{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,9]],"date-time":"2025-11-09T03:50:08Z","timestamp":1762660208239,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032067562","type":"print"},{"value":"9783032067579","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T00:00:00Z","timestamp":1762732800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T00:00:00Z","timestamp":1762732800000},"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\/978-3-032-06757-9_12","type":"book-chapter","created":{"date-parts":[[2025,11,9]],"date-time":"2025-11-09T03:42:30Z","timestamp":1762659750000},"page":"127-137","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Toward an\u00a0Understanding of\u00a0the\u00a0Self-Coherence and\u00a0the\u00a0Cross-Coherence of\u00a0LLMs An Empirical Investigation"],"prefix":"10.1007","author":[{"given":"Farouq","family":"Anbar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrei","family":"Mikriukov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaroslav","family":"Plaksin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vladimir","family":"Sitnikov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Giancarlo","family":"Succi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander","family":"Tormasov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ekaterina","family":"Trofimova","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,11,10]]},"reference":[{"key":"12_CR1","doi-asserted-by":"publisher","unstructured":"Li, J., et al.: Fundamental capabilities of large language models and their applications in domain scenarios: a survey. In: Ku, L.-W., Martins, A., Srikumar, V. (eds.) Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Bangkok, Thailand: Association for Computational Linguistics, pp. 11116\u201311141 (2024). https:\/\/doi.org\/10.18653\/v1\/2024.acl-long.599, https:\/\/aclanthology.org\/2024.acl-long.599\/","DOI":"10.18653\/v1\/2024.acl-long.599"},{"key":"12_CR2","doi-asserted-by":"publisher","unstructured":"Shen, S., Logeswaran, L., Lee, M., Lee, H., Poria, S., Mihalcea, R.: Understanding the capabilities and limitations of large language models for cultural commonsense. In: Duh, K., Gomez, H., Bethard, S. (eds.) Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). Mexico City, Mexico: Association for Computational Linguistics, pp. 5668\u20135680 (2024). https:\/\/doi.org\/10.18653\/v1\/2024.naacl-long.316. https:\/\/aclanthology.org\/2024.naacl-long.316\/","DOI":"10.18653\/v1\/2024.naacl-long.316"},{"issue":"2","key":"12_CR3","doi-asserted-by":"publisher","first-page":"2076","DOI":"10.3390\/app15020671","volume":"15","author":"H Seo","year":"2025","unstructured":"Seo, H., et al.: Large language models as evaluators in education: verification of feedback consistency and accuracy. Appl. Sci. 15(2), 2076\u20133417 (2025)","journal-title":"Appl. Sci."},{"key":"12_CR4","doi-asserted-by":"crossref","unstructured":"Cheng, F., Zouhar, V., Arora, S., Sachan, M., Strobelt, H., El-Assady, M.: Model checking using large language models\u2014evaluation and future directions. Electron. 14(2), 1\u201334 (2025)","DOI":"10.1145\/3613904.3641904"},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Cheng, F., Zouhar, V., Arora, S., Sachan, M., Strobelt, H., El-Assady, M.: Relic: investigating large language model responses using self-consistency. In: Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems, pp. 1\u201318 (2024)","DOI":"10.1145\/3613904.3641904"},{"key":"12_CR6","doi-asserted-by":"publisher","unstructured":"Kalyan, K.S.: A survey of GPT-3 family large language models including ChatGPT and GPT-4. Nat. Lang. Process. J. 6, 00048 (2024). ISSN: 2949-7191. https:\/\/doi.org\/10.1016\/j.nlp.2023.100048, https:\/\/www.sciencedirect.com\/science\/article\/pii\/ S2949719123000456","DOI":"10.1016\/j.nlp.2023.100048"},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Leon, M.: Benchmarking large language models with a unified performance ranking metric. Int. J. Found. Comput. Sci. Technol. 4 (2024)","DOI":"10.5121\/ijfcst.2024.14302"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Saxena, Y., Chopra, S., Tripathi, A.M.: Evaluating consistency and reasoning capabilities of large language models. In: 2024 Second International Conference on Data Science and Information System (ICDSIS), pp. 1\u20135. IEEE (2024)","DOI":"10.1109\/ICDSIS61070.2024.10594233"},{"key":"12_CR9","unstructured":"Clark, C., Lee, K., Chang, M.W., Kwiatkowski, T., Collins, M., Toutanova, K.: \u201cBOOLQ: exploring the surprising difficulty of natural yes\/no questions. arXiv preprint arXiv:1905.10044 (2019)"},{"key":"12_CR10","unstructured":"Zhang, T., Kishore, V., Wu, F., Weinberger, K.Q., Artzi, Y.: BERTscore: evaluating text