{"id":"https://openalex.org/W4400526729","doi":"https://doi.org/10.1145/3626772.3657945","title":"Can LLMs Master Math? Investigating Large Language Models on Math Stack Exchange","display_name":"Can LLMs Master Math? Investigating Large Language Models on Math Stack Exchange","publication_year":2024,"publication_date":"2024-07-10","ids":{"openalex":"https://openalex.org/W4400526729","doi":"https://doi.org/10.1145/3626772.3657945"},"language":"en","primary_location":{"id":"doi:10.1145/3626772.3657945","doi":"https://doi.org/10.1145/3626772.3657945","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3626772.3657945","pdf_url":null,"source":{"id":"https://openalex.org/S4363608773","display_name":"International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2404.00344","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000746968","display_name":"Ankit Satpute","orcid":"https://orcid.org/0000-0003-3219-026X","observed_orcids":["https://orcid.org/0000-0003-3219-026X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ankit Satpute","raw_affiliation_strings":["FIZ Karlsruhe, Berlin, Germany"],"raw_orcid":"https://orcid.org/0000-0003-3219-026X","affiliations":[{"raw_affiliation_string":"FIZ Karlsruhe, Berlin, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093836286","display_name":"Noah Gie\u00dfing","orcid":"https://orcid.org/0009-0006-5268-2519","observed_orcids":["https://orcid.org/0009-0006-5268-2519"]},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Noah Gie\u00dfing","raw_affiliation_strings":["Technical University Berlin, Berlin, Germany"],"raw_orcid":"https://orcid.org/0009-0006-5268-2519","affiliations":[{"raw_affiliation_string":"Technical University Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029478950","display_name":"Andr\u00e9 Greiner-Petter","orcid":"https://orcid.org/0000-0002-5828-5497","observed_orcids":["https://orcid.org/0000-0002-5828-5497"]},"institutions":[{"id":"https://openalex.org/I74656192","display_name":"University of G\u00f6ttingen","ror":"https://ror.org/01y9bpm73","country_code":"DE","type":"education","lineage":["https://openalex.org/I74656192"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andr\u00e9 Greiner-Petter","raw_affiliation_strings":["University of G\u00f6ttingen, G\u00f6ttingen, Germany"],"raw_orcid":"https://orcid.org/0000-0002-5828-5497","affiliations":[{"raw_affiliation_string":"University of G\u00f6ttingen, G\u00f6ttingen, Germany","institution_ids":["https://openalex.org/I74656192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038664667","display_name":"Moritz Schubotz","orcid":"https://orcid.org/0000-0001-7141-4997","observed_orcids":["https://orcid.org/0000-0001-7141-4997"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Moritz Schubotz","raw_affiliation_strings":["FIZ Karlsruhe, Berlin, Germany"],"raw_orcid":"https://orcid.org/0000-0001-7141-4997","affiliations":[{"raw_affiliation_string":"FIZ Karlsruhe, Berlin, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015124068","display_name":"Olaf Teschke","orcid":"https://orcid.org/0009-0003-4089-9647","observed_orcids":["https://orcid.org/0009-0003-4089-9647"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Olaf Teschke","raw_affiliation_strings":["FIZ Karlsruhe, Berlin, Germany"],"raw_orcid":"https://orcid.org/0009-0003-4089-9647","affiliations":[{"raw_affiliation_string":"FIZ Karlsruhe, Berlin, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041062417","display_name":"Akiko Aizawa","orcid":"https://orcid.org/0000-0001-6544-5076","observed_orcids":["https://orcid.org/0000-0001-6544-5076"]},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akiko Aizawa","raw_affiliation_strings":["National Insutitute of Informatics, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0001-6544-5076","affiliations":[{"raw_affiliation_string":"National Insutitute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058837356","display_name":"B\u00e9la Gipp","orcid":"https://orcid.org/0000-0001-6522-3019","observed_orcids":["https://orcid.org/0000-0001-6522-3019"]},"institutions":[{"id":"https://openalex.org/I74656192","display_name":"University of G\u00f6ttingen","ror":"https://ror.org/01y9bpm73","country_code":"DE","type":"education","lineage":["https://openalex.org/I74656192"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bela Gipp","raw_affiliation_strings":["University of G\u00f6ttingen, G\u00f6ttingen, Germany"],"raw_orcid":"https://orcid.org/0000-0001-6522-3019","affiliations":[{"raw_affiliation_string":"University of G\u00f6ttingen, G\u00f6ttingen, Germany","institution_ids":["https://openalex.org/I74656192"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.2094,"has_fulltext":true,"cited_by_count":33,"citation_normalized_percentile":{"value":0.96699049,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2316","last_page":"2320"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.8022000193595886,"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":0.8022000193595886,"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.0714000016450882,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T13274","display_name":"Expert finding and Q&A systems","score":0.029899999499320984,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/large-language-models","display_name":"large language models","score":0.996999979019165},{"id":"https://openalex.org/keywords/gpt-4","display_name":"GPT-4","score":0.9900000095367432},{"id":"https://openalex.org/keywords/llm-accuracy","display_name":"LLM accuracy","score":0.4580000042915344},{"id":"https://openalex.org/keywords/answer-quality-evaluation","display_name":"answer quality evaluation","score":0.5659999847412109},{"id":"https://openalex.org/keywords/llm-limitations","display_name":"LLM limitations","score":0.546999990940094}],"concepts":[{"id":"https://openalex.org/C9395851","wikidata":"https://www.wikidata.org/wiki/Q177929","display_name":"Stack (abstract data