{"id":"https://openalex.org/W4412888409","doi":"https://doi.org/10.18653/v1/2025.findings-acl.573","title":"WirelessMathBench: A Mathematical Modeling Benchmark for LLMs in Wireless Communications","display_name":"WirelessMathBench: A Mathematical Modeling Benchmark for LLMs in Wireless Communications","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888409","doi":"https://doi.org/10.18653/v1/2025.findings-acl.573"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.573","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.573","pdf_url":"https://aclanthology.org/2025.findings-acl.573.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.573.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100730490","display_name":"Li Xin","orcid":"https://orcid.org/0000-0002-5992-6161"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090268549","display_name":"Mengbing Liu","orcid":"https://orcid.org/0000-0002-4920-5280"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mengbing Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100670216","display_name":"Li Wei","orcid":"https://orcid.org/0000-0003-2938-7758"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052340806","display_name":"Jiancheng An","orcid":"https://orcid.org/0000-0003-2512-9989"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiancheng An","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056145687","display_name":"M\u00e9rouane Debbah","orcid":"https://orcid.org/0000-0001-8941-8080"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Merouane Abdelkader Debbah","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5060020877","display_name":"Chau Yuen","orcid":"https://orcid.org/0000-0002-9307-2120"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chau Yuen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10984","last_page":"11009"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10796","display_name":"Cooperative Communication and Network Coding","score":0.9678000211715698,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10796","display_name":"Cooperative Communication and Network Coding","score":0.9678000211715698,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10651","display_name":"IPv6, Mobility, Handover, Networks, Security","score":0.9535999894142151,"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/T11158","display_name":"Wireless Networks and Protocols","score":0.9524999856948853,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8005199432373047},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.7020930051803589},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6490259170532227},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.37196457386016846},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.0796390175819397}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8005199432373047},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.7020930051803589},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6490259170532227},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.37196457386016846},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0796390175819397},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.573","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.573","pdf_url":"https://aclanthology.org/2025.findings-acl.573.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.573","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.573","pdf_url":"https://aclanthology.org/2025.findings-acl.573.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8186112941","display_name":null,"funder_award_id":"FCP-NTU-RG-2024-025","funder_id":"https://openalex.org/F4320325256","funder_display_name":"Info-communications Media Development Authority"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"},{"id":"https://openalex.org/F4320325256","display_name":"Info-communications Media Development Authority","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888409.pdf","grobid_xml":"https://content.openalex.org/works/W4412888409.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4],"achieved":[5],"impressive":[6],"results":[7],"across":[8],"a":[9,31,61,140],"broad":[10],"array":[11],"of":[12,49,64,83,136,163],"tasks,":[13,75,107],"yet":[14],"their":[15,108],"capacity":[16],"for":[17,168],"complex,":[18],"domain-specific":[19],"mathematical":[20,40],"reasoning-particularly":[21],"in":[22,104,122,145],"wireless":[23,44,169],"communications-remains":[24],"underexplored.In":[25],"this":[26],"work,":[27],"we":[28,97,157],"introduce":[29],"WirelessMathBench":[30],"novel":[32],"benchmark":[33,47],"specifically":[34],"designed":[35],"to":[36,43,71,87,159],"evaluate":[37],"LLMs":[38,167],"on":[39,129],"modeling":[41],"challenges":[42],"communications":[45],"engineering.Our":[46],"consists":[48],"587":[50],"meticulously":[51],"curated":[52],"questions":[53,70],"sourced":[54],"from":[55,67],"40":[56],"state-of-theart":[57],"research":[58],"papers,":[59],"encompassing":[60],"diverse":[62],"spectrum":[63],"tasks":[65],"ranging":[66],"basic":[68,105],"multiplechoice":[69],"complex":[72],"equation":[73,147],"completion":[74],"including":[76],"both":[77],"partial":[78],"and":[79,89,172],"full":[80,146],"completions,":[81],"all":[82],"which":[84],"rigorously":[85],"adhere":[86],"physical":[88],"dimensional":[90],"constraints.Through":[91],"extensive":[92],"experimentation":[93],"with":[94,139,153],"leading":[95],"LLMs,":[96],"observe":[98],"that":[99],"while":[100],"many":[101],"models":[102],"excel":[103],"recall":[106],"performance":[109],"degrades":[110],"significantly":[111],"when":[112],"reconstructing":[113],"partially":[114],"or":[115],"fully":[116],"obscured":[117],"equations,":[118],"exposing":[119],"fundamental":[120],"limitations":[121],"current":[123],"LLMs.Even":[124],"DeepSeek-R1,":[125],"the":[126,154,161],"best":[127],"performer":[128],"our":[130],"benchmark,":[131],"achieves":[132],"an":[133],"average":[134],"accuracy":[135],"only":[137],"38.05%,":[138],"mere":[141],"7.83%":[142],"success":[143],"rate":[144],"completion.By":[148],"publicly":[149],"releasing":[150],"WirelessMath-Bench":[151],"along":[152],"evaluation":[155],"toolkit,":[156],"aim":[158],"advance":[160],"development":[162],"more":[164],"robust,":[165],"domain-aware":[166],"system":[170],"analysis":[171],"broader":[173],"engineering":[174],"applications.Benchmark":[175]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}