{"id":"https://openalex.org/W4412886673","doi":"https://doi.org/10.18653/v1/2025.acl-long.169","title":"Which of These Best Describes Multiple Choice Evaluation with LLMs? A) Forced B) Flawed C) Fixable D) All of the Above","display_name":"Which of These Best Describes Multiple Choice Evaluation with LLMs? A) Forced B) Flawed C) Fixable D) All of the Above","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412886673","doi":"https://doi.org/10.18653/v1/2025.acl-long.169"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.169","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.169","pdf_url":"https://aclanthology.org/2025.acl-long.169.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.169.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091963084","display_name":"Nishant Balepur","orcid":null},"institutions":[{"id":"https://openalex.org/I126744593","display_name":"University of Maryland, Baltimore","ror":"https://ror.org/04rq5mt64","country_code":"US","type":"education","lineage":["https://openalex.org/I126744593"]},{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nishant Balepur","raw_affiliation_strings":["University of Maryland University of Maryland University of Maryland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland University of Maryland University of Maryland","institution_ids":["https://openalex.org/I66946132","https://openalex.org/I126744593"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082447472","display_name":"Rachel Rudinger","orcid":"https://orcid.org/0000-0002-5506-4701"},"institutions":[{"id":"https://openalex.org/I126744593","display_name":"University of Maryland, Baltimore","ror":"https://ror.org/04rq5mt64","country_code":"US","type":"education","lineage":["https://openalex.org/I126744593"]},{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rachel Rudinger","raw_affiliation_strings":["University of Maryland University of Maryland University of Maryland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland University of Maryland University of Maryland","institution_ids":["https://openalex.org/I66946132","https://openalex.org/I126744593"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5092513269","display_name":"Jordan Lee Boyd-Graber","orcid":null},"institutions":[{"id":"https://openalex.org/I126744593","display_name":"University of Maryland, Baltimore","ror":"https://ror.org/04rq5mt64","country_code":"US","type":"education","lineage":["https://openalex.org/I126744593"]},{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jordan Lee Boyd-Graber","raw_affiliation_strings":["University of Maryland University of Maryland University of Maryland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland University of Maryland University of Maryland","institution_ids":["https://openalex.org/I66946132","https://openalex.org/I126744593"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":47.2084,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.99807319,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3394","last_page":"3418"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12755","display_name":"Legal Education and Practice Innovations","score":0.8198000192642212,"subfield":{"id":"https://openalex.org/subfields/3308","display_name":"Law"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12755","display_name":"Legal Education and Practice Innovations","score":0.8198000192642212,"subfield":{"id":"https://openalex.org/subfields/3308","display_name":"Law"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13643","display_name":"Artificial Intelligence in Law","score":0.7347999811172485,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T14230","display_name":"Occupational and Professional Licensing Regulation","score":0.7081999778747559,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/operations-research","display_name":"Operations research","score":0.3661677837371826},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.34971535205841064},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.219371497631073}],"concepts":[{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.3661677837371826},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.34971535205841064},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.219371497631073}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.169","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.169","pdf_url":"https://aclanthology.org/2025.acl-long.169.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 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.169","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.169","pdf_url":"https://aclanthology.org/2025.acl-long.169.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412886673.pdf","grobid_xml":"https://content.openalex.org/works/W4412886673.