{"id":"https://openalex.org/W4412886797","doi":"https://doi.org/10.18653/v1/2025.acl-long.75","title":"Wait, that\u2019s not an option: LLMs Robustness with Incorrect Multiple-Choice Options","display_name":"Wait, that\u2019s not an option: LLMs Robustness with Incorrect Multiple-Choice Options","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412886797","doi":"https://doi.org/10.18653/v1/2025.acl-long.75"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.75","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.75","pdf_url":"https://aclanthology.org/2025.acl-long.75.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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.75.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5099055016","display_name":"Gracjan G\u00f3ral","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gracjan G\u00f3ral","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030501571","display_name":"Emilia Wi\u015bnios","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Emilia Wi\u015bnios","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025494465","display_name":"Piotr Sankowski","orcid":"https://orcid.org/0000-0002-0907-3754"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Piotr Sankowski","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5088210639","display_name":"Pawe\u0142 Budzianowski","orcid":"https://orcid.org/0000-0003-0013-7931"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pawe\u0142 Budzianowski","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":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1495","last_page":"1515"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11976","display_name":"Capital Investment and Risk Analysis","score":0.9423999786376953,"subfield":{"id":"https://openalex.org/subfields/2003","display_name":"Finance"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11976","display_name":"Capital Investment and Risk Analysis","score":0.9423999786376953,"subfield":{"id":"https://openalex.org/subfields/2003","display_name":"Finance"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11182","display_name":"Auction Theory and Applications","score":0.9347000122070312,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7533530592918396},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.46076062321662903},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.35926997661590576},{"id":"https://openalex.org/keywords/risk-analysis","display_name":"Risk analysis (engineering)","score":0.3370351791381836},{"id":"https://openalex.org/keywords/actuarial-science","display_name":"Actuarial science","score":0.3323252499103546},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.26569920778274536},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.06429088115692139}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7533530592918396},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.46076062321662903},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.35926997661590576},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.3370351791381836},{"id":"https://openalex.org/C162118730","wikidata":"https://www.wikidata.org/wiki/Q1128453","display_name":"Actuarial science","level":1,"score":0.3323252499103546},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.26569920778274536},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.06429088115692139},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.75","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.75","pdf_url":"https://aclanthology.org/2025.acl-long.75.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.75","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.75","pdf_url":"https://aclanthology.org/2025.acl-long.75.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":[{"id":"https://openalex.org/F4320326815","display_name":"Infrastruktura PL-Grid","ror":null},{"id":"https://openalex.org/F4320337160","display_name":"Academic Computer Centre Cyfronet, AGH University of Science and Technology","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412886797.pdf","grobid_xml":"https://content.openalex.org/works/W4412886797.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4391375266","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":{"This":[0],"work":[1],"introduces":[2],"a":[3,88],"novel":[4],"framework":[5],"for":[6,98,142,148],"evaluating":[7],"LLMs'":[8],"capacity":[9],"to":[10,44,67,77],"balance":[11],"instruction-following":[12,94],"with":[13,18,57,83,96,139],"critical":[14,136],"reasoning":[15,137],"when":[16,81],"presented":[17],"multiple-choice":[19],"questions":[20],"containing":[21],"no":[22],"valid":[23],"answers.Through":[24],"systematic":[25],"evaluation":[26],"across":[27],"arithmetic,":[28],"domainspecific":[29],"knowledge,":[30],"and":[31,123,133],"high-stakes":[32],"medical":[33],"decision":[34],"tasks,":[35],"we":[36],"demonstrate":[37],"that":[38,55,62],"posttraining":[39],"aligned":[40],"models":[41,50],"often":[42],"default":[43,79],"selecting":[45],"invalid":[46,84],"options,":[47],"while":[48],"base":[49],"exhibit":[51],"improved":[52],"refusal":[53],"capabilities":[54],"scale":[56],"model":[58,119],"size.Our":[59],"analysis":[60],"reveals":[61],"alignment":[63,131],"techniques,":[64,122],"though":[65],"intended":[66],"enhance":[68],"helpfulness,":[69],"can":[70],"inadvertently":[71],"impair":[72],"models'":[73],"reflective":[74],"judgment-the":[75],"ability":[76],"override":[78],"behaviors":[80],"faced":[82],"options.We":[85],"additionally":[86],"conduct":[87],"parallel":[89],"human":[90,105],"study":[91],"showing":[92],"similar":[93],"biases,":[95],"implications":[97,141],"how":[99],"these":[100],"biases":[101],"may":[102],"propagate":[103],"through":[104],"feedback":[106],"datasets":[107],"used":[108],"in":[109],"alignment.We":[110],"provide":[111],"extensive":[112],"ablation":[113],"studies":[114],"examining":[115],"the":[116],"impact":[117],"of":[118,135],"size,":[120],"training":[121],"prompt":[124],"engineering.Our":[125],"findings":[126],"highlight":[127],"fundamental":[128],"tensions":[129],"between":[130],"optimization":[132],"preservation":[134],"capabilities,":[138],"important":[140],"developing":[143],"more":[144],"robust":[145],"AI":[146],"systems":[147],"real-world":[149],"deployment.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
