{"id":"https://openalex.org/W4416398377","doi":"https://doi.org/10.18653/v1/2026.acl-short.23","title":"Test-Time Reasoners Are Strategic Multiple-Choice Test-Takers","display_name":"Test-Time Reasoners Are Strategic Multiple-Choice Test-Takers","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4416398377","doi":"https://doi.org/10.18653/v1/2026.acl-short.23"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.acl-short.23","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-short.23","pdf_url":"https://aclanthology.org/2026.acl-short.23.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 2: Short Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-short.23.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091963084","display_name":"Nishant Balepur","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]},{"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":["New York University","University of Maryland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"University of Maryland","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Atrey Desai","orcid":null},"institutions":[{"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":"Atrey Desai","raw_affiliation_strings":["University of Maryland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082447472","display_name":"Rachel Rudinger","orcid":"https://orcid.org/0000-0002-5506-4701"},"institutions":[{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.02664132,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"250","last_page":"272"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5059999823570251,"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":0.5059999823570251,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0786999985575676,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.03929999843239784,"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/analytic-reasoning","display_name":"Analytic reasoning","score":0.49869999289512634},{"id":"https://openalex.org/keywords/deductive-reasoning","display_name":"Deductive reasoning","score":0.46549999713897705},{"id":"https://openalex.org/keywords/automated-reasoning","display_name":"Automated reasoning","score":0.4472000002861023},{"id":"https://openalex.org/keywords/psychology-of-reasoning","display_name":"Psychology of reasoning","score":0.4065999984741211},{"id":"https://openalex.org/keywords/verbal-reasoning","display_name":"Verbal reasoning","score":0.39730000495910645},{"id":"https://openalex.org/keywords/case-based-reasoning","display_name":"Case-based reasoning","score":0.3813999891281128},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.37860000133514404}],"concepts":[{"id":"https://openalex.org/C103057564","wikidata":"https://www.wikidata.org/wiki/Q4751139","display_name":"Analytic reasoning","level":3,"score":0.49869999289512634},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4799000024795532},{"id":"https://openalex.org/C97364631","wikidata":"https://www.wikidata.org/wiki/Q484284","display_name":"Deductive reasoning","level":2,"score":0.46549999713897705},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.4472000002861023},{"id":"https://openalex.org/C183521366","wikidata":"https://www.wikidata.org/wiki/Q7256422","display_name":"Psychology of reasoning","level":4,"score":0.4065999984741211},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3977999985218048},{"id":"https://openalex.org/C36964233","wikidata":"https://www.wikidata.org/wiki/Q7920942","display_name":"Verbal reasoning","level":3,"score":0.39730000495910645},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.39340001344680786},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.3813999891281128},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.37860000133514404},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.3465999960899353},{"id":"https://openalex.org/C2776325391","wikidata":"https://www.wikidata.org/wiki/Q6917865","display_name":"Motivated reasoning","level":3,"score":0.335099995136261},{"id":"https://openalex.org/C43971567","wikidata":"https://www.wikidata.org/wiki/Q3142865","display_name":"Logical reasoning","level":2,"score":0.3294999897480011},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.31630000472068787},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.31220000982284546},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.30570000410079956},{"id":"https://openalex.org/C86827895","wikidata":"https://www.wikidata.org/wiki/Q7098582","display_name":"Opportunistic reasoning","level":4,"score":0.3003999888896942},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.2904999852180481},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28769999742507935},{"id":"https://openalex.org/C2994050667","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstract reasoning","level":3,"score":0.2824000120162964},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.2806999981403351},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.2702000141143799}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.acl-short.23","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-short.23","pdf_url":"https://aclanthology.org/2026.acl-short.23.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 2: Short Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.07761","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2510.07761","pdf_url":"https://arxiv.org/pdf/2510.07761","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2510.07761","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.07761","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-short.23","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-short.23","pdf_url":"https://aclanthology.org/2026.acl-short.23.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 2: Short Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"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/W4416398377.pdf","grobid_xml":"https://content.openalex.org/works/W4416398377.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"now":[4],"give":[5],"reasoning":[6,33,52,67,77,103,138],"before":[7],"answering,":[8],"excelling":[9],"in":[10,35,71,81,84],"tasks":[11],"like":[12,119],"multiple-choice":[13],"question":[14],"answering":[15],"(MCQA).Yet,":[16],"a":[17,132],"concern":[18],"is":[19,45,96,130],"that":[20,127],"LLMs":[21,31,68],"do":[22],"not":[23],"solve":[24,69],"MCQs":[25,70],"as":[26,28],"intended,":[27],"work":[29],"finds":[30],"sans":[32],"succeed":[34],"MCQA":[36],"without":[37],"using":[38],"the":[39,87,100],"question,":[40],"i.e.,":[41],"choices-only.Such":[42],"partial-input":[43,128],"success":[44,95,129],"often":[46,78],"linked":[47],"to":[48,91],"trivial":[49],"shortcuts,":[50,93],"but":[51],"traces":[53,108,139],"could":[54,140],"reveal":[55],"if":[56],"choices-only":[57,74,94],"strategies":[58,118],"are":[59],"truly":[60],"shallow.To":[61],"examine":[62],"these":[63],"strategies,":[64],"we":[65,112,124,135],"have":[66],"full":[72,82],"and":[73,83,105],"inputs;":[75],"test-time":[76],"boosts":[79],"accuracy":[80],"choices-only,":[85],"half":[86],"time.While":[88],"possibly":[89],"due":[90],"shallow":[92],"barely":[97],"affected":[98],"by":[99],"length":[101],"of":[102],"traces,":[104],"after":[106],"finding":[107],"pass":[109],"faithfulness":[110],"tests,":[111],"show":[113],"they":[114],"use":[115],"less":[116,145],"problematic":[117,142,146],"inferring":[120],"missing":[121],"questions.In":[122],"all,":[123],"challenge":[125],"claims":[126],"always":[131],"flaw,":[133],"so":[134],"propose":[136],"how":[137],"separate":[141],"data":[143],"from":[144],"reasoning.":[147],"1G-Lite":[148],"G-Flash":[149],"G-Pro":[150],"GPT-5":[151,155],"Mini":[152],"GPT":[153],"4.1":[154],"C-Haiku":[156],"C-Sonnet":[157],"R":[158],"R+":[159],"DS-V3":[160],"Q-Instr":[161],"0.00":[162],"0.25":[163],"0.50":[164],"0":[165]},"counts_by_year":[],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-11T00:00:00"}