{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T08:51:53Z","timestamp":1781772713699,"version":"3.54.5"},"reference-count":32,"publisher":"China Science Publishing & Media Ltd.","issue":"2","content-domain":{"domain":["engine.scichina.com"],"crossmark-restriction":false},"short-container-title":["DI"],"published-print":{"date-parts":[[2026,6,1]]},"DOI":"10.3724\/2096-7004.di.2025.0393","type":"journal-article","created":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T08:00:09Z","timestamp":1778486409000},"page":"20250393","update-policy":"https:\/\/doi.org\/10.1360\/scp-crossmark-policy-page","source":"Crossref","is-referenced-by-count":0,"title":["Feature-Assisted Thought Chain Generation and Adaptive Feature Enhancement for Logical Reasoning in Large Language Models"],"prefix":"10.3724","volume":"8","author":[{"given":"Chenglin","family":"Jiang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qidong","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingjie","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ning","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"2026","published-online":{"date-parts":[[2026,5,11]]},"reference":[{"key":"null","unstructured":"Chang Y., Wang X., Wang J., Wu Y., Yang L., Zhu K., Chen H., Yi X., Wang C., Wang Y. et al., \u201cA survey on evaluation of large language models,\u201d ACM Trans. Intell. Syst. Technol., vol. 15, no. 3, pp. 1\u201345, 2024."},{"key":"null","unstructured":"Hoffmann J., Borgeaud S., Mensch A., Buchatskaya E., Cai T., Rutherford E., Casas D. de L., Hendricks L. A., Welbl J., Clark A. et al., \u201cTraining compute-optimal large language models,\u201d in Proc. 36th Int. Conf. Neural Inf. Process. Syst., New Orleans, LA, USA, 2022."},{"key":"null","unstructured":"Chowdhery A., Narang S., Devlin J., Bosma M., Mishra G., Roberts A., Barham P., Chung H. W., Sutton C., Gehrmann S. et al., \u201cPaLM: Scaling language modeling with pathways,\u201d J. Mach. Learn. Res., vol. 24, no. 240, pp. 1\u2013113, 2023."},{"key":"null","unstructured":"Zheng C., Zhou H., Meng F., Zhou J., and Huang M., \u201cLarge language models are not robust multiple choice selectors,\u201d in Proc. 12th Int. Conf. Learn. Represent., Kigali, Rwanda, 2023."},{"key":"null","unstructured":"Li J., Wang J., Zhang Z., and Zhao H., \u201cSelf-prompting large language models for zero-shot open-domain QA,\u201d in Proc. 2024 Conf. North Amer. Chapter Assoc. Comput. Linguistics, Hum. Lang. Technol., vol. 1, Mexico City, Mexico, 2024, pp. 296\u2013310."},{"key":"null","unstructured":"Kamalloo E., Dziri N., Clarke C. L. A., and Rafiei D., \u201cEvaluating open-domain question answering in the era of large language models,\u201d in Proc. 61st Annu. Meeting Assoc. Comput. Linguistics, vol. 1, Toronto, Canada, 2023, pp. 5591\u20135606."},{"key":"null","unstructured":"Zhou W. and Chen M., \u201cAn improved baseline for sentence-level relation extraction,\u201d in Proc. 2nd Conf. Asia-Pac. Chapter Assoc. Comput. Linguistics 12th Int. Joint Conf. Nat. Lang. Process., vol. 2, 2022, pp. 161\u2013168."},{"key":"null","unstructured":"Xu X., Zhu Y., Wang X., and Zhang N., \u201cHow to unleash the power of large language models for few-shot relation extraction?\u201d in Proc. 4th Workshop Simple Efficient Nat. Lang. Process., Singapore, 2023, pp. 190\u2013200."},{"key":"null","unstructured":"Nye M., Andreassen A. J., Gur-Ari G., Michalewski H., Austin J., Bieber D., Dohan D., Lewkowycz A., Bosma M., Luan D. et al., \u201cShow your work: Scratchpads for intermediate computation with language models,\u201d in Deep Learn. Code Workshop, 2021."