{"id":"https://openalex.org/W7160014640","doi":"https://doi.org/10.63317/2jvxj7kwecuo","title":"CRiT-QA: Evaluating Multi-hop Reasoning with Counterfactual Chains and Distractor Traps","display_name":"CRiT-QA: Evaluating Multi-hop Reasoning with Counterfactual Chains and Distractor Traps","publication_year":2026,"publication_date":"2026-04-30","ids":{"openalex":"https://openalex.org/W7160014640","doi":"https://doi.org/10.63317/2jvxj7kwecuo"},"language":null,"primary_location":{"id":"doi:10.63317/2jvxj7kwecuo","is_oa":false,"landing_page_url":"https://doi.org/10.63317/2jvxj7kwecuo","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2607.10562","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135242185","display_name":"Jungmin Yun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jungmin Yun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125728928","display_name":"June Hyoung Kwon","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"June Hyoung Kwon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135172007","display_name":"Youngbin Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Youngbin Kim","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":0.41639754,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5246","last_page":"5255"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11010","display_name":"Logic, Reasoning, and Knowledge","score":0.33469998836517334,"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/T11010","display_name":"Logic, Reasoning, and Knowledge","score":0.33469998836517334,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.12970000505447388,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.09160000085830688,"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/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.6588000059127808},{"id":"https://openalex.org/keywords/motivated-reasoning","display_name":"Motivated reasoning","score":0.2303999960422516},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.21969999372959137}],"concepts":[{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.6588000059127808},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44839999079704285},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4408999979496002},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3239000141620636},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28619998693466187},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2687999904155731},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.24879999458789825},{"id":"https://openalex.org/C2776325391","wikidata":"https://www.wikidata.org/wiki/Q6917865","display_name":"Motivated reasoning","level":3,"score":0.2303999960422516},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.22120000422000885},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.21969999372959137}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.63317/2jvxj7kwecuo","is_oa":false,"landing_page_url":"https://doi.org/10.63317/2jvxj7kwecuo","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2607.10562","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2607.10562","pdf_url":"https://arxiv.org/pdf/2607.10562","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2607.10562","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2607.10562","pdf_url":"https://arxiv.org/pdf/2607.10562","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"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G13572568","display_name":null,"funder_award_id":"RS-2021-II211341","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G4244160943","display_name":null,"funder_award_id":"RS-2021-II211341","funder_id":"https://openalex.org/F4320321202","funder_display_name":"Chung-Ang University"},{"id":"https://openalex.org/G552592315","display_name":null,"funder_award_id":"RS-2021-II211341","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320321202","display_name":"Chung-Ang University","ror":"https://ror.org/01r024a98"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7160014640.pdf","grobid_xml":"https://content.openalex.org/works/W7160014640.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Evaluating":[0],"the":[1,42,59,124],"multi-hop":[2,21,168],"reasoning":[3,97,111,126,169],"capabilities":[4],"of":[5,48],"large":[6],"language":[7],"models":[8,15,121],"remains":[9],"a":[10,75,161,172],"significant":[11],"challenge.":[12],"Although":[13],"current":[14],"achieve":[16],"strong":[17],"results":[18],"on":[19,34,86,142],"existing":[20],"question":[22],"answering":[23],"datasets,":[24,147],"such":[25,51],"performance":[26,140],"often":[27],"masks":[28],"two":[29],"critical":[30],"vulnerabilities:":[31],"(1)":[32],"reliance":[33,85],"internal":[35],"parametric":[36],"knowledge":[37,88],"rather":[38,128],"than":[39,129],"adherence":[40],"to":[41,79,122,145,151],"provided":[43],"context,":[44],"and":[45,89,154,170],"(2)":[46],"exploitation":[47],"dataset":[49,76],"shortcuts,":[50],"as":[52,160],"single-document":[53],"cues":[54],"or":[55],"type-matching,":[56],"that":[57,113,136],"diminish":[58],"need":[60],"for":[61,165,174],"genuine":[62,167],"evidence":[63],"aggregation":[64],"across":[65],"multiple":[66],"documents.":[67],"We":[68],"introduce":[69],"CRiT-QA":[70,94,143,157],"(Counterfactual":[71],"Reasoning":[72],"with":[73,99],"Traps),":[74],"explicitly":[77],"designed":[78],"address":[80],"both":[81],"limitations.":[82],"To":[83],"neutralize":[84],"memorized":[87],"enforce":[90],"strict":[91],"context":[92],"dependency,":[93],"transforms":[95],"factual":[96],"chains":[98],"counterfactual":[100,152],"entities.":[101],"Furthermore,":[102],"it":[103],"injects":[104],"multi-anchor":[105],"distractor":[106,155],"chains,":[107],"plausible":[108],"but":[109],"incorrect":[110],"paths":[112],"diverge":[114],"at":[115],"different":[116],"hops.":[117],"These":[118],"traps":[119],"require":[120],"follow":[123],"entire":[125],"process":[127],"exploiting":[130],"shallow":[131],"heuristics.":[132],"Our":[133],"experiments":[134],"show":[135],"LLMs":[137],"exhibit":[138],"substantial":[139],"degradation":[141],"compared":[144],"standard":[146],"exposing":[148],"their":[149],"vulnerability":[150],"conditions":[153],"traps.":[156],"thus":[158],"serves":[159],"rigorous":[162],"diagnostic":[163],"tool":[164],"evaluating":[166],"provides":[171],"foundation":[173],"developing":[175],"more":[176],"reliable,":[177],"evidence-grounded":[178],"LLMs.":[179]},"counts_by_year":[],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2026-05-05T00:00:00"}
