{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T05:28:16Z","timestamp":1782538096377,"version":"3.54.5"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Science Fund for Distinguished Young Scholars of China","award":["62325604"],"award-info":[{"award-number":["62325604"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276271"],"award-info":[{"award-number":["62276271"]}],"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":["62421002"],"award-info":[{"award-number":["62421002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tkde.2025.3591056","type":"journal-article","created":{"date-parts":[[2025,7,21]],"date-time":"2025-07-21T18:10:07Z","timestamp":1753121407000},"page":"6202-6215","source":"Crossref","is-referenced-by-count":1,"title":["Thinking on Context: Inductive Relation Prediction Guided by the Reasoning Ability of Large Language Models"],"prefix":"10.1109","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0704-4543","authenticated-orcid":false,"given":"Xiaoshu","family":"Chen","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1491-4594","authenticated-orcid":false,"given":"Sihang","family":"Zhou","sequence":"additional","affiliation":[{"name":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4837-455X","authenticated-orcid":false,"given":"Ke","family":"Liang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiafei","family":"Wu","sequence":"additional","affiliation":[{"name":"Zhejiang Lab, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9066-1475","authenticated-orcid":false,"given":"Xinwang","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9743-2034","authenticated-orcid":false,"given":"Dongsheng","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2284-7897","authenticated-orcid":false,"given":"Kai","family":"Lu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3432767"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3417451"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3464516"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29889"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3471508"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2025.3548160"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3282989"},{"key":"ref8","first-page":"2787","article-title":"Translating embeddings for modeling multi-relational data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bordes"},{"issue":"1","key":"ref9","first-page":"4735","article-title":"Knowledge graph completion via complex tensor factorization","volume":"18","author":"Trouillon","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"ref10","first-page":"15239","article-title":"Knowledge graph completion with relation-aware anchor enhancement","volume-title":"Proc. AAAI Conf. Artif. Intell.","author":"Yuan"},{"key":"ref11","first-page":"9448","article-title":"Inductive relation prediction by subgraph reasoning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Teru"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i5.20537"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3177212"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2941685"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i5.25803"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16554"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28750"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i9.28935"},{"key":"ref19","first-page":"3517","article-title":"Learning rule-induced subgraph representations for inductive relation prediction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-024-01264-5"},{"key":"ref21","first-page":"564","article-title":"DeepPath: A reinforcement learning method for knowledge graph reasoning","volume-title":"Proc. 2017 Conf. Empir. Methods Natural Lang. Process.","author":"Xiong"},{"key":"ref22","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref23","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.1109\/VIS49827.2021.9623291","article-title":"Gemini2: Generating keyframe-oriented animated transitions between statistical graphics","author":"Kim","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.362"},{"key":"ref26","first-page":"458","article-title":"Contextualization distillation from large language model for knowledge graph completion","volume-title":"Proc. Findings Assoc. Comput. Linguistics","author":"Li"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10889242"},{"key":"ref28","first-page":"9668","article-title":"KC-GenRe: A knowledge-constrained generative re-ranking method based on large language models for knowledge graph completion","volume-title":"Proc. 2024 Joint Int. Conf. Comput. Linguistics, Lang. Resour. Eval.","author":"Wang"},{"key":"ref29","first-page":"8667","article-title":"KICGPT: Large language model with knowledge in context for knowledge graph completion","volume-title":"Proc. Findings Assoc. Comput. Linguistics","author":"Wei"},{"key":"ref30","first-page":"14852","article-title":"Large language models are reasoning teachers","volume-title":"Proc. 61st Annu. Meeting Assoc. Comput. Linguistics","author":"Ho"},{"key":"ref31","first-page":"1773","article-title":"Teaching small language models to reason","volume-title":"Proc. 61st Annu. Meeting