{"id":"https://openalex.org/W4387849079","doi":"https://doi.org/10.1145/3583780.3615111","title":"A Test Collection of Synthetic Documents for Training Rankers: ChatGPT vs. Human Experts","display_name":"A Test Collection of Synthetic Documents for Training Rankers: ChatGPT vs. Human Experts","publication_year":2023,"publication_date":"2023-10-21","ids":{"openalex":"https://openalex.org/W4387849079","doi":"https://doi.org/10.1145/3583780.3615111"},"language":"en","primary_location":{"id":"doi:10.1145/3583780.3615111","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3583780.3615111","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3583780.3615111","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 32nd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3583780.3615111","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059759006","display_name":"Arian Askari","orcid":"https://orcid.org/0000-0003-4712-832X"},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Arian Askari","raw_affiliation_strings":["Leiden Institute of Advanced Computer Science, Leiden University, Leiden, Netherlands"],"affiliations":[{"raw_affiliation_string":"Leiden Institute of Advanced Computer Science, Leiden University, Leiden, Netherlands","institution_ids":["https://openalex.org/I121797337"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063466614","display_name":"Mohammad Aliannejadi","orcid":"https://orcid.org/0000-0002-9447-4172"},"institutions":[{"id":"https://openalex.org/I4210135670","display_name":"Amsterdam University of the Arts","ror":"https://ror.org/04dde1554","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210135670"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Mohammad Aliannejadi","raw_affiliation_strings":["University of Amsterdam, Amsterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055639036","display_name":"Evangelos Kanoulas","orcid":"https://orcid.org/0000-0002-8312-0694"},"institutions":[{"id":"https://openalex.org/I4210135670","display_name":"Amsterdam University of the Arts","ror":"https://ror.org/04dde1554","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210135670"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Evangelos Kanoulas","raw_affiliation_strings":["University of Amsterdam, Amsterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"University of Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4210135670","https://openalex.org/I887064364"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027124439","display_name":"Suzan Verberne","orcid":"https://orcid.org/0000-0002-9609-9505"},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Suzan Verberne","raw_affiliation_strings":["LIACS, Leiden University, Leiden, Netherlands"],"affiliations":[{"raw_affiliation_string":"LIACS, Leiden University, Leiden, Netherlands","institution_ids":["https://openalex.org/I121797337"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5059759006"],"corresponding_institution_ids":["https://openalex.org/I121797337"],"apc_list":null,"apc_paid":null,"fwci":2.0739,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.89705298,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5311","last_page":"5315"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9922000169754028,"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/T13274","display_name":"Expert finding and Q&A systems","score":0.9864000082015991,"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/computer-science","display_name":"Computer science","score":0.7651280164718628},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.665087103843689},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.612226128578186},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5831530690193176},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5787358283996582},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5672463774681091},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5039839148521423},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.4981546401977539},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.43969401717185974},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.43700703978538513},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.4210791289806366},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.37203407287597656},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3625607192516327},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.30330079793930054}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7651280164718628},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.665087103843689},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.612226128578186},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5831530690193176},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5787358283996582},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5672463774681091},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5039839148521423},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.4981546401977539},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.43969401717185974},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.43700703978538513},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.4210791289806366},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37203407287597656},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3625607192516327},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.30330079793930054},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3583780.3615111","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3583780.3615111","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3583780.3615111","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 