{"id":"https://openalex.org/W4416034098","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.979","title":"AssistedDS: Benchmarking How External Domain Knowledge Assists LLMs in Automated Data Science","display_name":"AssistedDS: Benchmarking How External Domain Knowledge Assists LLMs in Automated Data Science","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034098","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.979"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.979","is_oa":false,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.979","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025874786","display_name":"An Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"An Luo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043161215","display_name":"Xun Xian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xun Xian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100927047","display_name":"Du Jin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin Du","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113555795","display_name":"Fangqiao Tian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fangqiao Tian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082958363","display_name":"Ganghua Wang","orcid":"https://orcid.org/0000-0002-0888-167X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ganghua Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100633979","display_name":"Zhong Ming","orcid":"https://orcid.org/0000-0002-6933-5760"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ming Zhong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101800889","display_name":"Shaoqiong Zhao","orcid":"https://orcid.org/0000-0003-1021-5307"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shengchun Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070768111","display_name":"Xuan Bi","orcid":"https://orcid.org/0000-0002-4683-1411"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuan Bi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075644135","display_name":"Zirui Liu","orcid":"https://orcid.org/0000-0002-1939-9715"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zirui Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101805947","display_name":"Jiawei Zhou","orcid":"https://orcid.org/0000-0001-5590-6270"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiawei Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036007832","display_name":"Jayanth Srinivasa","orcid":"https://orcid.org/0000-0002-7732-8827"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jayanth Srinivasa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032325271","display_name":"Ashish Kundu","orcid":"https://orcid.org/0000-0003-1499-5558"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ashish Kundu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050613322","display_name":"Charles B. Fleming","orcid":"https://orcid.org/0000-0002-1357-5706"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Charles Fleming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100633783","display_name":"Mingyi Hong","orcid":"https://orcid.org/0000-0003-1263-9365"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingyi Hong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100622784","display_name":"Jie Ding","orcid":"https://orcid.org/0000-0002-1427-9618"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jie Ding","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":15,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35044215,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"18017","last_page":"18060"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.23849999904632568,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.23849999904632568,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.08839999884366989,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11937","display_name":"Research Data Management Practices","score":0.03150000050663948,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/benchmarking","display_name":"Benchmarking","score":0.6764000058174133},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5820000171661377},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.30390000343322754},{"id":"https://openalex.org/keywords/knowledge-representation-and-reasoning","display_name":"Knowledge representation and reasoning","score":0.27379998564720154},{"id":"https://openalex.org/keywords/information-system","display_name":"Information system","score":0.26930001378059387}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.6764000058174133},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5820000171661377},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5777999758720398},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4941999912261963},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.4372999966144562},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2827000021934509},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C180198813","wikidata":"https://www.wikidata.org/wiki/Q121182","display_name":"Information system","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.979","is_oa":false,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.979","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-08T00:00:00"}
