{"id":"https://openalex.org/W4412888803","doi":"https://doi.org/10.18653/v1/2025.findings-acl.120","title":"Domain Regeneration: How well do LLMs match syntactic properties of text domains?","display_name":"Domain Regeneration: How well do LLMs match syntactic properties of text domains?","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888803","doi":"https://doi.org/10.18653/v1/2025.findings-acl.120"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.120","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.120","pdf_url":"https://aclanthology.org/2025.findings-acl.120.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: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.120.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024825692","display_name":"Da Young Ju","orcid":"https://orcid.org/0000-0003-0618-9089"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Da Ju","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002688040","display_name":"Hagen Blix","orcid":"https://orcid.org/0000-0002-8838-9393"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hagen Blix","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062696000","display_name":"Adina Williams","orcid":"https://orcid.org/0000-0001-5281-3343"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adina Williams","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I57206974"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2367","last_page":"2388"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9973000288009644,"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":0.9973000288009644,"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/T10028","display_name":"Topic Modeling","score":0.9898999929428101,"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/T13629","display_name":"Text Readability and Simplification","score":0.9086999893188477,"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/domain","display_name":"Domain (mathematical analysis)","score":0.6679834127426147},{"id":"https://openalex.org/keywords/regeneration","display_name":"Regeneration (biology)","score":0.6428619623184204},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5904969573020935},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41365569829940796},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12230762839317322},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.10231268405914307}],"concepts":[{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6679834127426147},{"id":"https://openalex.org/C171056886","wikidata":"https://www.wikidata.org/wiki/Q193119","display_name":"Regeneration (biology)","level":2,"score":0.6428619623184204},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5904969573020935},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41365569829940796},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12230762839317322},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.10231268405914307},{"id":"https://openalex.org/C95444343","wikidata":"https://www.wikidata.org/wiki/Q7141","display_name":"Cell biology","level":1,"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/v1/2025.findings-acl.120","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.120","pdf_url":"https://aclanthology.org/2025.findings-acl.120.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: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.120","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.120","pdf_url":"https://aclanthology.org/2025.findings-acl.120.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: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888803.pdf","grobid_xml":"https://content.openalex.org/works/W4412888803.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W3128261063"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2058795891","https://openalex.org/W2390279801","https://openalex.org/W2521179722","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W1981919236"],"abstract_inverted_index":{"Recent":[0],"improvements":[1,14],"in":[2,8,15,77],"large":[3],"language":[4],"model":[5],"performance":[6],"have,":[7],"all":[9],"likelihood,":[10],"been":[11],"accompanied":[12],"by":[13],"how":[16,44],"well":[17,45],"they":[18,47],"can":[19,98],"approximate":[20],"the":[21,31,139,142,157,163],"distribution":[22],"of":[23,36,68,108,141,156],"their":[24],"training":[25,79],"data.In":[26],"this":[27,89],"work,":[28],"we":[29,56],"explore":[30],"following":[32],"question:":[33],"which":[34,73],"properties":[35,113,126],"text":[37,64,72,103],"domains":[38,67],"do":[39,46,48],"LLMs":[40,61,97],"faithfully":[41,99],"approximate,":[42],"and":[43,83,117,123,134,153],"so?Applying":[49],"observational":[50],"approaches":[51],"familiar":[52],"from":[53,65,111],"corpus":[54],"linguistics,":[55],"prompt":[57],"commonly":[58],"used,":[59],"opensource":[60],"to":[62,94,120,162],"regenerate":[63],"three":[66],"permissively":[69],"licensed":[70],"English":[71],"are":[74],"often":[75],"contained":[76],"LLM":[78],"data-Wikipedia,":[80],"news":[81],"text,":[82],"ELI5.In":[84],"a":[85,146,149,154],"fairly":[86],"semantically-controlled":[87],"setting,":[88],"regeneration":[90],"paradigm":[91],"allows":[92],"us":[93],"investigate":[95,105],"whether":[96],"match":[100],"original":[101],"human":[102,164],"domains.We":[104],"varying":[106],"levels":[107],"syntactic":[109],"abstraction,":[110],"simpler":[112],"like":[114],"sentence":[115],"length,":[116],"article":[118],"readability,":[119],"more":[121],"complex":[122],"higher":[124],"order":[125],"such":[127],"as":[128,160],"dependency":[129],"tag":[130],"distribution,":[131],"parse":[132,135],"depth,":[133],"complexity.We":[136],"find":[137],"that":[138],"majority":[140],"regenerated":[143],"distributions":[144],"show":[145],"shifted":[147],"mean,":[148],"lower":[150],"standard":[151],"deviation,":[152],"reduction":[155],"long":[158],"tail,":[159],"compared":[161],"originals.":[165]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}