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Multiple":[0,156],"choice":[1,159],"question":[2,160],"answering":[3,161],"(MCQA)":[4,162],"is":[5,75,163,222,231],"popular":[6,217],"for":[7,20,48,166,173,246,346],"LLM":[8,38,116,221,305],"evaluation":[9,271],"due":[10],"to":[11,68,97,103,110,138,177,190,201,214,233,242,296,412],"its":[12,21,79,276],"simplicity":[13,174],"and":[14,41,57,63,86,106,121,175,181,196,273],"human-like":[15],"testing,":[16,152],"but":[17],"we":[18,90,114,134,141],"argue":[19],"reform.We":[22],"first":[23],"reveal":[24],"flaws":[25,287],"in":[26,118,145,255],"MCQA's":[27,291],"format,":[28,78],"as":[29],"it":[30,230],"struggles":[31],"to:":[32],"1)":[33,264],"test":[34,44,314,391,432],"generation/subjectivity;":[35],"2)":[36,274],"match":[37],"use":[39,244,254,306],"cases;":[40],"3)":[42],"fully":[43,313],"knowledge.We":[45],"instead":[46],"advocate":[47],"generative":[49,385],"formats":[50,386],"based":[51,149],"on":[52,150],"human":[53,178],"testing-where":[54],"LLMs":[55,200,283,347,352],"construct":[56],"explain":[58],"answers-better":[59],"capturing":[60],"user":[61],"needs":[62],"knowledge":[64,315,382],"while":[65],"remaining":[66],"easy":[67,189,345],"score.We":[69],"then":[70],"show":[71],"even":[72,225],"when":[73,197],"MCQA":[74,187,203,245,266,285,321],"a":[76,216,227,268],"useful":[77],"datasets":[80,277],"suffer":[81],"from:":[82],"leakage;":[83],"unanswerability;":[84],"shortcuts;":[85],"saturation.In":[87],"each":[88],"issue,":[89],"give":[91,369],"fixes":[92],"from":[93,377],"education,":[94],"like":[95],"rubrics":[96,405],"guide":[98],"MCQ":[99],"writing;":[100],"scoring":[101,411],"methods":[102],"bridle":[104],"guessing;":[105],"Item":[107],"Response":[108],"Theory":[109],"build":[111,215],"harder":[112,418],"MCQs.Lastly,":[113],"discuss":[115],"errors":[117],"MCQA-robustness,":[119],"biases,":[120],"unfaithful":[122,370],"explanations-showing":[123],"how":[124],"our":[125,206],"prior":[126],"solutions":[127],"better":[128,243],"measure":[129],"or":[130,224],"address":[131],"these":[132],"issues.While":[133],"do":[135,351],"not":[136],"need":[137],"desert":[139],"MCQA,":[140],"encourage":[142],"more":[143],"efforts":[144],"refining":[146],"the":[147,164],"task":[148],"educational":[151,404],"advancing":[153],"evaluations.":[154],"Questioning":[155],"Choice":[157],"QuestionsMultiple":[158],"standard":[165,269],"large":[167],"language":[168],"model":[169,270],"(LLM)":[170],"evaluations,":[171],"prized":[172],"similarity":[176],"testing":[179,236,248,383],"(Robinson":[180],"Wingate,":[182],"2023).When":[183],"designing":[184],"new":[185,199],"benchmarks,":[186],"seems":[188],"implement":[191],"(Guo":[192],"et":[193,209,258,435],"al.,":[194,210,259,436],"2023),":[195],"selecting":[198],"use,":[202],"leaderboards":[204],"inform":[205],"decisions":[207],"(Fourrier":[208],"2024).If":[211],"you":[212],"want":[213],"dataset,":[218],"prove":[219],"your":[220],"smart,":[223],"publish":[226],"position":[228,279],"paper,":[229],"hard":[232],"avoid":[234],"MCQA.Standardized":[235],"groups":[237],"have":[238,262,331],"long":[239],"explored":[240],"ways":[241],"student":[247],"(Angoff,":[249],"1971).But":[250],"despite":[251],"years":[252],"of":[253,430],"NLP":[256],"(Turney":[257],"2003),":[260],"few":[261],"asked:":[263],"should":[265],"be":[267],"format;":[272],"are":[275,325],"well-designed?This":[278],"paper":[280],"argues:":[281],"Evaluating":[282],"with":[284,290,304,320,354,394,420],"has":[286,427],"Q1.What's":[288],"wrong":[289,319],"format?A)":[292],"It":[293,311],"doesn't":[294,312],"apply":[295],"many":[297],"tasks":[298],"(":[299,308,316,327,334,340,348,359,365,372,387,397,406,415,424],"3.1)":[300],"B)":[301,329,361,389],"It's":[302],"misaligned":[303],"cases":[307],"3.2)":[309],"C)":[310,336,367,399],"3.3)":[317],"Q2.What's":[318],"datasets?A)":[322],"Test":[323],"sets":[324],"contaminated":[326],"5.1)":[328,398],"They":[330,337,356,362,368],"unanswerable":[332],"questions":[333,396],"5.2)":[335,407],"contain":[338],"shortcuts":[339],"5.3)":[341],"D)":[342,408],"They're":[343],"too":[344],"5.4)":[349],"Q3.How":[350],"struggle":[353],"MCQA?A)":[355,380],"lack":[357],"robustness":[358],"6.1)":[360],"exhibit":[363],"biases":[364],"6.2)":[366],"explanations":[371],"6.3)":[373],"Q4.How":[374],"can":[375],"insights":[376],"education":[378],"improve":[379],"Improve":[381],"via":[384],"4)":[388],"Combat":[390],"set":[392,433],"leakage":[393],"fresh":[395],"Write":[400],"MCQs":[401,419],"informed":[402],"by":[403],"Use":[409],"calibration":[410],"curb":[413],"guessing":[414],"5.3.1)E)":[416],"Find":[417],"item":[421],"response":[422],"theory":[423],"5.4.1)7":[425],"gpt-3":[426],"seen":[428],"45%":[429],"RACE's":[431],"(Sainz":[434],"2023).":[437]},"counts_by_year":[{"year":2026,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}