32nd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:dare.uva.nl:openaire/a3aac532-b09e-40b0-9074-9ae8be2fb4c5","is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/a-test-collection-of-synthetic-documents-for-training-rankers(a3aac532-b09e-40b0-9074-9ae8be2fb4c5).html","pdf_url":"https://pure.uva.nl/ws/files/169472407/3583780.3615111.pdf","source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Askari, A, Aliannejadi, M, Kanoulas, E & Verberne, S 2023, A Test Collection of Synthetic Documents for Training Rankers : ChatGPT vs. Human Experts. in CIKM '23 : Proceedings of the 32nd ACM International Conference on Information and Knowledge Management : October 21-25, 2023, Birmingham, England. Association for Computing Machinery, New York, NY, pp. 5311-5315, 32nd ACM International Conference on Information and Knowledge Management, CIKM 2023, Birmingham, United Kingdom, 21/10/23. https://doi.org/10.1145/3583780.3615111","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:scholarlypublications.universiteitleiden.nl:item_3718743","is_oa":true,"landing_page_url":"https://hdl.handle.net/1887/3718743","pdf_url":"https://scholarlypublications.universiteitleiden.nl/access/item%3A3718744/view","source":{"id":"https://openalex.org/S4306400850","display_name":"Leiden Repository (Leiden University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I121797337","host_organization_name":"Leiden University","host_organization_lineage":["https://openalex.org/I121797337"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Information and Knowledge Management (CIKM)","raw_type":"Article in monograph or in proceedings"}],"best_oa_location":{"id":"doi:10.1145/3583780.3615111","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3583780.3615111","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3583780.3615111","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 32nd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2280656080","display_name":null,"funder_award_id":"H2020-EU.1.3.1","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G7501014153","display_name":null,"funder_award_id":"860721","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387849079.pdf","grobid_xml":"https://content.openalex.org/works/W4387849079.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W2040659137","https://openalex.org/W2251818205","https://openalex.org/W2798658104","https://openalex.org/W2979826702","https://openalex.org/W3008374555","https://openalex.org/W3021397474","https://openalex.org/W3021779606","https://openalex.org/W3099384026","https://openalex.org/W3105966348","https://openalex.org/W3148323213","https://openalex.org/W3155114168","https://openalex.org/W3208821253","https://openalex.org/W4226251537","https://openalex.org/W4251326898","https://openalex.org/W4323050332","https://openalex.org/W4361282369","https://openalex.org/W4380875567","https://openalex.org/W4385688511","https://openalex.org/W4389520758"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W2470043383","https://openalex.org/W4380551139","https://openalex.org/W2953501176","https://openalex.org/W2965095304","https://openalex.org/W2280377497","https://openalex.org/W3034474024","https://openalex.org/W3174044702","https://openalex.org/W4238433571"],"abstract_inverted_index":{"In":[0],"this":[1],"resource":[2],"paper,":[3],"we":[4],"investigate":[5],"the":[6,40,126,130],"usefulness":[7],"of":[8,29,42,66,81,165],"generative":[9,138],"Large":[10],"Language":[11],"Models":[12],"(LLMs)":[13],"in":[14,21,143,160],"generating":[15,25,144],"training":[16,145,157],"data":[17,146],"for":[18,114,147,177,195],"cross-encoder":[19,82,103],"re-rankers":[20,83,128],"a":[22,34,79],"novel":[23,134],"direction:":[24],"synthetic":[26,30,185],"documents":[27],"instead":[28],"queries.":[31],"We":[32,52,77,168,187],"introduce":[33],"new":[35],"dataset,":[36,59,172],"ChatGPT-RetrievalQA,":[37,173],"and":[38,49,73,98,151,179,184,192],"compare":[39],"effectiveness":[41],"strong":[43],"models":[44,105,150],"fine-tuned":[45],"on":[46,56,84,92,107,120],"both":[47],"LLM-generated":[48,108],"human-generated":[50,86],"data.":[51,89,167,186],"build":[53],"ChatGPT-RetrievalQA":[54],"based":[55],"an":[57],"existing":[58],"human":[60,71,121,183],"ChatGPT":[61],"Comparison":[62],"Corpus":[63],"(HC3),":[64],"consisting":[65],"public":[67],"question":[68],"collections":[69],"with":[70,162,182],"responses":[72,109],"answers":[74],"from":[75],"ChatGPT.":[76],"fine-tune":[78],"range":[80],"either":[85],"or":[87],"ChatGPT-generated":[88],"Our":[90,133],"evaluation":[91],"MS":[93],"MARCO":[94],"DEV,":[95],"TREC":[96,99],"DL'19,":[97],"DL'20":[100],"demonstrates":[101],"that":[102,137,170],"re-ranking":[104,116],"trained":[106,119],"are":[110],"significantly":[111],"more":[112],"effective":[113],"out-of-domain":[115],"than":[117],"those":[118],"responses.":[122],"For":[123],"in-domain":[124],"re-ranking,":[125],"human-trained":[127],"outperform":[129],"LLM-trained":[131],"re-rankers.":[132],"findings":[135],"suggest":[136],"LLMs":[139],"have":[140],"high":[141],"potential":[142],"neural":[148],"retrieval":[149],"can":[152],"be":[153],"used":[154],"to":[155],"augment":[156],"data,":[158,190],"especially":[159],"domains":[161],"smaller":[163],"amounts":[164],"labeled":[166],"believe":[169],"our":[171,189],"presents":[174],"various":[175],"opportunities":[176],"analyzing":[178],"improving":[180],"rankers":[181],"release":[188],"code,":[191],"model":[193],"checkpoints":[194],"future":[196],"work.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}