{"id":"https://openalex.org/W7168423013","doi":"https://doi.org/10.1145/3805712.3808601","title":"Auto-Judge: A Cross-Task Benchmark for Comparing LLM Judges for Citation-Grounded RAG Systems","display_name":"Auto-Judge: A Cross-Task Benchmark for Comparing LLM Judges for Citation-Grounded RAG Systems","publication_year":2026,"publication_date":"2026-07-15","ids":{"openalex":"https://openalex.org/W7168423013","doi":"https://doi.org/10.1145/3805712.3808601"},"language":null,"primary_location":{"id":"doi:10.1145/3805712.3808601","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3808601","pdf_url":null,"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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805712.3808601","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140910435","display_name":"Naghmeh Farzi","orcid":"https://orcid.org/0009-0000-3297-8888"},"institutions":[{"id":"https://openalex.org/I161057412","display_name":"University of New Hampshire","ror":"https://ror.org/01rmh9n78","country_code":"US","type":"education","lineage":["https://openalex.org/I161057412"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Naghmeh Farzi","raw_affiliation_strings":["University of New Hampshire, Durham, NH, USA"],"raw_orcid":"https://orcid.org/0009-0000-3297-8888","affiliations":[{"raw_affiliation_string":"University of New Hampshire, Durham, NH, USA","institution_ids":["https://openalex.org/I161057412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140949638","display_name":"Tim Hagen","orcid":"https://orcid.org/0009-0000-4854-7249"},"institutions":[{"id":"https://openalex.org/I106157433","display_name":"University of Kassel","ror":"https://ror.org/04zc7p361","country_code":"DE","type":"education","lineage":["https://openalex.org/I106157433"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tim Hagen","raw_affiliation_strings":["University of Kassel, Kassel, Germany and hessian.AI, Darmstadt, Germany"],"raw_orcid":"https://orcid.org/0009-0000-4854-7249","affiliations":[{"raw_affiliation_string":"University of Kassel, Kassel, Germany and hessian.AI, Darmstadt, Germany","institution_ids":["https://openalex.org/I106157433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140783433","display_name":"Eugene Yang","orcid":"https://orcid.org/0000-0002-0051-1535"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eugene Yang","raw_affiliation_strings":["Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":"https://orcid.org/0000-0002-0051-1535","affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140947739","display_name":"Maik Fr\u00f6be","orcid":"https://orcid.org/0000-0002-1003-981X"},"institutions":[{"id":"https://openalex.org/I76198965","display_name":"Friedrich Schiller University Jena","ror":"https://ror.org/05qpz1x62","country_code":"DE","type":"education","lineage":["https://openalex.org/I76198965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Maik Fr\u00f6be","raw_affiliation_strings":["Friedrich-Schiller-Universit\u00e4t Jena, Jena, Germany"],"raw_orcid":"https://orcid.org/0000-0002-1003-981X","affiliations":[{"raw_affiliation_string":"Friedrich-Schiller-Universit\u00e4t Jena, Jena, Germany","institution_ids":["https://openalex.org/I76198965"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140776281","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"],"raw_orcid":"https://orcid.org/0000-0001-6296-601X","affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140827148","display_name":"Hossein A. Rahmani","orcid":"https://orcid.org/0000-0002-2779-4942"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hossein A. Rahmani","raw_affiliation_strings":["University College London, London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-2779-4942","affiliations":[{"raw_affiliation_string":"University College London, London, United Kingdom","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140917940","display_name":"Xi Wang","orcid":"https://orcid.org/0000-0001-5936-9919"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xi Wang","raw_affiliation_strings":["University of Sheffield, Sheffield, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0001-5936-9919","affiliations":[{"raw_affiliation_string":"University of Sheffield, Sheffield, United Kingdom","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140859619","display_name":"Oleg Zendel","orcid":"https://orcid.org/0000-0003-1535-0989"},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Oleg Zendel","raw_affiliation_strings":["RMIT University, Melbourne, Australia"],"raw_orcid":"https://orcid.org/0000-0003-1535-0989","affiliations":[{"raw_affiliation_string":"RMIT University, Melbourne, Australia","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140828243","display_name":"Martin Potthast","orcid":"https://orcid.org/0000-0003-2451-0665"},"institutions":[{"id":"https://openalex.org/I106157433","display_name":"University of