generation with BERT. arXiv preprint arXiv:1904.09675 (2019)"},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"issue":"5","key":"12_CR12","first-page":"1","volume":"1","author":"Y Sasaki","year":"2007","unstructured":"Sasaki, Y., et al.: The truth of the F-measure. Teach Tutor Mater 1(5), 1\u20135 (2007)","journal-title":"Teach Tutor Mater"},{"key":"12_CR13","unstructured":"Chen, L., et al.: A survey on evaluating large language models in code generation tasks. arXiv preprint arXiv:2408.16498 (2024)"},{"key":"12_CR14","doi-asserted-by":"crossref","unstructured":"Dibia, V., Fourney, A., Bansal, G., Poursabzi-Sangdeh, F., Liu, H., Amershi, S.: Aligning offline metrics and human judgments of value for code generation models. arXiv preprint arXiv:2210.16494 (2022)","DOI":"10.18653\/v1\/2023.findings-acl.540"},{"key":"12_CR15","unstructured":"Mozannar, H., et al.: The RealHumanEval: evaluating large language models\u2019 abilities to support programmers. preprint arXiv:2404.02806 (2024)"},{"key":"12_CR16","unstructured":"Raj, H., Gupta, V., Rosati, D., Majumdar, S.: Semantic consistency for assuring reliability of large language models. arXiv preprint arXiv:2308.09138 (2023)"},{"key":"12_CR17","unstructured":"Liu, Y., Guo, Z., Liang, T., Shareghi, E., Vuli\u0107, I., Collier, N.: Aligning with logic: measuring, evaluating and improving logical consistency in large language models. arXiv preprint arXiv:2410.02205 (2024)"},{"key":"12_CR18","doi-asserted-by":"crossref","unstructured":"Parcalabescu, L., Frank, A.: On measuring faithfulness or self consistency of natural language explanations. arXiv preprint arXiv:2311.07466 (2023)","DOI":"10.18653\/v1\/2024.acl-long.329"},{"key":"12_CR19","doi-asserted-by":"crossref","unstructured":"Hong, R., Zhang, H., Pang, X., Yu, D., Zhang, C.: A closer look at the self-verification abilities of large language models in logical reasoning. arXiv preprint arXiv:2311.07954 (2023)","DOI":"10.18653\/v1\/2024.naacl-long.52"},{"key":"12_CR20","doi-asserted-by":"crossref","unstructured":"Rajan, S.S., Soremekun, E., Chattopadhyay, S.: Knowledge based consistency testing of large language models. arXiv preprint arXiv:2407.12830 (2024)","DOI":"10.18653\/v1\/2024.findings-emnlp.596"},{"key":"12_CR21","doi-asserted-by":"crossref","unstructured":"Patwardhan, A., Vaidya, V., Kundu, A.: Automated consistency analysis of LLMs. In: 2024 IEEE 6th International Conference on Trust, Privacy and Security in Intelligent Systems, and Applications (TPS-ISA), pp. 118\u2013127. IEEE (2024)","DOI":"10.1109\/TPS-ISA62245.2024.00023"},{"key":"12_CR22","unstructured":"Chern, S., Chern, E., Neubig, G., Liu, P.: Can large language models be trusted for evaluation? Scalable meta-evaluation of LLMS as evaluators via agent debate. arXiv preprint arXiv:2401.16788 (2024)"},{"key":"12_CR23","unstructured":"Microsoft: Azure (n.d.). https:\/\/azure.microsoft.com\/en-gb\/. Accessed 10 Mar 2025"},{"key":"12_CR24","unstructured":"Constructor: Research platform ( n.d.). https:\/\/constructor.tech\/products\/research-platform. Accessed 10 Mar 2025"},{"issue":"260","key":"12_CR25","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1080\/01621459.1952.10483441","volume":"47","author":"WH Kruskal","year":"1952","unstructured":"Kruskal, W.H., Wallis, W.A.: Use of ranks in one-criterion variance analysis. J. Am. Stat. Assoc. 47(260), 583\u2013621 (1952)","journal-title":"J. Am. Stat. Assoc."},{"key":"12_CR26","unstructured":"Campbell, D.T., Stanley, J.C.: Experimental and Quasi-Experimental Designs for Research. Ravenio books (2015)"}],"container-title":["Communications in Computer and Information Science","Computer and Communication Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-06757-9_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,9]],"date-time":"2025-11-09T03:42:33Z","timestamp":1762659753000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-06757-9_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,10]]},"ISBN":["9783032067562","9783032067579"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-06757-9_12","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,10]]},"assertion":[{"value":"10 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CCCE","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computer and Communication Engineering","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Helsinki","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Finland","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 May 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 May 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccce2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.ccce.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}