{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T16:05:56Z","timestamp":1783008356137,"version":"3.54.5"},"reference-count":42,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100000183","name":"Army Research Office","doi-asserted-by":"publisher","award":["W911NF-23-1-0088"],"award-info":[{"award-number":["W911NF-23-1-0088"]}],"id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Roberts Innovation Award 2025"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3698683","type":"journal-article","created":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T19:36:04Z","timestamp":1780342564000},"page":"86424-86441","source":"Crossref","is-referenced-by-count":1,"title":["Tele-LLMs: A Series of Specialized Large Language Models for Telecommunications"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3436-7068","authenticated-orcid":false,"given":"Ali","family":"Maatouk","sequence":"first","affiliation":[{"name":"Yale University, New Haven, CT, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kenny Chirino","family":"Ampudia","sequence":"additional","affiliation":[{"name":"Amazon Web Services, New York, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rex","family":"Ying","sequence":"additional","affiliation":[{"name":"Yale University, New Haven, CT, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0932-774X","authenticated-orcid":false,"given":"Leandros","family":"Tassiulas","sequence":"additional","affiliation":[{"name":"Yale University, New Haven, CT, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref2","article-title":"Textbooks are all you need","author":"Gunasekar","year":"2023","journal-title":"arXiv:2306.11644"},{"key":"ref3","article-title":"The Llama 3 herd of models","author":"Grattafiori","year":"2024","journal-title":"arXiv:2407.21783"},{"key":"ref4","article-title":"Language models are unsupervised multitask learners","author":"Radford","year":"2019"},{"key":"ref5","article-title":"Adapting foundation models for information synthesis of wireless communication specifications","author":"Kotaru","year":"2023","journal-title":"arXiv:2308.04033"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM54140.2023.10437725"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2300473"},{"key":"ref8","article-title":"The power of large language models for wireless communication system development: A case study on FPGA platforms","author":"Du","year":"2023","journal-title":"arXiv:2307.07319"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2024.3427313"},{"key":"ref10","article-title":"Large language models for telecom: The next big thing?","author":"Bariah","year":"2023","journal-title":"arXiv:2306.10249"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/lwc.2024.3520995"},{"key":"ref12","first-page":"8342","article-title":"Don\u2019t stop pretraining: Adapt language models to domains and tasks","volume-title":"Proc. 58th Annu. Meeting Assoc. Comput. Linguistics","author":"Gururangan"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.348"},{"key":"ref14","article-title":"SauLLM-7b: A pioneering large language model for law","author":"Colombo","year":"2024","journal-title":"arXiv:2403.03883"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.606"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/tmlcn.2025.3593184"},{"key":"ref17","article-title":"Bidirectional encoder representations from transformers (BERT) for question answering in the telecom domain: Adapting a BERT-like language model to the telecom domain using the ELECTRA pre-training approach","author":"Holm","year":"2021"},{"key":"ref18","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","author":"Lewis","year":"2021","journal-title":"arXiv:2005.11401"},{"key":"ref19","article-title":"Investigating continual pretraining in large language models: Insights and implications","author":"Yildiz","year":"2024","journal-title":"arXiv:2402.17400"},{"key":"ref20","article-title":"An empirical study of catastrophic forgetting in large language models during continual fine-tuning","author":"Luo","year":"2024","journal-title":"arXiv:2308.08747"},{"key":"ref21","article-title":"The RefinedWeb dataset for falcon LLM: Outperforming curated corpora with Web data, and Web data only","author":"Penedo","year":"2023","journal-title":"arXiv:2306.01116"},{"key":"ref22","article-title":"Teleqna: A benchmark dataset to assess large language models telecommunications knowledge","author":"Maatouk","year":"2023","journal-title":"arXiv:2310.15051"},{"key":"ref23","first-page":"19426","article-title":"Large language models are not robust multiple choice selectors","volume-title":"Proc. The 12th Int. Conf. Learn. Represent.","author":"Zheng"},{"key":"ref24","article-title":"Multiple choice questions and large languages models: A case study with fictional medical data","author":"Griot","year":"2024","journal-title":"arXiv:2406.02394"},{"key":"ref25","first-page":"1601","article-title":"TriviaQA: A large scale distantly supervised challenge dataset for reading comprehension","volume-title":"Proc. 55th Annu. Meeting Assoc. Comput. Linguistics","author":"Joshi"},{"key":"ref26","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proc. Text Summarization Branches Out","author":"Lin"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref28","article-title":"SemScore: Automated evaluation of instruction-tuned LLMs based on semantic textual similarity","author":"Aynetdinov","year":"2024","journal-title":"arXiv:2401.17072"},{"key":"ref29","article-title":"Judging LLM-as-a-judge with mt-bench and chatbot arena","author":"Zheng","year":"2023","journal-title":"arXiv:2306.05685"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.365"},{"key":"ref31","article-title":"Continual pre-training of large language models: How to re-warm your model?","volume-title":"Proc. Workshop Efficient Syst. Found. Models","author":"Gupta"},{"key":"ref32","article-title":"Gemma: Open models based on Gemini research and technology","author":"Team","year":"2024","journal-title":"arXiv:2403.08295"},{"key":"ref33","article-title":"Efficient sequence packing without cross-contamination: Accelerating large language models without impacting performance","author":"Krell","year":"2022","journal-title":"arXiv:2107.02027"},{"key":"ref34","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hu"},{"key":"ref35","article-title":"Measuring massive multitask language understanding","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hendrycks"},{"key":"ref36","first-page":"4791","article-title":"HellaSwag: Can a machine really finish your sentence?","volume-title":"Proc. 57th Annu. Meeting Assoc. Comput. Linguistics","author":"Zellers"},{"key":"ref37","article-title":"Training verifiers to solve math word problems","author":"Cobbe","year":"2021","journal-title":"arXiv:2110.14168"},{"key":"ref38","article-title":"Bertscore: Evaluating text generation with bert","author":"Zhang","year":"2020","journal-title":"arXiv:1904.09675"},{"key":"ref39","first-page":"46595","article-title":"Judging LLM-as-a-judge with MT-bench and chatbot arena","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst.","author":"Zheng"},{"key":"ref40","article-title":"Alpacaeval: An automatic evaluator of instruction-following models","author":"Li","year":"2023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0441"},{"key":"ref42","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019","journal-title":"arXiv:1711.05101"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6287639\/11323511\/11540995-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11540995.pdf?arnumber=11540995","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T04:51:15Z","timestamp":1781326275000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11540995\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3698683","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}