{"id":"https://openalex.org/W4413180049","doi":"https://doi.org/10.1109/gcwkshp64532.2024.11101012","title":"TSpec-LLM: An Open-source Dataset for LLM Understanding of 3GPP Specifications","display_name":"TSpec-LLM: An Open-source Dataset for LLM Understanding of 3GPP Specifications","publication_year":2024,"publication_date":"2024-12-08","ids":{"openalex":"https://openalex.org/W4413180049","doi":"https://doi.org/10.1109/gcwkshp64532.2024.11101012"},"language":"en","primary_location":{"id":"doi:10.1109/gcwkshp64532.2024.11101012","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gcwkshp64532.2024.11101012","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Globecom Workshops (GC Wkshps)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010558830","display_name":"Rasoul Nikbakht","orcid":"https://orcid.org/0000-0002-4086-1839"},"institutions":[{"id":"https://openalex.org/I4210087295","display_name":"Centre Tecnologic de Telecomunicacions de Catalunya","ror":"https://ror.org/001cwea56","country_code":"ES","type":"nonprofit","lineage":["https://openalex.org/I4210087295","https://openalex.org/I4387153040"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Rasoul Nikbakht","raw_affiliation_strings":["Centre Tecnologic de Telecomunicacions de Catalunya (CTTC),Barcelona,Spain"],"affiliations":[{"raw_affiliation_string":"Centre Tecnologic de Telecomunicacions de Catalunya (CTTC),Barcelona,Spain","institution_ids":["https://openalex.org/I4210087295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010659232","display_name":"Mohamed Benzaghta","orcid":"https://orcid.org/0000-0002-9927-1649"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Pompeu Fabra University","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Mohamed Benzaghta","raw_affiliation_strings":["Universitat Pompeu Fabra (UPF),Barcelona,Spain"],"affiliations":[{"raw_affiliation_string":"Universitat Pompeu Fabra (UPF),Barcelona,Spain","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055972962","display_name":"Giovanni Geraci","orcid":"https://orcid.org/0000-0002-9998-1747"},"institutions":[{"id":"https://openalex.org/I4210134591","display_name":"Telefonica Research and Development","ror":"https://ror.org/03qgzzb04","country_code":"ES","type":"company","lineage":["https://openalex.org/I4210097190","https://openalex.org/I4210134591"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Giovanni Geraci","raw_affiliation_strings":["Telefónica Research,Barcelona,Spain"],"affiliations":[{"raw_affiliation_string":"Telefónica Research,Barcelona,Spain","institution_ids":["https://openalex.org/I4210134591"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5010558830"],"corresponding_institution_ids":["https://openalex.org/I4210087295"],"apc_list":null,"apc_paid":null,"fwci":2.5286,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.90163454,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10651","display_name":"IPv6, Mobility, Handover, Networks, Security","score":0.9731000065803528,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10651","display_name":"IPv6, Mobility, Handover, Networks, Security","score":0.9731000065803528,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12720","display_name":"Multimedia Communication and Technology","score":0.9200000166893005,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7521616220474243},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.7275934219360352},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.4663839340209961},{"id":"https://openalex.org/keywords/open-source-software","display_name":"Open source software","score":0.4174085557460785},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2712309956550598},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.10898539423942566}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7521616220474243},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.7275934219360352},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.4663839340209961},{"id":"https://openalex.org/C2988343187","wikidata":"https://www.wikidata.org/wiki/Q1130645","display_name":"Open source