{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T13:57:01Z","timestamp":1774360621155,"version":"3.50.1"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032212993","type":"print"},{"value":"9783032213006","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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\/978-3-032-21300-6_53","type":"book-chapter","created":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T13:03:38Z","timestamp":1774357418000},"page":"615-623","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Correct but\u00a0Incomplete: Why Chain-of-Thought Cannot Currently Support Auditable Reasoning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-1130-3767","authenticated-orcid":false,"given":"Edward","family":"Richards","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7829-5174","authenticated-orcid":false,"given":"Javier","family":"Sanz-Cruzado Puig","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2751-2087","authenticated-orcid":false,"given":"Richard","family":"Mccreadie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,3,25]]},"reference":[{"key":"53_CR1","unstructured":"Arcuschin, I., Janiak, J., Krzyzanowski, R., Rajamanoharan, S., Nanda, N., Conmy, A.: Chain-of-thought reasoning in the wild is not always faithful. In: Workshop on Reasoning and Planning for Large Language Models, co-located with the 13th International Conference on Leraning Representations (ICLR 2025). Singapore (2025)"},{"key":"53_CR2","unstructured":"Barez, F., et al.: Chain-of-thought is not explainability (2025)"},{"key":"53_CR3","unstructured":"Bricken, T., et al.: Towards monosemanticity: decomposing language models with dictionary learning. Transformer circuits thread (2023). https:\/\/transformer-circuits.pub\/2023\/monosemantic-features\/index.html"},{"key":"53_CR4","unstructured":"Chen, Y., et al.: Reasoning models don\u2019t always say what they think (2025). https:\/\/arxiv.org\/abs\/2505.05410"},{"key":"53_CR5","doi-asserted-by":"publisher","unstructured":"Clark, C., Lee, K., Chang, M., Kwiatkowski, T., Collins, M., Toutanova, K.: BoolQ: exploring the surprising difficulty of natural yes\/no questions. In: Burstein, J., Doran, C., Solorio, T. (eds.) 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT 2019), pp. 2924\u20132936. Association for Computational Linguistics, Minneapolis, USA (2019). https:\/\/doi.org\/10.18653\/V1\/N19-1300","DOI":"10.18653\/V1\/N19-1300"},{"key":"53_CR6","unstructured":"Clark, P., et al.: Think you have solved question answering? Try arc, the AI2 reasoning challenge. CoRR abs\/1803.05457 (2018). http:\/\/arxiv.org\/abs\/1803.05457"},{"key":"53_CR7","unstructured":"Cobbe, K., et al.: Training verifiers to solve math word problems. CoRR abs\/2110.14168 (2021). https:\/\/arxiv.org\/abs\/2110.14168"},{"key":"53_CR8","unstructured":"DeepSeek-AI, Guo, D., Yang, D., et\u00a0al.: DeepSeek-R1: Incentivizing reasoning capability in LLMs via reinforcement learning (2025). https:\/\/arxiv.org\/abs\/2501.12948"},{"key":"53_CR9","unstructured":"Gou, B., et al.: Mind2Web 2: evaluating agentic search with agent-as-a-judge. In: 39th Annual Conference on Neural Information Processing Systems (NeurIPS 2025). Datasets and Benchmarks track. Mexico (2025)"},{"key":"53_CR10","unstructured":"Grattafiori, A., et\u00a0al.: The Llama 3 herd of models (2024). https:\/\/arxiv.org\/abs\/2407.21783"},{"key":"53_CR11","doi-asserted-by":"publisher","unstructured":"Groeneveld, D., et al.: OLMo: accelerating the science of language models. In: 62nd Annual Meeting of the Association of Computational Linguistics (ACL 2024). Bangkok, Thailand (2024). https:\/\/doi.org\/10.18653\/v1\/2024.acl-long.841","DOI":"10.18653\/v1\/2024.acl-long.841"},{"key":"53_CR12","unstructured":"Jiang, A.Q., et al.: Mistral 7b (2023). https:\/\/arxiv.org\/abs\/2310.06825"},{"key":"53_CR13","doi-asserted-by":"publisher","unstructured":"Lanham, T., et al.: Measuring faithfulness in chain-of-thought reasoning. CoRR abs\/2307.13702 (2023). https:\/\/doi.org\/10.48550\/ARXIV.2307.13702","DOI":"10.48550\/ARXIV.2307.13702"},{"key":"53_CR14","unstructured":"Lightman, H., et al.: Let\u2019s verify step by step. In: 12th International Conference on Learning Representations (ICLR 2024). Vienna, Austria (2024)"},{"key":"53_CR15","unstructured":"Liu, X., et al.: AgentBench: evaluating LLMs as agents. In: 12th International Conference on Learning Representations (ICLR 2024). Vienna, Austria (2024)"},{"key":"53_CR16","doi-asserted-by":"publisher","unstructured":"M kander, J.: Auditing of AI: legal, ethical and technical approaches. Digit. Soc. 2(3) (2023). https:\/\/doi.org\/10.1007\/s44206-023-00074-y","DOI":"10.1007\/s44206-023-00074-y"},{"key":"53_CR17","unstructured":"Qiao, S., et al.: Benchmarking agentic workflow generation. In: 13th International Conference on Learning Representations (ICLR 2025). Singapore (2025)"},{"key":"53_CR18","unstructured":"Templeton, A., et al.: Scaling monosemanticity: extracting interpretable features from claude 3 sonnet. Transformer circuits thread (2024). https:\/\/transformer-circuits.pub\/2024\/scaling-monosemanticity\/index.html"},{"key":"53_CR19","unstructured":"Turpin, M., Michael, J., Perez, E., Bowman, S.R.: Language models don\u2019t always say what they think: unfaithful explanations in chain-of-thought prompting. In: 37th Conference on Neural Information Processing Systems (NeurIPS 2023). New Orleans, USA (2023)"},{"key":"53_CR20","unstructured":"Wang, X., et al.: Self-consistency improves chain of thought reasoning in language models. In: 11th International Conference on Learning Representations (ICLR 2023). Kigali, Rwanda (2023)"},{"key":"53_CR21","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models. In: 36th Conference on Neural Information Processing Systems 2022 (NeurIPS 2022). New Orleans, USA (2022)"},{"issue":"10","key":"53_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2025.101370","volume":"6","author":"F Xu","year":"2025","unstructured":"Xu, F., et al.: Toward large reasoning models: a survey of reinforced reasoning with large language models. Patterns 6(10), 101370 (2025). https:\/\/doi.org\/10.1016\/j.patter.2025.101370","journal-title":"Patterns"},{"key":"53_CR23","unstructured":"Yang, A., et al.: Qwen2.5 technical report (2025). https:\/\/arxiv.org\/abs\/2412.15115"},{"key":"53_CR24","unstructured":"Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K.R., Cao, Y.: React: Synergizing reasoning and acting in language models. In: The eleventh international conference on learning representations (2022)"},{"key":"53_CR25","doi-asserted-by":"publisher","unstructured":"Zhang, S., Wang, Z., Qi, J., Liu, J., Ying, Z.: Accurate assessment via process data. Psychometrika 88(1), 76\u201397 (2023). https:\/\/doi.org\/10.1007\/s11336-022-09880-8","DOI":"10.1007\/s11336-022-09880-8"},{"key":"53_CR26","unstructured":"Zhou, S., et al.: WebArena: a realistic web environment for building autonomous agents. In: 12th International Conference on Learning Representations (ICLR 2024). Vienna, Austria (2024)"},{"key":"53_CR27","doi-asserted-by":"crossref","unstructured":"Zhu, A., Hwang, A., Dugan, L., Callison-Burch, C.: FanOutQA: a multi-hop, multi-document question answering benchmark for large language models. In: 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024). Short papers, pp. 18\u201337. Bangkok, Thailand (2024)","DOI":"10.18653\/v1\/2024.acl-short.2"}],"container-title":["Lecture Notes in Computer Science","Advances in Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-21300-6_53","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T13:03:54Z","timestamp":1774357434000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-21300-6_53"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032212993","9783032213006"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-21300-6_53","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"25 March 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ECIR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Information Retrieval","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Delft","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","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":"29 March 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 April 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"48","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecir2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecir2026.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}