},{"key":"null","unstructured":"Wei J., Wang X., Schuurmans D., Bosma M., Xia F., Chi E., Le Q. V., Zhou D. et al., \u201cChain-of-thought prompting elicits reasoning in large language models,\u201d Adv. Neural Inf. Process. Syst., vol. 35, pp. 24824\u201324837, 2022."},{"key":"null","unstructured":"Zhang K., Guti\u00e9rrez B. J., and Su Y., \u201cAligning instruction tasks unlocks large language models as zero-shot relation extractors,\u201d in Findings Assoc. Comput. Linguistics, ACL, Toronto, Canada, 2023, pp. 794\u2013812."},{"key":"null","unstructured":"Li G., Wang P., and Ke W., \u201cRevisiting large language models as zero-shot relation extractors,\u201d in Findings Assoc. Comput. Linguistics, EMNLP, Singapore, 2023, pp. 6877\u20136892."},{"key":"null","unstructured":"Wan Z., Cheng F., Mao Z., Liu Q., Song H., Li J., and Kurohashi S., \u201cGPT-RE: In-context learning for relation extraction using large language models,\u201d in Proc. 2023 Conf. Empirical Methods Nat. Lang. Process., Singapore, 2023, pp. 3534\u20133547."},{"key":"null","unstructured":"Chen L., Sun M., Liu J., Ding P., Ma Y., Li L., Qian L., and Yang Y., \u201cA method for extracting information from long documents that combines large language models with natural language understanding techniques,\u201d in Proc. 2023 4th Int. Conf. Comput., Big Data Artif. Intell. Huludao, China: IEEE, 2023, pp. 43\u201347."},{"key":"null","unstructured":"Zeng A., Liu X., Du Z., Wang Z., Lai H., Ding M., Yang Z., Xu Y., Zheng W., Xia X. et al., \u201cGLM-130B: An open bilingual pre-trained model,\u201d in Proc. 11th Int. Conf. Learn. Represent., 2022."},{"key":"null","unstructured":"Kojima T., Gu S. S., Reid M., Matsuo Y., and Iwasawa Y., \u201cLarge language models are zero-shot reasoners,\u201d Adv. Neural Inf. Process. Syst., vol. 35, pp. 22199\u201322213, 2022."},{"key":"null","unstructured":"Zhang Z., Zhang A., Li M., and Smola A., \u201cAutomatic chain of thought prompting in large language models,\u201d in Proc. 11th Int. Conf. Learn. Represent., Kigali, Rwanda, 2023."},{"key":"null","unstructured":"Fu Y., Peng H., Sabharwal A., Clark P., and Khot T., \u201cComplexity-based prompting for multi-step reasoning,\u201d in Proc. 11th Int. Conf. Learn. Represent., 2022."},{"key":"null","unstructured":"Lu Y., Liu Q., Dai D., Xiao X., Lin H., Han X., Sun L., and Wu H., \u201cUnified structure generation for universal information extraction,\u201d in Proc. 60th Annu. Meeting Assoc. Comput. Linguistics, Dublin, Ireland, 2022."},{"key":"null","unstructured":"Lou J., Lu Y., Dai D., Jia W., Lin H., Han X., Sun L., and Wu H., \u201cUniversal information extraction as unified semantic matching,\u201d in Proc. AAAI Conf. Artif. Intell., vol. 37, no. 11, Washington, DC, USA, 2023, pp. 13318\u201313326."},{"key":"null","unstructured":"Yan F., Yu P., and Chen X., \u201cLTNER: Large language model tagging for named entity recognition with contextualized entity marking,\u201d in Int. Conf. Pattern Recognit. Kolkata, India: Springer, 2025, pp. 399\u2013411."},{"key":"null","unstructured":"Wei J. and Zou K., \u201cEDA: Easy data augmentation techniques for boosting performance on text classification tasks,\u201d in Proc. 2019 Conf. Empirical Methods Nat. Lang. Process. 9th Int. Joint Conf. Nat. Lang. Process., Hong Kong, China, 2019."