{"id":"https://openalex.org/W7166798950","doi":"https://doi.org/10.18653/v1/2026.acl-long.719","title":"BenchMarker: An Education-Inspired Toolkit for Highlighting Flaws in Multiple-Choice Benchmarks","display_name":"BenchMarker: An Education-Inspired Toolkit for Highlighting Flaws in Multiple-Choice Benchmarks","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166798950","doi":"https://doi.org/10.18653/v1/2026.acl-long.719"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.719","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.719","pdf_url":"https://aclanthology.org/2026.acl-long.719.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.719.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139730387","display_name":"Nishant Balepur","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nishant Balepur","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125390950","display_name":"Bhavya Rajasekaran","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bhavya Rajasekaran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139848253","display_name":"Hyunjin Jane Oh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hyunjin Jane Oh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125398769","display_name":"Michael Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Xie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125387726","display_name":"Atrey Desai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Atrey Desai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139831424","display_name":"Vipul Gupta","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vipul Gupta","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102851918","display_name":"Steven James Moore","orcid":"https://orcid.org/0000-0003-1864-0076"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Steven James Moore","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139818165","display_name":"Eunsol Choi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eunsol Choi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139797652","display_name":"Rachel Rudinger","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rachel Rudinger","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139800553","display_name":"Jordan Lee Boyd-Graber","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jordan Lee Boyd-Graber","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.78822215,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"15793","last_page":"15824"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.25920000672340393,"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":0.25920000672340393,"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":0.1160999983549118,"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/T13629","display_name":"Text Readability and Simplification","score":0.05889999866485596,"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/key","display_name":"Key (lock)","score":0.2921000123023987},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.2476000040769577}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4993000030517578},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3255999982357025},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.32170000672340393},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.2915000021457672},{"id":"https://openalex.org/C55587333","wikidata":"https://www.wikidata.org/wiki/Q1133029","display_name":"Engineering ethics","level":1,"score":0.2915000021457672},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.25949999690055847},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.2476000040769577},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.23340000212192535},{"id":"https://openalex.org/C161191863","wikidata":"https://www.wikidata.org/wiki/Q199655","display_name":"Library science","level":1,"score":0.23340000212192535}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.719","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.719","pdf_url":"https://aclanthology.org/2026.acl-long.719.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.719","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.719","pdf_url":"https://aclanthology.org/2026.acl-long.719.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.818208634853363,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G5052875863","display_name":"Collaborative Research: RI: Medium: Hard Data to the Model: Personalized, Diverse Preferences for Language Models","funder_award_id":"2403436","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6317553775","display_name":"Graduate Research Fellowship Program (GRFP)","funder_award_id":"2236417","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8830764304","display_name":"CAREER: Robust, Fair, and Culturally Aware Commonsense Reasoning in Natural Language","funder_award_id":"2339746","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166798950.pdf","grobid_xml":"https://content.openalex.org/works/W7166798950.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Nishant":[0],"Balepur,":[1],"Bhavya":[2],"Rajasekaran,":[3],"Hyunjin":[4],"Jane":[5],"Oh,":[6],"Michael":[7],"Xie,":[8],"Atrey":[9],"Desai,":[10],"Vipul":[11],"Gupta,":[12],"Steven":[13],"James":[14],"Moore,":[15],"Eunsol":[16],"Choi,":[17],"Rachel":[18],"Rudinger,":[19],"Jordan":[20],"Lee":[21],"Boyd-Graber.":[22],"Proceedings":[23],"of":[24,29],"the":[25,30],"64th":[26],"Annual":[27],"Meeting":[28],"Association":[31],"for":[32],"Computational":[33],"Linguistics":[34],"(Volume":[35],"1:":[36],"Long":[37],"Papers).":[38],"2026.":[39]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}
