{"id":"https://openalex.org/W4416241961","doi":"https://doi.org/10.63317/4bcqprdhjoxv","title":"ObfusQAte: A Proposed Framework to Evaluate LLM Robustness on Obfuscated Factual Question Answering","display_name":"ObfusQAte: A Proposed Framework to Evaluate LLM Robustness on Obfuscated Factual Question Answering","publication_year":2026,"publication_date":"2026-04-30","ids":{"openalex":"https://openalex.org/W4416241961","doi":"https://doi.org/10.63317/4bcqprdhjoxv"},"language":"en","primary_location":{"id":"doi:10.63317/4bcqprdhjoxv","is_oa":false,"landing_page_url":"https://doi.org/10.63317/4bcqprdhjoxv","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","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.07321","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Shubhra Ghosh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shubhra Ghosh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Abhilekh Borah","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abhilekh Borah","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Aditya Kumar Guru","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aditya Kumar Guru","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5082286441","display_name":"Kripabandhu Ghosh","orcid":"https://orcid.org/0000-0002-8130-1221"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kripabandhu Ghosh","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":0.02333576,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5129","last_page":"5145"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.569599986076355,"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":0.569599986076355,"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/T11147","display_name":"Misinformation and Its Impacts","score":0.10509999841451645,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.04690000042319298,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.8267999887466431},{"id":"https://openalex.org/keywords/obfuscation","display_name":"Obfuscation","score":0.4823000133037567},{"id":"https://openalex.org/keywords/hallucinating","display_name":"Hallucinating","score":0.4507000148296356},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.39419999718666077}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8267999887466431},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7160999774932861},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5194000005722046},{"id":"https://openalex.org/C40305131","wikidata":"https://www.wikidata.org/wiki/Q2616305","display_name":"Obfuscation","level":2,"score":0.4823000133037567},{"id":"https://openalex.org/C2911011789","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Hallucinating","level":2,"score":0.4507000148296356},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4458000063896179},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.39419999718666077},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3855000138282776},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.3628999888896942},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26190000772476196}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.63317/4bcqprdhjoxv","is_oa":false,"landing_page_url":"https://doi.org/10.63317/4bcqprdhjoxv","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:2508.07321","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.07321","pdf_url":"https://arxiv.org/pdf/2508.07321","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.2508.07321","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.07321","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":"pmh:oai:arXiv.org:2508.07321","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.07321","pdf_url":"https://arxiv.org/pdf/2508.07321","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":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416241961.pdf","grobid_xml":"https://content.openalex.org/works/W4416241961.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"rapid":[1],"proliferation":[2],"of":[3,14,19,36],"Large":[4],"Language":[5],"Models":[6],"(LLMs)":[7],"has":[8],"significantly":[9],"contributed":[10],"to":[11,64,108],"the":[12,28,51],"development":[13],"equitable":[15],"AI":[16],"systems":[17],"capable":[18],"factual":[20],"question-answering":[21],"(QA).":[22],"However,":[23],"no":[24],"known":[25],"study":[26,101],"tests":[27],"LLMs'":[29],"robustness":[30,97],"when":[31,114],"presented":[32],"with":[33,59,116],"obfuscated":[34],"versions":[35],"questions.":[37],"To":[38,121],"systematically":[39],"evaluate":[40],"these":[41,84,117],"limitations,":[42],"we":[43,127],"propose":[44],"a":[45,55,91,106],"novel":[46],"technique,":[47],"ObfusQAte,":[48],"and":[49,78,98],"leveraging":[50],"same,":[52],"introduce":[53],"ObfusQA,":[54],"comprehensive,":[56],"first-of-its-kind":[57],"framework":[58],"multi-tiered":[60],"obfuscation":[61],"levels":[62],"designed":[63],"examine":[65],"LLM":[66,96],"capabilities":[67],"across":[68],"three":[69],"distinct":[70],"dimensions:":[71],"(i)":[72],"Named-Entity":[73],"Indirection,":[74,77],"(ii)":[75],"Distractor":[76],"(iii)":[79],"Contextual":[80],"Overload.":[81],"By":[82],"capturing":[83],"fine-grained":[85],"distinctions":[86],"in":[87,124],"language,":[88],"ObfusQA":[89],"provides":[90],"comprehensive":[92],"benchmark":[93],"for":[94],"evaluating":[95],"adaptability.":[99],"Our":[100],"observes":[102],"that":[103],"LLMs":[104],"exhibit":[105],"tendency":[107],"fail":[109],"or":[110],"generate":[111],"hallucinated":[112],"responses":[113],"confronted":[115],"increasingly":[118],"nuanced":[119],"variations.":[120],"foster":[122],"research":[123],"this":[125],"direction,":[126],"make":[128],"ObfusQAte":[129],"publicly":[130],"available.":[131]},"counts_by_year":[],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}