{"id":"https://openalex.org/W4411630071","doi":"https://doi.org/10.18653/v1/2024.eacl-long.113","title":"CATfOOD: Counterfactual Augmented Training for Improving Out-of-Domain Performance and Calibration","display_name":"CATfOOD: Counterfactual Augmented Training for Improving Out-of-Domain Performance and Calibration","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4411630071","doi":"https://doi.org/10.18653/v1/2024.eacl-long.113"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.eacl-long.113","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.eacl-long.113","pdf_url":"https://aclanthology.org/2024.eacl-long.113.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":"Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.eacl-long.113.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022030280","display_name":"Rachneet Sachdeva","orcid":null},"institutions":[{"id":"https://openalex.org/I16718484","display_name":"Hess (United States)","ror":"https://ror.org/00zbk1w77","country_code":"US","type":"company","lineage":["https://openalex.org/I16718484"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rachneet Sachdeva","raw_affiliation_strings":["Ubiquitous Knowledge Processing Lab (UKP Lab) Department of Computer Science and Hessian Center for AI (hessian.AI ) Technical University of Darmstadt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ubiquitous Knowledge Processing Lab (UKP Lab) Department of Computer Science and Hessian Center for AI (hessian.AI ) Technical University of Darmstadt","institution_ids":["https://openalex.org/I16718484"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020691628","display_name":"Martin Tutek","orcid":"https://orcid.org/0000-0001-5227-5397"},"institutions":[{"id":"https://openalex.org/I16718484","display_name":"Hess (United States)","ror":"https://ror.org/00zbk1w77","country_code":"US","type":"company","lineage":["https://openalex.org/I16718484"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martin Tutek","raw_affiliation_strings":["Ubiquitous Knowledge Processing Lab (UKP Lab) Department of Computer Science and Hessian Center for AI (hessian.AI ) Technical University of Darmstadt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ubiquitous Knowledge Processing Lab (UKP Lab) Department of Computer Science and Hessian Center for AI (hessian.AI ) Technical University of Darmstadt","institution_ids":["https://openalex.org/I16718484"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027450194","display_name":"Iryna Gurevych","orcid":"https://orcid.org/0000-0003-2187-7621"},"institutions":[{"id":"https://openalex.org/I16718484","display_name":"Hess (United States)","ror":"https://ror.org/00zbk1w77","country_code":"US","type":"company","lineage":["https://openalex.org/I16718484"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Iryna Gurevych","raw_affiliation_strings":["Ubiquitous Knowledge Processing Lab (UKP Lab) Department of Computer Science and Hessian Center for AI (hessian.AI ) Technical University of Darmstadt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ubiquitous Knowledge Processing Lab (UKP Lab) Department of Computer Science and Hessian Center for AI (hessian.AI ) Technical University of Darmstadt","institution_ids":["https://openalex.org/I16718484"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I16718484"],"apc_list":null,"apc_paid":null,"fwci":0.9862,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.83100466,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1876","last_page":"1898"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12153","display_name":"Advanced Optical Sensing Technologies","score":0.832099974155426,"subfield":{"id":"https://openalex.org/subfields/3105","display_name":"Instrumentation"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12153","display_name":"Advanced Optical Sensing Technologies","score":0.832099974155426,"subfield":{"id":"https://openalex.org/subfields/3105","display_name":"Instrumentation"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12537","display_name":"Flow Measurement and Analysis","score":0.8122000098228455,"subfield":{"id":"https://openalex.org/subfields/2211","display_name":"Mechanics of Materials"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13928","display_name":"Advanced Sensor Technologies Research","score":0.7523000240325928,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.8321197032928467},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.7330743074417114},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6718604564666748},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6337972283363342},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5201661586761475},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34938228130340576},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13267406821250916},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08961594104766846},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08644124865531921}],"concepts":[{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.8321197032928467},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.7330743074417114},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6718604564666748},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6337972283363342},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5201661586761475},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34938228130340576},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13267406821250916},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08961594104766846},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08644124865531921},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.eacl-long.113","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.eacl-long.113","pdf_url":"https://aclanthology.org/2024.eacl-long.113.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":"Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.eacl-long.113","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.eacl-long.113","pdf_url":"https://aclanthology.org/2024.eacl-long.113.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":"Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411630071.pdf","grobid_xml":"https://content.openalex.org/works/W4411630071.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3201448254","https://openalex.org/W4286970243","https://openalex.org/W2066431708","https://openalex.org/W4384133558","https://openalex.org/W3025615835","https://openalex.org/W173210993","https://openalex.org/W2390660599","https://openalex.org/W3028847759","https://openalex.org/W2393688264","https://openalex.org/W3170174360"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"large":[3],"language":[4,35],"models":[5,36,111],"(LLMs)":[6],"have":[7],"shown":[8],"remarkable":[9],"capabilities":[10],"at":[11,14],"scale,":[12],"particularly":[13],"generating":[15],"text":[16],"conditioned":[17],"on":[18],"a":[19],"prompt.In":[20],"our":[21],"work,":[22],"we":[23,106],"investigate":[24],"the":[25,57],"use":[26],"of":[27,33,54,94,99],"LLMs":[28],"to":[29,49,115],"augment":[30],"training":[31],"data":[32,70],"smaller":[34],"(SLMs)":[37],"with":[38,91],"automatically":[39],"generated":[40],"counterfactual":[41],"(CF)":[42],"instances":[43,96],"-i.e.minimally":[44],"altered":[45],"inputs":[46],"-in":[47],"order":[48],"improve":[50],"out-of-domain":[51],"(OOD)":[52],"performance":[53,75,88],"SLMs":[55],"in":[56,97],"extractive":[58],"question":[59],"answering":[60],"(QA)":[61],"setup.We":[62],"show":[63,107],"that,":[64],"across":[65],"various":[66],"LLM":[67],"generators,":[68],"such":[69],"augmentation":[71],"consistently":[72],"enhances":[73],"OOD":[74],"and":[76,83,103],"improves":[77],"model":[78],"calibration":[79],"for":[80],"both":[81],"confidence-based":[82],"rationaleaugmented":[84],"calibrator":[85],"models.Furthermore,":[86],"these":[87],"improvements":[89],"correlate":[90],"higher":[92],"diversity":[93],"CF":[95,109],"terms":[98],"their":[100],"surface":[101],"form":[102],"semantic":[104],"content.Finally,":[105],"that":[108,126],"augmented":[110],"which":[112],"are":[113],"easier":[114],"calibrate":[116],"also":[117],"exhibit":[118],"much":[119],"lower":[120],"entropy":[121],"when":[122],"assigning":[123],"importance,":[124],"indicating":[125],"rationale-augmented":[127],"calibrators":[128],"prefer":[129],"concise":[130],"explanations.":[131]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}