{"id":"https://openalex.org/W7166847979","doi":"https://doi.org/10.18653/v1/2026.acl-long.1995","title":"Explain the Synth: Interpretable Evaluation of LLM Data Synthesis","display_name":"Explain the Synth: Interpretable Evaluation of LLM Data Synthesis","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166847979","doi":"https://doi.org/10.18653/v1/2026.acl-long.1995"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1995","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1995","pdf_url":"https://aclanthology.org/2026.acl-long.1995.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 64th Annual Meeting 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/2026.acl-long.1995.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139775764","display_name":"Yue Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yue Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139824390","display_name":"Fan Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139818659","display_name":"Yu Bai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Bai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139793910","display_name":"Hao Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Wang","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":0.83782849,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"43054","last_page":"43077"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.0868000015616417,"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":0.0868000015616417,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.07680000364780426,"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/T13650","display_name":"Computational Physics and Python Applications","score":0.04349999874830246,"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/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.302700012922287},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2883000075817108},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.2786000072956085},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.26170000433921814},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.2596000134944916}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5138000249862671},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5059000253677368},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27149999141693115},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2522999942302704},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.24770000576972961}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1995","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1995","pdf_url":"https://aclanthology.org/2026.acl-long.1995.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.1995","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1995","pdf_url":"https://aclanthology.org/2026.acl-long.1995.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166847979.pdf","grobid_xml":"https://content.openalex.org/works/W7166847979.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"are":[4,105,124],"increasingly":[5],"used":[6],"to":[7,67,84,89,154],"generate":[8],"synthetic":[9,36,62,165],"data,":[10],"in":[11],"which":[12,122],"tabular":[13,178],"data":[14,18,37,83,166],"constitute":[15],"a":[16,21,47,69,74,143,169],"fundamental":[17],"modality":[19],"across":[20],"wide":[22],"range":[23],"of":[24,172],"domains.Yet,":[25],"current":[26],"evaluation":[27,167],"practices":[28],"often":[29],"provide":[30,142],"limited":[31],"insights":[32],"into":[33,168],"whether":[34],"the":[35,55,115,132],"preserve":[38],"real":[39,60,82],"data-generating":[40],"relationships":[41,123],"or":[42,128],"introduce":[43],"plausible-looking":[44],"artifacts.We":[45],"present":[46],"conceptually":[48],"simple,":[49],"interpretable":[50,159],"auditing":[51],"framework":[52],"that":[53,146],"compares":[54],"explanatory":[56,76],"structure":[57,96],"induced":[58],"by":[59,107,114,131],"versus":[61],"data.The":[63],"key":[64],"idea":[65],"is":[66],"use":[68],"transparent":[70],"rule-based":[71],"model":[72],"as":[73],"shared":[75],"language:":[77],"we":[78],"extract":[79],"rules":[80,104],"from":[81],"summarize":[85],"how":[86,93],"features":[87],"relate":[88],"labels,":[90],"then":[91],"examine":[92],"this":[94],"rule":[95,110],"changes":[97],"when":[98],"explained":[99],"using":[100],"LLM-generated":[101],"data.Importantly,":[102],"these":[103],"derived":[106],"an":[108,158],"independent":[109],"auditor":[111],"rather":[112],"than":[113],"generator":[116],"itself.The":[117],"resulting":[118],"\"explanation":[119],"shift\"":[120],"reveals":[121],"preserved,":[125],"weakened,":[126],"removed,":[127],"newly":[129],"introduced":[130],"generator,":[133],"offering":[134],"actionable":[135],"diagnostics":[136],"beyond":[137],"aggregate":[138],"fidelity":[139],"scores.We":[140],"further":[141],"theoretical":[144],"perspective":[145],"links":[147],"explanation":[148],"shift":[149],"and":[150],"cross-domain":[151],"predictive":[152],"gaps":[153],"distribution":[155],"mismatch":[156],"within":[157],"hypothesis":[160],"class.Overall,":[161],"our":[162],"approach":[163],"turns":[164],"human-auditable":[170],"comparison":[171],"explanations,":[173],"improving":[174],"transparency":[175],"for":[176],"LLM-based":[177],"synthesis.":[179]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}