{"id":"https://openalex.org/W6912294418","doi":"https://doi.org/10.5281/zenodo.16731584","title":"Incorrect Context Uncertainty","display_name":"Incorrect Context Uncertainty","publication_year":2025,"publication_date":"2025-08-03","ids":{"openalex":"https://openalex.org/W6912294418","doi":"https://doi.org/10.5281/zenodo.16731584"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.16731584","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.16731584","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.16731584","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Medina, Johanne Gren","orcid":"https://orcid.org/0000-0003-0642-7681"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Medina, Johanne Gren","raw_affiliation_strings":["Qatar Computing Research Institute"],"raw_orcid":"https://orcid.org/0000-0003-0642-7681","affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhou, Tianyi","orcid":"https://orcid.org/0000-0001-9566-8035"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Zhou, Tianyi","raw_affiliation_strings":["KTH Royal Institute of Technology"],"raw_orcid":"https://orcid.org/0000-0001-9566-8035","affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":null,"display_name":"Chawla, Sanjay","orcid":"https://orcid.org/0000-0002-8102-2572"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chawla, Sanjay","raw_affiliation_strings":["Qatar Computing Research Institute"],"raw_orcid":"https://orcid.org/0000-0002-8102-2572","affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5120000243186951,"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":0.5120000243186951,"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":0.07090000063180923,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.06239999830722809,"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/context","display_name":"Context (archaeology)","score":0.5884000062942505},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5457000136375427},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5289000272750854},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.49410000443458557},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.3781000077724457}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6740999817848206},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5884000062942505},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5457000136375427},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5289000272750854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5242999792098999},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.49410000443458557},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42669999599456787},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3831000030040741},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.3781000077724457},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.32350000739097595},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3111000061035156},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.3021000027656555},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.26570001244544983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.16731584","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.16731584","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.16731584","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.16731584","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"dataset"},"sustainable_development_goals":[{"score":0.8283140659332275,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"To":[0],"evaluate":[1],"the":[2,18,43,58,65,77,99],"robustness":[3],"and":[4,21],"context":[5,28,47,89],"sensitivity":[6],"of":[7,67],"large":[8],"language":[9],"models":[10],"(LLMs),":[11],"we":[12,37],"construct":[13],"a":[14,39],"dataset":[15,78,101],"by":[16,92],"augmenting":[17],"widely-used":[19],"HotpotQA":[20,84],"Natural":[22],"Questions":[23],"(NQ)":[24],"datasets":[25],"with":[26,55],"incorrect":[27,54,68,88],"passages.":[29],"For":[30],"each":[31],"original":[32,81,100],"question":[33,75,82],"in":[34,76],"these":[35],"datasets,":[36],"generate":[38],"corresponding":[40],"variant":[41],"where":[42],"retrieved":[44],"or":[45,52,85],"provided":[46],"is":[48],"intentionally":[49],"misleading,":[50],"irrelevant,":[51],"factually":[53],"respect":[56],"to":[57,63],"question.":[59],"This":[60],"allows":[61],"us":[62],"analyze":[64],"influence":[66],"contextual":[69],"grounding":[70],"on":[71],"model":[72,136],"behavior.":[73],"Each":[74],"includes:":[79],"The":[80,95,106],"(from":[83],"NQ),":[86],"An":[87],"passage":[90],"(generated":[91],"GPT4.1":[93],"mini),":[94],"gold":[96],"answer":[97],"from":[98,116,130,137],"(used":[102],"only":[103],"for":[104],"reference),":[105],"generated":[107],"responses":[108],"+":[109,111,113],"logits":[110],"probabilities":[112],"additional":[114],"metadata":[115],"three":[117],"LLMs:":[118],"Fanar-9B:":[119],"Our":[120],"in-house":[121],"Arabic-English":[122],"bilingual":[123],"model,":[124],"Qwen-7B-Chat:":[125],"A":[126,133],"state-of-the-art":[127],"open-source":[128],"LLM":[129],"Alibaba,":[131],"Gemma-13B-IT:":[132],"strong":[134],"instruction-tuned":[135],"Google.":[138]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}