{"id":"https://openalex.org/W7129087102","doi":"https://doi.org/10.1145/3773966.3779380","title":"On Causal and Anticausal LLM-based Data Synthesis","display_name":"On Causal and Anticausal LLM-based Data Synthesis","publication_year":2026,"publication_date":"2026-02-16","ids":{"openalex":"https://openalex.org/W7129087102","doi":"https://doi.org/10.1145/3773966.3779380"},"language":null,"primary_location":{"id":"doi:10.1145/3773966.3779380","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3773966.3779380","pdf_url":null,"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 Nineteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3773966.3779380","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101643665","display_name":"Bohan Jiang","orcid":"https://orcid.org/0000-0001-8552-2681"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bohan Jiang","raw_affiliation_strings":["Arizona State University, Tempe, AZ, USA"],"raw_orcid":"https://orcid.org/0000-0001-8552-2681","affiliations":[{"raw_affiliation_string":"Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Pingchuan Ma","orcid":"https://orcid.org/0009-0007-2380-3796"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pingchuan Ma","raw_affiliation_strings":["Arizona State University, Tempe, AZ, USA"],"raw_orcid":"https://orcid.org/0009-0007-2380-3796","affiliations":[{"raw_affiliation_string":"Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101369657","display_name":"Zhuoyu Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuoyu Shi","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"raw_orcid":"https://orcid.org/0009-0009-7936-3931","affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002709735","display_name":"Fred Morstatter","orcid":"https://orcid.org/0000-0002-0247-4328"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fred Morstatter","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-0247-4328","affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126150681","display_name":"Adrienne Raglin","orcid":null},"institutions":[{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]},{"id":"https://openalex.org/I2802705668","display_name":"United States Army Combat Capabilities Development Command","ror":"https://ror.org/02rdkx920","country_code":"US","type":"other","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adrienne Raglin","raw_affiliation_strings":["DEVCOM Army Research Lab, Adelphi, MD, USA"],"raw_orcid":"https://orcid.org/0000-0002-5489-1633","affiliations":[{"raw_affiliation_string":"DEVCOM Army Research Lab, Adelphi, MD, USA","institution_ids":["https://openalex.org/I166416128","https://openalex.org/I2802705668"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126158987","display_name":"Huan Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huan Liu","raw_affiliation_strings":["Arizona State University, Tempe, AZ, USA"],"raw_orcid":"https://orcid.org/0000-0002-3264-7904","affiliations":[{"raw_affiliation_string":"Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"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":"1160","last_page":"1164"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.30300000309944153,"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":0.30300000309944153,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.13840000331401825,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.06469999998807907,"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/synthetic-data","display_name":"Synthetic data","score":0.8004999756813049},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.5846999883651733},{"id":"https://openalex.org/keywords/causal-model","display_name":"Causal model","score":0.5633999705314636},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5450999736785889},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5038999915122986},{"id":"https://openalex.org/keywords/downstream","display_name":"Downstream (manufacturing)","score":0.414900004863739},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.3950999975204468},{"id":"https://openalex.org/keywords/causal-inference","display_name":"Causal inference","score":0.36390000581741333},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.33739998936653137}],"concepts":[{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.8004999756813049},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7087000012397766},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.5846999883651733},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.5633999705314636},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5450999736785889},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5038999915122986},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47189998626708984},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4499000012874603},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.414900004863739},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.3950999975204468},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39399999380111694},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.36390000581741333},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.33739998936653137},{"id":"https://openalex.org/C55037315","wikidata":"https://www.wikidata.org/wiki/Q5421151","display_name":"Experimental data","level":2,"score":0.32580000162124634},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3197000026702881},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.31529998779296875},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3125},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.3111000061035156},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.305400013923645},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.30160000920295715},{"id":"https://openalex.org/C3020493868","wikidata":"https://www.wikidata.org/wiki/Q55631277","display_name":"Real world data","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2815999984741211},{"id":"https://openalex.org/C2987525970","wikidata":"https://www.wikidata.org/wiki/Q96374569","display_name":"Causal analysis","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C163504300","wikidata":"https://www.wikidata.org/wiki/Q2364925","display_name":"Causal structure","level":2,"score":0.2578999996185303}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3773966.3779380","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3773966.3779380","pdf_url":null,"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 Nineteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3773966.3779380","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3773966.3779380","pdf_url":null,"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 Nineteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2979826702","https://openalex.org/W3164883482","https://openalex.org/W4404783774"],"related_works":[],"abstract_inverted_index":{"While":[0],"Large":[1],"Language":[2],"Models":[3],"(LLMs)":[4],"have":[5],"been":[6],"increasingly":[7],"used":[8],"to":[9,61,64,115,211],"generate":[10,65,212],"synthetic":[11,88,132,166,197,214],"data":[12,24,37,79,102,122,128,167,215],"for":[13,44,134,184,188],"various":[14],"downstream":[15,45],"tasks,":[16],"researchers":[17],"overlook":[18],"the":[19,23,59,76,82,87,96,117,127],"causal":[20,29,99,118],"direction":[21,30,77,119],"in":[22,58],"synthesis":[25,80],"process.":[26],"A":[27],"natural":[28],"should":[31],"contain":[32],"two":[33],"steps:":[34],"diverse":[35],"raw":[36],"are":[38],"generated":[39],"first,":[40],"and":[41,84,100,144,150,175,186,190,216],"subsequently":[42],"annotated":[43],"tasks.":[46,139],"However,":[47],"most":[48],"LLM-based":[49,121],"methods":[50],"adopt":[51],"an":[52],"anticausal":[53,101,165,196],"direction:":[54],"embedding":[55],"label":[56],"information":[57],"prompt":[60],"force":[62],"LLMs":[63],"targeted":[66],"data.":[67,203],"This":[68],"reversal":[69],"raises":[70],"a":[71],"critical":[72],"question:":[73],"How":[74],"does":[75],"of":[78,86,98,120,220],"impact":[81,97],"quality":[83],"utility":[85],"data?":[89],"In":[90],"this":[91],"work,":[92],"we":[93,107,130],"empirically":[94],"study":[95],"synthesis.":[103,123],"To":[104],"do":[105],"so,":[106],"first":[108],"design":[109],"simple":[110],"yet":[111],"effective":[112],"prompting":[113],"strategies":[114],"control":[116],"Using":[124],"GPT-5":[125],"as":[126],"generator,":[129],"construct":[131],"datasets":[133,149,198],"three":[135],"distinct":[136],"machine":[137],"learning":[138],"We":[140],"then":[141],"fine-tune":[142],"BERT-base":[143],"LLaMA-3.2-1B":[145],"models":[146,162],"on":[147,164,209],"these":[148],"evaluate":[151],"them":[152],"against":[153],"human-curated":[154],"benchmarks.":[155],"Our":[156,204],"experiments":[157],"reveal":[158],"consistent":[159],"patterns:":[160],"(1)":[161],"trained":[163],"suffer":[168],"larger":[169],"performance":[170],"drops":[171],"across":[172],"all":[173],"tasks":[174],"model":[176],"families":[177],"---":[178],"Accuracy":[179],"declines":[180],"range":[181],"from":[182,201],"13.7%-59.1%":[183],"BERT":[185],"4.9%-54.3%":[187],"LLaMA,":[189],"(2)":[191],"distributional":[192],"analysis":[193],"shows":[194],"that":[195],"deviate":[199],"further":[200],"human":[202],"findings":[205],"provide":[206],"practical":[207],"guidance":[208],"how":[210],"better":[213],"make":[217],"good":[218],"use":[219],"it.":[221]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-17T00:00:00"}