{"id":"https://openalex.org/W4411638671","doi":"https://doi.org/10.18653/v1/2024.eacl-srw.20","title":"Generative Data Augmentation using LLMs improves Distributional Robustness in Question Answering","display_name":"Generative Data Augmentation using LLMs improves Distributional Robustness in Question Answering","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4411638671","doi":"https://doi.org/10.18653/v1/2024.eacl-srw.20"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.eacl-srw.20","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.eacl-srw.20","pdf_url":"https://aclanthology.org/2024.eacl-srw.20.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: Student Research Workshop","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-srw.20.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101841169","display_name":"Arijit Chowdhury","orcid":"https://orcid.org/0000-0003-3400-2007"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arijit Chowdhury","raw_affiliation_strings":["University of Illinois Urbana Champaign Stanford University Amazon GenAI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana Champaign Stanford University Amazon GenAI","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047032131","display_name":"Aman Chadha","orcid":"https://orcid.org/0000-0001-6621-9003"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aman Chadha","raw_affiliation_strings":["University of Illinois Urbana Champaign Stanford University Amazon GenAI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana Champaign Stanford University Amazon GenAI","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"258","last_page":"265"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9936000108718872,"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":0.9936000108718872,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9539999961853027,"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/T12031","display_name":"Speech and dialogue systems","score":0.9243000149726868,"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/robustness","display_name":"Robustness (evolution)","score":0.8150351643562317},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.5646818280220032},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5528332591056824},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5457881689071655},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45550939440727234},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.44166243076324463},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.341298371553421},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3298570513725281},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.07639452815055847}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8150351643562317},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.5646818280220032},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5528332591056824},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5457881689071655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45550939440727234},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.44166243076324463},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.341298371553421},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3298570513725281},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.07639452815055847},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.eacl-srw.20","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.eacl-srw.20","pdf_url":"https://aclanthology.org/2024.eacl-srw.20.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: Student Research Workshop","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.eacl-srw.20","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.eacl-srw.20","pdf_url":"https://aclanthology.org/2024.eacl-srw.20.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: Student Research Workshop","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411638671.pdf","grobid_xml":"https://content.openalex.org/works/W4411638671.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4391584540","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4395044357","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071","https://openalex.org/W2967848559"],"abstract_inverted_index":{"Robustness":[0],"in":[1,64],"Natural":[2],"Language":[3],"Processing":[4],"continues":[5,32],"to":[6,33,46,70,124,141],"be":[7,34],"a":[8,35,114],"pertinent":[9],"issue,":[10],"where":[11,56],"state":[12],"of":[13,24,38,49,67,84,100],"the":[14,22,47,57,65,75,82],"art":[15],"models":[16,86],"under-perform":[17],"under":[18,52,87,97],"naturally":[19],"shifted":[20],"distributions.In":[21],"context":[23],"Question":[25],"Answering,":[26],"work":[27],"on":[28,93],"domain":[29,50,59,111],"adaptation":[30],"methods":[31],"growing":[36],"body":[37],"research.However,":[39],"very":[40],"little":[41],"attention":[42],"has":[43],"been":[44],"given":[45],"notion":[48],"generalization":[51],"natural":[53,88,145],"distribution":[54,89,101,146],"shifts,":[55],"target":[58],"is":[60],"unknown.With":[61],"drastic":[62],"improvements":[63],"quality":[66],"and":[68,103,121],"access":[69],"generative":[71],"models,":[72],"we":[73,130],"answer":[74],"question:":[76],"How":[77],"do":[78],"generated":[79,138],"datasets":[80,96,136],"influence":[81],"performance":[83],"QA":[85,122],"shifts?We":[90],"perform":[91],"experiments":[92],"4":[94],"different":[95],"varying":[98],"amounts":[99],"shift,":[102],"analyze":[104],"how":[105,132],"\"in-the-wild\"":[106],"generation":[107,116],"can":[108],"help":[109],"achieve":[110],"generalization.We":[112],"take":[113],"twostep":[115],"approach,":[117],"generating":[118],"both":[119],"contexts":[120],"pairs":[123],"augment":[125],"existing":[126],"datasets.Through":[127],"our":[128],"experiments,":[129],"demonstrate":[131],"augmenting":[133],"reading":[134],"comprehension":[135],"with":[137],"data":[139],"leads":[140],"better":[142],"robustness":[143],"towards":[144],"shifts.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}