{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T19:23:00Z","timestamp":1788463380297,"version":"build-2803163510"},"reference-count":279,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"crossref","award":["ZR2025QC1591"],"award-info":[{"award-number":["ZR2025QC1591"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62576221"],"award-info":[{"award-number":["62576221"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"crossref","award":["2025A1515010288"],"award-info":[{"award-number":["2025A1515010288"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Guangdong Provincial Key Laboratory","award":["2023B1212060076"],"award-info":[{"award-number":["2023B1212060076"]}]},{"name":"Shenzhen Science and Technology Program","award":["ZDSYS20220527171400002"],"award-info":[{"award-number":["ZDSYS20220527171400002"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1109\/tkde.2026.3721883","type":"journal-article","created":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T19:09:22Z","timestamp":1786475362000},"page":"6480-6498","source":"Crossref","is-referenced-by-count":0,"title":["Data and Knowledge Dual-Driven Text Embedding Approaches: A Survey"],"prefix":"10.1109","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-6835-1523","authenticated-orcid":false,"given":"Xiaoyin","family":"Chen","sequence":"first","affiliation":[{"name":"Shenzhen University","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaqing","family":"Zhan","sequence":"additional","affiliation":[{"name":"Shenzhen University","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiayi","family":"Lin","sequence":"additional","affiliation":[{"name":"Shenzhen University","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7731-8258","authenticated-orcid":false,"given":"Han","family":"Liu","sequence":"additional","affiliation":[{"name":"Shenzhen University","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1449-5046","authenticated-orcid":false,"given":"Qin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shenzhen University","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1139-8654","authenticated-orcid":false,"given":"Junyang","family":"Chen","sequence":"additional","affiliation":[{"name":"Shenzhen University","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6559-1043","authenticated-orcid":false,"given":"Hao","family":"Chen","sequence":"additional","affiliation":[{"name":"Shenzhen University","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Efficient estimation of word representations in vector space","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Mikolov"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.5555\/3044805.3045025"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-1600-9"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1080\/00437956.1954.11659520"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1987.1165125"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref10","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018","journal-title":"OpenAI"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2104765118"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3233\/JIFS-169976"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.06.073"},{"key":"ref14","article-title":"Trends in integration of knowledge and large language models: A survey and taxonomy of methods, benchmarks, and applications","author":"Feng","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3310002"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3266377"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1455567.1455605"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1515\/9783110218329"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21236\/ad0616323"},{"key":"ref20","first-page":"8399","article-title":"Rule-KBQA: Rule-guided reasoning for complex knowledge base question answering with large language models","volume-title":"Proc. 31st Int. Conf. Comput. Linguist.","author":"Zhang"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.27"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11164"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.423"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/383"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1005"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i15.17592"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1255"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3142260"},{"key":"ref29","first-page":"993","article-title":"Latent Dirichlet allocation","volume":"3","author":"Blei","year":"2003","journal-title":"J. Mach. Learn. Res."},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1206"},{"key":"ref31","first-page":"1807","article-title":"Topic-informed neural machine translation","volume-title":"Proc. 26th Int. Conf. Comput. Linguist.: Tech. Papers","author":"Zhang"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10981"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3358102"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2009"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6333"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1359"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11325"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2023.107474"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.262"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3656471"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.374"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2022.955850"},{"key":"ref43","doi-asserted-by":"crossref","DOI":"10.2139\/ssrn.5390799","article-title":"Domain lexical knowledge-based word embedding enhancement for text classification under small data","author":"Zhu","year":"2025"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0313092"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-023-00861-x"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.930"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s42001-024-00286-3"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1097-4571(199009)41:6<391::AID-ASI1>3.0.CO;2-9"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/312624.312649"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(00)00026-5"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00051"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K16-1006"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1031"},{"key":"ref54","first-page":"6294","article-title":"Learned in translation: Contextualized word