{"id":"https://openalex.org/W4406231189","doi":"https://doi.org/10.48550/arxiv.2501.04249","title":"IOLBENCH: Benchmarking LLMs on Linguistic Reasoning","display_name":"IOLBENCH: Benchmarking LLMs on Linguistic Reasoning","publication_year":2025,"publication_date":"2025-01-08","ids":{"openalex":"https://openalex.org/W4406231189","doi":"https://doi.org/10.48550/arxiv.2501.04249"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2501.04249","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.04249","pdf_url":"https://arxiv.org/pdf/2501.04249","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2501.04249","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112765131","display_name":"SUNIL AUDICH S. P. GOYAL","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Goyal, Satyam","raw_affiliation_strings":["University of Michigan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047523675","display_name":"Soham Dan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dan, Soham","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.48539999127388,"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":0.48539999127388,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.47609999775886536,"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/T10034","display_name":"Syntax, Semantics, Linguistic Variation","score":0.01209999993443489,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/linguistic-reasoning","display_name":"linguistic reasoning","score":0.7279999852180481},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8859999775886536},{"id":"https://openalex.org/keywords/benchmark-dataset","display_name":"benchmark dataset","score":0.6690000295639038},{"id":"https://openalex.org/keywords/rule-abstraction","display_name":"rule abstraction","score":0.7009999752044678},{"id":"https://openalex.org/keywords/compositional-generalization","display_name":"compositional generalization","score":0.9909999966621399},{"id":"https://openalex.org/keywords/syntax","display_name":"syntax","score":0.7440000176429749},{"id":"https://openalex.org/keywords/morphology-linguistics","display_name":"morphology (linguistics)","score":0.9909999966621399},{"id":"https://openalex.org/keywords/phonology","display_name":"phonology","score":1.0},{"id":"https://openalex.org/keywords/semantics","display_name":"semantics","score":0.9760000109672546}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7525458335876465},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4898521602153778},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.18423029780387878},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.10839658975601196},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.06612735986709595}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2501.04249","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.04249","pdf_url":"https://arxiv.org/pdf/2501.04249","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2501.04249","doi":"https://doi.org/10.48550/arxiv.2501.04249","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2501.04249","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2501.04249","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.04249","pdf_url":"https://arxiv.org/pdf/2501.04249","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4406231189.pdf","grobid_xml":"https://content.openalex.org/works/W4406231189.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7203786259","https://openalex.org/W7161579947","https://openalex.org/W4415202964","https://openalex.org/W4403746687","https://openalex.org/W4415798445","https://openalex.org/W4400064586","https://openalex.org/W4416045839","https://openalex.org/W7166886971","https://openalex.org/W4412887876","https://openalex.org/W7103104089"],"abstract_inverted_index":{"Despite":[0],"the":[1,31,87,107,114,132,170],"remarkable":[2],"advancements":[3],"and":[4,63,71,92,125,134,175],"widespread":[5],"applications":[6],"of":[7,35,73,89,100,116,137,163,172],"deep":[8],"neural":[9],"networks,":[10],"their":[11,147],"ability":[12],"to":[13,68,80,112,155],"perform":[14],"reasoning":[15,33,148],"tasks":[16,77],"remains":[17],"limited,":[18],"particularly":[19,119],"in":[20,82,120,140],"domains":[21],"requiring":[22,86],"structured,":[23],"abstract":[24],"thought.":[25],"In":[26],"this":[27],"paper,":[28],"we":[29,103,153],"investigate":[30],"linguistic":[32,84,90,117,141],"capabilities":[34],"state-of-the-art":[36],"large":[37],"language":[38],"models":[39,79,110,139,161],"(LLMs)":[40],"by":[41],"introducing":[42,151],"IOLBENCH,":[43,152],"a":[44],"novel":[45],"benchmark":[46],"derived":[47],"from":[48,94],"International":[49],"Linguistics":[50],"Olympiad":[51],"(IOL)":[52],"problems.":[53],"This":[54],"dataset":[55],"encompasses":[56],"diverse":[57],"problems":[58],"testing":[59],"syntax,":[60],"morphology,":[61],"phonology,":[62],"semantics,":[64],"all":[65],"carefully":[66],"designed":[67],"be":[69],"self-contained":[70],"independent":[72],"external":[74],"knowledge.":[75],"These":[76],"challenge":[78],"engage":[81],"metacognitive":[83],"reasoning,":[85,165],"deduction":[88],"rules":[91],"patterns":[93],"minimal":[95],"examples.":[96],"Through":[97],"extensive":[98],"benchmarking":[99],"leading":[101],"LLMs,":[102],"find":[104],"that":[105],"even":[106],"most":[108],"advanced":[109],"struggle":[111],"handle":[113],"intricacies":[115],"complexity,":[118],"areas":[121],"demanding":[122],"compositional":[123],"generalization":[124],"rule":[126],"abstraction.":[127],"Our":[128],"analysis":[129],"highlights":[130],"both":[131],"strengths":[133],"persistent":[135],"limitations":[136],"current":[138],"problem-solving,":[142],"offering":[143],"valuable":[144],"insights":[145],"into":[146,159],"capabilities.":[149],"By":[150],"aim":[154],"foster":[156],"further":[157],"research":[158],"developing":[160],"capable":[162],"human-like":[164],"with":[166],"broader":[167],"implications":[168],"for":[169],"fields":[171],"computational":[173],"linguistics":[174],"artificial":[176],"intelligence.":[177]},"counts_by_year":[],"updated_date":"2026-10-03T13:16:28.481748","created_date":"2025-01-10T00:00:00"}
