{"id":"https://openalex.org/W4412376941","doi":"https://doi.org/10.1145/3726302.3730165","title":"Assessing Support for the TREC 2024 RAG Track: A Large-Scale Comparative Study of LLM and Human Evaluations","display_name":"Assessing Support for the TREC 2024 RAG Track: A Large-Scale Comparative Study of LLM and Human Evaluations","publication_year":2025,"publication_date":"2025-07-13","ids":{"openalex":"https://openalex.org/W4412376941","doi":"https://doi.org/10.1145/3726302.3730165"},"language":"en","primary_location":{"id":"doi:10.1145/3726302.3730165","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730165","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730165","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 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","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/10.1145/3726302.3730165","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052977545","display_name":"Nandan Thakur","orcid":"https://orcid.org/0000-0001-6107-2460"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Nandan Thakur","raw_affiliation_strings":["University of Waterloo, Waterloo, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101480198","display_name":"Ronak Pradeep","orcid":"https://orcid.org/0000-0001-6296-601X"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ronak Pradeep","raw_affiliation_strings":["University of Waterloo, Waterloo, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103308060","display_name":"Shivani Upadhyay","orcid":"https://orcid.org/0009-0007-7071-2344"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Shivani Upadhyay","raw_affiliation_strings":["University of Waterloo, Waterloo, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103325247","display_name":"Daniel Campos","orcid":"https://orcid.org/0000-0002-5138-8426"},"institutions":[{"id":"https://openalex.org/I142600864","display_name":"College of San Mateo","ror":"https://ror.org/01gwn6z70","country_code":"US","type":"education","lineage":["https://openalex.org/I142600864"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Campos","raw_affiliation_strings":["Snowflake, San Mateo, USA"],"affiliations":[{"raw_affiliation_string":"Snowflake, San Mateo, USA","institution_ids":["https://openalex.org/I142600864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055132321","display_name":"Nick Craswell","orcid":"https://orcid.org/0000-0002-9351-8137"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I58610484","display_name":"Seattle University","ror":"https://ror.org/02jqc0m91","country_code":"US","type":"education","lineage":["https://openalex.org/I58610484"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nick Craswell","raw_affiliation_strings":["Microsoft, Seattle, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Seattle, USA","institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I58610484"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053747568","display_name":"Ian Soboroff","orcid":"https://orcid.org/0000-0003-2363-3014"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ian Soboroff","raw_affiliation_strings":["NIST, Gaithersburg, USA"],"affiliations":[{"raw_affiliation_string":"NIST, Gaithersburg, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109409280","display_name":"Hoa Trang Dang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hoa Trang Dang","raw_affiliation_strings":["NIST, Gaithersburg, USA"],"affiliations":[{"raw_affiliation_string":"NIST, Gaithersburg, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082997975","display_name":"Jimmy Lin","orcid":"https://orcid.org/0000-0002-0661-7189"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jimmy Lin","raw_affiliation_strings":["University of Waterloo, Waterloo, Canada"],"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5052977545"],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":1.2907,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.81162872,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2759","last_page":"2763"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12422","display_name":"Radiomics and Machine Learning in Medical Imaging","score":0.9814000129699707,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T12422","display_name":"Radiomics and Machine Learning in Medical Imaging","score":0.9814000129699707,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.9526000022888184,"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":0.9434000253677368,"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/computer-science","display_name":"Computer science","score":0.7399290800094604},{"id":"https://openalex.org/keywords/track","display_name":"Track (disk drive)","score":0.7322548627853394},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5840228199958801},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.37464791536331177},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32952234148979187},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.14653286337852478},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.0869610607624054},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07087117433547974}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7399290800094604},{"id":"https://openalex.org/C89992363","wikidata":"https://www.wikidata.org/wiki/Q5961558","display_name":"Track (disk drive)","level":2,"score":0.7322548627853394},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5840228199958801},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37464791536331177},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32952234148979187},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.14653286337852478},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0869610607624054},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07087117433547974}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3726302.3730165","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730165","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730165","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 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3726302.3730165","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730165","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730165","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 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332178","display_name":"National Institute of Standards and Technology","ror":"https://ror.org/05xpvk416"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412376941.pdf","grobid_xml":"https://content.openalex.org/works/W4412376941.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W2560674852","https://openalex.org/W2747329762","https://openalex.org/W3156789018","https://openalex.org/W4389518954","https://openalex.org/W4389520670","https://openalex.org/W4391876619","https://openalex.org/W4393147129","https://openalex.org/W4394906088","https://openalex.org/W4396913672","https://openalex.org/W4401042808","https://openalex.org/W4401065928","https://openalex.org/W4401306886","https://openalex.org/W4403928879","https://openalex.org/W4409167861","https://openalex.org/W6948119035"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W2789518417","https://openalex.org/W4213217485","https://openalex.org/W4396701345","https://openalex.org/W2376932109"],"abstract_inverted_index":{"Retrieval-augmented":[0],"generation":[1],"(RAG)":[2],"enables":[3],"large":[4],"language":[5],"models":[6],"(LLMs)":[7],"to":[8,45,133],"generate":[9],"answers":[10],"with":[11,77,105],"citations":[12],"from":[13,71],"source":[14],"documents":[15,34],"containing":[16],"''ground":[17],"truth''.":[18],"A":[19],"crucial":[20],"factor":[21],"in":[22,31],"RAG":[23,49],"evaluation":[24],"is":[25],"''support'',":[26],"or":[27],"whether":[28],"the":[29,32,36,46,95],"information":[30],"cited":[33],"supports":[35],"answer.":[37],"We":[38,63,123],"conducted":[39],"a":[40,108,117,125],"comparative":[41],"study":[42],"of":[43,79,94,128],"submissions":[44],"TREC":[47],"2024":[48],"Track,":[50],"evaluating":[51],"an":[52,99],"automatic":[53],"LLM":[54,80,113],"judge":[55,102],"(GPT-4o)":[56],"against":[57],"human":[58,88,101,109,129],"judges":[59,114],"for":[60,120],"support":[61,121],"assessment.":[62,122],"considered":[64],"two":[65],"conditions:":[66],"(1)":[67],"fully":[68],"manual":[69,75],"assessments":[70,76],"scratch":[72],"and":[73,89,130],"(2)":[74],"post-editing":[78],"predictions.":[81,91],"Our":[82],"results":[83],"indicate":[84],"good":[85],"agreement":[86],"between":[87],"GPT-4o":[90,106,131],"Further":[92],"analysis":[93,127],"disagreements":[96],"shows":[97],"that":[98,112],"independent":[100],"correlates":[103],"better":[104],"than":[107],"judge,":[110],"suggesting":[111],"can":[115],"be":[116],"reliable":[118],"alternative":[119],"provide":[124],"qualitative":[126],"errors":[132],"help":[134],"guide":[135],"future":[136],"evaluations.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}