{"id":"https://openalex.org/W7162499704","doi":"https://doi.org/10.48550/arxiv.2605.26730","title":"PRISM: A Multi-Dimensional Benchmark for Evaluating LLM Peer Reviewers","display_name":"PRISM: A Multi-Dimensional Benchmark for Evaluating LLM Peer Reviewers","publication_year":2026,"publication_date":"2026-05-26","ids":{"openalex":"https://openalex.org/W7162499704","doi":"https://doi.org/10.48550/arxiv.2605.26730"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.26730","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.26730","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.26730","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137147630","display_name":"Ngoc Phan Phuoc Loc","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Loc, Ngoc Phan Phuoc","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137124218","display_name":"Toan Huynh La Viet","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"La Viet, Toan Huynh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137133769","display_name":"Thanh Tran Khanh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khanh, Thanh Tran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102016984","display_name":"Duy Anh Nguy\u1ec5n","orcid":"https://orcid.org/0000-0002-2432-2050"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nguyen, Duy A","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137107419","display_name":"Tuan Anh Nguyen Pham","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pham, Tuan Anh Nguyen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113796172","display_name":"Th\u00e0nh Nguyen","orcid":"https://orcid.org/0009-0001-1723-3164"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nguyen, Thanh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137117920","display_name":"Nitesh V. Chawla","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chawla, Nitesh V.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137134533","display_name":"Wray Buntine","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Buntine, Wray","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137121901","display_name":"Kok-Seng Wong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wong, Kok-Seng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080642445","display_name":"Khoa D. Doan","orcid":"https://orcid.org/0000-0002-1610-8206"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Doan, Khoa D.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137119329","display_name":"Binh T. Nguyen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nguyen, Binh T.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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/T13274","display_name":"Expert finding and Q&A systems","score":0.3499999940395355,"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"}},"topics":[{"id":"https://openalex.org/T13274","display_name":"Expert finding and Q&A systems","score":0.3499999940395355,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.16670000553131104,"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/T11492","display_name":"Academic integrity and plagiarism","score":0.05490000173449516,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.7807999849319458},{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.745199978351593},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6308000087738037},{"id":"https://openalex.org/keywords/fluency","display_name":"Fluency","score":0.5309000015258789},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4334000051021576},{"id":"https://openalex.org/keywords/prism","display_name":"Prism","score":0.3984000086784363},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.36649999022483826}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7807999849319458},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7493000030517578},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.745199978351593},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6308000087738037},{"id":"https://openalex.org/C2777413886","wikidata":"https://www.wikidata.org/wiki/Q3276013","display_name":"Fluency","level":2,"score":0.5309000015258789},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5110999941825867},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5042999982833862},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4830999970436096},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4334000051021576},{"id":"https://openalex.org/C67666897","wikidata":"https://www.wikidata.org/wiki/Q165896","display_name":"Prism","level":2,"score":0.3984000086784363},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.36649999022483826},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3418999910354614},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32179999351501465},{"id":"https://openalex.org/C120060458","wikidata":"https://www.wikidata.org/wiki/Q10145","display_name":"Milestone","level":2,"score":0.3156999945640564},{"id":"https://openalex.org/C63882131","wikidata":"https://www.wikidata.org/wiki/Q17122954","display_name":"Strengths and weaknesses","level":2,"score":0.31060001254081726},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30230000615119934},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2904999852180481},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C98184364","wikidata":"https://www.wikidata.org/wiki/Q1780131","display_name":"Argument (complex analysis)","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C34585555","wikidata":"https://www.wikidata.org/wiki/Q1368723","display_name":"Learning curve","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.26730","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.26730","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.26730","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.26730","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"score":0.5790303349494934,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,135,197],"rapid":[1],"growth":[2],"in":[3,18,103],"submissions":[4],"to":[5,32,114,209],"machine":[6],"learning":[7],"venues":[8],"has":[9],"strained":[10],"the":[11,167,171],"scientific":[12,37],"peer-review":[13],"system":[14,164],"and":[15,75,88,108,121,133,156,223],"intensified":[16],"interest":[17],"LLM-based":[19],"automated":[20,118],"peer":[21],"reviewers.":[22],"However,":[23,161],"how":[24],"good":[25],"these":[26],"systems":[27,120],"are":[28,203],"actually,":[29],"especially":[30],"compared":[31],"human":[33,122,144,172,210],"reviewers":[34,123,145,202],"at":[35,177,229],"catching":[36],"gaps,":[38],"remains":[39],"poorly":[40],"understood.":[41],"In":[42],"this":[43],"work,":[44],"we":[45],"introduce":[46],"PRISM":[47,99,113],"(Peer":[48],"Review":[49],"Intelligence":[50],"via":[51],"Structured":[52],"Multi-dimensional":[53,76],"assessment),":[54],"a":[55,125,181],"benchmarking":[56],"framework":[57],"that":[58,94,138,192,200],"evaluates":[59],"review":[60],"quality":[61],"across":[62,174],"four":[63],"dimensions:":[64,148],"Depth":[65],"of":[66,128,151,170],"Analysis,":[67],"Novelty":[68],"Assessment,Flaw":[69],"Identification":[70],"&":[71],"Major":[72],"Issues":[73],"Prioritization,":[74],"Constructiveness.":[77],"Unlike":[78],"most":[79],"existing":[80],"evaluations":[81],"based":[82],"on":[83,124,146],"surface-level":[84],"metrics":[85,194],"like":[86],"ROUGE":[87],"BLEU,":[89],"or":[90,142],"unconstrained":[91],"LLM-as-a-judge":[92],"prompting":[93],"conflates":[95],"fluency":[96],"with":[97,185],"rigor,":[98],"grounds":[100],"each":[101],"dimension":[102],"argument":[104],"mining,":[105],"retrieval-augmented":[106],"verification,":[107,155],"consensus-based":[109],"scoring.":[110],"We":[111],"apply":[112],"benchmark":[115],"five":[116],"leading":[117],"reviewer":[119],"stratified":[126],"corpus":[127],"reviews":[129],"from":[130],"ICLR,":[131],"ICML,":[132],"NeurIPS.":[134],"results":[136,225],"reveal":[137],"LLMs":[139],"can":[140,226],"match":[141],"beat":[143],"individual":[147],"comparable":[149],"depth":[150],"analysis,":[152],"stronger":[153],"novelty":[154],"highly":[157],"accurate":[158],"critique":[159],"prioritization.":[160],"no":[162],"single":[163],"consistently":[165],"matches":[166],"balanced":[168],"performance":[169],"baseline":[173],"all":[175],"dimensions":[176],"once.":[178],"Each":[179],"exhibits":[180],"distinct":[182],"specialization":[183],"profile":[184],"characteristic":[186],"blind":[187],"spots":[188],"--":[189],"failure":[190],"modes":[191],"aggregate":[193],"miss":[195],"entirely.":[196],"implication":[198],"is":[199],"LLM":[201],"best":[204],"understood":[205],"as":[206,218],"targeted":[207],"supplements":[208],"review,":[211],"effective":[212],"within":[213],"specific":[214],"dimensions,":[215],"but":[216],"unreliable":[217],"standalone":[219],"replacements.":[220],"Our":[221],"demo":[222],"key":[224],"be":[227],"found":[228],"https://khanhthanhdev.github.io/prism-page/.":[230]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-28T00:00:00"}