{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T14:50:08Z","timestamp":1787323808982,"version":"build-2736575974"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:00:00Z","timestamp":1773792000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T00:00:00Z","timestamp":1781740800000},"content-version":"vor","delay-in-days":92,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"The National Social Science Fund of China","award":["22BTY071"],"award-info":[{"award-number":["22BTY071"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J. King Saud Univ. Comput. Inf. Sci."],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1007\/s44443-026-00643-4","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T15:35:35Z","timestamp":1773848135000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Structured elimination with self-consistency and verification for robust multiple-choice reasoning: a large-scale sports training benchmark and cross-domain evaluation"],"prefix":"10.1007","volume":"38","author":[{"given":"Ye","family":"Teng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,18]]},"reference":[{"key":"643_CR1","unstructured":"Almazrouei E et al (2023) The falcon series of open language models. arXiv preprint arXiv:2311.16867"},{"key":"643_CR2","unstructured":"Bai J, Bai S, Li Y et al (2023) Qwen technical report. arXiv preprint arXiv:2309.16609"},{"key":"643_CR3","first-page":"1877","volume":"33","author":"TB Brown","year":"2020","unstructured":"Brown TB, Mann B, Ryder N, Subbiah M, Kaplan J et al (2020) Language models are few-shot learners. Adv Neural Inf Process Syst 33:1877\u20131901","journal-title":"Adv Neural Inf Process Syst"},{"key":"643_CR4","unstructured":"Chowdhery A, Narang S, Devlin J et al (2022) Palm: Scaling language modeling with pathways. arXiv preprint arXiv:2204.02311"},{"key":"643_CR5","unstructured":"Chung HW, Hou L, Longpre S et al (2022) Scaling instruction-finetuned language models. arXiv preprint arXiv:2210.11416"},{"key":"643_CR6","unstructured":"Clark P, Cowhey I, Etzioni O, Khot T et al (2018) Think you have solved question answering? try arc, the ai2 reasoning challenge. arXiv preprint arXiv:1803.05457"},{"key":"643_CR7","unstructured":"Cobbe K, Kosaraju V, Bavarian M et al (2021) Training verifiers to solve math word problems. arXiv preprint arXiv:2110.14168"},{"key":"643_CR8","doi-asserted-by":"crossref","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K (2019) Bert: Pre-training of deep bidirectional transformers for language understanding. Proceedings of NAACL-HLT, (pp 4171\u20134186)","DOI":"10.18653\/v1\/N19-1423"},{"key":"643_CR9","unstructured":"Hendrycks D, Burns C, Basart S, Nye M et al (2021) Measuring massive multitask language understanding. International Conference on Learning Representations"},{"key":"643_CR10","unstructured":"Izacard G, Petroni F, Hosseini L, Dwivedi-Yu J et al (2022) Atlas: Few-shot learning with retrieval augmented language models. Proceedings of ICML, (pp 9526\u20139558)"},{"key":"643_CR11","doi-asserted-by":"crossref","unstructured":"Jain S, Wallace BC (2019) Attention is not explanation. In: Proceedings of NAACL-HLT, (pp 3543\u20133556)","DOI":"10.18653\/v1\/N19-1357"},{"key":"643_CR12","doi-asserted-by":"crossref","unstructured":"Khashabi D, Choi E, Hajishirzi H, Roth D, Sabharwal A (2020) Unifiedqa: Crossing format boundaries with a single qa system. Findings of the Association for Computational Linguistics: EMNLP, (pp 1896\u20131907)","DOI":"10.18653\/v1\/2020.findings-emnlp.171"},{"key":"643_CR13","doi-asserted-by":"crossref","unstructured":"Kojima T, Gu SS, Reid M, Matsuo Y, Iwasawa Y (2022) Large language models are zero-shot reasoners. arXiv preprint arXiv:2205.11916","DOI":"10.52202\/068431-1613"},{"key":"643_CR14","doi-asserted-by":"crossref","unstructured":"Lai G, Xie Q, Liu H, Yang Y, Hovy E (2017) Race: Large-scale reading comprehension dataset from examinations. In: Proceedings of EMNLP, (pp 785\u2013794)","DOI":"10.18653\/v1\/D17-1082"},{"key":"643_CR15","first-page":"9459","volume":"33","author":"P Lewis","year":"2020","unstructured":"Lewis P, Perez E, Piktus A, Petroni F et al (2020) Retrieval-augmented generation for knowledge-intensive nlp tasks. Adv Neural Inf Process Syst 33:9459\u20139474","journal-title":"Adv Neural Inf Process Syst"},{"key":"643_CR16","unstructured":"Li Y, Goyal N, Chen X et al (2023) Textbooks are all you need ii: phi-1.5 technical report. arXiv preprint arXiv:2309.05463"},{"key":"643_CR17","unstructured":"Liu Y, Ott M, Goyal N, Du J et al (2019) Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692"},{"key":"643_CR18","doi-asserted-by":"crossref","unstructured":"Ma C, Du X (2023) Process of elimination for multiple choice reasoning. In: Proceedings of the 2023 conference on empirical methods in natural language processing, (pp 15650\u201315663)","DOI":"10.18653\/v1\/2023.emnlp-main.273"},{"key":"643_CR19","doi-asserted-by":"crossref","unstructured":"Madaan A, Yazdanbakhsh A, Shi W et al (2023) Self-refine: Iterative refinement with self-feedback. arXiv preprint arXiv:2303.17651","DOI":"10.52202\/075280-2019"},{"key":"643_CR20","doi-asserted-by":"crossref","unstructured":"Mihaylov T, Clark P, Khot