Assoc. Comput. Linguistics","author":"Magister"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d19-1522"},{"key":"ref33","article-title":"Deep gaussian embedding of graphs: Unsupervised inductive learning via ranking","author":"Bojchevski","year":"2017"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017152"},{"key":"ref35","first-page":"18796","article-title":"InGram: Inductive knowledge graph embedding via relation graphs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lee"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599551"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3679200"},{"key":"ref38","first-page":"4281","article-title":"SimKGC: Simple contrastive knowledge graph completion with pre-trained language models","volume-title":"Proc. 60th Annu. Meeting Assoc. Comput. Linguistics","author":"Wang"},{"key":"ref39","article-title":"KG-BERT: BERT for knowledge graph completion","author":"Yao","year":"2019"},{"key":"ref40","first-page":"11956","article-title":"Multi-perspective improvement of knowledge graph completion with large language models","volume-title":"Proc. Joint Int. Conf. Comput. Linguistics, Lang. Resour. Eval.","author":"Xu"},{"key":"ref41","first-page":"2814","article-title":"Sequence-to-sequence knowledge graph completion and question answering","volume-title":"Proc. 60th Annu. Meeting Assoc. Comput. Linguistics","author":"Saxena"},{"key":"ref42","first-page":"4005","article-title":"Knowledge is flat: A Seq2Seq generative framework for various knowledge graph completion","volume-title":"Proc. 29th Int. Conf. Comput. Linguistics","author":"Chen"},{"key":"ref43","first-page":"131","article-title":"Friendly neighbors: Contextualized sequence-to-sequence link prediction","volume-title":"Proc. 8th Workshop Representation Learn. NLP","author":"Kochsiek"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681327"},{"key":"ref45","article-title":"Finetuning generative large language models with discrimination instructions for knowledge graph completion","author":"Liu","year":"2024"},{"key":"ref46","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wei"},{"key":"ref47","first-page":"8003","article-title":"Distilling step-by-step! outperforming larger language models with less training data and smaller model sizes","volume-title":"Findings Assoc. Comput. Linguistics","author":"Hsieh","year":"2023"},{"key":"ref48","first-page":"2571","article-title":"PaD: Program-aided distillation can teach small models reasoning better than chain-of-thought fine-tuning","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics: Hum. Lang. Technol.","author":"Zhu"},{"key":"ref49","first-page":"5514","article-title":"DISCO: Distilling counterfactuals with large language models","volume-title":"Proc. 61st Annu. Meeting Assoc. Comput. Linguistics","author":"Chen"},{"key":"ref50","first-page":"7059","article-title":"Distilling reasoning capabilities into smaller language models","volume-title":"Proc. Findings Assoc. Comput. Linguistics","author":"Shridhar"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29821"},{"key":"ref52","article-title":"Distilling reasoning ability from large language models with adaptive thinking","author":"Chen","year":"2024"},{"key":"ref53","article-title":"Skip-thinking: Chunk-wise chain-of-thought distillation enable smaller language models to reason better and faster","author":"Chen","year":"2025"},{"key":"ref54","article-title":"Think-on-graph: Deep and responsible reasoning of large language model on knowledge graph","author":"Sun","year":"2023"},{"key":"ref55","article-title":"Think-on-graph 2.0: Deep and faithful large language model reasoning with knowledge-guided retrieval augmented generation","author":"Ma","year":"2024"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11573"},{"key":"ref57","first-page":"1499","article-title":"Representing text for joint embedding of text and knowledge bases","volume-title":"Proc. Conf. Empir. Methods Natural Lang. Process.","author":"Toutanova"},{"key":"ref58","article-title":"OpenELM: An efficient language model family with open training and inference framework","author":"Mehta","year":"2024"},{"key":"ref59","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i11.33318"},{"key":"ref61","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ouyang"},{"issue":"8","key":"ref62","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref63","first-page":"176","article-title":"KEPLER: A unified model for knowledge embedding and pre-trained language representation","volume-title":"Trans. Assoc. Comput. Linguistics","volume":"9","author":"Wang","year":"2021"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/69\/11163535\/11086374.pdf?arnumber=11086374","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,13]],"date-time":"2025-09-13T05:42:30Z","timestamp":1757742150000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11086374\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":63,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tkde.2025.3591056","relation":{},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"value":"1041-4347","type":"print"},{"value":"1558-2191","type":"electronic"},{"value":"2326-3865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}