{"id":"https://openalex.org/W4412887729","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1031","title":"None of the Above, Less of the Right Parallel Patterns in Human and LLM Performance on Multi-Choice Questions Answering","display_name":"None of the Above, Less of the Right Parallel Patterns in Human and LLM Performance on Multi-Choice Questions Answering","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412887729","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1031"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.1031","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1031","pdf_url":"https://aclanthology.org/2025.findings-acl.1031.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.1031.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028150164","display_name":"Zhi Rui Tam","orcid":"https://orcid.org/0000-0001-9968-2416"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhi Rui Tam","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032589855","display_name":"Chunfei Wu","orcid":"https://orcid.org/0000-0001-7961-1186"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng-Kuang Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012260456","display_name":"Chieh-Yen Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chieh-Yen Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5058211616","display_name":"Yun-Nung Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yun-Nung Chen","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":1.9246,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.8494033,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"20112","last_page":"20134"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13274","display_name":"Expert finding and Q&A systems","score":0.9833999872207642,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T13274","display_name":"Expert finding and Q&A systems","score":0.9833999872207642,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10028","display_name":"Topic Modeling","score":0.9441999793052673,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9376000165939331,"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/computer-science","display_name":"Computer science","score":0.582403838634491},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.567557692527771},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4018441438674927}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.582403838634491},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.567557692527771},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4018441438674927}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.1031","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1031","pdf_url":"https://aclanthology.org/2025.findings-acl.1031.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.1031","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1031","pdf_url":"https://aclanthology.org/2025.findings-acl.1031.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412887729.pdf","grobid_xml":"https://content.openalex.org/works/W4412887729.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/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W2349927912"],"abstract_inverted_index":{"Multiple-choice":[0],"exam":[1],"questions":[2,134],"with":[3,40,104],"\"None":[4],"of":[5,79,153],"the":[6,44,66,84,154],"above\"":[7],"(NA)":[8],"options":[9,51,94],"have":[10],"been":[11],"extensively":[12],"studied":[13],"in":[14,17,141],"educational":[15],"testing,":[16],"which":[18],"existing":[19],"research":[20],"suggests":[21],"that":[22,60,81],"they":[23],"better":[24],"assess":[25],"true":[26],"knowledge.However,":[27],"their":[28],"impact":[29,106],"on":[30,43,107,115],"Large":[31],"Language":[32],"Models":[33],"(LLMs)":[34],"evaluation":[35],"remains":[36],"underexplored.Through":[37],"systematic":[38],"experiments":[39],"28":[41],"LLMs":[42,82],"MMLU":[45],"benchmark,":[46],"we":[47],"examine":[48],"how":[49],"NA":[50,61],"affect":[52],"model":[53],"performance":[54,74],"and":[55,90,132,175,179,184,192,197],"confidence":[56],"calibration.Our":[57],"analysis":[58],"reveals":[59],"options,":[62],"when":[63,95],"used":[64],"as":[65],"correct":[67],"answer,":[68],"lead":[69],"to":[70,87,138],"a":[71],"consistent":[72],"30-50%":[73],"drop":[75],"across":[76],"models":[77],"regardless":[78],"scale-suggesting":[80],"lack":[83],"meta-cognitive":[85],"ability":[86,137],"systematically":[88],"evaluate":[89],"reject":[91],"all":[92],"given":[93],"none":[96],"are":[97,156],"correct.This":[98],"degradation":[99],"shows":[100],"strong":[101],"domain":[102],"dependence,":[103],"minimal":[105],"mathematical":[108],"reasoning":[109],"(14.6%":[110],"drop)":[111],"but":[112],"severe":[113],"effects":[114],"tasks":[116],"requiring":[117],"uncertainty":[118,140],"handling":[119],"like":[120],"business":[121],"ethics":[122],"(48.1%":[123],"drop).Our":[124],"results":[125],"highlight":[126],"important":[127],"implications":[128],"for":[129],"benchmark":[130],"design":[131],"raise":[133],"about":[135],"LLMs'":[136],"handle":[139],"realworld":[142],"applications.":[143],"*":[144],"Equal":[145],"contributionStandard":[146],"choice":[147,150],"Answer":[148],"absent":[149],"Question:":[151],"Which":[152],"following":[155],"steroid-based":[157],"molecules?I.":[158],"Testosterone":[159],"(":[160,165],")":[161,166],"II.Triglycerides":[162],"()":[163,168],"III.Progesterone":[164],"IV.DNA":[167],"A.":[169,186],"I":[170,178,187],"only":[171,188],"B.":[172,189],"I,":[173,182,190,195],"II,":[174,191],"III":[176,180,193],"C.":[177,194],"D.":[181],"III,":[183,196],"IV":[185,198]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}