{"id":"https://openalex.org/W4415456690","doi":"https://doi.org/10.3390/info16110926","title":"PEARL: A Rubric-Driven Multi-Metric Framework for LLM Evaluation","display_name":"PEARL: A Rubric-Driven Multi-Metric Framework for LLM Evaluation","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4415456690","doi":"https://doi.org/10.3390/info16110926"},"language":"en","primary_location":{"id":"doi:10.3390/info16110926","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info16110926","pdf_url":"https://www.mdpi.com/2078-2489/16/11/926/pdf?version=1761134065","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2078-2489/16/11/926/pdf?version=1761134065","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049418389","display_name":"C\u0103t\u0103lin Anghel","orcid":"https://orcid.org/0000-0002-1849-3072"},"institutions":[{"id":"https://openalex.org/I3122748864","display_name":"\"Dunarea de Jos\" University of Galati","ror":"https://ror.org/052sta926","country_code":"RO","type":"education","lineage":["https://openalex.org/I3122748864"]}],"countries":["RO"],"is_corresponding":true,"raw_author_name":"Catalin Anghel","raw_affiliation_strings":["Department of Computer Science and Information Technology, \u201cDun\u0103rea de Jos\u201d University of Galati, \u0218tiin\u021bei St. 2, 800146 Galati, Romania"],"raw_orcid":"https://orcid.org/0000-0002-1849-3072","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Technology, \u201cDun\u0103rea de Jos\u201d University of Galati, \u0218tiin\u021bei St. 2, 800146 Galati, Romania","institution_ids":["https://openalex.org/I3122748864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119223040","display_name":"Andreea Alexandra Anghel","orcid":"https://orcid.org/0009-0008-2537-6713"},"institutions":[{"id":"https://openalex.org/I3122748864","display_name":"\"Dunarea de Jos\" University of Galati","ror":"https://ror.org/052sta926","country_code":"RO","type":"education","lineage":["https://openalex.org/I3122748864"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Andreea Alexandra Anghel","raw_affiliation_strings":["Computer Science and Information Technology Program, Faculty of \u201cAutomation, Computer Science, Electrical and Electronic Engineering\u201d, \u201cDun\u0103rea de Jos\u201d University of Galati, 800008 Galati, Romania"],"raw_orcid":"https://orcid.org/0009-0008-2537-6713","affiliations":[{"raw_affiliation_string":"Computer Science and Information Technology Program, Faculty of \u201cAutomation, Computer Science, Electrical and Electronic Engineering\u201d, \u201cDun\u0103rea de Jos\u201d University of Galati, 800008 Galati, Romania","institution_ids":["https://openalex.org/I3122748864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052924860","display_name":"Emilia Pecheanu","orcid":"https://orcid.org/0000-0003-1155-5274"},"institutions":[{"id":"https://openalex.org/I3122748864","display_name":"\"Dunarea de Jos\" University of Galati","ror":"https://ror.org/052sta926","country_code":"RO","type":"education","lineage":["https://openalex.org/I3122748864"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Emilia Pecheanu","raw_affiliation_strings":["Department of Computer Science and Information Technology, \u201cDun\u0103rea de Jos\u201d University of Galati, \u0218tiin\u021bei St. 2, 800146 Galati, Romania"],"raw_orcid":"https://orcid.org/0000-0003-1155-5274","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Technology, \u201cDun\u0103rea de Jos\u201d University of Galati, \u0218tiin\u021bei St. 2, 800146 Galati, Romania","institution_ids":["https://openalex.org/I3122748864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110800740","display_name":"Marian Cr\u0103ciun","orcid":"https://orcid.org/0009-0006-9970-2556"},"institutions":[{"id":"https://openalex.org/I3122748864","display_name":"\"Dunarea de Jos\" University of Galati","ror":"https://ror.org/052sta926","country_code":"RO","type":"education","lineage":["https://openalex.org/I3122748864"]}],"countries":["RO"],"is_corresponding":true,"raw_author_name":"Marian