vectors","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"McCann"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s00354-024-00245-6"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3627820"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.17762\/ijritcc.v11i10.8611"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.33395\/sinkron.v9i1.13005"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.106057"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-024-11595-z"},{"key":"ref61","first-page":"2227","article-title":"Deep contextualized word representations","volume-title":"Proc. 2018 Conf. North Amer. Chapter Assoc. Comput. Linguist.: Hum. Lang. Technol.","author":"Peters"},{"key":"ref62","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yang"},{"issue":"140","key":"ref63","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref64","first-page":"79310","article-title":"NV-Embed: Improved techniques for training LLMs as generalist embedding models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lee"},{"key":"ref65","article-title":"Jina-embeddings-V3: Multilingual embeddings with task LoRA","author":"Sturua","year":"2024"},{"key":"ref66","article-title":"Nomic embed: Training a reproducible long context text embedder","volume-title":"Trans. Mach. Learn. Res.","author":"Nussbaum","year":"2025"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.71"},{"key":"ref68","article-title":"Generative representational instruction tuning","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Muennighoff"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.642"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.645"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/s12490-018-0146-3"},{"key":"ref72","article-title":"Spanish pre-trained BERT model and evaluation data","volume-title":"Proc. PML4DC Workshop Int. Conf. Learn. Representations","author":"Ca\u00f1ete"},{"key":"ref73","article-title":"ERNIE: Enhanced representation through knowledge integration","author":"Sun","year":"2019"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1183"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1493"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00065"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00633"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00343"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6256"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btz682"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1371"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-1909"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2020.103395"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.2196\/15371"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.321"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3121646"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.110"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2022.11.003"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11918"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.393"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.269"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.150"},{"key":"ref93","article-title":"Taking notes on the fly helps language pre-training","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wu"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-17120-8_11"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3680037"},{"key":"ref96","article-title":"ERNIE 3.0: Large-scale knowledge enhanced pre-training for language understanding and generation","author":"Sun","year":"2021"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3185154"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.122269"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21417"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.121"},{"key":"ref101","article-title":"GreaseLM: Graph REASoning enhanced language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531997"},{"key":"ref103","article-title":"DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter","author":"Sanh","year":"2019"},{"key":"ref104","article-title":"Explanations from large language models make small reasoners better","author":"Li","year":"2022"},{"key":"ref105","article-title":"PINTO: Faithful language reasoning using prompt-generated rationales","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.137"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.441"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.225"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.27"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.611"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.68"},{"key":"ref112","article-title":"Augmented large language models with parametric knowledge guiding","author":"Luo","year":"2023"},{"key":"ref113","article-title":"Knowledge refinement via interaction between search engines and large language models","author":"Feng","year":"2023"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3104310"},{"key":"ref115","article-title":"Knowledge-driven cot: Exploring faithful reasoning in LLms for knowledge-intensive question answering","author":"Wang","year":"2023"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.392"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.55"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.107907"},{"key":"ref119","article-title":"Chain of knowledge: A framework for grounding large language models with structured knowledge bases","author":"Li","year":"2023"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.271"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i22.34510"},{"key":"ref122","article-title":"Knowledge-consistent dialogue generation with knowledge graphs","volume-title":"Proc. ICML Workshop Knowl. Retrieval Lang. Models","author":"Kang"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.910"},{"key":"ref124","article-title":"Check your facts and try again: Improving large language models with external knowledge and automated feedback","author":"Peng","year":"2023"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447647"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.468"},{"key":"ref128","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref129","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref132","article-title":"LLM2CLIP: Powerful language model unlock richer visual representation","volume-title":"Proc. NeurIPS Workshop: Self-Supervised Learn.