{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T12:10:48Z","timestamp":1780056648139,"version":"3.54.0"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T00:00:00Z","timestamp":1776729600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T00:00:00Z","timestamp":1776729600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100004909","name":"Universidade Federal Do Rio Grande","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100004909","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1007\/s00521-026-12052-9","type":"journal-article","created":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T05:20:47Z","timestamp":1776748847000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["2T-FT: Two-Token Fine-tuning improves zero-shot performance with minimal training"],"prefix":"10.1007","volume":"38","author":[{"given":"Paulo S.","family":"Neto","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jardel D. S.","family":"Dyonisio","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jo\u00e3o F. S. S.","family":"Lemos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Felipe","family":"K\u00fchne","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4011-0901","authenticated-orcid":false,"given":"Rodrigo S.","family":"Guerra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"suffix":"Jr.","given":"Paulo L. J.","family":"Drews","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,21]]},"reference":[{"key":"12052_CR1","unstructured":"Anil R, Dai AM, Firat O et al (2023) Palm 2 technical report. arXiv:2305.10403"},{"key":"12052_CR2","doi-asserted-by":"crossref","unstructured":"Bisk Y, Zellers R, Bras RL et al (2019) Piqa: Reasoning about physical commonsense in natural language. arXiv:1911.11641","DOI":"10.1609\/aaai.v34i05.6239"},{"key":"12052_CR3","unstructured":"Brown T, Mann B, Ryder N et al (2020) Language models are few-shot learners. In: Larochelle H, Ranzato M, Hadsell R et al (eds) Advances in Neural Information Processing Systems, vol\u00a033. Curran Associates, Inc., pp 1877\u20131901, https:\/\/papers.nips.cc\/paper\/2020\/hash\/1457c0d6bfcb4967418bfb8ac142f64a-Abstract.html"},{"key":"12052_CR4","unstructured":"Chung HW, Hou L, Longpre S et al (2024) Scaling instruction-finetuned language models. Journal of Machine Learning Research 25(70):1\u201353. http:\/\/jmlr.org\/papers\/v25\/23-0870.html"},{"key":"12052_CR5","unstructured":"Cobbe K, Kosaraju V, Bavarian M et al (2021) Training verifiers to solve math word problems. arXiv:2110.14168"},{"key":"12052_CR6","doi-asserted-by":"publisher","unstructured":"Cui L, Wu Y, Liu S et al (2020) MuTual: A dataset for multi-turn dialogue reasoning. In: Jurafsky D, Chai J, Schluter N et al (eds) Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Online, pp 1406\u20131416, https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.130. https:\/\/aclanthology.org\/2020.acl-main.130","DOI":"10.18653\/v1\/2020.acl-main.130"},{"key":"12052_CR7","unstructured":"Deng Y, Prasad K, Fernandez R et al (2024) Implicit chain of thought reasoning via knowledge distillation. https:\/\/openreview.net\/forum?id=9cumTvvlHG"},{"key":"12052_CR8","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.10256836","author":"L Gao","year":"2023","unstructured":"Gao L, Tow J, Abbasi B et al (2023). A framework for few-shot language model evaluation. https:\/\/doi.org\/10.5281\/zenodo.10256836 (https:\/\/zenodo.org\/records\/10256836)","journal-title":"A framework for few-shot language model evaluation"},{"key":"12052_CR9","unstructured":"Gunasekar S, Zhang Y, Aneja J et al (2023) Textbooks are all you need. CoRR arXiv:2306.11644"},{"key":"12052_CR10","doi-asserted-by":"crossref","unstructured":"Hayati SA, Jung T, Bodding-Long T et al (2024) Chain-of-instructions: Compositional instruction tuning on large language models. CoRR arXiv:2402.11532","DOI":"10.1609\/aaai.v39i22.34574"},{"key":"12052_CR11","unstructured":"Hendrycks D, Burns C, Basart S et al (2023) Aligning ai with shared human values. arXiv:2008.02275"},{"key":"12052_CR12","doi-asserted-by":"publisher","unstructured":"Ho N, Schmid L, Yun SY (2023) Large language models are reasoning teachers. In: Rogers A, Boyd-Graber J, Okazaki N (eds) Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, Toronto, Canada, pp 14852\u201314882. https:\/\/doi.org\/10.18653\/v1\/2023.acl-long.830","DOI":"10.18653\/v1\/2023.acl-long.830"},{"key":"12052_CR13","doi-asserted-by":"publisher","unstructured":"Ji