{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T04:52:33Z","timestamp":1781931153060,"version":"3.54.5"},"reference-count":12,"publisher":"Association for Natural Language Processing","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Journal of Natural Language Processing"],"published-print":{"date-parts":[[2026]]},"DOI":"10.5715\/jnlp.33.1033","type":"journal-article","created":{"date-parts":[[2026,6,14]],"date-time":"2026-06-14T22:11:27Z","timestamp":1781475087000},"page":"1033-1042","source":"Crossref","is-referenced-by-count":0,"title":["An Attempt to Teach Large Language Models \u201cHow to Think\u201d: Starting from an Encounter with a Single Paper","\u4e00\u3064\u306e\u8ad6\u6587\u3068\u306e\u51fa\u4f1a\u3044\u304b\u3089\u59cb\u307e\u3063\u305f\uff0c\u5927\u898f\u6a21\u8a00\u8a9e\u30e2\u30c7\u30eb\u306b\u300c\u8003\u3048\u308b\u3053\u3068\u300d\u3092\u6559\u3048\u308b\u4f01\u307f"],"prefix":"10.5715","volume":"33","author":[{"given":"Terufumi","family":"Morishita","sequence":"first","affiliation":[{"name":"Advanced AI Innovatoin Center, Hitachi."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"3685","reference":[{"key":"1","doi-asserted-by":"crossref","unstructured":"Clark, P., Tafjord, O., and Richardson, K. (2021). \u201cTransformers as Soft Reasoners Over Language.\u201d In <i>Proceedings of the 29th International Conference on International Joint Conferences on Artificial Intelligence<\/i>, pp. 3882\u20133890.","DOI":"10.24963\/ijcai.2020\/537"},{"key":"2","unstructured":"DeepSeek-AI et al. (2025). \u201cDeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.\u201d <i>Nature<\/i>, <b>645<\/b>, pp. 633\u2013638."},{"key":"3","unstructured":"G\u00f6del, K. (1929). <i>\u00dcber die Vollst\u00e4ndigkeit des Logikkalk\u00fcls<\/i>. Ph.D. thesis, University of Vienna."},{"key":"4","unstructured":"\u68ee\u4e0b\u7693\u6587\uff0c\u68ee\u5c3e\u5b66\uff0c\u5c71\u53e3\u7be4\u5b63\uff0c\u5341\u6cb3\u6cf0\u5f18 (2023). \u4eba\u5de5\u6f14\u7e79\u63a8\u8ad6\u30b3\u30fc\u30d1\u30b9\u306b\u3088\u308b\u5b66\u7fd2\u306f\u8a00\u8a9e\u30e2\u30c7\u30eb\u3092\u3069\u306e\u3088\u3046\u306b\u5f37\u5316\u3059\u308b\u304b? \u4eba\u5de5\u77e5\u80fd\u5b66\u4f1a\u5168\u56fd\u5927\u4f1a\u8ad6\u6587\u96c6. [T. Morishita, et al. (2023). How Do Synthetic Deduction Corpora Enhance Language Models? The 37th Annual Conference of the Japanese Society for Artificial Intelligence.]."},{"key":"5","unstructured":"\u68ee\u4e0b\u7693\u6587\uff0c\u5c71\u53e3\u7be4\u5b63\uff0c\u68ee\u5c3e\u5b66\uff0c\u4eca\u4e00\u4fee\uff0c\u5341\u6cb3\u6cf0\u5f18 (2024a). \u5e30\u7d0d\u7684\u306b\u591a\u69d8\u306a\u5de8\u5927\u8ad6\u7406\u63a8\u8ad6\u30b3\u30fc\u30d1\u30b9\u306b\u3088\u308aLLM\u306e\u6c4e\u7528\u8ad6\u7406\u63a8\u8ad6\u80fd\u529b\u3092\u5411\u4e0a\u3055\u305b\u308b. \u4eba\u5de5\u77e5\u80fd\u5b66\u4f1a\u5168\u56fd\u5927\u4f1a\u8ad6\u6587\u96c6 \u7b2c 38 \u56de. [T. Morishita, et al. (2024a). Acquiring Generalizable Reasoning Ability through a Large-Scale Logical Corpus with Inductively Diverse Examples. The 38th Annual Conference of the Japanese Society for Artificial Intelligence.]."},{"key":"6","unstructured":"\u68ee\u4e0b\u7693\u6587\uff0c\u5c71\u53e3\u7be4\u5b63\uff0c\u68ee\u5c3e\u5b66\uff0c\u89d2\u639b\u6b63\u5f25\uff0c\u53cb\u6210\u5149\uff0c\u4eca\u4e00\u4fee\uff0c\u5341\u6cb3\u6cf0\u5f18 (2024b). \u65e5\u672c\u8a9e\u8ad6\u7406\u63a8\u8ad6\u30d9\u30f3\u30c1\u30de\u30fc\u30afJFLD\u306e\u63d0\u6848. \u8a00\u8a9e\u51e6\u7406\u5b66\u4f1a \u7b2c30\u5e74\u6b21\u5927\u4f1a \u767a\u8868\u8ad6\u6587\u96c6. [T. Morishita et al. (2024b). Nihongo Ronri Suiron Benchimaku JFLD no Teian. Proceedings of the 30th Annual Meeting of the Association for Natural Language Processing, pp. 925\u2013930.]