{"id":"https://openalex.org/W4396816204","doi":"https://doi.org/10.48550/arxiv.2405.04727","title":"LLMs Can Patch Up Missing Relevance Judgments in Evaluation","display_name":"LLMs Can Patch Up Missing Relevance Judgments in Evaluation","publication_year":2024,"publication_date":"2024-05-08","ids":{"openalex":"https://openalex.org/W4396816204","doi":"https://doi.org/10.48550/arxiv.2405.04727"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2405.04727","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.04727","pdf_url":"https://arxiv.org/pdf/2405.04727","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2405.04727","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111226586","display_name":"Shivani Upadhyay","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Upadhyay, Shivani","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043026875","display_name":"Ehsan Kamalloo","orcid":"https://orcid.org/0000-0003-3081-8762"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kamalloo, Ehsan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5082997975","display_name":"Jimmy Lin","orcid":"https://orcid.org/0000-0002-0661-7189"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Jimmy","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5111226586"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13643","display_name":"Artificial Intelligence in Law","score":0.13040000200271606,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13643","display_name":"Artificial Intelligence in Law","score":0.13040000200271606,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.11590000241994858,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.783611536026001},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.4438275694847107},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.4367348849773407},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.34103453159332275},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.2962144613265991}],"concepts":[{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.783611536026001},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4438275694847107},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.4367348849773407},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.34103453159332275},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.2962144613265991},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2405.04727","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.04727","pdf_url":"https://arxiv.org/pdf/2405.04727","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2405.04727","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2405.04727","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2405.04727","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.04727","pdf_url":"https://arxiv.org/pdf/2405.04727","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8284766523","display_name":null,"funder_award_id":"(NSERC)","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F4320326644","display_name":"Canada First Research Excellence Fund","ror":null},{"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/W4396816204.pdf","grobid_xml":"https://content.openalex.org/works/W4396816204.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W4391375266","https://openalex.org/W2085384747","https://openalex.org/W2088166309","https://openalex.org/W1891216533","https://openalex.org/W2106071040","https://openalex.org/W4312133475","https://openalex.org/W4238976562","https://openalex.org/W2276587472","https://openalex.org/W2010073985"],"abstract_inverted_index":{"Unjudged":[0],"documents":[1,60,114],"or":[2],"holes":[3,46,109],"in":[4,11,16,49,119,148],"information":[5],"retrieval":[6,35],"benchmarks":[7],"are":[8],"considered":[9],"non-relevant":[10],"evaluation,":[12],"yielding":[13],"no":[14],"gains":[15],"measuring":[17],"effectiveness.":[18],"However,":[19],"these":[20],"missing":[21],"judgments":[22,95],"may":[23],"inadvertently":[24],"introduce":[25],"biases":[26],"into":[27],"the":[28,41,116,149],"evaluation":[29],"as":[30],"their":[31],"prevalence":[32],"for":[33,58,172],"a":[34,126,161],"model":[36],"is":[37,61,83],"heavily":[38],"contingent":[39],"on":[40,138,143,169],"pooling":[42],"process.":[43],"Thus,":[44],"filling":[45],"becomes":[47],"crucial":[48],"ensuring":[50],"reliable":[51],"and":[52,63,133,167,174],"accurate":[53],"evaluation.":[54],"Collecting":[55],"human":[56],"judgment":[57,118],"all":[59],"cumbersome":[62],"impractical.":[64],"In":[65],"this":[66,99],"paper,":[67],"we":[68,101],"aim":[69],"at":[70],"leveraging":[71],"large":[72],"language":[73],"models":[74],"(LLMs)":[75],"to":[76,84,91,96],"automatically":[77],"label":[78],"unjudged":[79],"documents.":[80],"Our":[81,123],"goal":[82],"instruct":[85],"an":[86,170],"LLM":[87],"using":[88],"detailed":[89],"instructions":[90],"assign":[92],"fine-grained":[93],"relevance":[94,117,135],"holes.":[97],"To":[98],"end,":[100],"systematically":[102],"simulate":[103],"scenarios":[104],"with":[105],"varying":[106],"degrees":[107],"of":[108,152,156,165],"by":[110],"randomly":[111],"dropping":[112],"relevant":[113],"from":[115],"TREC":[120,145],"DL":[121,146],"tracks.":[122],"experiments":[124,141],"reveal":[125],"strong":[127],"correlation":[128,164],"between":[129],"our":[130,139,158],"LLM-based":[131],"method":[132,159],"ground-truth":[134],"judgments.":[136],"Based":[137],"simulation":[140],"conducted":[142],"three":[144],"datasets,":[147],"extreme":[150],"scenario":[151],"retaining":[153],"only":[154],"10%":[155],"judgments,":[157],"achieves":[160],"Kendall":[162],"tau":[163],"0.87":[166],"0.92":[168],"average":[171],"Vicu\u00f1a-7B":[173],"GPT-3.5":[175],"Turbo":[176],"respectively.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}