software","level":3,"score":0.4174085557460785},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2712309956550598},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.10898539423942566}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/gcwkshp64532.2024.11101012","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gcwkshp64532.2024.11101012","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Globecom Workshops (GC Wkshps)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321505","display_name":"Generalitat de Catalunya","ror":"https://ror.org/01bg62x04"},{"id":"https://openalex.org/F4320322835","display_name":"Ministry of Economic Affairs","ror":"https://ror.org/042ge0913"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W3119760890","https://openalex.org/W4223908421","https://openalex.org/W4281690148","https://openalex.org/W4292779060","https://openalex.org/W4381743266","https://openalex.org/W4384615799","https://openalex.org/W4385245566","https://openalex.org/W4385714633","https://openalex.org/W4387293242","https://openalex.org/W4388650807","https://openalex.org/W4390041933","https://openalex.org/W4390659326","https://openalex.org/W4391384239","https://openalex.org/W4392152396","https://openalex.org/W4392669704","https://openalex.org/W4395474395","https://openalex.org/W4400228202","https://openalex.org/W4400647460","https://openalex.org/W4405974780","https://openalex.org/W4408223168","https://openalex.org/W4408325149","https://openalex.org/W4410949934","https://openalex.org/W6778883912","https://openalex.org/W6809583738","https://openalex.org/W6839193947","https://openalex.org/W6846966473","https://openalex.org/W6853458019","https://openalex.org/W6854999601","https://openalex.org/W6855551526","https://openalex.org/W6856823467","https://openalex.org/W6858274250","https://openalex.org/W6860710830","https://openalex.org/W6865118152","https://openalex.org/W7064175541"],"related_works":["https://openalex.org/W4376877853","https://openalex.org/W1493891899","https://openalex.org/W4250928611","https://openalex.org/W166480398","https://openalex.org/W1612808768","https://openalex.org/W167327709","https://openalex.org/W1977393088","https://openalex.org/W4387839566","https://openalex.org/W4210922265","https://openalex.org/W2288962794"],"abstract_inverted_index":{"Understanding":[0],"telecom":[1],"standards":[2],"involves":[3],"sorting":[4],"through":[5],"numerous":[6],"technical":[7,85],"documents,":[8,82],"such":[9],"as":[10],"those":[11],"produced":[12],"by":[13,107],"the":[14,33,89,112,126],"3rd":[15],"Generation":[16],"Partnership":[17],"Project":[18],"(3GPP),":[19],"which":[20],"is":[21,41],"time-consuming":[22],"and":[23,47,87,133,138,143],"labor-intensive.":[24],"While":[25],"large":[26],"language":[27],"models":[28],"(LLMs)":[29],"can":[30],"assist":[31],"with":[32],"extensive":[34],"3GPP":[35,61,81],"knowledge":[36],"base,":[37],"an":[38,55],"inclusive":[39],"dataset":[40,58],"crucial":[42],"for":[43],"their":[44],"effective":[45],"pre-training":[46],"fine-tuning.":[48],"In":[49],"this":[50],"paper,":[51],"we":[52,74],"introduce":[53],"TSpec-LLM,":[54],"open-source":[56],"comprehensive":[57],"covering":[59],"all":[60],"documents":[62],"from":[63,111,135],"Release":[64,67],"8":[65],"to":[66,103,140],"19":[68],"(1999\u20132023).":[69],"To":[70],"evaluate":[71],"its":[72],"efficacy,":[73],"first":[75],"select":[76],"a":[77,98,120],"representative":[78],"sample":[79],"of":[80,92,128],"create":[83],"corresponding":[84],"questions,":[86],"assess":[88],"baseline":[90],"performance":[91],"various":[93],"LLMs.":[94],"We":[95],"then":[96],"incorporate":[97],"retrieval-augmented":[99],"generation":[100],"(RAG)":[101],"framework":[102,122],"enhance":[104],"LLM":[105],"capabilities":[106],"retrieving":[108],"relevant":[109],"context":[110],"TSpec-LLM":[113,124],"dataset.":[114],"Our":[115],"evaluation":[116],"shows":[117],"that":[118],"using":[119],"naive-RAG":[121],"on":[123],"improves":[125],"accuracy":[127],"GPT-3.5,":[129],"Gemini":[130],"1.0":[131],"Pro,":[132],"GPT-4":[134],"44%,":[136],"46%,":[137],"51%":[139],"71%,":[141],"75%,":[142],"72%,":[144],"respectively.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-25T14:56:36.534964","created_date":"2025-10-10T00:00:00"}