{"id":"https://openalex.org/W7166800770","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1003","title":"Rethinking Multiple-Choice Questions for RLVR: Unlocking Potential via Distractor Design","display_name":"Rethinking Multiple-Choice Questions for RLVR: Unlocking Potential via Distractor Design","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166800770","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1003"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1003","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1003","pdf_url":"https://aclanthology.org/2026.findings-acl.1003.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 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.1003.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139783996","display_name":"Xu Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu Guo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109786310","display_name":"Qiming Ge","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiming Ge","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025411088","display_name":"Jian Tong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jian Tong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139729416","display_name":"Kedi Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kedi Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139803434","display_name":"Jin Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139746151","display_name":"Xiaogui Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaogui Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139785776","display_name":"Xuan Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuan Gao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139786882","display_name":"Haijun Lv","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haijun Lv","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139743331","display_name":"Zhihui Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhihui Lu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139766022","display_name":"Yicheng Zou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yicheng Zou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139747848","display_name":"Qipeng Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qipeng Guo","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":0.79013725,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20092","last_page":"20113"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.21389999985694885,"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/T12031","display_name":"Speech and dialogue systems","score":0.21389999985694885,"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/T10028","display_name":"Topic Modeling","score":0.11840000003576279,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.07729999721050262,"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/perception","display_name":"Perception","score":0.2840999960899353},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.2615000009536743},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.2614000141620636},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.2606000006198883},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.26019999384880066}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4472000002861023},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3617999851703644},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2971999943256378},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.289900004863739},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2840999960899353},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.27950000762939453},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.258899986743927},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1003","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1003","pdf_url":"https://aclanthology.org/2026.findings-acl.1003.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 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.1003","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1003","pdf_url":"https://aclanthology.org/2026.findings-acl.1003.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 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2053532743","display_name":null,"funder_award_id":"72595845","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166800770.pdf","grobid_xml":"https://content.openalex.org/works/W7166800770.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"with":[2,101],"Verifiable":[3],"Rewards":[4],"(RLVR)":[5],"significantly":[6],"enhances":[7,136],"the":[8,55,67,148],"reasoning":[9,36],"capabilities":[10],"of":[11,25,69],"Large":[12],"Language":[13],"Models.When":[14],"applied":[15],"to":[16,50,120,147],"RLVR,":[17],"Multiple-Choice":[18],"Questions":[19],"(MCQs)":[20],"offer":[21],"a":[22,113],"scalable":[23],"source":[24],"verifiable":[26],"data":[27],"but":[28],"risk":[29],"inducing":[30],"reward":[31],"hacking,":[32],"where":[33],"models":[34],"shortcut":[35],"via":[37],"random":[38,94],"guessing":[39],"or":[40],"simple":[41],"elimination.Current":[42],"approaches":[43],"often":[44],"mitigate":[45,93],"this":[46,62],"by":[47,59,104],"converting":[48],"MCQs":[49],"open-ended":[51],"formats,":[52],"thereby":[53],"discarding":[54],"contrastive":[56],"signal":[57],"provided":[58],"expertdesigned":[60],"distractors.In":[61],"work,":[63],"we":[64,107],"systematically":[65],"investigate":[66],"impact":[68],"option":[70,82],"design":[71],"on":[72,128],"RLVR.Our":[73],"analysis":[74],"highlights":[75],"two":[76],"primary":[77],"insights:":[78],"(1)":[79],"Mismatches":[80],"in":[81,143],"counts":[83],"between":[84],"training":[85,99,145],"and":[86,124,139],"testing":[87],"degrade":[88],"performance.(2)":[89],"Strong":[90],"distractors":[91,119],"effectively":[92,135],"guessing,":[95],"enabling":[96],"effective":[97],"RLVR":[98,144],"even":[100],"2-way":[102],"questions.Motivated":[103],"these":[105],"findings,":[106],"propose":[108],"Iterative":[109],"Distractor":[110],"Curation":[111],"(IDC),":[112],"framework":[114],"that":[115,132],"actively":[116],"constructs":[117],"high-quality":[118],"block":[121],"elimination":[122],"shortcuts":[123],"promote":[125],"deep":[126],"reasoning.Experiments":[127],"various":[129],"benchmarks":[130],"demonstrate":[131],"our":[133],"method":[134],"distractor":[137],"quality":[138],"yields":[140],"significant":[141],"gains":[142],"compared":[146],"original":[149],"data.":[150]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}