{"id":"https://openalex.org/W7134255296","doi":"https://doi.org/10.1145/3742414.3795100","title":"MultEval: Collaboratively Creating Criteria for LLM-as-a-Judge Systems","display_name":"MultEval: Collaboratively Creating Criteria for LLM-as-a-Judge Systems","publication_year":2026,"publication_date":"2026-03-09","ids":{"openalex":"https://openalex.org/W7134255296","doi":"https://doi.org/10.1145/3742414.3795100"},"language":null,"primary_location":{"id":"doi:10.1145/3742414.3795100","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3742414.3795100","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":"Companion Proceedings of the 31st International Conference on Intelligent User Interfaces","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3742414.3795100","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109909965","display_name":"Charles Chiang","orcid":"https://orcid.org/0009-0008-6079-4355"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Charles Chiang","raw_affiliation_strings":["Computer Science and Engineering, University of Notre Dame, Notre Dame, Indiana, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, University of Notre Dame, Notre Dame, Indiana, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029995655","display_name":"Simret Araya Gebreegziabher","orcid":"https://orcid.org/0000-0002-1772-6065"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Simret Araya Gebreegziabher","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, Indiana, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, Indiana, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093206754","display_name":"Annalisa Szymanski","orcid":null},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Annalisa Szymanski","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, Indiana, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, Indiana, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102965060","display_name":"Yukun Yang","orcid":"https://orcid.org/0009-0003-1971-4468"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yukun Yang","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, Indiana, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, Indiana, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010514636","display_name":"Hyo Jin","orcid":"https://orcid.org/0000-0001-8297-6792"},"institutions":[{"id":"https://openalex.org/I4210087032","display_name":"Cambridge Scientific (United States)","ror":"https://ror.org/001s4dh65","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087032"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hyo Jin Do","raw_affiliation_strings":["IBM Research, Cambridge, Massachusetts, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research, Cambridge, Massachusetts, USA","institution_ids":["https://openalex.org/I4210087032"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003440919","display_name":"Zahra Ashktorab","orcid":"https://orcid.org/0000-0002-0686-7911"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zahra Ashktorab","raw_affiliation_strings":["Thomas J. Watson Center, IBM Research, Yorktown Heights, New York, USA"],"affiliations":[{"raw_affiliation_string":"Thomas J. Watson Center, IBM Research, Yorktown Heights, New York, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022799238","display_name":"Werner Geyer","orcid":"https://orcid.org/0000-0003-4699-5026"},"institutions":[{"id":"https://openalex.org/I4210087032","display_name":"Cambridge Scientific (United States)","ror":"https://ror.org/001s4dh65","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087032"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Werner Geyer","raw_affiliation_strings":["IBM Research, Cambridge, Massachusetts, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research, Cambridge, Massachusetts, USA","institution_ids":["https://openalex.org/I4210087032"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007240808","display_name":"Toby Jia-Jun Li","orcid":"https://orcid.org/0000-0001-7902-7625"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Toby Jia-Jun Li","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, Indiana, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, Indiana, USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046270537","display_name":"Diego G\u00f3mez-Zar\u00e1","orcid":"https://orcid.org/0000-0002-4609-6293"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Diego G\u00f3mez-Zar\u00e1","raw_affiliation_strings":["Computer Science and Engineering, University of Notre Dame, Notre Dame, Indiana, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, University of Notre Dame, Notre Dame, Indiana, USA","institution_ids":["https://openalex.org/I107639228"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5109909965"],"corresponding_institution_ids":["https://openalex.org/I107639228"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.67385257,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"180","last_page":"184"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.36160001158714294,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.36160001158714294,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.21480000019073486,"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/T13643","display_name":"Artificial Intelligence in Law","score":0.06859999895095825,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.636900007724762},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5008999705314636},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.40149998664855957},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.37119999527931213},{"id":"https://openalex.org/keywords/collaboration","display_name":"Collaboration","score":0.31520000100135803}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.666100025177002},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.636900007724762},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5008999705314636},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.40149998664855957},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.39890000224113464},{"id":"https://openalex.org/C195094911","wikidata":"https://www.wikidata.org/wiki/Q14167904","display_name":"Process management","level":1,"score":0.397599995136261},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.37119999527931213},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35040000081062317},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.3409999907016754},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33980000019073486},{"id":"https://openalex.org/C559553711","wikidata":"https://www.wikidata.org/wiki/Q1145523","display_name":"Collaboration","level":2,"score":0.31520000100135803},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C554579003","wikidata":"https://www.wikidata.org/wiki/Q474157","display_name":"Collaborative software","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.2549999952316284}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3742414.3795100","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3742414.3795100","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":"Companion Proceedings of the 31st International Conference on Intelligent User Interfaces","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3742414.3795100","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3742414.3795100","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":"Companion Proceedings of the 31st International Conference on Intelligent User Interfaces","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2806532810","https://openalex.org/W2963903950","https://openalex.org/W4393971165","https://openalex.org/W4396832834","https://openalex.org/W4396833505","https://openalex.org/W4403334020","https://openalex.org/W4403826361","https://openalex.org/W4404986534","https://openalex.org/W4411505886","https://openalex.org/W4415314730","https://openalex.org/W4416037109","https://openalex.org/W7133239970"],"related_works":[],"abstract_inverted_index":{"LLM-as-a-judge":[0,70],"approaches":[1],"have":[2],"emerged":[3],"as":[4],"a":[5,21,38,61],"scalable":[6],"solution":[7],"for":[8,69],"evaluating":[9],"model":[10],"behaviors,":[11],"yet":[12],"they":[13],"rely":[14],"on":[15],"evaluation":[16,82],"criteria":[17,36,67,83,101],"often":[18],"created":[19],"by":[20,55,84],"single":[22],"individual,":[23],"embedding":[24],"that":[25],"person\u2019s":[26],"assumptions,":[27],"priorities,":[28],"and":[29,40,50,80,95],"interpretive":[30],"lens.":[31],"In":[32],"practice,":[33],"defining":[34],"such":[35],"is":[37],"collaborative":[39,66],"contested":[41],"process":[42],"involving":[43],"multiple":[44,74],"evaluators":[45,75],"with":[46],"different":[47],"values,":[48],"interpretations,":[49],"priorities\u2014an":[51],"aspect":[52],"largely":[53],"unsupported":[54],"existing":[56],"tools.":[57],"We":[58],"present":[59],"MultEval,":[60],"system":[62,104],"designed":[63],"to":[64,76],"support":[65,112],"creation":[68],"workflows.":[71],"MultEval":[72],"enables":[73],"jointly":[77],"create,":[78],"compare,":[79],"refine":[81],"surfacing":[85],"disagreements":[86],"early,":[87],"diagnosing":[88],"sources":[89],"of":[90,99],"conflict":[91],"using":[92],"consensus-building":[93],"theory,":[94],"encouraging":[96],"structured":[97],"exploration":[98],"alternative":[100],"formulations.":[102],"Our":[103],"demonstrates":[105],"how":[106],"intelligent":[107],"user":[108],"interfaces":[109],"can":[110],"better":[111],"multi-stakeholder":[113],"alignment":[114],"in":[115],"human\u2013AI":[116],"evaluation.":[117]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2026-03-10T00:00:00"}