."},{"key":"7","doi-asserted-by":"crossref","unstructured":"\u68ee\u4e0b\u7693\u6587\uff0c\u68ee\u5c3e\u5b66\uff0c\u5c71\u53e3\u7be4\u5b63\uff0c\u5341\u6cb3\u6cf0\u5f18 (2025). \u5927\u898f\u6a21\u8a00\u8a9e\u30e2\u30c7\u30eb\u306b\u63a8\u8ad6\u3092\u6559\u3048\u308b\u305f\u3081\u306e\u4eba\u5de5\u8ad6\u7406\u63a8\u8ad6\u30b3\u30fc\u30d1\u30b9\u3092\u7528\u3044\u305f\u30a2\u30d7\u30ed\u30fc\u30c1. \u81ea\u7136\u8a00\u8a9e\u51e6\u7406, <b>32<\/b> (2), pp. 520\u2013571. [T. Morishita et al. (2025). Toward Enhancing Reasoning Capabilities of LLMs: An Approach via Synthetic Logic Corpus, Journal of Natural Language Processing, 2025, 32, pp. 520\u2013571.].","DOI":"10.5715\/jnlp.32.520"},{"key":"8","unstructured":"Morishita, T., Morio, G., Horiguchi, S., Ozaki, H., and Nukaga, N. (2022). \u201cRethinking Fano\u2019s Inequality in Ensemble Learning.\u201d In <i>Proceedings of the 39th International Conference on Machine Learning<\/i>, Vol. 162 of <i>Proceedings of Machine Learning Research<\/i>, pp. 15976\u201316016. PMLR."},{"key":"9","unstructured":"Morishita, T., Morio, G., Yamaguchi, A., and Sogawa, Y. (2023). \u201cLearning Deductive Reasoning from Synthetic Corpus based on Formal Logic.\u201d In <i>Proceedings of the 40th International Conference on Machine Learning<\/i>, Vol. 202 of <i>Proceedings of Machine Learning Research<\/i>, pp. 25254\u201325274. PMLR."},{"key":"10","doi-asserted-by":"crossref","unstructured":"Morishita, T., Morio, G., Yamaguchi, A., and Sogawa, Y. (2024a). \u201cEnhancing Reasoning Capabilities of LLMs via Principled Synthetic Logic Corpus.\u201d In <i>Annual Conference on Neural Information Processing Systems<\/i>.","DOI":"10.52202\/079017-2340"},{"key":"11","doi-asserted-by":"crossref","unstructured":"Morishita, T., Yamaguchi, A., Morio, G., Tomonari, H., Imaichi, O., and Sogawa, Y. (2024b). \u201cJFLD: A Japanese Benchmark for Deductive Reasoning Based on Formal Logic.\u201d In Calzolari, N., Kan, M.-Y., Hoste, V., Lenci, A., Sakti, S., and Xue, N. (Eds.), <i>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)<\/i>, pp. 9526\u20139535, Torino, Italia. ELRA and ICCL.","DOI":"10.63317\/2fb93vacm2mf"},{"key":"12","doi-asserted-by":"crossref","unstructured":"Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., and Bowman, S. (2018). \u201cGLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding.\u201d In <i>BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP<\/i>, pp. 353\u2013355.","DOI":"10.18653\/v1\/W18-5446"}],"container-title":["Journal of Natural Language Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/jnlp\/33\/2\/33_1033\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T04:43:11Z","timestamp":1781930591000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/jnlp\/33\/2\/33_1033\/_article\/-char\/ja\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":12,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026]]}},"URL":"https:\/\/doi.org\/10.5715\/jnlp.33.1033","relation":{},"ISSN":["1340-7619","2185-8314"],"issn-type":[{"value":"1340-7619","type":"print"},{"value":"2185-8314","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}