K, Xu J, Liang T et al (2025) The first few tokens are all you need: An efficient and effective unsupervised prefix fine-tuning method for reasoning models. https:\/\/doi.org\/10.13140\/RG.2.2.33772.07043, https:\/\/www.researchgate.net\/doi\/10.13140\/RG.2.2.33772.07043, unpublished, ResearchGate preprint","DOI":"10.13140\/RG.2.2.33772.07043"},{"key":"12052_CR14","unstructured":"Jiang AQ, Sablayrolles A, Mensch A et al (2023) Mistral 7b. https:\/\/arxiv.org\/abs\/2310.06825, arXiv:2310.06825"},{"key":"12052_CR15","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1162\/tacl_a_00300","volume":"8","author":"M Joshi","year":"2020","unstructured":"Joshi M, Chen D, Liu Y et al (2020) SpanBERT: improving pre-training by representing and predicting spans. Trans Assoc Comput Linguist 8:64\u201377. https:\/\/doi.org\/10.1162\/tacl_a_00300","journal-title":"Trans Assoc Comput Linguist"},{"key":"12052_CR16","unstructured":"Kojima T, Gu SS, Reid M et al (2022) Large language models are zero-shot reasoners. In: Oh AH, Agarwal A, Belgrave D et al (eds) Advances in Neural Information Processing Systems, https:\/\/openreview.net\/forum?id=e2TBb5y0yFf"},{"key":"12052_CR17","unstructured":"Lin Z, Gou Z, Gong Y et al (2024) Rho-1: Not all tokens are what you need. https:\/\/arxiv.org\/abs\/2404.07965, arXiv:2404.07965"},{"key":"12052_CR18","doi-asserted-by":"publisher","unstructured":"Liu J, Cui L, Liu H et al (2020) Logiqa: A challenge dataset for machine reading comprehension with logical reasoning. In: Bessiere C (ed) Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI-20. International Joint Conferences on Artificial Intelligence Organization, pp 3622\u20133628, https:\/\/doi.org\/10.24963\/ijcai.2020\/501, main track","DOI":"10.24963\/ijcai.2020\/501"},{"key":"12052_CR19","doi-asserted-by":"publisher","unstructured":"Mihaylov T, Clark P, Khot T et al (2018) Can a suit of armor conduct electricity? a new dataset for open book question answering. In: Riloff E, Chiang D, Hockenmaier J et al (eds) Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Brussels, Belgium, pp 2381\u20132391, https:\/\/doi.org\/10.18653\/v1\/D18-1260","DOI":"10.18653\/v1\/D18-1260"},{"key":"12052_CR20","doi-asserted-by":"publisher","unstructured":"Mosbach M, Pimentel T, Ravfogel S (2023) Few-shot fine-tuning vs. in-context learning: A fair comparison and evaluation. In: Rogers A, Boyd-Graber J, Okazaki N (eds) Findings of the Association for Computational Linguistics: ACL 2023. Association for Computational Linguistics, Toronto, Canada, pp 12284\u201312314. https:\/\/doi.org\/10.18653\/v1\/2023.findings-acl.779","DOI":"10.18653\/v1\/2023.findings-acl.779"},{"key":"12052_CR21","unstructured":"OpenAI (2024) Gpt-4 technical report. arXiv:2303.08774"},{"key":"12052_CR22","doi-asserted-by":"publisher","unstructured":"Patel A, Bhattamishra S, Goyal N (2021) Are NLP models really able to solve simple math word problems? In: Toutanova K, Rumshisky A, Zettlemoyer L et al (eds) Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, Online, pp 2080\u20132094, https:\/\/doi.org\/10.18653\/v1\/2021.naacl-main.168","DOI":"10.18653\/v1\/2021.naacl-main.168"},{"key":"12052_CR23","unstructured":"Puerto H, Chubakov T, Zhu X et al (2024) Fine-tuning with divergent chains of thought boosts reasoning through self-correction in language models. arXiv:2407.03181"},{"key":"12052_CR24","unstructured":"Rein D, Hou BL, Stickland AC et al (2024) Gpqa: A graduate-level google-proof q&a benchmark. In: First Conference on Language Modeling, https:\/\/openreview.net\/forum?id=Ti67584b98"},{"key":"12052_CR25","doi-asserted-by":"publisher","unstructured":"Roy S, Roth D (2015) Solving general arithmetic word problems. In: M\u00e0rquez L, Callison-Burch C, Su J (eds) Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Lisbon, Portugal, pp 1743\u20131752, https:\/\/doi.org\/10.18653\/v1\/D15-1202","DOI":"10.18653\/v1\/D15-1202"},{"key":"12052_CR26","doi-asserted-by":"publisher","unstructured":"Segal E, Efrat A, Shoham M et al (2020) A simple and effective model for answering multi-span questions. In: Webber B, Cohn T, He Y et al (eds) Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). Association for Computational Linguistics, Online, pp 3074\u20133080, https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-main.248","DOI":"10.18653\/v1\/2020.emnlp-main.248"},{"key":"12052_CR27","unstructured":"Shalev