{"id":"https://openalex.org/W4412377928","doi":"https://doi.org/10.1145/3726302.3730348","title":"Rankers, Judges, and Assistants: Towards Understanding the Interplay of LLMs in Information Retrieval Evaluation","display_name":"Rankers, Judges, and Assistants: Towards Understanding the Interplay of LLMs in Information Retrieval Evaluation","publication_year":2025,"publication_date":"2025-07-13","ids":{"openalex":"https://openalex.org/W4412377928","doi":"https://doi.org/10.1145/3726302.3730348"},"language":"en","primary_location":{"id":"doi:10.1145/3726302.3730348","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730348","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730348","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730348","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059926999","display_name":"Krisztian Balog","orcid":"https://orcid.org/0000-0003-2762-721X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Krisztian Balog","raw_affiliation_strings":["Google DeepMind, Stavanger, Norway"],"affiliations":[{"raw_affiliation_string":"Google DeepMind, Stavanger, Norway","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000115067","display_name":"Donald Metzler","orcid":"https://orcid.org/0000-0003-4276-6269"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Don Metzler","raw_affiliation_strings":["Google DeepMind, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google DeepMind, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100763094","display_name":"Zhen Qin","orcid":"https://orcid.org/0000-0001-6739-134X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhen Qin","raw_affiliation_strings":["Google DeepMind, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google DeepMind, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5059926999"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":25.3275,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.99583642,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3865","last_page":"3875"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9829000234603882,"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":0.9829000234603882,"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/T10028","display_name":"Topic Modeling","score":0.9793000221252441,"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/T14330","display_name":"Library Science and Information Systems","score":0.9498000144958496,"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":0.5254147052764893},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.331204891204834},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32733625173568726}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5254147052764893},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.331204891204834},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32733625173568726}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3726302.3730348","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730348","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730348","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"},{"id":"pmh:oai:arXiv.org:2503.19092","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.19092","pdf_url":"https://arxiv.org/pdf/2503.19092","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3726302.3730348","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730348","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730348","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":[{"score":0.5899999737739563,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412377928.pdf","grobid_xml":"https://content.openalex.org/works/W4412377928.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W569478347","https://openalex.org/W2970419734","https://openalex.org/W2970785793","https://openalex.org/W2981852735","https://openalex.org/W3100107515","https://openalex.org/W3180230246","https://openalex.org/W4284669679","https://openalex.org/W4288089799","https://openalex.org/W4376643691","https://openalex.org/W4384107234","https://openalex.org/W4384662964","https://openalex.org/W4384890816","https://openalex.org/W4385573057","https://openalex.org/W4385688511","https://openalex.org/W4389518726","https://openalex.org/W4389519254","https://openalex.org/W4389523765","https://openalex.org/W4391876619","https://openalex.org/W4392846374","https://openalex.org/W4394947904","https://openalex.org/W4399528455","https://openalex.org/W4400374549","https://openalex.org/W4400526908","https://openalex.org/W4400949264","https://openalex.org/W4401043313","https://openalex.org/W4401857670","https://openalex.org/W4401863498","https://openalex.org/W4402670032","https://openalex.org/W4402671190","https://openalex.org/W4404782181","https://openalex.org/W4405144074","https://openalex.org/W4408811965","https://openalex.org/W4411549495","https://openalex.org/W6602744131"],"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/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"are":[4],"increasingly":[5],"integral":[6],"to":[7,79,86,128],"information":[8,115],"retrieval":[9],"(IR),":[10],"powering":[11],"ranking,":[12],"evaluation,":[13],"and":[14,41,51,124],"AI-assisted":[15],"content":[16],"creation.":[17],"This":[18,36],"widespread":[19],"adoption":[20],"necessitates":[21],"a":[22,108,125],"critical":[23],"examination":[24],"of":[25,62,97,112,133],"potential":[26],"biases":[27],"arising":[28],"from":[29],"the":[30,58,105,113,130],"interplay":[31],"between":[32],"these":[33],"LLM-based":[34,49,54,69],"components.":[35],"paper":[37],"synthesizes":[38],"existing":[39],"research":[40,126],"presents":[42],"novel":[43],"experiment":[44],"designs":[45],"that":[46],"explore":[47],"how":[48],"rankers":[50],"assistants":[52],"influence":[53],"judges.":[55],"We":[56],"provide":[57],"first":[59],"empirical":[60],"evidence":[61,96],"LLM":[63,76],"judges":[64],"exhibiting":[65],"significant":[66],"bias":[67,98],"towards":[68],"rankers.":[70],"Furthermore,":[71],"we":[72,120],"observe":[73],"limitations":[74],"in":[75,135],"judges'":[77],"ability":[78],"discern":[80],"subtle":[81],"system":[82],"performance":[83],"differences.":[84],"Contrary":[85],"some":[87],"previous":[88],"findings,":[89],"our":[90],"preliminary":[91],"study":[92],"does":[93],"not":[94],"find":[95],"against":[99],"AI-generated":[100],"content.":[101],"These":[102],"results":[103],"highlight":[104],"need":[106],"for":[107],"more":[109],"holistic":[110],"view":[111],"LLM-driven":[114],"ecosystem.":[116],"To":[117],"this":[118],"end,":[119],"offer":[121],"initial":[122],"guidelines":[123],"agenda":[127],"ensure":[129],"reliable":[131],"use":[132],"LLMs":[134],"IR":[136],"evaluation.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}