{"id":"https://openalex.org/W4417170171","doi":"https://doi.org/10.1109/jsac.2025.3641905","title":"Go Gentle Into the Final Dance: A Benchmark for Evaluating LLMs in Telecom","display_name":"Go Gentle Into the Final Dance: A Benchmark for Evaluating LLMs in Telecom","publication_year":2025,"publication_date":"2025-12-09","ids":{"openalex":"https://openalex.org/W4417170171","doi":"https://doi.org/10.1109/jsac.2025.3641905"},"language":"en","primary_location":{"id":"doi:10.1109/jsac.2025.3641905","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jsac.2025.3641905","pdf_url":null,"source":{"id":"https://openalex.org/S90422530","display_name":"IEEE Journal on Selected Areas in Communications","issn_l":"0733-8716","issn":["0733-8716","1558-0008"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal on Selected Areas in Communications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pure.manchester.ac.uk/ws/files/1735451189/JSAC_Wireless_Dataset_accept.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090858283","display_name":"Yushen Lin","orcid":"https://orcid.org/0000-0002-8311-6601"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Yushen Lin","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, The University of Manchester, Manchester, U.K","Department of Electrical and Electronic Engineering, University of Manchester, Manchester, U.K"],"raw_orcid":"https://orcid.org/0000-0002-8311-6601","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, The University of Manchester, Manchester, U.K","institution_ids":["https://openalex.org/I28407311"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, University of Manchester, Manchester, U.K","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002904166","display_name":"Zhiguo Ding","orcid":"https://orcid.org/0000-0001-5280-384X"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhiguo Ding","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, The University of Manchester, Manchester, U.K","Department of Electrical and Electronic Engineering, University of Manchester, Manchester, U.K"],"raw_orcid":"https://orcid.org/0000-0001-5280-384X","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, The University of Manchester, Manchester, U.K","institution_ids":["https://openalex.org/I28407311"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, University of Manchester, Manchester, U.K","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049587970","display_name":"Ruichen Zhang","orcid":"https://orcid.org/0000-0002-6859-3645"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ruichen Zhang","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University, Jurong West, Singapore","College of Computing and Data Science, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-6859-3645","affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University, Jurong West, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036412443","display_name":"Daniel K. C. So","orcid":"https://orcid.org/0000-0002-7642-1755"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Daniel K. C. So","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, The University of Manchester, Manchester, U.K","Department of Electrical and Electronic Engineering, University of Manchester, Manchester, U.K"],"raw_orcid":"https://orcid.org/0000-0002-7642-1755","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, The University of Manchester, Manchester, U.K","institution_ids":["https://openalex.org/I28407311"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, University of Manchester, Manchester, U.K","institution_ids":["https://openalex.org/I28407311"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5090858283"],"corresponding_institution_ids":["https://openalex.org/I28407311"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20084631,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"44","issue":null,"first_page":"2365","last_page":"2377"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.43950000405311584,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.43950000405311584,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.12540000677108765,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.10249999910593033,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.805400013923645},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.5351999998092651},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.46939998865127563},{"id":"https://openalex.org/keywords/wireless-network","display_name":"Wireless network","score":0.414900004863739},{"id":"https://openalex.org/keywords/conceptual-model","display_name":"Conceptual model","score":0.3337000012397766},{"id":"https://openalex.org/keywords/case-based-reasoning","display_name":"Case-based reasoning","score":0.3330000042915344}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.805400013923645},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7307999730110168},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.571399986743927},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.5351999998092651},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.46939998865127563},{"id":"https://openalex.org/C108037233","wikidata":"https://www.wikidata.org/wiki/Q11375","display_name":"Wireless