{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T04:29:44Z","timestamp":1783571384363,"version":"3.55.0"},"reference-count":31,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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 J. Sel. Areas Commun."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/jsac.2025.3641573","type":"journal-article","created":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T18:40:54Z","timestamp":1765219254000},"page":"2334-2347","source":"Crossref","is-referenced-by-count":3,"title":["Telco-oRAG: Optimizing Retrieval-Augmented Generation for Telecom Queries via Hybrid Retrieval and Neural Routing"],"prefix":"10.1109","volume":"44","author":[{"given":"Andrei-Laurentiu","family":"Bornea","sequence":"first","affiliation":[{"name":"Paris Research Center, Huawei Technologies, Boulogne-Billancourt, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4234-7682","authenticated-orcid":false,"given":"Fadhel","family":"Ayed","sequence":"additional","affiliation":[{"name":"Paris Research Center, Huawei Technologies, Boulogne-Billancourt, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1229-4045","authenticated-orcid":false,"given":"Antonio","family":"De Domenico","sequence":"additional","affiliation":[{"name":"Paris Research Center, Huawei Technologies, Boulogne-Billancourt, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5397-5248","authenticated-orcid":false,"given":"Nicola","family":"Piovesan","sequence":"additional","affiliation":[{"name":"Paris Research Center, Huawei Technologies, Boulogne-Billancourt, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tareq Si","family":"Salem","sequence":"additional","affiliation":[{"name":"Paris Research Center, Huawei Technologies, Boulogne-Billancourt, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3436-7068","authenticated-orcid":false,"given":"Ali","family":"Maatouk","sequence":"additional","affiliation":[{"name":"Yale University, New Haven, CT, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"TeleQnA: A benchmark dataset to assess large language models telecommunications knowledge","author":"Maatouk","year":"2023","journal-title":"arXiv:2310.15051"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.740"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21428\/bf6fb269.1f033948"},{"key":"ref4","volume-title":"IBM: RAG Vs. Fine-Tuning","author":"Belcic","year":"2024"},{"issue":"2","key":"ref5","doi-asserted-by":"crossref","DOI":"10.1162\/99608f92.5317da47","article-title":"How is ChatGPT\u2019s behavior changing over time?","volume":"6","author":"Chen","year":"2024","journal-title":"Harvard Data Sci. Rev."},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3777411"},{"key":"ref7","first-page":"1022","article-title":"Compacter: Efficient low-rank hypercomplex adapter layers","volume-title":"Proc. 35th Int. Conf. Neural Inf. Process. Syst. (NIPS)","volume":"34","author":"Mahabadi"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acllong.353"},{"key":"ref9","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Hu"},{"key":"ref10","first-page":"10088","article-title":"QLoRA: Efficient finetuning of quantized LLMs","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Dettmers"},{"key":"ref11","article-title":"Tele-LLMS: A series of specialized large language models for telecommunications","author":"Maatouk","year":"2024","journal-title":"arXiv:2409.05314"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/tmlcn.2025.3593184"},{"key":"ref13","article-title":"Direct preference optimization: Your language model is secretly a reward model","author":"Rafailov","year":"2024","journal-title":"arXiv:2305.18290"},{"key":"ref14","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst. (NIPS)","volume":"33","author":"Lewis"},{"issue":"1","key":"ref15","first-page":"11912","article-title":"Atlas: Few-shot learning with retrieval augmented language models","volume-title":"J. Mach. Learn. Res.","volume":"24","author":"Izacard","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s41019-025-00335-5"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/PIMRC59610.2024.10817162"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3711992.3711996"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM52923.2024.10901158"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCWorkshops67674.2025.11162262"},{"key":"ref21","article-title":"CommGPT: A graph and retrieval-augmented multimodal communication foundation model","author":"Jiang","year":"2025","journal-title":"arXiv:2502. 18763"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2021.103076"},{"key":"ref23","volume-title":"New Embedding Models and API Updates","year":"2024"},{"key":"ref24","volume-title":"TR 21.905, Vocabulary for 3GPP Specifications, 3GPP TSG SA","year":"2024"},{"key":"ref25","volume-title":"Specifications By Series","year":"2025"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2305016120"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2025.101260"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210183"},{"key":"ref29","first-page":"30233","article-title":"Matryoshka representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Kusupati"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"ref31","article-title":"QE-RAG: A robust retrieval-augmented generation benchmark for query entry errors","author":"Zhang","year":"2025","journal-title":"arXiv:2504.04062"}],"container-title":["IEEE Journal on Selected Areas in Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/49\/11372474\/11284862.pdf?arnumber=11284862","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T20:48:24Z","timestamp":1771879704000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11284862\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/jsac.2025.3641573","relation":{},"ISSN":["1558-0008","0733-8716"],"issn-type":[{"value":"1558-0008","type":"electronic"},{"value":"0733-8716","type":"print"}],"subject":[],"published":{"date-parts":[[2026]]}}}