":"10.18653\/v1\/2023.findings-emnlp.68","volume-title":"Findings of the Association for Computational Linguistics: EMNLP 2023","author":"A Azaria","year":"2023","unstructured":"Azaria, A., Mitchell, T.: The internal state of an llm knows when it\u2019s lying. In: Findings of the Association for Computational Linguistics: EMNLP 2023, pp. 967\u2013976 (2023)"},{"key":"50_CR3","unstructured":"Bouchard, D., Chauhan, M.S.: Uncertainty quantification for language models: a suite of black-box, white-box, llm judge, and ensemble scorers. arXiv preprint https:\/\/arxiv.org\/abs\/2504.19254 (2025)"},{"key":"50_CR4","unstructured":"Chen, C., Liu, K., Chen, Z., Gu, Y., Wu, Y., Tao, M., Fu, Z., Ye, J.: Inside: Llms\u2019 internal states retain the power of hallucination detection. arXiv preprint https:\/\/arxiv.org\/abs\/2402.03744 (2024)"},{"key":"50_CR5","doi-asserted-by":"crossref","unstructured":"Chuang, Y.S., Qiu, L., Hsieh, C.Y., Krishna, R., Kim, Y., Glass, J.: Lookback lens: detecting and mitigating contextual hallucinations in large language models using only attention maps. In: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp. 1419\u20131436 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.84"},{"key":"50_CR6","doi-asserted-by":"crossref","unstructured":"Duan, J. et al.: Shifting attention to relevance: towards the predictive uncertainty quan- tification of free-form large language models. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 5050\u20135063 (2024)","DOI":"10.18653\/v1\/2024.acl-long.276"},{"issue":"8017","key":"50_CR7","doi-asserted-by":"publisher","first-page":"625","DOI":"10.1038\/s41586-024-07421-0","volume":"630","author":"S Farquhar","year":"2024","unstructured":"Farquhar, S., Kossen, J., Kuhn, L., Gal, Y.: Detecting hallucinations in large language models using semantic entropy. Nature. 630(8017), 625\u2013630 (2024)","journal-title":"Nature"},{"key":"50_CR8","unstructured":"Grattafiori, A., Dubey, A., Jauhri, A., Pandey, A., Kadian, A., Al-Dahle, A., Letman, A., Mathur, A., Schelten, A., Vaughan, A., et al.: The llama 3 herd of models. arXiv preprint https:\/\/arxiv.org\/abs\/2407.21783 (2024)"},{"issue":"1","key":"50_CR9","doi-asserted-by":"publisher","first-page":"16375","DOI":"10.1038\/s41598-024-66708-4","volume":"14","author":"G Hao","year":"2024","unstructured":"Hao, G., Wu, J., Pan, Q., Morello, R.: Quantifying the uncertainty of llm hallucination spreading in complex adaptive social networks. Sci. Rep. 14(1), 16375 (2024)","journal-title":"Sci. Rep."},{"key":"50_CR10","unstructured":"He, P., Liu, X., Gao, J., Chen, W.: Deberta: decoding-enhanced bert with disen- tangled attention. arXiv preprint https:\/\/arxiv.org\/abs\/2006.03654 (2020)"},{"key":"50_CR11","unstructured":"Hendrycks, D., Gimpel, K.: A baseline for detecting misclassified and out-of- distribution examples in neural networks. arXiv preprint https:\/\/arxiv.org\/abs\/1610.02136 (2016)"},{"issue":"2","key":"50_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3703155","volume":"43","author":"L Huang","year":"2025","unstructured":"Huang, L. et al.: A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions. ACM Trans. Inf. Syst. 43(2), 1\u201355 (2025)","journal-title":"ACM Trans. Inf. Syst."},{"key":"50_CR13","unstructured":"Jiang, A.Q., et al..: Mistral 7b (2023), https:\/\/arxiv.org\/abs\/2310.06825"},{"key":"50_CR14","doi-asserted-by":"crossref","unstructured":"Joshi, M., Choi, E., Weld, D.S., Zettlemoyer, L.: Triviaqa: a large scale distantly supervised challenge dataset for reading comprehension. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1601\u20131611 (2017)","DOI":"10.18653\/v1\/P17-1147"},{"key":"50_CR15","unstructured":"Kadavath, S., et al.: Language models (mostly) know what they know. arXiv preprint https:\/\/arxiv.org\/abs\/2207.05221 (2022)"},{"key":"50_CR16","unstructured":"Kuhn, L., Gal, Y., Farquhar, S.: Semantic uncertainty: Linguistic invari- ances for uncertainty estimation in natural language generation. arXiv preprint https:\/\/arxiv.org\/abs\/2302.09664 (2023)"},{"key":"50_CR17","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 bench- mark for question answering research. Trans. Assoc. Comput. Linguist. 7, 453\u2013466 (2019)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"50_CR18","unstructured":"Lin, S., Hilton, J., Evans, O.: Teaching models to express their uncertainty in words. arXiv preprint https:\/\/arxiv.org\/abs\/2205.14334 (2022)"},{"key":"50_CR19","unstructured":"Lin, Z., Trivedi, S., Sun, J.: Generating with confidence: Uncertainty quantification for black-box large language models. arXiv preprint https:\/\/arxiv.org\/abs\/2305.19187 (2023)"},{"key":"50_CR20","doi-asserted-by":"crossref","unstructured":"Liu, X., Lochman, Y., Zach, C.: Gen: Pushing the limits of softmax-based out-of-distribution detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23946\u201323955 (2023)","DOI":"10.1109\/CVPR52729.2023.02293"},{"key":"50_CR21","unstructured":"Malinin, A., Gales, M.: Uncertainty estimation in autoregressive structured prediction. arXiv preprint https:\/\/arxiv.org\/abs\/2002.07650 (2020)"},{"key":"50_CR22","doi-asserted-by":"crossref","unstructured":"Manakul, P., Liusie, A., Gales, M.: Selfcheckgpt: zero-resource black-box halluci- nation detection for generative large language models. