{"id":"https://openalex.org/W4413948895","doi":"https://doi.org/10.14778/3746405.3746426","title":"DocETL: Agentic Query Rewriting and Evaluation for Complex Document Processing","display_name":"DocETL: Agentic Query Rewriting and Evaluation for Complex Document Processing","publication_year":2025,"publication_date":"2025-05-01","ids":{"openalex":"https://openalex.org/W4413948895","doi":"https://doi.org/10.14778/3746405.3746426"},"language":"en","primary_location":{"id":"doi:10.14778/3746405.3746426","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3746405.3746426","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-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/A5023956968","display_name":"Shreya Shankar","orcid":"https://orcid.org/0000-0002-0919-9672"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shreya Shankar","raw_affiliation_strings":["UC Berkeley EECS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley EECS","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114567651","display_name":"Tristan Chambers","orcid":null},"institutions":[{"id":"https://openalex.org/I4210108245","display_name":"Police Department","ror":"https://ror.org/01pd36221","country_code":"LT","type":"government","lineage":["https://openalex.org/I4210108245","https://openalex.org/I4210150337"]}],"countries":["LT"],"is_corresponding":false,"raw_author_name":"Tristan Chambers","raw_affiliation_strings":["BIDS Police Records Access Project"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BIDS Police Records Access Project","institution_ids":["https://openalex.org/I4210108245"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106734071","display_name":"T. Shah","orcid":null},"institutions":[{"id":"https://openalex.org/I4210108245","display_name":"Police Department","ror":"https://ror.org/01pd36221","country_code":"LT","type":"government","lineage":["https://openalex.org/I4210108245","https://openalex.org/I4210150337"]}],"countries":["LT"],"is_corresponding":false,"raw_author_name":"Tarak Shah","raw_affiliation_strings":["BIDS Police Records Access Project"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BIDS Police Records Access Project","institution_ids":["https://openalex.org/I4210108245"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013608601","display_name":"Aditya Parameswaran","orcid":"https://orcid.org/0000-0002-4538-4752"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aditya G. Parameswaran","raw_affiliation_strings":["UC Berkeley EECS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley EECS","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049016095","display_name":"Eugene Wu","orcid":"https://orcid.org/0000-0003-4254-6688"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eugene Wu","raw_affiliation_strings":["Columbia University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":18.0805,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.99128856,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"18","issue":"9","first_page":"3035","last_page":"3048"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9879999756813049,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9879999756813049,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9879000186920166,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.9865999817848206,"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/rewriting","display_name":"Rewriting","score":0.8948870301246643},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6621377468109131},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5597149729728699},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33473896980285645},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2892199456691742}],"concepts":[{"id":"https://openalex.org/C154690210","wikidata":"https://www.wikidata.org/wiki/Q1668499","display_name":"Rewriting","level":2,"score":0.8948870301246643},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6621377468109131},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5597149729728699},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33473896980285645},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2892199456691742}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3746405.3746426","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3746405.3746426","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W135863099","https://openalex.org/W1483819513","https://openalex.org/W1977810318","https://openalex.org/W1991271936","https://openalex.org/W2079992169","https://openalex.org/W2099813784","https://openalex.org/W2168144930","https://openalex.org/W2752236330","https://openalex.org/W2889357608","https://openalex.org/W4230201548","https://openalex.org/W4281972940","https://openalex.org/W4386128198","https://openalex.org/W4391876619","https://openalex.org/W4392455862","https://openalex.org/W4398234802","https://openalex.org/W4399208169","https://openalex.org/W4399521940","https://openalex.org/W4403334020","https://openalex.org/W4404181169","https://openalex.org/W6949549905"],"related_works":["https://openalex.org/W2120204135","https://openalex.org/W2139396251","https://openalex.org/W1796293478","https://openalex.org/W1577544887","https://openalex.org/W2168276503","https://openalex.org/W1573537275","https://openalex.org/W2105713543","https://openalex.org/W174435416","https://openalex.org/W2132239740","https://openalex.org/W2115945951"],"abstract_inverted_index":{"Analyzing":[0],"unstructured":[1,20],"data":[2,9],"has":[3,186],"been":[4],"a":[5,30,60,78,93],"persistent":[6],"challenge":[7],"in":[8,29],"processing.":[10],"Recent":[11],"proposals":[12],"offer":[13],"declarative":[14,94],"frameworks":[15],"for":[16,42,88,96,137],"LLM-powered":[17],"processing":[18,84,166],"of":[19,59,134,159,183],"data,":[21,72],"but":[22],"they":[23],"typically":[24],"execute":[25],"user-specified":[26],"operations":[27],"as-is":[28],"single":[31],"LLM":[32,89,160],"call\u2014focusing":[33],"on":[34],"cost":[35],"rather":[36],"than":[37],"accuracy.":[38],"This":[39],"is":[40,177],"problematic":[41],"complex":[43,82],"tasks,":[44,139,167],"where":[45],"even":[46],"well-prompted":[47],"LLMs":[48],"can":[49],"miss":[50],"relevant":[51],"information.":[52],"For":[53],"instance,":[54],"reliably":[55],"extracting":[56],"all":[57],"instances":[58],"specific":[61],"clause":[62],"from":[63],"legal":[64],"documents":[65],"often":[66],"requires":[67],"decomposing":[68],"the":[69,71,157],"task,":[70],"or":[73],"both.":[74],"We":[75,129],"present":[76],"DocETL,":[77],"system":[79],"that":[80,151],"optimizes":[81],"document":[83,165],"pipelines,":[85,135],"while":[86],"accounting":[87],"shortcomings.":[90],"DocETL":[91,168,176],"offers":[92],"interface":[95],"users":[97],"to":[98,107],"deine":[99],"such":[100],"pipelines":[101],"and":[102,126,146],"uses":[103],"an":[104,124,141,148],"agent-based":[105,113],"approach":[106],"automatically":[108],"optimize":[109],"them,":[110],"leveraging":[111],"novel":[112],"rewrites":[114],"(that":[115],"we":[116],"call":[117],"rewrite":[118],"directives":[119],"),":[120],"as":[121,123,182],"well":[122],"optimization":[125,149],"evaluation":[127,144],"framework.":[128],"introduce":[130],"(i)":[131],"logical":[132],"rewriting":[133],"tailored":[136],"LLM-based":[138],"(ii)":[140],"agent-guided":[142],"plan":[143],"mechanism,":[145],"(iii)":[147],"algorithm":[150],"efficiently":[152],"finds":[153],"promising":[154],"plans,":[155],"considering":[156],"latencies":[158],"execution.":[161],"Across":[162],"four":[163],"real-world":[164],"improves":[169],"accuracy":[170],"by":[171],"21\u201380%":[172],"over":[173,187],"strong":[174],"baselines.":[175],"open-source":[178],"at":[179],"docetl.org":[180],"and,":[181],"March":[184],"2025,":[185],"1.7k":[188],"GitHub":[189],"stars":[190],"across":[191],"diverse":[192],"domains.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-10T00:00:00"}