Viorel Craciun","raw_affiliation_strings":["Department of Computer Science and Information Technology, \u201cDun\u0103rea de Jos\u201d University of Galati, \u0218tiin\u021bei St. 2, 800146 Galati, Romania"],"raw_orcid":"https://orcid.org/0009-0006-9970-2556","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Technology, \u201cDun\u0103rea de Jos\u201d University of Galati, \u0218tiin\u021bei St. 2, 800146 Galati, Romania","institution_ids":["https://openalex.org/I3122748864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103039137","display_name":"Adina Cocu","orcid":"https://orcid.org/0000-0003-0935-4713"},"institutions":[{"id":"https://openalex.org/I3122748864","display_name":"\"Dunarea de Jos\" University of Galati","ror":"https://ror.org/052sta926","country_code":"RO","type":"education","lineage":["https://openalex.org/I3122748864"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Adina Cocu","raw_affiliation_strings":["Department of Computer Science and Information Technology, \u201cDun\u0103rea de Jos\u201d University of Galati, \u0218tiin\u021bei St. 2, 800146 Galati, Romania"],"raw_orcid":"https://orcid.org/0000-0003-0935-4713","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Technology, \u201cDun\u0103rea de Jos\u201d University of Galati, \u0218tiin\u021bei St. 2, 800146 Galati, Romania","institution_ids":["https://openalex.org/I3122748864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044134990","display_name":"Cristian Niculita","orcid":null},"institutions":[{"id":"https://openalex.org/I3122748864","display_name":"\"Dunarea de Jos\" University of Galati","ror":"https://ror.org/052sta926","country_code":"RO","type":"education","lineage":["https://openalex.org/I3122748864"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Cristian Niculita","raw_affiliation_strings":["Department of Computer Science and Information Technology, \u201cDun\u0103rea de Jos\u201d University of Galati, \u0218tiin\u021bei St. 2, 800146 Galati, Romania"],"raw_orcid":"https://orcid.org/0009-0004-1461-4115","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Technology, \u201cDun\u0103rea de Jos\u201d University of Galati, \u0218tiin\u021bei St. 2, 800146 Galati, Romania","institution_ids":["https://openalex.org/I3122748864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5049418389","https://openalex.org/A5110800740"],"corresponding_institution_ids":["https://openalex.org/I3122748864"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":1.9057,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.89849304,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"16","issue":"11","first_page":"926","last_page":"926"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9520000219345093,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9520000219345093,"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/T10028","display_name":"Topic Modeling","score":0.9473999738693237,"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/T10260","display_name":"Software Engineering Research","score":0.9156000018119812,"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/rubric","display_name":"Rubric","score":0.85589998960495},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5512999892234802},{"id":"https://openalex.org/keywords/proxy","display_name":"Proxy (statistics)","score":0.5105000138282776},{"id":"https://openalex.org/keywords/pearl","display_name":"Pearl","score":0.3456999957561493},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.34529998898506165},{"id":"https://openalex.org/keywords/confidence-interval","display_name":"Confidence