{"id":"https://openalex.org/W4412945276","doi":"https://doi.org/10.18653/v1/2025.acl-long.627","title":"Beyond Surface Simplicity: Revealing Hidden Reasoning Attributes for Precise Commonsense Diagnosis","display_name":"Beyond Surface Simplicity: Revealing Hidden Reasoning Attributes for Precise Commonsense Diagnosis","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945276","doi":"https://doi.org/10.18653/v1/2025.acl-long.627"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.627","doi":"https://doi.org/10.18653/v1/2025.acl-long.627","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.627","pdf_url":"https://aclanthology.org/2025.acl-long.627.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2025.acl-long.627.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104243868","display_name":"Huijun Lian","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huijun Lian","raw_affiliation_strings":["Beijing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zekai Sun","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zekai Sun","raw_affiliation_strings":["Beijing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084927370","display_name":"Keqi Chen","orcid":"https://orcid.org/0000-0001-9383-9910","observed_orcids":["https://orcid.org/0000-0001-9383-9910"]},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Keqi Chen","raw_affiliation_strings":["Beijing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033063238","display_name":"Yingming Gao","orcid":"https://orcid.org/0000-0001-5881-3723","observed_orcids":["https://orcid.org/0000-0001-5881-3723"]},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingming Gao","raw_affiliation_strings":["Beijing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110683071","display_name":"Ya Li","orcid":"https://orcid.org/0009-0004-3095-3707","observed_orcids":["https://orcid.org/0009-0004-3095-3707"]},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ya Li","raw_affiliation_strings":["Beijing University of Posts and Telecommunications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12820","last_page":"12835"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.7803000211715698,"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":0.7803000211715698,"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":0.12929999828338623,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.029600000008940697,"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-question-answering","display_name":"commonsense question answering","score":0.9380000233650208},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.6819999814033508}],"concepts":[{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.8176000714302063},{"id":"https://openalex.org/C2776372474","wikidata":"https://www.wikidata.org/wiki/Q508291","display_name":"Simplicity","level":2,"score":0.780716061592102},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6666502356529236},{"id":"https://openalex.org/C30542707","wikidata":"https://www.wikidata.org/wiki/Q1603203","display_name":"Commonsense knowledge","level":3,"score":0.4918351173400879},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49175241589546204},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3658187985420227},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.16782605648040771},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.12436133623123169},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.1095111072063446}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.627","doi":"https://doi.org/10.18653/v1/2025.acl-long.627","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.627","pdf_url":"https://aclanthology.org/2025.acl-long.627.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.627","doi":"https://doi.org/10.18653/v1/2025.acl-long.627","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.627","pdf_url":"https://aclanthology.org/2025.acl-long.627.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2217149964","display_name":null,"funder_award_id":"2023RC73","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G2249315591","display_name":null,"funder_award_id":"62271083","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5362841155","display_name":null,"funder_award_id":"62271083","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412945276.pdf","grobid_xml":"https://content.openalex.org/works/W4412945276.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W2950339735","https://openalex.org/W2968629361","https://openalex.org/W4404370677","https://openalex.org/W4410357164","https://openalex.org/W4411119124"],"related_works":["https://openalex.org/W4411120074","https://openalex.org/W7144936336","https://openalex.org/W1541261843","https://openalex.org/W7166873032","https://openalex.org/W4401042462","https://openalex.org/W4415278945","https://openalex.org/W7168388712","https://openalex.org/W3207553988","https://openalex.org/W3216671886","https://openalex.org/W2963995027"],"abstract_inverted_index":{"Commonsense":[0],"question":[1],"answering":[2,16],"(QA)":[3],"are":[4],"widely":[5],"used":[6],"to":[7,47,66,179],"evaluate":[8],"the":[9,54,97,101,147,167],"commonsense":[10,17,38,73,93,161,172,182],"abilities":[11],"of":[12,45,72],"large":[13],"language":[14],"models.However,":[15],"questions":[18,39,94],"correctly":[19],"requires":[20],"not":[21],"only":[22],"knowledge":[23,74,98],"but":[24,150],"also":[25],"reasoning-even":[26],"for":[27,109,157],"seemingly":[28],"simple":[29],"questions.We":[30],"demonstrate":[31],"that":[32,87,123,130],"such":[33],"hidden":[34,60,89,140,168],"reasoning":[35,61,76,90,102,141,162,169],"attributes":[36,91,142,170],"in":[37,53,171],"can":[40],"lead":[41],"evaluation":[42],"accuracy":[43],"differences":[44],"up":[46],"24.8%":[48],"across":[49],"different":[50],"difficulty":[51,135],"levels":[52,71],"same":[55],"benchmark.Current":[56],"benchmarks":[57,132],"overlook":[58],"these":[59],"attributes,":[62],"making":[63],"it":[64],"difficult":[65],"assess":[67],"a":[68,84,159,176],"model's":[69,160],"specific":[70],"and":[75,118,154,165],"ability.To":[77],"address":[78],"this":[79],"issue,":[80],"we":[81],"introduce":[82],"Re-ComSBench,":[83],"novel":[85],"framework":[86],"reveals":[88],"behind":[92],"by":[95],"leveraging":[96],"generated":[99],"during":[100],"process.Additionally,":[103],"ReComSBench":[104,124,174],"proposes":[105],"three":[106],"new":[107,177],"metrics":[108],"decoupled":[110],"evaluation:":[111],"Knowledge":[112,119],"Balanced":[113],"Accuracy,":[114],"Marginal":[115],"Sampling":[116],"Gain,":[117],"Coverage":[120],"Ratio.Experiments":[121],"show":[122],"provides":[125],"insights":[126],"into":[127],"model":[128],"performance":[129],"traditional":[131],"cannot":[133],"offer.The":[134],"stratification":[136],"based":[137],"on":[138],"revealed":[139],"performs":[143],"as":[144,146],"effectively":[145],"model-probabilitybased":[148],"approach":[149,178],"is":[151],"more":[152],"generalizable":[153],"better":[155],"suited":[156],"improving":[158],"abilities.By":[163],"uncovering":[164],"analyzing":[166],"data,":[173],"offers":[175],"enhancing":[180],"existing":[181],"benchmarks.":[183]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2025-10-10T00:00:00"}