\u2013Theory Pract.","author":"Huang"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3754845"},{"key":"ref134","article-title":"Jina-CLIP-v2: Multilingual multimodal embeddings for text and images","author":"Koukounas","year":"2024"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-industry.145"},{"key":"ref136","article-title":"LIFT: Improving long context understanding through long input fine-tuning","author":"Pan","year":"2024"},{"key":"ref137","volume-title":"The Handbook of Artificial Intelligence","volume":"1","author":"Barr","year":"1981"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-343"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1406.1078"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref145","first-page":"38107","article-title":"Making text embedders few-shot learners","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.26615\/978-954-452-092-2_112"},{"key":"ref147","first-page":"21528","article-title":"NUDGE: Lightweight non-parametric fine-tuning of embeddings for retrieval","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zeighami"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1177\/0008125619864925"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1145\/3571730"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00342"},{"key":"ref152","first-page":"3929","article-title":"Retrieval augmented language model pre-training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Guu"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3070843"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2017.2754499"},{"key":"ref155","article-title":"Towards AI-complete question answering: A set of prerequisite toy tasks","author":"Weston","year":"2015"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21383"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1458"},{"key":"ref158","first-page":"19861","article-title":"A benchmark for systematic generalization in grounded language understanding","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ruis"},{"key":"ref159","first-page":"2787","article-title":"Translating embeddings for modeling multi-relational data","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Bordes"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1019"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.698"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.442"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.200"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.165"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1093\/database\/bav123"},{"key":"ref167","first-page":"649","article-title":"Character-level convolutional networks for text classification","volume-title":"Proc. 28th Int. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref168","first-page":"142","article-title":"Learning word vectors for sentiment analysis","volume-title":"Proc. 49th Annu. Meeting Assoc. Comput. Linguist.: Hum. Lang. Technol.","author":"Maas"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.3390\/app11146421"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1454"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1145\/2827872"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1057\/dbm.2012.17"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1514"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12057"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1009"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00141"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d19-1243"},{"key":"ref178","article-title":"Quasar: Datasets for question answering by search and reading","author":"Dhingra","year":"2017"},{"key":"ref179","article-title":"SearchQA: A new Q&A dataset augmented with context from a search engine","author":"Dunn","year":"2017"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1004"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1421"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1260"},{"key":"ref183","article-title":"MS MARCO: A human-generated machine reading comprehension dataset","volume-title":"Proc. 30th Conf. Neural Inf. Process. Syst.","author":"Nguyen"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1109"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1250"},{"key":"ref186","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref187","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref188","first-page":"81","article-title":"Deep learning, dark knowledge, and dark matter","volume-title":"Proc. NIPS 2014 Workshop High-Energy Phys. Mach. Learn.","author":"Sadowski"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-025-41434-w"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-032-31404-8_27"},{"key":"ref191","article-title":"VeriCoT: Neuro-symbolic chain-of-thought validation via logical consistency checks","volume-title":"Proc. 14th Int. Conf. Learn. Representations","author":"Feng"},{"key":"ref192","article-title":"Training verifiers to solve math word problems","author":"Cobbe","year":"2021"},{"key":"ref193","article-title":"CommonsenseQA 2.0: Exposing the limits of AI through gamification","author":"Talmor","year":"2022"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00290"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D13-1170"},{"key":"ref197","article-title":"Automatically constructing a corpus of sentential paraphrases","volume-title":"Proc. 3rd Int. Workshop Paraphrasing","author":"Dolan"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/s17-2001"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1101"},{"key":"ref200","article-title":"The fifth PASCAL recognizing textual entailment challenge","volume-title":"Proc. 2nd Text Anal. Conf.","author":"Bentivogli"},{"key":"ref201","first-page":"552","article-title":"The Winograd schema challenge","volume-title":"Proc. 13th Int. Conf. Princ. Knowl. Representation Reasoning","author":"Levesque"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.447"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.891"},{"key":"ref204","first-page":"218","article-title":"news-please: A generic news crawler and extractor","volume-title":"Proc. 15th Int. Symp. Inf. Sci.","author":"Hamborg"},{"key":"ref205","article-title":"No language left behind: Scaling human-centered machine translation","author":"Costa-juss","year":"2022"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.507"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00370"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.168"},{"key":"ref209","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.557"},{"key":"ref210","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1421"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6319"},{"key":"ref212","doi-asserted-by":"publisher","DOI":"10.1145\/3474381"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.6028\/nist.sp.1266.deep-overview"},{"key":"ref214","article-title":"BEIR: A heterogenous benchmark for zero-shot evaluation of information retrieval