T, Sabharwal A (2018) Can a suit of armor conduct electricity? a new dataset for open book question answering. In: Proceedings of EMNLP, (pp 2381\u20132391)","DOI":"10.18653\/v1\/D18-1260"},{"key":"643_CR21","unstructured":"Nakano R, Hilton J, Balaji S et al (2021) Webgpt: Browser-assisted question-answering with human feedback. arXiv preprint arXiv:2112.09332"},{"key":"643_CR22","doi-asserted-by":"publisher","first-page":"27730","DOI":"10.52202\/068431-2011","volume":"35","author":"L Ouyang","year":"2022","unstructured":"Ouyang L, Wu J, Jiang X et al (2022) Training language models to follow instructions with human feedback. Adv Neural Inf Process Syst 35:27730\u201327744","journal-title":"Adv Neural Inf Process Syst"},{"key":"643_CR23","unstructured":"Pal A, Umapathi LK, Sankarasubbu M (2022) Medmcqa: A large-scale multi-subject multi-choice dataset for medical domain question answering. In: Proceedings of the ACM Conference on Health, Inference, and Learning (CHIL), (pp 248\u2013260)"},{"key":"643_CR24","doi-asserted-by":"crossref","unstructured":"Parikh S., T\u00e4ckstr\u00f6m O, Das D, Uszkoreit J (2018) Eliminet: A model for eliminating options for reading comprehension with multiple choice questions. In: Proceedings of the 27th international joint conference on artificial intelligence, (pp 5190\u20135197)","DOI":"10.24963\/ijcai.2018\/594"},{"key":"643_CR25","doi-asserted-by":"crossref","unstructured":"Sap M, Rashkin H, Chen D, Le Bras R, Choi Y (2019) Social iqa: Commonsense reasoning about social interactions. In: Proceedings of EMNLP-IJCNLP, (pp 4463\u20134473)","DOI":"10.18653\/v1\/D19-1454"},{"key":"643_CR26","doi-asserted-by":"crossref","unstructured":"Shinn N, Cassano A, Labash K et al (2023) Reflexion: Language agents with verbal reinforcement learning. arXiv preprint arXiv:2303.11366","DOI":"10.52202\/075280-0377"},{"key":"643_CR27","doi-asserted-by":"crossref","unstructured":"Talmor A, Herzig J, Lourie N, Berant J (2019) Commonsenseqa: A question answering challenge targeting commonsense knowledge. In: Proceedings of NAACL-HLT, (pp 4149\u20134158)","DOI":"10.18653\/v1\/N19-1421"},{"key":"643_CR28","unstructured":"Touvron H, Lavril T, Izacard G et al (2023a) Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971"},{"key":"643_CR29","unstructured":"Touvron H, Martin L, Stone K et al (2023b) Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288"},{"key":"643_CR30","unstructured":"Wang X, Wei J, Schuurmans D et al (2023) Self-consistency improves chain-of-thought reasoning in language models. International Conference on Learning Representations"},{"key":"643_CR31","doi-asserted-by":"publisher","first-page":"24824","DOI":"10.52202\/068431-1800","volume":"35","author":"J Wei","year":"2022","unstructured":"Wei J, Wang X, Schuurmans D, Bosma M et al (2022) Chain-of-thought prompting elicits reasoning in large language models. Adv Neural Inf Process Syst 35:24824\u201324837","journal-title":"Adv Neural Inf Process Syst"},{"key":"643_CR32","doi-asserted-by":"crossref","unstructured":"Weng Y, Liu T, Zhong M et al (2023) Large language models are better reasoners with self-verification. Findings of the Association for Computational Linguistics: EMNLP, (pp 14145\u201314158)","DOI":"10.18653\/v1\/2023.findings-emnlp.167"},{"key":"643_CR33","unstructured":"Yao S, Zhao J, Yu D et al (2022) React: Synergizing reasoning and acting in language models. arXiv preprint arXiv:2210.03629"},{"key":"643_CR34","first-page":"15491","volume":"35","author":"E Zelikman","year":"2022","unstructured":"Zelikman E, Wu Y, Mu J, Goodman N (2022) Star: Bootstrapping reasoning with reasoning. Adv Neural Inf Process Syst 35:15491\u201315505","journal-title":"Adv Neural Inf Process Syst"},{"key":"643_CR35","unstructured":"Zhang Z, Yang A, Bai J et al (2023) Baichuan 2: Open large-scale language models. arXiv preprint arXiv:2309.10305"},{"key":"643_CR36","unstructured":"Zhou D, Sch\u00e4rli N, Hou L et al (2022) Least-to-most prompting enables complex reasoning in large language models. International Conference on Learning Representations"}],"container-title":["Journal of King Saud University Computer and Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s44443-026-00643-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44443-026-00643-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44443-026-00643-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T14:13:57Z","timestamp":1787321637000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s44443-026-00643-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,18]]},"references-count":36,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,7]]}},"alternative-id":["643"],"URL":"https:\/\/doi.org\/10.1007\/s44443-026-00643-4","relation":{},"ISSN":["1319-1578","2213-1248"],"issn-type":[{"value":"1319-1578","type":"print"},{"value":"2213-1248","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,18]]},"assertion":[{"value":"11 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"This study did not involve human participants, animal subjects, or any sensitive personal data.","order":1,"name":"Ethics","label":"Ethics declaration","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"239"}}