{"id":"https://openalex.org/W4403582514","doi":"https://doi.org/10.1145/3627673.3679677","title":"Automatic Large Language Model Evaluation via Peer Review","display_name":"Automatic Large Language Model Evaluation via Peer Review","publication_year":2024,"publication_date":"2024-10-20","ids":{"openalex":"https://openalex.org/W4403582514","doi":"https://doi.org/10.1145/3627673.3679677"},"language":"en","primary_location":{"id":"doi:10.1145/3627673.3679677","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3627673.3679677","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 33rd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3627673.3679677","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030377390","display_name":"Zhumin Chu","orcid":"https://orcid.org/0000-0002-1233-0184"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhumin Chu","raw_affiliation_strings":["DCST, Tsinghua University & Quan Cheng Laboratory, Beijing, China"],"affiliations":[{"raw_affiliation_string":"DCST, Tsinghua University & Quan Cheng Laboratory, Beijing, China","institution_ids":["https://openalex.org/I4210136793","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089655391","display_name":"Qingyao Ai","orcid":"https://orcid.org/0000-0002-5030-709X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingyao Ai","raw_affiliation_strings":["Quan Cheng Laboratory & DCST, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Quan Cheng Laboratory & DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083011279","display_name":"Y. L. Tu","orcid":"https://orcid.org/0009-0001-7392-0524"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiteng Tu","raw_affiliation_strings":["DCST, Tsinghua University & Zhongguancun Laboratory, Beijing, China"],"affiliations":[{"raw_affiliation_string":"DCST, Tsinghua University & Zhongguancun Laboratory, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101638981","display_name":"Haitao Li","orcid":"https://orcid.org/0009-0006-8766-8610"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haitao Li","raw_affiliation_strings":["DCST, Tsinghua University & Zhongguancun Laboratory, Beijing, China"],"affiliations":[{"raw_affiliation_string":"DCST, Tsinghua University & Zhongguancun Laboratory, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668121","display_name":"Yiqun Liu","orcid":"https://orcid.org/0000-0002-0140-4512"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiqun Liu","raw_affiliation_strings":["DCST, Tsinghua University & Zhongguancun Laboratory, Beijing, China"],"affiliations":[{"raw_affiliation_string":"DCST, Tsinghua University & Zhongguancun Laboratory, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5030377390"],"corresponding_institution_ids":["https://openalex.org/I4210136793","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.695,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.76338139,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"384","last_page":"393"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991999864578247,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9939000010490417,"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/T13274","display_name":"Expert finding and Q&A systems","score":0.9850000143051147,"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":0.7745335698127747},{"id":"https://openalex.org/keywords/peer-to-peer","display_name":"Peer-to-peer","score":0.44935843348503113},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.439910888671875},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39631959795951843},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.24923625588417053}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7745335698127747},{"id":"https://openalex.org/C534932454","wikidata":"https://www.wikidata.org/wiki/Q161410","display_name":"Peer-to-peer","level":2,"score":0.44935843348503113},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.439910888671875},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39631959795951843},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.24923625588417053}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3627673.3679677","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3627673.3679677","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 33rd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3627673.3679677","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3627673.3679677","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 33rd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6399999856948853,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1593271688","https://openalex.org/W1985514943","https://openalex.org/W2740887992","https://openalex.org/W4284689799"],"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/W2002490650","https://openalex.org/W2322032246","https://openalex.org/W2057688614","https://openalex.org/W2067368164"],"abstract_inverted_index":{"The":[0,177,210],"impressive":[1],"performance":[2,59],"of":[3,33,60,84,89,132,149,180,215,234],"large":[4],"language":[5],"models":[6],"(LLMs)":[7],"has":[8,35],"attracted":[9],"considerable":[10],"attention":[11],"from":[12,70,146],"the":[13,31,58,86,92,103,110,130,156,164,168,175,187,213,229,232,235],"academic":[14,111],"and":[15,22,29,75,201],"industrial":[16],"communities.":[17],"Besides":[18],"how":[19,25],"to":[20,26,56,97,143,153,171],"construct":[21,138],"train":[23],"LLMs,":[24,162],"effectively":[27],"evaluate":[28,57,122,155],"compare":[30,174],"capacity":[32],"LLMs":[34,61,90,123,170,182,207],"also":[36],"been":[37],"well":[38],"recognized":[39],"as":[40],"an":[41],"important":[42],"yet":[43],"difficult":[44],"problem.":[45],"Existing":[46],"paradigms":[47,67],"rely":[48],"on":[49,62,186,197],"either":[50],"human":[51],"annotators":[52],"or":[53,173],"model-based":[54],"evaluators":[55],"different":[63,160],"tasks.":[64],"However,":[65],"these":[66,99],"often":[68],"suffer":[69],"high":[71],"cost,":[72],"low":[73],"generalizability,":[74],"inherited":[76],"biases":[77],"in":[78,91,109],"practice,":[79],"which":[80],"make":[81],"them":[82],"incapable":[83],"supporting":[85],"sustainable":[87],"development":[88],"long":[93],"term.":[94],"In":[95],"order":[96],"address":[98],"issues,":[100],"inspired":[101],"by":[102,159,190],"peer":[104,236],"review":[105,237],"systems":[106],"widely":[107],"used":[108],"publication":[112],"process,":[113],"we":[114,136,166],"propose":[115],"a":[116,125,133,139,147,220],"novel":[117],"framework":[118],"that":[119],"can":[120],"automatically":[121],"through":[124],"peer-review":[126],"process.":[127],"Specifically,":[128],"for":[129],"evaluation":[131],"specific":[134],"task,":[135],"first":[137],"small":[140],"qualification":[141],"exam":[142],"select":[144],"\"reviewers''":[145],"couple":[148],"powerful":[150],"LLMs.":[151],"Then,":[152],"actually":[154],"\"submissions\"":[157],"written":[158],"candidate":[161],"i.e.,":[163],"evaluatees,":[165],"use":[167],"reviewer":[169],"rate":[172],"submissions.":[176],"final":[178],"ranking":[179],"evaluatee":[181],"is":[183],"generated":[184],"based":[185],"results":[188,211],"provided":[189],"all":[191,228],"reviewers.":[192],"We":[193],"conducted":[194],"extensive":[195],"experiments":[196],"both":[198],"text":[199],"summarization":[200],"non-factoid":[202],"question-answering":[203],"tasks":[204],"with":[205],"eleven":[206],"including":[208],"GPT-4.":[209],"demonstrate":[212],"existence":[214],"biasness":[216],"when":[217],"evaluating":[218],"using":[219],"single":[221],"LLM.":[222],"Also,":[223],"our":[224],"PRE":[225],"model":[226],"outperforms":[227],"baselines,":[230],"illustrating":[231],"effectiveness":[233],"mechanism.":[238]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}