{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T06:26:18Z","timestamp":1770963978138,"version":"3.50.1"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/tkde.2025.3649907","type":"journal-article","created":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T18:45:41Z","timestamp":1767206741000},"page":"1710-1724","source":"Crossref","is-referenced-by-count":0,"title":["Empowering Large Language Models to Set Up Knowledge Retrieval Indexing via Self-Learning"],"prefix":"10.1109","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-1862-8959","authenticated-orcid":false,"given":"Simin","family":"Niu","sequence":"first","affiliation":[{"name":"Renmin University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengwei","family":"Wang","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xun","family":"Liang","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3196-7739","authenticated-orcid":false,"given":"Zhiyu","family":"Li","sequence":"additional","affiliation":[{"name":"Institute for Advanced Algorithms Research, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0449-4699","authenticated-orcid":false,"given":"Sensen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4575-9592","authenticated-orcid":false,"given":"Shichao","family":"Song","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiawei","family":"Yang","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feiyu","family":"Xiong","sequence":"additional","affiliation":[{"name":"Institute for Advanced Algorithms Research, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenyang","family":"Xi","sequence":"additional","affiliation":[{"name":"Institute for Advanced Algorithms Research, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3352100"},{"key":"ref2","first-page":"15696","article-title":"Large language models struggle to learn long-tail knowledge","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kandpal","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1162\/COLI.a.16"},{"issue":"944","key":"ref4","first-page":"21573","article-title":"LeanDojo: Theorem proving with retrieval-augmented language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3676957"},{"key":"ref6","article-title":"Corrective retrieval augmented generation","author":"Yan","year":"2024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.281"},{"key":"ref8","article-title":"Parent document retriever","year":"2024"},{"key":"ref9","article-title":"Ensemble retriever","year":"2023"},{"key":"ref10","article-title":"T-RAG: Lessons from the LLM trenches","author":"Fatehkia","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btae560"},{"key":"ref12","article-title":"Knowledge graph-augmented language models for knowledge-grounded dialogue generation","author":"Kang","year":"2023"},{"key":"ref13","article-title":"Parent document retriever","author":"Bratani\u010d","year":"2024"},{"key":"ref14","first-page":"54903","article-title":"Model-Enhanced vector index","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29889"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.693"},{"key":"ref17","article-title":"Self-Rag: Learning to retrieve, generate, and critique through self-reflection","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Asai","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.389"},{"key":"ref19","article-title":"How colbert helps developers overcome the limits of rag","year":"2024"},{"key":"ref20","article-title":"Azure AI search: Outperforming vector search with hybrid retrieval and ranking capabilities","author":"Berntson","year":"2023"},{"key":"ref21","article-title":"Sprag","author":"McCormick","year":"2024"},{"key":"ref22","article-title":"Semantic chunking","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.845"},{"key":"ref24","article-title":"Walking down the memory maze: Beyond context limit through interactive reading","author":"Chen","year":"2023"},{"key":"ref25","article-title":"RAPTOR: Recursive abstractive processing for tree-organized retrieval","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Sarthi","year":"2024"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.558"},{"key":"ref27","article-title":"From local to global: A graph RAG approach to query-focused summarization","author":"Edge","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d19-1410"},{"key":"ref29","first-page":"281","article-title":"Some methods for classification and analysis of multivariate observations","volume-title":"Proc. Symp. Math. Statist. Probability","volume":"1","author":"Macqueen","year":"1967"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3701228"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.288"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1561\/1500000019"},{"key":"ref33","article-title":"Flagembedding","year":"2023"},{"key":"ref34","article-title":"Graph rag: Unleashing the power of knowledge graphs with LLM","year":"2023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.1999.784637"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1967.1053964"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.217"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.424"},{"key":"ref39","article-title":"From doc2query to doctttttquery","author":"Nogueira","year":"2019"},{"key":"ref40","article-title":"Document expansion by query prediction","author":"Nogueira","year":"2019"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/69\/11393947\/11320578.pdf?arnumber=11320578","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T05:44:37Z","timestamp":1770961477000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11320578\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":40,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tkde.2025.3649907","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":[[2026,3]]}}}