type)","level":2,"score":0.810100257396698},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.49551403522491455},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47177577018737793},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3229420781135559},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.28742432594299316}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3626772.3657945","doi":"https://doi.org/10.1145/3626772.3657945","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3626772.3657945","pdf_url":null,"source":{"id":"https://openalex.org/S4363608773","display_name":"International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2404.00344","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.00344","pdf_url":"https://arxiv.org/pdf/2404.00344","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:publications.goettingen-research-online.de:2/161765","doi":null,"is_oa":false,"landing_page_url":"https://resolver.sub.uni-goettingen.de/purl?gro-2/154588","pdf_url":null,"source":{"id":"https://openalex.org/S4306401634","display_name":"GoeScholar  The Publication Server of the Georg-August-Universit\u00e4t G\u00f6ttingen (Georg-August-Universit\u00e4t G\u00f6ttingen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210122495","host_organization_name":"Asklepios Klinik St. Georg","host_organization_lineage":["https://openalex.org/I4210122495"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.2404.00344","doi":"https://doi.org/10.48550/arxiv.2404.00344","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2404.00344","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2404.00344","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.00344","pdf_url":"https://arxiv.org/pdf/2404.00344","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3260395871","display_name":null,"funder_award_id":"437179652","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G4964679585","display_name":"Analyse mathematischer Ausdr\u00fccke zur Erkennung verschleierter wissenschaftlicher Plagiate","funder_award_id":"437179652","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G6761952205","display_name":null,"funder_award_id":"57515245","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320313139","display_name":"Nieders\u00e4chsische Ministerium f\u00fcr Wissenschaft und Kultur","ror":"https://ror.org/0116z8r77"},{"id":"https://openalex.org/F4320320875","display_name":"Deutscher Akademischer Austauschdienst","ror":"https://ror.org/039djdh30"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400526729.pdf","grobid_xml":"https://content.openalex.org/works/W4400526729.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W2951939640","https://openalex.org/W2962800603","https://openalex.org/W3097392354","https://openalex.org/W3134642945","https://openalex.org/W3210904070","https://openalex.org/W4226354959","https://openalex.org/W4382246105","https://openalex.org/W4384625799","https://openalex.org/W4384652592","https://openalex.org/W4384918448","https://openalex.org/W4385890378","https://openalex.org/W4386161583","https://openalex.org/W4386185625","https://openalex.org/W4387294612","https://openalex.org/W4387356138","https://openalex.org/W4387561528","https://openalex.org/W4387725649","https://openalex.org/W4388574960","https://openalex.org/W4390647650","https://openalex.org/W4402670119","https://openalex.org/W4412887680","https://openalex.org/W7039287486"],"related_works":["https://openalex.org/W7152402057","https://openalex.org/W7103374186","https://openalex.org/W4399554582","https://openalex.org/W4408793693","https://openalex.org/W4411757634","https://openalex.org/W6967224792","https://openalex.org/W7162792555","https://openalex.org/W4403809976","https://openalex.org/W7171394092","https://openalex.org/W4399281666"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4],"demonstrated":[5],"exceptional":[6],"capabilities":[7],"in":[8,57,170],"various":[9],"natural":[10],"language":[11],"tasks,":[12],"often":[13],"achieving":[14],"performances":[15],"that":[16,98,117,151],"surpass":[17],"those":[18],"of":[19,26,55,109,122,126,168],"humans.":[20],"Despite":[21],"these":[22],"advancements,":[23],"the":[24,39,53,64,84,96,100,105,138,165],"domain":[25],"mathematics":[27,134],"presents":[28],"a":[29,48,90],"distinctive":[30],"challenge,":[31],"primarily":[32],"due":[33],"to":[34,51,77,80],"its":[35,110],"specialized":[36],"structure":[37],"and":[38,107,124,136,179],"precision":[40],"it":[41,158],"demands.":[42],"In":[43],"this":[44],"work,":[45],"we":[46,62],"follow":[47],"two-step":[49],"approach":[50,141],"investigating":[52],"proficiency":[54],"LLMs":[56,130,169],"answering":[58,133],"mathematical":[59,173],"questions.":[60],"First,":[61],"employ":[63],"most":[65],"effective":[66],"LLMs,":[67],"as":[68],"identified":[69],"by":[70],"their":[71],"performance":[72],"on":[73,95,104,142],"math":[74],"question-answer":[75],"benchmarks,":[76],"generate":[78,155],"answers":[79,111],"78":[81],"questions":[82,135],"from":[83],"Math":[85],"Stack":[86],"Exchange":[87],"(MSE).":[88],"Second,":[89],"case":[91,148],"analysis":[92,149],"is":[93],"conducted":[94],"LLM":[97],"showed":[99],"highest":[101],"performance,":[102],"focusing":[103],"quality":[106],"accuracy":[108],"through":[112],"manual":[113],"evaluation.":[114],"We":[115,175],"found":[116],"GPT-4":[118,153],"performs":[119],"best":[120,140],"(nDCG":[121],"0.48":[123],"P@10":[125],"0.37)":[127],"amongst":[128],"existing":[129],"fine-tuned":[131],"for":[132,183],"outperforms":[137],"current":[139,166],"ArqMATH3":[143],"Task1,":[144],"considering":[145],"P@10.":[146],"Our":[147],"indicates":[150],"while":[152],"can":[154],"relevant":[156],"answers,":[157],"isn't":[159],"consistently":[160],"accurate.":[161],"This":[162],"paper":[163],"explores":[164],"limitations":[167],"navigating":[171],"complex":[172],"question-answering.":[174],"make":[176],"our":[177],"code":[178],"findings":[180],"publicly":[181],"available":[182],"research:":[184],"https://github.com/gipplab/LLM-Investig-MathStackExchange":[185]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":6}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2024-07-12T00:00:00"}