{"id":"https://openalex.org/W7140094739","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.269","title":"FLUKE: A Linguistically-Driven and Task-Agnostic Framework for Robustness Evaluation","display_name":"FLUKE: A Linguistically-Driven and Task-Agnostic Framework for Robustness Evaluation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140094739","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.269"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-eacl.269","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.269","pdf_url":"https://aclanthology.org/2026.findings-eacl.269.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: EACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-eacl.269.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yulia Otmakhova","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yulia Otmakhova","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Thinh Hung Truong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thinh Hung Truong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Rahmad Mahendra","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rahmad Mahendra","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zenan Zhai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zenan Zhai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Rongxin Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rongxin Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Daniel Beck","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel Beck","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Jey Han Lau","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jey Han Lau","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":0.24555804,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5103","last_page":"5123"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.1687999963760376,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.1687999963760376,"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/T10465","display_name":"Neurobiology of Language and Bilingualism","score":0.06549999862909317,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.041999999433755875,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.521399974822998},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.24529999494552612},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.22779999673366547},{"id":"https://openalex.org/keywords/control-system","display_name":"Control system","score":0.2142000049352646}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5543000102043152},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.521399974822998},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2712000012397766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25440001487731934},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25429999828338623},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.24529999494552612},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.24410000443458557},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.22779999673366547},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.2142000049352646},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.20900000631809235}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-eacl.269","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.269","pdf_url":"https://aclanthology.org/2026.findings-eacl.269.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: EACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-eacl.269","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.269","pdf_url":"https://aclanthology.org/2026.findings-eacl.269.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: EACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.5986255407333374,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140094739.pdf","grobid_xml":"https://content.openalex.org/works/W7140094739.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"present":[1],"FLUKE":[2],"(framework":[3],"for":[4,12,85,90,121,185],"linguistically-driven":[5],"and":[6,33,55,64,68,116],"task-agnostic":[7],"robustness":[8,15,108,119,170,183],"evaluation),":[9],"a":[10,156,160],"framework":[11],"assessing":[13],"model":[14,157,187],"through":[16],"systematic":[17,182],"minimal":[18],"variations":[19,25,76],"of":[20,74,155,181],"test":[21],"data.FLUKE":[22],"introduces":[23],"controlled":[24],"across":[26,57],"linguistic":[27,75,100,161],"levels":[28],"-from":[29],"orthography":[30],"to":[31,44,98,113,130,142,145,158,168,171],"dialect":[32],"style":[34,138],"-and":[35],"leverages":[36],"large":[37],"language":[38],"models":[39,54,125],"(LLMs)":[40],"with":[41,80,102],"human":[42],"validation":[43],"generate":[45],"modifications.We":[46],"demonstrate":[47],"FLUKE's":[48],"utility":[49],"by":[50],"evaluating":[51],"both":[52],"fine-tuned":[53],"LLMs":[56,93,104],"six":[58],"diverse":[59],"NLP":[60],"tasks":[61,87,111],"(four":[62],"classification":[63],"two":[65],"generation":[66,164],"tasks),":[67],"reveal":[69],"that":[70],"(1)":[71],"the":[72,153,179],"impact":[73],"is":[77],"highly":[78],"task-dependent,":[79],"some":[81,110],"tests":[82,147],"being":[83],"critical":[84],"certain":[86,99],"but":[88],"irrelevant":[89],"others;":[91],"(2)":[92],"still":[94],"exhibit":[95],"significant":[96],"brittleness":[97],"variations,":[101],"reasoning":[103],"surprisingly":[105],"showing":[106],"less":[107],"on":[109,174],"compared":[112,144],"base":[114],"models,":[115],"scaling":[117],"improving":[118],"only":[120],"surface-level":[122],"modifications;":[123],"(3)":[124],"are":[126],"overall":[127],"more":[128],"brittle":[129],"natural,":[131],"fluent":[132],"modifications":[133],"such":[134,148],"as":[135,149],"syntax":[136],"or":[137],"changes":[139],"(and":[140],"especially":[141],"negation),":[143],"corruption-style":[146],"letter":[150],"flipping;":[151],"(4)":[152],"ability":[154],"use":[159],"feature":[162,173],"in":[163],"does":[165],"not":[166],"correlate":[167],"its":[169],"this":[172],"downstream":[175],"tasks.These":[176],"findings":[177],"highlight":[178],"importance":[180],"testing":[184],"understanding":[186],"behaviors.":[188]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-02-27T00:00:00"}