},{"key":"null","unstructured":"Houlsby N., Giurgiu A., Jastrzebski S., Morrone B., Laroussilhe Q. D., Gesmundo A., Attariyan M., and Gelly S., \u201cParameter-efficient transfer learning for NLP,\u201d in Proc. 36th Int. Conf. Mach. Learn., vol. 97. Long Beach, CA, USA: PMLR, 2019, pp. 2790\u20132799."},{"key":"null","unstructured":"Hu Z., Wang L., Lan Y., Xu W., Lim E., Bing L., Xu X., Poria S., and Lee R. K., \u201cLLM-Adapters: An adapter family for parameter-efficient fine-tuning of large language models,\u201d in Proc. 2023 Conf. Empirical Methods Nat. Lang. Process., Singapore, 2023, pp. 5254\u20135276."},{"key":"null","unstructured":"Benkassioui B., Kharmoum N., Hadi M. Y., and Ezziyyani M., \u201cNLP methods\u2019 information extraction for textual data: an analytical study,\u201d in Adv. Intell. Syst. Sustain. Develop. Rabat, Morocco: Springer, 2022, pp. 515\u2013527."},{"key":"null","unstructured":"Zhu Y., Wang X., Chen J., Qiao S., Ou Y., Yao Y., Deng S., Chen H., and Zhang N., \u201cLLMs for knowledge graph construction and reasoning: Recent capabilities and future opportunities,\u201d World Wide Web, vol. 27, no. 5, p. 58, 2024."},{"key":"null","unstructured":"Liu H., Teng Z., Cui L., Zhang C., Zhou Q., and Zhang Y., \u201cLogiCoT: Logical chain-of-thought instruction-tuning,\u201d in Findings Assoc. Comput. Linguistics, EMNLP, Singapore, 2023."},{"key":"null","unstructured":"Wang X., Wei J., Schuurmans D., Le Q., Chi E., Narang S., Chowdhery A., and Zhou D., \u201cSelf-consistency improves chain of thought reasoning in language models,\u201d in Proc. 11th Int. Conf. Learn. Represent., 2022."},{"key":"null","unstructured":"Gu Y., Yang M., Yang X., Wei K., Zhu H., Goenawan G. J., and Deng C., \u201cDynamic adapter tuning for long-tailed class-incremental learning,\u201d in Proc. 2025 IEEE\/CVF Winter Conf. Appl. Comput. Vis., Waikoloa, HI, USA, 2025, pp. 8176\u20138185."},{"key":"null","unstructured":"Liu J., Cui L., Liu H., Huang D., Wang Y., and Zhang Y., \u201cLogiQA: A challenge dataset for machine reading comprehension with logical reasoning,\u201d arXiv:2007.08124, 2020."},{"key":"null","unstructured":"Yu W., Jiang Z., Dong Y., and Feng J., \u201cReClor: A reading comprehension dataset requiring logical reasoning,\u201d arXiv:2002.04326, 2020."},{"key":"null","unstructured":"Liu H., Liu J., Cui L., Teng Z., Duan N., Zhou M., and Zhang Y., \u201cLogiQA 2.0\u2014an improved dataset for logical reasoning in natural language understanding,\u201d IEEE\/ACM Trans. Audio, Speech, Lang. Process., vol. 31, pp. 2947\u20132962, 2023."}],"container-title":["Data Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.sciengine.com\/sci-open\/api\/v1\/open\/file\/pdf\/6938C02A742E4DAD8B99D24EC82ECBD8","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.sciengine.com\/doi\/10.3724\/2096-7004.di.2025.0393","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.sciengine.com\/sci-open\/api\/v1\/open\/file\/pdf\/6938C02A742E4DAD8B99D24EC82ECBD8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T08:00:47Z","timestamp":1781769647000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.sciengine.com\/doi\/10.3724\/2096-7004.di.2025.0393"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,11]]},"references-count":32,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,5,11]]},"published-print":{"date-parts":[[2026,6,1]]}},"URL":"https:\/\/doi.org\/10.3724\/2096-7004.di.2025.0393","relation":{},"ISSN":["2096-7004"],"issn-type":[{"value":"2096-7004","type":"print"}],"subject":[],"published":{"date-parts":[[2026,5,11]]}}}