models","author":"Thakur","year":"2021"},{"key":"ref215","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1174"},{"key":"ref216","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11573"},{"key":"ref217","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p16-2033"},{"key":"ref218","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n18-1059"},{"key":"ref219","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1015"},{"key":"ref220","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1246"},{"key":"ref221","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.441"},{"key":"ref222","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1393"},{"key":"ref223","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1300"},{"key":"ref224","article-title":"Beyond the imitation game: Quantifying and extrapolating the capabilities of language models","author":"Srivastava","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref225","article-title":"Think you have solved question answering? Try ARC, the AI2 reasoning challenge","author":"Clark","year":"2018"},{"key":"ref226","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1081"},{"key":"ref227","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00276"},{"key":"ref228","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.44"},{"key":"ref229","article-title":"Open question answering over tables and text","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref230","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref231","article-title":"HallE-Control: Controlling object hallucination in large multimodal models","author":"Zhai","year":"2023"},{"key":"ref232","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.775"},{"key":"ref233","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4251-x"},{"key":"ref234","article-title":"Aligning multimodal representations through an information bottleneck","volume-title":"Proc. 42nd Int. Conf. Mach. Learn.","author":"Alm\u00f9devar"},{"key":"ref235","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref236","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref237","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"ref238","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref239","article-title":"SuperGLUE: A stickier benchmark for general-purpose language understanding systems","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref240","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.148"},{"key":"ref241","article-title":"MMTEB: Massive multilingual text embedding benchmark","author":"Enevoldsen","year":"2025"},{"key":"ref242","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.109"},{"key":"ref243","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.137"},{"key":"ref244","article-title":"Context embeddings for efficient answer generation in RAG","author":"Rau","year":"2024"},{"key":"ref245","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939673"},{"key":"ref246","article-title":"ClinicalBERT: Modeling clinical notes and predicting hospital readmission","author":"Huang","year":"2019"},{"key":"ref247","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-019-01433-3"},{"key":"ref248","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.232"},{"key":"ref249","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.765"},{"key":"ref250","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01831"},{"key":"ref251","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-short.45"},{"key":"ref252","article-title":"Content conditional debiasing for fair text embedding","author":"Deng","year":"2024"},{"key":"ref253","article-title":"On debiasing text embeddings through context injection","author":"Uriot","year":"2024"},{"key":"ref254","first-page":"4356","article-title":"Man is to computer programmer as woman is to homemaker? Debiasing word embeddings","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Bolukbasi"},{"key":"ref255","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1062"},{"key":"ref256","doi-asserted-by":"publisher","DOI":"10.1145\/3278721.3278779"},{"key":"ref257","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1064"},{"key":"ref258","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.107"},{"key":"ref259","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1061"},{"key":"ref260","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.778"},{"key":"ref261","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.774"},{"key":"ref262","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26279"},{"key":"ref263","doi-asserted-by":"publisher","DOI":"10.1016\/j.dss.2024.114208"},{"key":"ref264","first-page":"9482","article-title":"Mitigating fine-tuning bias: A parameter-efficient debiasing framework for large language models","volume-title":"Proc. ACM Web Conf.","author":"Li"},{"key":"ref265","article-title":"Data, not model: Explaining bias toward LLM texts in neural retrievers","author":"Huang","year":"2026"},{"key":"ref266","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2026.01.006"},{"key":"ref267","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.416"},{"key":"ref268","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02238"},{"key":"ref269","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-020-01297-6"},{"key":"ref270","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-025-02888-3"},{"key":"ref271","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.482"},{"issue":"240","key":"ref272","first-page":"1","article-title":"PaLM: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref273","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref274","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.98"},{"key":"ref275","article-title":"Time travel in LLMs: Tracing data contamination in large language models","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Golchin"},{"key":"ref276","article-title":"Proving test set contamination in black-box language models","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Oren"},{"key":"ref277","article-title":"Rethinking benchmark and contamination for language models with rephrased samples","author":"Yang","year":"2023"},{"key":"ref278","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.324"},{"key":"ref279","article-title":"Fool your (vision and) language model with embarrassingly simple permutations","author":"Zong","year":"2023"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/69\/11673943\/11646471.pdf?arnumber=11646471","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T19:04:11Z","timestamp":1788462251000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11646471\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":279,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tkde.2026.3721883","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":[[2026,10]]}}}