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 9004\u20139017 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.557"},{"key":"50_CR23","unstructured":"Marks, S., Tegmark, M.: The geometry of truth: Emergent linear structure in large language model representations of true\/false datasets. arXiv preprint https:\/\/arxiv.org\/abs\/2310.06824 (2023)"},{"key":"50_CR24","doi-asserted-by":"crossref","unstructured":"Patel, A., Bhattamishra, S., Goyal, N.: Are NLP models really able to solve simple math word problems? In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 2080\u20132094 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.168"},{"key":"50_CR25","doi-asserted-by":"publisher","first-page":"134507","DOI":"10.52202\/079017-4274","volume":"37","author":"X Qiu","year":"2024","unstructured":"Qiu, X., Miikkulainen, R.: Semantic density: Uncertainty quantification for large language models through confidence measurement in semantic space. Adv. Neural Inf. Proces. Syst. 37, 134507\u2013134533 (2024)","journal-title":"Adv. Neural Inf. Proces. Syst."},{"key":"50_CR26","doi-asserted-by":"crossref","unstructured":"Rajpurkar, P., Zhang, J., Lopyrev, K., Liang, P.: Squad: 100,000+ questions for machine comprehension of text. In: Proceedings of the 2016 conference on empirical methods in natural language processing, pp. 2383\u20132392 (2016)","DOI":"10.18653\/v1\/D16-1264"},{"key":"50_CR27","unstructured":"Ren, J. et al.: Out-of-distribution detection and selective generation for conditional language models. arXiv preprint https:\/\/arxiv.org\/abs\/2209.15558 (2022)"},{"key":"50_CR28","doi-asserted-by":"publisher","first-page":"34188","DOI":"10.52202\/079017-1077","volume":"37","author":"G Sriramanan","year":"2024","unstructured":"Sriramanan, G., Bharti, S., Sadasivan, V.S., Saha, S., Kattakinda, P., Feizi, S.: Llm- check: Investigating detection of hallucinations in large language models. Adv. Neural Inf. Proces. Syst. 37, 34188\u201334216 (2024)","journal-title":"Adv. Neural Inf. Proces. Syst."},{"issue":"1","key":"50_CR29","doi-asserted-by":"publisher","first-page":"138","DOI":"10.1186\/s12859-015-0564-6","volume":"16","author":"G Tsatsaronis","year":"2015","unstructured":"Tsatsaronis, G., et al.: An overview of the bioasq large-scale biomedical semantic indexing and question answering competition. BMC Bioinformatics. 16(1), 138 (2015)","journal-title":"BMC Bioinformatics"},{"key":"50_CR30","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1162\/tacl_a_00737","volume":"13","author":"R Vashurin","year":"2025","unstructured":"Vashurin, R., et al.: Benchmarking un- certainty quantification methods for large language models with lm-polygraph. Trans. Assoc. Comput. Linguist. 13, 220\u2013248 (2025)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"50_CR31","unstructured":"Vashurin, R., et al.: Uncertainty quantification for llms through minimum Bayes risk: Bridging confidence and consistency. arXiv preprint https:\/\/arxiv.org\/abs\/2502.04964 (2025)"},{"key":"50_CR32","doi-asserted-by":"crossref","unstructured":"Vazhentsev, A., et al.: Unconditional truthfulness: learning unconditional uncertainty of large language models. In: Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pp. 35661\u201335682 (2025)","DOI":"10.18653\/v1\/2025.emnlp-main.1807"},{"key":"50_CR33","unstructured":"Xiong, M., et al.: Can llms express their uncertainty? An empirical evaluation of confidence elicitation in llms. arXiv preprint https:\/\/arxiv.org\/abs\/2306.13063 (2023)"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-3417-2_50","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T07:11:26Z","timestamp":1784185886000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3417-2_50"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,17]]},"ISBN":["9789819234165","9789819234172"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3417-2_50","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,17]]},"assertion":[{"value":"17 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Toronto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","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":"22 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2026a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2026\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}