{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T10:02:38Z","timestamp":1789725758436,"version":"4.0.1"},"reference-count":36,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["92567301"],"award-info":[{"award-number":["92567301"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62132018"],"award-info":[{"award-number":["62132018"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.eswa.2026.133255","type":"journal-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T23:35:20Z","timestamp":1781566520000},"page":"133255","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PB","title":["KnowPath: leveraging large language model prior reasoning paths for dynamic self-reflective reasoning via knowledge graph subgraph exploration"],"prefix":"10.1016","volume":"331","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5966-0201","authenticated-orcid":false,"given":"Qi","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongyu","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1726-7858","authenticated-orcid":false,"given":"Qi","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangyang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.133255_bib0001","series-title":"Proceedings of the 2013 conference on empirical methods in natural language processing","first-page":"1533","article-title":"Semantic parsing on freebase from question-answer pairs","author":"Berant","year":"2013"},{"key":"10.1016\/j.eswa.2026.133255_bib0002","unstructured":"Bordes, A., Usunier, N., Chopra, S., & Weston, J. (2015). Large-scale simple question answering with memory networks. arXiv preprint arXiv: 1506.02075."},{"key":"10.1016\/j.eswa.2026.133255_bib0003","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.133255_bib0004","doi-asserted-by":"crossref","unstructured":"Cao, Y., Li, X., Liu, H., Dai, W., Chen, S., Wang, B., Chen, M., & Hershcovich, D. (2023). Pay more attention to relation exploration for knowledge base question answering. arXiv preprint arXiv: 2305.02118.","DOI":"10.18653\/v1\/2023.findings-acl.133"},{"key":"10.1016\/j.eswa.2026.133255_sbref0005","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.121054","article-title":"Supplementing domain knowledge to BERT with semi-structured information of documents","volume":"235","author":"Chen","year":"2024","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.133255_bib0006","article-title":"Plan-on-graph: Self-correcting adaptive planning of large language model on knowledge graphs","author":"Chen","year":"2024","journal-title":"CoRR"},{"key":"10.1016\/j.eswa.2026.133255_bib0007","series-title":"Proceedings of the 60th annual meeting of the association for computational linguistics (volume 1: Long papers)","first-page":"8493","article-title":"Knowledge neurons in pretrained transformers","author":"Dai","year":"2022"},{"key":"10.1016\/j.eswa.2026.133255_bib0008","unstructured":"Dong, X., Wang, Y., Yu, P. S., & Caverlee, J. (2023). Probing explicit and implicit gender bias through LLM conditional text generation. arXiv preprint arXiv: 2311.00306."},{"key":"10.1016\/j.eswa.2026.133255_sbref0009","series-title":"Proceedings of the thirty-third international joint conference on artificial intelligence, IJCAI 2024, Jeju, South Korea, August 3\u20139, 2024","first-page":"8048","article-title":"Large language model based multi-agents: A survey of progress and challenges","author":"Guo","year":"2024"},{"key":"10.1016\/j.eswa.2026.133255_bib0010","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112805","article-title":"A plug-and-play knowledge-enhanced module for medical reports generation","volume":"309","author":"Han","year":"2025","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.eswa.2026.133255_sbref0011","series-title":"Proceedings of the thirty-third international joint conference on artificial intelligence, IJCAI 2024, Jeju, South Korea, August 3\u20139, 2024","first-page":"8679","article-title":"An LLM-enhanced agent-based simulation tool for information propagation","author":"Hu","year":"2024"},{"key":"10.1016\/j.eswa.2026.133255_bib0012","unstructured":"Huang, X., Liu, W., Chen, X., Wang, X., Wang, H., Lian, D., Wang, Y., Tang, R., & Chen, E. (2024). Understanding the planning of LLM agents: A survey. arXiv preprint arXiv: 2402.02716."},{"key":"10.1016\/j.eswa.2026.133255_bib0013","doi-asserted-by":"crossref","unstructured":"Jiang, J., Zhou, K., Dong, Z., Ye, K., Zhao, W. X., & Wen, J.-R. (2023). Structgpt: A general framework for large language model to reason over structured data. arXiv preprint arXiv: 2305.09645.","DOI":"10.18653\/v1\/2023.emnlp-main.574"},{"key":"10.1016\/j.eswa.2026.133255_bib0014","unstructured":"Jiang, J., Zhou, K., Zhao, W. X., & Wen, J.-R. (2022). Unikgqa: Unified retrieval and reasoning for solving multi-hop question answering over knowledge graph. arXiv preprint arXiv: 2212.00959."},{"key":"10.1016\/j.eswa.2026.133255_bib0015","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1162\/tacl_a_00324","article-title":"How can we know what language models know?","volume":"8","author":"Jiang","year":"2020","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"10.1016\/j.eswa.2026.133255_bib0016","unstructured":"Li, J., Consul, S., Zhou, E., Wong, J., Farooqui, N., Ye, Y., Manohar, N., Wei, Z., Wu, T., Echols, B. et al. (2024). Banishing LLM hallucinations requires rethinking generalization. arXiv preprint arXiv: 2406.17642."},{"key":"10.1016\/j.eswa.2026.133255_sbref0017","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.128718","article-title":"Intelligent generation of personalized cardiovascular healthcare program based on knowledge network","volume":"294","author":"Lin","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.133255_sbref0018","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.128289","article-title":"Multi-hop reasoning over sparse knowledge graphs with deep reinforcement learning","volume":"290","author":"Liu","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.133255_bib0019","series-title":"Findings of the association for computational linguistics, ACL 2024, Bangkok, Thailand and Virtual Meeting, August 11\u201316, 2024","first-page":"2039","article-title":"ChatKBQA: A generate-then-retrieveframework for knowledge base question answering with fine-tuned large language models","author":"Luo","year":"2024"},{"key":"10.1016\/j.eswa.2026.133255_bib0020","series-title":"Reasoning on graphs: Faithful and interpretable large language model reasoning","author":"Luo","year":"2024"},{"key":"10.1016\/j.eswa.2026.133255_bib0021","unstructured":"Ma, S., Xu, C., Jiang, X., Li, M., Qu, H., & Guo, J. (2024). Think-on-graph 2.0: Deep and interpretable large language model reasoning with knowledge graph-guided retrieval. arXiv e-prints, arXiv\u20132407)."