interval","score":0.31310001015663147}],"concepts":[{"id":"https://openalex.org/C111640148","wikidata":"https://www.wikidata.org/wiki/Q847349","display_name":"Rubric","level":2,"score":0.85589998960495},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5512999892234802},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5329999923706055},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.5105000138282776},{"id":"https://openalex.org/C2779251273","wikidata":"https://www.wikidata.org/wiki/Q43436","display_name":"Pearl","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.34529998898506165},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.31310001015663147},{"id":"https://openalex.org/C2781306805","wikidata":"https://www.wikidata.org/wiki/Q4789761","display_name":"Argumentative","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26930001378059387},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.266400009393692},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.2596000134944916},{"id":"https://openalex.org/C3018260909","wikidata":"https://www.wikidata.org/wiki/Q1322871","display_name":"Exploratory analysis","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.25380000472068787},{"id":"https://openalex.org/C166052673","wikidata":"https://www.wikidata.org/wiki/Q83021","display_name":"Empirical evidence","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/info16110926","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info16110926","pdf_url":"https://www.mdpi.com/2078-2489/16/11/926/pdf?version=1761134065","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:240de091c2d5434397a61eff000d19fc","is_oa":true,"landing_page_url":"https://doaj.org/article/240de091c2d5434397a61eff000d19fc","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Information, Vol 16, Iss 11, p 926 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/info16110926","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info16110926","pdf_url":"https://www.mdpi.com/2078-2489/16/11/926/pdf?version=1761134065","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415456690.pdf","grobid_xml":"https://content.openalex.org/works/W4415456690.grobid-xml"},"referenced_works_count":51,"referenced_works":["https://openalex.org/W2739046565","https://openalex.org/W2806532810","https://openalex.org/W2888159079","https://openalex.org/W2890771450","https://openalex.org/W2981731882","https://openalex.org/W3103450644","https://openalex.org/W3121603349","https://openalex.org/W3133543405","https://openalex.org/W3198690080","https://openalex.org/W3211402614","https://openalex.org/W4285245049","https://openalex.org/W4296467532","https://openalex.org/W4309689362","https://openalex.org/W4385571412","https://openalex.org/W4389134770","https://openalex.org/W4389344855","https://openalex.org/W4389408896","https://openalex.org/W4389520436","https://openalex.org/W4392976364","https://openalex.org/W4402481124","https://openalex.org/W4402671506","https://openalex.org/W4402671934","https://openalex.org/W4402683930","https://openalex.org/W4402684074","https://openalex.org/W4402819936","https://openalex.org/W4403503813","https://openalex.org/W4403764183","https://openalex.org/W4404515031","https://openalex.org/W4404781628","https://openalex.org/W4404782348","https://openalex.org/W4404782748","https://openalex.org/W4404783401","https://openalex.org/W4405183979","https://openalex.org/W4405239924","https://openalex.org/W4407108350","https://openalex.org/W4407623306","https://openalex.org/W4407743320","https://openalex.org/W4408292186","https://openalex.org/W4408598315","https://openalex.org/W4408906028","https://openalex.org/W4410550984","https://openalex.org/W4410862854","https://openalex.org/W4410988526","https://openalex.org/W4411119926","https://openalex.org/W4411429801","https://openalex.org/W4411630288","https://openalex.org/W4412944575","https://openalex.org/W4412995610","https://openalex.org/W4413025843","https://openalex.org/W4413072353","https://openalex.org/W6908891043"],"related_works":[],"abstract_inverted_index":{"Background":[0],"and":[1,22,34,59,75,89,115,147,170,177,193,205,216,218,234,245,251,275,290,298,304,311],"objectives:":[2],"Evaluating":[3],"Large":[4],"Language":[5],"Models":[6],"(LLMs)":[7],"presents":[8],"two":[9],"interrelated":[10],"challenges:":[11],"the":[12,23