Kassel","ror":"https://ror.org/04zc7p361","country_code":"DE","type":"education","lineage":["https://openalex.org/I106157433"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Martin Potthast","raw_affiliation_strings":["University of Kassel, Kassel, Germany, hessian.AI, Darmstadt, Germany, and ScaDS.AI, Leipzig, Germany"],"raw_orcid":"https://orcid.org/0000-0003-2451-0665","affiliations":[{"raw_affiliation_string":"University of Kassel, Kassel, Germany, hessian.AI, Darmstadt, Germany, and ScaDS.AI, Leipzig, Germany","institution_ids":["https://openalex.org/I106157433"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5140816684","display_name":"Laura Dietz","orcid":"https://orcid.org/0000-0003-1624-3907"},"institutions":[{"id":"https://openalex.org/I161057412","display_name":"University of New Hampshire","ror":"https://ror.org/01rmh9n78","country_code":"US","type":"education","lineage":["https://openalex.org/I161057412"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Laura Dietz","raw_affiliation_strings":["University of New Hampshire, Durham, NH, USA"],"raw_orcid":"https://orcid.org/0000-0003-1624-3907","affiliations":[{"raw_affiliation_string":"University of New Hampshire, Durham, NH, USA","institution_ids":["https://openalex.org/I161057412"]}]}],"institutions":[],"countries_distinct_count":5,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3159","last_page":"3166"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5177000164985657},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.320499986410141},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.25859999656677246},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.25209999084472656},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.24330000579357147}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6344000101089478},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5177000164985657},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39579999446868896},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.320499986410141},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2897000014781952},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.25859999656677246},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2563000023365021},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.25209999084472656},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.24330000579357147},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.23849999904632568}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805712.3808601","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3808601","pdf_url":null,"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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805712.3808601","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3808601","pdf_url":null,"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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1965690069","https://openalex.org/W1979562318","https://openalex.org/W2115536324","https://openalex.org/W2963961878","https://openalex.org/W3034471540","https://openalex.org/W3099977667","https://openalex.org/W3133594109","https://openalex.org/W3142305657","https://openalex.org/W3169283738","https://openalex.org/W4284698816","https://openalex.org/W4385571232","https://openalex.org/W4385688511","https://openalex.org/W4389519254","https://openalex.org/W4400526284","https://openalex.org/W4400526908","https://openalex.org/W4401042854","https://openalex.org/W4401330297","https://openalex.org/W4402670032","https://openalex.org/W4404782847","https://openalex.org/W4405143965","https://openalex.org/W4405767463","https://openalex.org/W4409166944","https://openalex.org/W4412377041","https://openalex.org/W4412377058","https://openalex.org/W4412673258","https://openalex.org/W4412886854","https://openalex.org/W4415797148","https://openalex.org/W4416017378","https://openalex.org/W4416017619","https://openalex.org/W6929435551","https://openalex.org/W7133239970","https://openalex.org/W7140083211","https://openalex.org/W7167899113"],"related_works":[],"abstract_inverted_index":{"We":[0],"present":[1],"the":[2,6],"Auto-Judge":[3],"resource":[4,27],"for":[5,49,61],"meta-evaluation":[7],"of":[8,33],"automated":[9],"LLM":[10],"judges,":[11],"especially":[12],"judges":[13],"that":[14,20],"evaluate":[15],"Retrieval-Augmented":[16],"Generation":[17],"(RAG)":[18],"systems":[19],"ground":[21],"their":[22],"response":[23],"with":[24,41],"citations.":[25],"The":[26],"couples":[28],"(i)":[29],"a":[30,43,54],"data":[31],"release":[32],"topics,":[34],"pooled":[35],"RAG":[36],"responses,":[37],"and":[38,46,56,64],"human":[39],"judgments,":[40],"(ii)":[42],"standardized":[44],"protocol":[45],"software":[47],"infrastructure":[48],"implementing":[50],"\"LLM-as-a-judge\"":[51],"methods":[52],"in":[53],"reproducible":[55],"extensible":[57],"way,":[58],"including":[59],"support":[60],"parameter":[62],"sweeps":[63],"variant":[65],"tracking.":[66]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-17T05:52:16.776730","created_date":"2026-07-16T00:00:00"}