{"id":"https://openalex.org/W4416157181","doi":"https://doi.org/10.18653/v1/2026.findings-acl.571","title":"Evaluating Implicit Biases in LLM Reasoning through Logic Grid Puzzles","display_name":"Evaluating Implicit Biases in LLM Reasoning through Logic Grid Puzzles","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4416157181","doi":"https://doi.org/10.18653/v1/2026.findings-acl.571"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.571","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.571","pdf_url":"https://aclanthology.org/2026.findings-acl.571.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":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.571.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120347397","display_name":"Fatima Jahara","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fatima Jahara","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120595377","display_name":"Mark Dredze","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mark Dredze","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5102014871","display_name":"Sha\u0159on Levy","orcid":"https://orcid.org/0000-0001-6208-6928"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sharon Levy","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":0.01148851,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11755","last_page":"11780"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.29330000281333923,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.29330000281333923,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.08540000021457672,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.07829999923706055,"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/prime","display_name":"Prime (order theory)","score":0.6780999898910522},{"id":"https://openalex.org/keywords/implicit-association-test","display_name":"Implicit-association test","score":0.6090999841690063},{"id":"https://openalex.org/keywords/deductive-reasoning","display_name":"Deductive reasoning","score":0.5932999849319458},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.5304999947547913},{"id":"https://openalex.org/keywords/logical-reasoning","display_name":"Logical reasoning","score":0.4226999878883362},{"id":"https://openalex.org/keywords/logical-consequence","display_name":"Logical consequence","score":0.4138999879360199},{"id":"https://openalex.org/keywords/non-monotonic-logic","display_name":"Non-monotonic logic","score":0.3296000063419342}],"concepts":[{"id":"https://openalex.org/C184992742","wikidata":"https://www.wikidata.org/wiki/Q7243229","display_name":"Prime (order theory)","level":2,"score":0.6780999898910522},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6238999962806702},{"id":"https://openalex.org/C2779778163","wikidata":"https://www.wikidata.org/wiki/Q774081","display_name":"Implicit-association test","level":2,"score":0.6090999841690063},{"id":"https://openalex.org/C97364631","wikidata":"https://www.wikidata.org/wiki/Q484284","display_name":"Deductive reasoning","level":2,"score":0.5932999849319458},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.5304999947547913},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4490000009536743},{"id":"https://openalex.org/C43971567","wikidata":"https://www.wikidata.org/wiki/Q3142865","display_name":"Logical reasoning","level":2,"score":0.4226999878883362},{"id":"https://openalex.org/C134752490","wikidata":"https://www.wikidata.org/wiki/Q374182","display_name":"Logical consequence","level":2,"score":0.4138999879360199},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.3296000063419342},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.323199987411499},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.32249999046325684},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.30959999561309814},{"id":"https://openalex.org/C115086926","wikidata":"https://www.wikidata.org/wiki/Q17004651","display_name":"Causal reasoning","level":3,"score":0.30799999833106995},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C2775940519","wikidata":"https://www.wikidata.org/wiki/Q17067742","display_name":"Logic model","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C189352744","wikidata":"https://www.wikidata.org/wiki/Q1971461","display_name":"Social choice theory","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.26429998874664307},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.257099986076355}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.571","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.571","pdf_url":"https://aclanthology.org/2026.findings-acl.571.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"},{"id":"pmh:oai:arXiv.org:2511.06160","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2511.06160","pdf_url":"https://arxiv.org/pdf/2511.06160","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2511.06160","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.06160","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.571","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.571","pdf_url":"https://aclanthology.org/2026.findings-acl.571.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":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416157181.pdf","grobid_xml":"https://content.openalex.org/works/W4416157181.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"While":[0],"recent":[1],"safety":[2],"guardrails":[3],"effectively":[4],"suppress":[5],"overtly":[6],"biased":[7,80],"outputs,":[8],"subtler":[9],"forms":[10],"of":[11,53,65,112,139,152],"social":[12,54,145],"bias":[13],"emerge":[14],"during":[15],"complex":[16],"logical":[17,57],"reasoning":[18,58,151],"tasks":[19],"that":[20,43,124],"evade":[21],"current":[22],"evaluation":[23,32],"benchmarks.To":[24],"fill":[25],"this":[26],"gap,":[27],"we":[28],"introduce":[29],"a":[30,91],"new":[31],"framework,":[33],"PRIME":[34,140],"(Puzzle":[35],"Reasoning":[36],"for":[37,96,141],"Implicit":[38],"Biases":[39],"in":[40,62,77,148],"Model":[41],"Evaluation),":[42],"uses":[44],"logic":[45,66],"grid":[46],"puzzles":[47,67],"to":[48],"systematically":[49],"probe":[50],"the":[51,110,137,149],"influence":[52],"stereotypes":[55],"on":[56,118],"and":[59,71,79,85,98,108,143],"decision":[60],"making":[61],"LLMs.Our":[63],"use":[64],"enables":[68],"automatic":[69],"generation":[70],"verification,":[72],"as":[73,75],"well":[74],"variability":[76],"complexity":[78],"settings.PRIME":[81],"includes":[82],"stereotypical,":[83],"anti-stereotypical,":[84],"neutral":[86],"puzzle":[87,93,106],"variants":[88],"generated":[89],"from":[90],"shared":[92],"structure,":[94],"allowing":[95],"controlled":[97],"fine-grained":[99],"comparisons.We":[100],"evaluate":[101],"multiple":[102],"model":[103],"families":[104],"across":[105],"sizes":[107],"test":[109],"effectiveness":[111],"prompt-based":[113],"mitigation":[114],"strategies.Focusing":[115],"our":[116,121],"experiments":[117],"gender":[119],"stereotypes,":[120],"findings":[122],"highlight":[123],"models":[125],"consistently":[126],"reason":[127],"more":[128],"accurately":[129],"when":[130],"solutions":[131],"align":[132],"with":[133],"stereotypical":[134],"associations.This":[135],"demonstrates":[136],"significance":[138],"diagnosing":[142],"quantifying":[144],"biases":[146],"perpetuated":[147],"deductive":[150],"LLMs,":[153],"where":[154],"fairness":[155],"is":[156],"critical.":[157]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-12T00:00:00"}