,78,181,242,249,262],"general":[13],"problem":[14,25],"of":[15,26,197,225,255],"assessing":[16],"model":[17],"performance":[18,95,226],"across":[19,93,161,186],"diverse":[20],"tasks":[21],"specific":[24],"using":[27,81],"LLMs":[28,160,308],"themselves":[29],"as":[30,55,108,207],"evaluators":[31],"in":[32,63,77,229,309],"pedagogical":[33],"educational":[35],"contexts.":[36,313],"Existing":[37],"approaches":[38],"often":[39],"rely":[40],"on":[41],"single":[42],"metrics":[43,190,221],"or":[44],"opaque":[45],"preference-based":[46],"methods,":[47],"which":[48],"fail":[49],"to":[50,85,210,267],"capture":[51,222],"critical":[52],"dimensions":[53],"such":[54,107],"explanation":[56],"quality,":[57],"robustness,":[58],"argumentative":[60],"diversity\u2014attributes":[61],"essential":[62],"instructional":[64,312],"settings.":[65],"This":[66,173],"paper":[67],"introduces":[68],"PEARL,":[69],"a":[70,279,295],"novel":[71],"framework":[72,119,266],"conceived,":[73],"operationalized,":[74],"evaluated":[76,153],"present":[79],"work":[80],"LLM-based":[82,175],"scorers,":[83],"designed":[84],"provide":[86],"interpretable,":[87],"reproducible,":[88],"pedagogically":[90],"meaningful":[91],"assessments":[92],"multiple":[94],"dimensions.":[96,258],"Methods:":[97],"PEARL":[98,154,260],"integrates":[99],"three":[100],"specialized":[101],"rubrics\u2014Technical,":[102],"Argumentative,":[103],"And":[104],"Explanation-focused\u2014covering":[105],"aspects":[106,224],"factual":[109],"accuracy,":[110],"clarity,":[111],"completeness,":[112],"originality,":[113],"dialecticality,":[114],"explanatory":[116],"usefulness.":[117],"The":[118],"defines":[120],"seven":[121],"complementary":[122,223,250],"metrics:":[123],"Rubric":[124,132],"Win":[125,129,139],"Count":[126],"(RWC),":[127],"Global":[128],"Rate":[130,150],"(GWR),":[131],"Mean":[133],"Advantage":[134],"(RMA),":[135],"Consistency":[136],"Spread":[137],"(CS),":[138],"Confidence":[140],"Score":[141],"(WCS),":[142],"Explanation":[143],"Quality":[144],"Index":[145],"(EQI),":[146],"Dialectical":[148],"Presence":[149],"(DPR).":[151],"We":[152],"by":[155,168],"evaluating":[156],"eight":[157],"open-weight":[158],"instruction-tuned":[159],"51":[162],"prompts,":[163],"with":[164,180,201,241,307],"outputs":[165],"scored":[166],"independently":[167],"GPT-4":[169,182,243],"LLaMA":[171],"3:instruct.":[172],"constitutes":[174],"evaluation,":[176],"observed":[178],"alignment":[179],"proxy":[183],"is":[184,261],"mixed":[185],"metrics.":[187],"Results:":[188],"Preference-based":[189],"(RMA,":[191],"RWC,":[192],"GWR)":[194],"show":[195],"evidence":[196],"group":[198],"separation,":[199],"reported":[200],"bootstrap":[202],"confidence":[203],"intervals":[204],"interpreted":[206],"exploratory":[208],"due":[209],"small":[211],"samples,":[212],"while":[213],"robustness-oriented":[214],"(CS":[215],"WCS)":[217],"reasoning-diversity":[219],"(DPR)":[220],"not":[227],"reflected":[228],"global":[230],"win":[231],"rate.":[232],"RMA":[233],"RWC":[235],"exhibit":[236],"statistically":[237],"significant,":[238],"FDR-controlled":[239],"correlations":[240],"proxy,":[244],"correlation":[246],"mapping":[247],"highlights":[248],"partially":[252],"orthogonal":[253],"nature":[254],"PEARL\u2019s":[256],"evaluation":[257,265],"Originality:":[259],"first":[263],"LLM":[264],"combine":[268],"multi-rubric":[269],"scoring,":[270],"explanation-aware":[271],"metrics,":[272],"robustness":[273],"analysis,":[274],"multi-LLM-evaluator":[276],"analysis":[277],"into":[278],"single,":[280],"extensible":[281],"system.":[282],"Its":[283],"multidimensional":[284],"design":[285],"supports":[286],"both":[287],"high-level":[288],"benchmarking":[289],"targeted":[291],"diagnostic":[292],"assessment,":[293],"offering":[294],"rigorous,":[296],"transparent,":[297],"versatile":[299],"methodology":[300],"for":[301],"researchers,":[302],"developers,":[303],"educators":[305],"working":[306],"high-stakes":[310]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-23T00:00:00"}