Y, Feder A, Goldstein A (2024) Distributional reasoning in llms: parallel reasoning processes in multi-hop reasoning. arXiv:2406.13858"},{"key":"12052_CR28","doi-asserted-by":"publisher","unstructured":"Shridhar K, Stolfo A, Sachan M (2023) Distilling reasoning capabilities into smaller language models. In: Rogers A, Boyd-Graber J, Okazaki N (eds) Findings of the Association for Computational Linguistics: ACL 2023. Association for Computational Linguistics, Toronto, Canada, pp 7059\u20137073, https:\/\/doi.org\/10.18653\/v1\/2023.findings-acl.441","DOI":"10.18653\/v1\/2023.findings-acl.441"},{"key":"12052_CR29","doi-asserted-by":"publisher","unstructured":"Suzgun M, Scales N, Sch\u00e4rli N et al (2023) Challenging BIG-bench tasks and whether chain-of-thought can solve them. In: Rogers A, Boyd-Graber J, Okazaki N (eds) Findings of the Association for Computational Linguistics: ACL 2023. Association for Computational Linguistics, Toronto, Canada, pp 13003\u201313051, https:\/\/doi.org\/10.18653\/v1\/2023.findings-acl.824","DOI":"10.18653\/v1\/2023.findings-acl.824"},{"key":"12052_CR30","unstructured":"Team G (2024) Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context. arXiv:2403.05530"},{"key":"12052_CR31","unstructured":"Team G, Mesnard T, Hardin C et al (2024) Gemma: Open models based on gemini research and technology. arXiv:2403.08295"},{"key":"12052_CR32","doi-asserted-by":"crossref","unstructured":"Trung L, Zhang X, Jie Z et al (2024) ReFT: Reasoning with reinforced fine-tuning. In: Ku LW, Martins A, Srikumar V (eds) Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, Bangkok, Thailand, pp 7601\u20137614, https:\/\/aclanthology.org\/2024.acl-long.410","DOI":"10.18653\/v1\/2024.acl-long.410"},{"key":"12052_CR33","doi-asserted-by":"crossref","unstructured":"Wang X, Zhou D (2024) Chain-of-thought reasoning without prompting. arXiv:2402.10200","DOI":"10.52202\/079017-2123"},{"key":"12052_CR34","unstructured":"Wang Y, Hu S, Zhang Y et al (2024) How large language models implement chain-of-thought? https:\/\/openreview.net\/forum?id=b2XfOm3RJa"},{"key":"12052_CR35","unstructured":"Wei J, Bosma M, Zhao V et al (2022) Finetuned language models are zero-shot learners. In: International Conference on Learning Representations, https:\/\/openreview.net\/forum?id=gEZrGCozdqR"},{"key":"12052_CR36","doi-asserted-by":"publisher","unstructured":"Yadav V, Bethard S, Surdeanu M (2019) Quick and (not so) dirty: Unsupervised selection of justification sentences for multi-hop question answering. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). Association for Computational Linguistics, https:\/\/doi.org\/10.18653\/v1\/d19-1260","DOI":"10.18653\/v1\/d19-1260"},{"key":"12052_CR37","unstructured":"Yang A, Yang B, Hui B et al (2024) Qwen2 technical report. arXiv:2407.10671"},{"key":"12052_CR38","unstructured":"YAO Y, Wu H, Guo Z et al (2024) Learning from correctness without prompting makes LLM efficient reasoner. In: First Conference on Language Modeling, https:\/\/openreview.net\/forum?id=dcbNzhVVQj"},{"key":"12052_CR39","unstructured":"Zhou D, Sch\u00e4rli N, Hou L et al (2023) Least-to-most prompting enables complex reasoning in large language models. In: The Eleventh International Conference on Learning Representations, https:\/\/openreview.net\/forum?id=WZH7099tgfM"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-026-12052-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-026-12052-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-026-12052-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:50:45Z","timestamp":1780055445000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-026-12052-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,21]]},"references-count":39,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2026,5]]}},"alternative-id":["12052"],"URL":"https:\/\/doi.org\/10.1007\/s00521-026-12052-9","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,21]]},"assertion":[{"value":"28 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 April 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"Not applicable.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Materials availability"}},{"value":"The code used to generate the results of this study is publicly available at:\n                      \n                      .","order":6,"name":"Ethics","group":{"name":"EthicsHeading","label":"Code availability"}}],"article-number":"321"}}