network","level":3,"score":0.414900004863739},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3441999852657318},{"id":"https://openalex.org/C13606891","wikidata":"https://www.wikidata.org/wiki/Q2623243","display_name":"Conceptual model","level":2,"score":0.3337000012397766},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.3330000042915344},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.319599986076355},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.29440000653266907},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.28610000014305115},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.28349998593330383},{"id":"https://openalex.org/C33271190","wikidata":"https://www.wikidata.org/wiki/Q3467747","display_name":"Telecommunications service","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C32896092","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Risk management","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26339998841285706},{"id":"https://openalex.org/C192126672","wikidata":"https://www.wikidata.org/wiki/Q1068715","display_name":"Telecommunications network","level":2,"score":0.25679999589920044}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/jsac.2025.3641905","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jsac.2025.3641905","pdf_url":null,"source":{"id":"https://openalex.org/S90422530","display_name":"IEEE Journal on Selected Areas in Communications","issn_l":"0733-8716","issn":["0733-8716","1558-0008"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal on Selected Areas in Communications","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/14a5c55c-c9b7-437f-8cb7-0bf3d131dea7","is_oa":true,"landing_page_url":"https://research.manchester.ac.uk/en/publications/14a5c55c-c9b7-437f-8cb7-0bf3d131dea7","pdf_url":"https://pure.manchester.ac.uk/ws/files/1735451189/JSAC_Wireless_Dataset_accept.pdf","source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Lin, Y, Ding, Z, Zhang, R & So, D K C 2026, 'Go Gentle into the Final Dance: A Benchmark For Evaluating LLMs in Telecom', IEEE Journal on Selected Areas in Communications. https://doi.org/10.1109/jsac.2025.3641905","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/14a5c55c-c9b7-437f-8cb7-0bf3d131dea7","is_oa":true,"landing_page_url":"https://research.manchester.ac.uk/en/publications/14a5c55c-c9b7-437f-8cb7-0bf3d131dea7","pdf_url":"https://pure.manchester.ac.uk/ws/files/1735451189/JSAC_Wireless_Dataset_accept.pdf","source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Lin, Y, Ding, Z, Zhang, R & So, D K C 2026, 'Go Gentle into the Final Dance: A Benchmark For Evaluating LLMs in Telecom', IEEE Journal on Selected Areas in Communications. https://doi.org/10.1109/jsac.2025.3641905","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417170171.pdf","grobid_xml":"https://content.openalex.org/works/W4417170171.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,39,131],"large":[3],"language":[4],"models":[5,20],"(LLMs)":[6],"have":[7],"driven":[8],"remarkable":[9],"progress":[10],"across":[11],"diverse":[12],"NLP":[13],"benchmarks.":[14,150],"However,":[15],"the":[16,34,137,182],"application":[17],"of":[18,45,61,184],"these":[19,160],"to":[21,80,157,180],"sophisticated":[22],"domains":[23],"such":[24],"as":[25],"wireless":[26,122,191],"communications":[27],"raises":[28],"new":[29],"challenges.":[30],"This":[31],"paper":[32],"addresses":[33],"evaluation":[35,177],"gap":[36],"for":[37,53,189],"LLMs":[38,95,109,188],"telecommunications":[40],"by":[41,135],"introducing":[42],"Last":[43],"Dance":[44],"Telecommunications":[46],"(LDOT)":[47],"\u2013":[48],"a":[49,58,153],"comprehensive":[50],"benchmark":[51],"suite":[52],"telecom-related":[54],"tasks.":[55,102],"LDOT":[56,132,173],"encompasses":[57],"broad":[59],"range":[60],"problem":[62],"categories,":[63],"including":[64],"conceptual":[65],"telecom":[66,115],"questions,":[67,117],"mathematical":[68],"and":[69,73,85,98,128,175],"logical":[70],"reasoning":[71,84,170],"problems,":[72],"complex":[74],"network":[75],"optimization":[76,127],"scenarios,":[77],"specifically":[78],"designed":[79],"challenging":[81],"LLMs\u2019":[82],"high-level":[83],"domain-specific":[86,101],"knowledge.":[87],"Using":[88],"LDOT,":[89],"we":[90],"rigorously":[91],"assess":[92],"state-of-the-art":[93],"(SOTA)":[94],"(both":[96],"closed-source":[97],"open-source)":[99],"on":[100,113],"Our":[103],"results":[104],"reveal":[105],"that":[106,143],"while":[107],"general-purpose":[108],"exhibit":[110],"strong":[111],"performance":[112,141],"basic":[114],"knowledge":[116,166],"they":[118],"struggle":[119],"with":[120],"reasoning-intensive":[121],"problems.":[123],"Notably,":[124],"certain":[125],"multi-step":[126],"planning":[129],"tasks":[130],"remain":[133],"unsolved":[134],"even":[136],"best":[138],"models,":[139],"exposing":[140],"gaps":[142],"are":[144],"not":[145],"apparent":[146],"from":[147,163,168],"existing":[148],"saturated":[149],"We":[151],"provide":[152],"detailed":[154],"failure":[155],"analysis":[156],"pinpoint":[158],"whether":[159],"limitations":[161],"arise":[162],"insufficient":[164],"telecom-specific":[165],"or":[167],"inadequate":[169],"capabilities.":[171],"The":[172],"dataset":[174],"our":[176],"findings":[178],"aim":[179],"facilitate":[181],"development":[183],"more":[185],"robust":[186],"domain-adapted":[187],"next-generation":[190],"communications.":[192]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-12-09T00:00:00"}