{"id":"https://openalex.org/W4412377136","doi":"https://doi.org/10.1145/3726302.3730291","title":"CoLoTa: A Dataset for Entity-based Commonsense Reasoning over Long-Tail Knowledge","display_name":"CoLoTa: A Dataset for Entity-based Commonsense Reasoning over Long-Tail Knowledge","publication_year":2025,"publication_date":"2025-07-13","ids":{"openalex":"https://openalex.org/W4412377136","doi":"https://doi.org/10.1145/3726302.3730291"},"language":"en","primary_location":{"id":"doi:10.1145/3726302.3730291","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730291","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730291","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730291","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012568207","display_name":"Armin Toroghi","orcid":"https://orcid.org/0009-0007-8058-2088"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Armin Toroghi","raw_affiliation_strings":["University of Toronto, Toronto, ON, Canada"],"raw_orcid":"https://orcid.org/0009-0007-8058-2088","affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, ON, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113134733","display_name":"Willis Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Willis Guo","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0009-0003-5409-7768","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028174137","display_name":"Scott Sanner","orcid":"https://orcid.org/0000-0001-7984-8394"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Scott Sanner","raw_affiliation_strings":["University of Toronto, Toronto, ON, Canada"],"raw_orcid":"https://orcid.org/0000-0001-7984-8394","affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, ON, Canada","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3444","last_page":"3454"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9994999766349792,"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":0.9994999766349792,"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/T11719","display_name":"Data Quality and Management","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9984999895095825,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/commonsense-reasoning","display_name":"Commonsense reasoning","score":0.8532556295394897},{"id":"https://openalex.org/keywords/commonsense-knowledge","display_name":"Commonsense knowledge","score":0.8387629985809326},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6968975067138672},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49948692321777344},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.481894314289093},{"id":"https://openalex.org/keywords/knowledge-based-systems","display_name":"Knowledge-based systems","score":0.238851398229599}],"concepts":[{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.8532556295394897},{"id":"https://openalex.org/C30542707","wikidata":"https://www.wikidata.org/wiki/Q1603203","display_name":"Commonsense knowledge","level":3,"score":0.8387629985809326},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6968975067138672},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49948692321777344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.481894314289093},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.238851398229599}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3726302.3730291","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730291","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730291","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3726302.3730291","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730291","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730291","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412377136.pdf","grobid_xml":"https://content.openalex.org/works/W4412377136.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W2069065514","https://openalex.org/W2073302931","https://openalex.org/W2084987750","https://openalex.org/W2094728533","https://openalex.org/W2252136820","https://openalex.org/W2561529111","https://openalex.org/W2763039547","https://openalex.org/W2767322653","https://openalex.org/W2907262778","https://openalex.org/W2963101081","https://openalex.org/W2963995027","https://openalex.org/W2970062726","https://openalex.org/W2998617917","https://openalex.org/W3100058503","https://openalex.org/W3156366114","https://openalex.org/W3159959439","https://openalex.org/W4213069590","https://openalex.org/W4299527668","https://openalex.org/W4366999868","https://openalex.org/W4380353746","https://openalex.org/W4385570777","https://openalex.org/W4389519598","https://openalex.org/W4393160124","https://openalex.org/W4393160970","https://openalex.org/W4401042451","https://openalex.org/W4404782451","https://openalex.org/W4404783031","https://openalex.org/W4412230188"],"related_works":["https://openalex.org/W3035583586","https://openalex.org/W4320165839","https://openalex.org/W2151799802","https://openalex.org/W2196562041","https://openalex.org/W4385488510","https://openalex.org/W2073302931","https://openalex.org/W3206107299","https://openalex.org/W3082691151","https://openalex.org/W4287633646","https://openalex.org/W4378501473"],"abstract_inverted_index":{"The":[0],"rise":[1],"of":[2,66,98,113,135,216],"Large":[3],"Language":[4],"Models":[5],"(LLMs)":[6],"has":[7],"redefined":[8],"the":[9,55,133,145,212],"AI":[10],"landscape,":[11],"particularly":[12],"due":[13],"to":[14,17,42,138,152,180,205],"their":[15,24,43,177,203],"ability":[16],"encode":[18],"factual":[19],"and":[20,23,35,69,104,108,202,210],"commonsense":[21,74,114,167,184,199,213],"knowledge,":[22],"outstanding":[25],"performance":[26],"in":[27,45,144],"tasks":[28,72,107],"requiring":[29,73],"reasoning.":[30,168,185],"Despite":[31],"these":[32],"advances,":[33],"hallucinations":[34,70,206],"reasoning":[36,67,75,91,115,200,214],"errors":[37,68],"remain":[38],"a":[39,86,110,125,191],"significant":[40],"barrier":[41],"deployment":[44],"high-stakes":[46],"settings.":[47],"In":[48],"this":[49,82],"work,":[50],"we":[51,84,187],"observe":[52],"that":[53,96,119,156],"even":[54],"most":[56],"prominent":[57],"LLMs,":[58],"such":[59],"as":[60,124,150,190],"OpenAI-o1,":[61],"suffer":[62],"from":[63,101],"high":[64],"rates":[65],"on":[71,159,207],"over":[76,92],"obscure,":[77],"long-tail":[78,208],"entities.":[79],"To":[80],"investigate":[81],"limitation,":[83],"present":[85,143],"new":[87],"dataset":[88,131],"for":[89,194],"Commonsense":[90],"Long-Tail":[93],"entities":[94,209],"(CoLoTa),":[95],"consists":[97],"3,300":[99],"queries":[100,141,164,182],"question":[102],"answering":[103],"claim":[105],"verification":[106],"covers":[109],"diverse":[111],"range":[112],"skills.":[116],"We":[117],"remark":[118],"CoLoTa":[120,163,189],"can":[121],"also":[122,165],"serve":[123],"Knowledge":[126],"Graph":[127],"Question":[128],"Answering":[129],"(KGQA)":[130],"since":[132],"support":[134],"knowledge":[136,147],"required":[137],"answer":[139,181],"its":[140],"is":[142],"Wikidata":[146],"graph.":[148],"However,":[149],"opposed":[151],"existing":[153],"KGQA":[154,174,217],"benchmarks":[155],"merely":[157],"focus":[158],"factoid":[160],"questions,":[161],"our":[162],"require":[166],"Our":[169],"experiments":[170],"with":[171],"strong":[172],"LLM-based":[173],"methodologies":[175],"indicate":[176],"severe":[178],"inability":[179],"involving":[183],"Hence,":[186],"propose":[188],"novel":[192],"benchmark":[193],"assessing":[195],"both":[196],"(i)":[197],"LLM":[198],"capabilities":[201,215],"robustness":[204],"(ii)":[211],"methods.":[218]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2025-10-10T00:00:00"}