},{"key":"10.1016\/j.eswa.2026.133255_bib0022","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113431","article-title":"Knowledge-embedded large language models for emergency triage","volume":"318","author":"Shen","year":"2025","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.eswa.2026.133255_sbref0023","series-title":"Think-on-graph: Deep and responsible reasoning of large language model on knowledge graph","author":"Sun","year":"2024"},{"key":"10.1016\/j.eswa.2026.133255_bib0024","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.112981","article-title":"Contreviews: A content-based recommendation system for updating living evidences in health care","volume":"311","author":"Tenti","year":"2025","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.eswa.2026.133255_bib0025","unstructured":"Wang, X., Wei, J., Schuurmans, D., Le, Q., Chi, E., Narang, S., Chowdhery, A., & Zhou, D. (2022). Self-consistency improves chain of thought reasoning in language models. arXiv preprint arXiv: 2203.11171,."},{"key":"10.1016\/j.eswa.2026.133255_sbref0026","series-title":"Proceedings of the thirty-third international joint conference on artificial intelligence, IJCAI 2024, Jeju, South Korea, August 3\u20139, 2024","first-page":"6522","article-title":"Beyond what if: Advancing counterfactual text generation with structural causal modeling","author":"Wang","year":"2024"},{"key":"10.1016\/j.eswa.2026.133255_bib0027","doi-asserted-by":"crossref","first-page":"24824","DOI":"10.52202\/068431-1800","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"1","key":"10.1016\/j.eswa.2026.133255_bib0028","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3688399","article-title":"Designing heterogeneous LLM agents for financial sentiment analysis","volume":"16","author":"Xing","year":"2025","journal-title":"ACM Transactions on Management Information Systems"},{"key":"10.1016\/j.eswa.2026.133255_bib0029","doi-asserted-by":"crossref","unstructured":"Xu, Y., He, S., Chen, J., Wang, Z., Song, Y., Tong, H., Liu, G., Liu, K., & Zhao, J. (2024). Generate-on-graph: Treat LLM as both agent and KG in incomplete knowledge graph question answering. arXiv preprint arXiv: 2404.14741.","DOI":"10.18653\/v1\/2024.emnlp-main.1023"},{"key":"10.1016\/j.eswa.2026.133255_bib0030","unstructured":"Yang, L., Chen, H., Li, Z., Ding, X., & Wu, X. (2023). ChatGpt is not enough: Enhancing large language models with knowledge graphs for fact-aware language modeling. arXiv preprint arXiv: 2306.11489."},{"key":"10.1016\/j.eswa.2026.133255_bib0031","doi-asserted-by":"crossref","DOI":"10.1109\/TKDE.2024.3360454","article-title":"Give us the facts: Enhancing large language models with knowledge graphs for fact-aware language modeling","author":"Yang","year":"2024","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"10.1016\/j.eswa.2026.133255_bib0032","series-title":"Proceedings of the 54th annual meeting of the association for computational linguistics (volume 2: Short papers)","first-page":"201","article-title":"The value of semantic parse labeling for knowledge base question answering","author":"Yih","year":"2016"},{"key":"10.1016\/j.eswa.2026.133255_bib0033","unstructured":"Yin, D., Dong, L., Cheng, H., Liu, X., Chang, K.-W., Wei, F., & Gao, J. (2022). A survey of knowledge-intensive nlp with pre-trained language models. arXiv preprint arXiv: 2202.08772."},{"key":"10.1016\/j.eswa.2026.133255_bib0034","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112837","article-title":"KoSEL: Knowledge subgraph enhanced large language model for medical question answering","volume":"309","author":"Zeng","year":"2025","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.eswa.2026.133255_sbref0035","series-title":"Proceedings of the thirty-third international joint conference on artificial intelligence, IJCAI 2024, Jeju, South Korea, August 3\u20139, 2024","first-page":"6642","article-title":"KG-cot: Chain-of-thought prompting of large language models over knowledge graphs for knowledge-aware question answering","author":"Zhao","year":"2024"},{"key":"10.1016\/j.eswa.2026.133255_bib0036","doi-asserted-by":"crossref","unstructured":"Zhu, R., Liu, X., Sun, Z., Wang, Y., & Hu, W. (2025). Mitigating lost-in-retrieval problems in retrieval augmented multi-hop question answering. In W. Che, J. Nabende, E. Shutova, & M.T. Pilehvar (Eds.), Proceedings of the 63rd annual meeting of the association for computational linguistics (volume 1: Long papers) (pp. 22362\u201322375). Vienna, Austria: Association for Computational Linguistics. https:\/\/aclanthology.org\/2025.acl-long.1089\/. 10.18653\/v1\/2025.acl-long.1089.","DOI":"10.18653\/v1\/2025.acl-long.1089"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426021640?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426021640?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T09:06:14Z","timestamp":1789722374000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426021640"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":36,"alternative-id":["S0957417426021640"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.133255","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"KnowPath: leveraging large language model prior reasoning paths for dynamic self-reflective reasoning via knowledge graph subgraph exploration","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.133255","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"133255"}}