{"id":"https://openalex.org/W7162801773","doi":"https://doi.org/10.48550/arxiv.2605.30018","title":"Latent Performance Profiling of Large Language Models","display_name":"Latent Performance Profiling of Large Language Models","publication_year":2026,"publication_date":"2026-05-28","ids":{"openalex":"https://openalex.org/W7162801773","doi":"https://doi.org/10.48550/arxiv.2605.30018"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.30018","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.30018","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2605.30018","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137376661","display_name":"Tanmoy Chakraborty","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chakraborty, Tanmoy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137355991","display_name":"Ayan Sengupta","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sengupta, Ayan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105513963","display_name":"Suparna Bhattacharya","orcid":"https://orcid.org/0000-0001-9541-4027"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bhattacharya, Suparna","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137378165","display_name":"Partha Pratim Chakrabarti","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chakrabarti, Partha Pratim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137311358","display_name":"Amlan Chakrabarti","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chakrabarti, Amlan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089236765","display_name":"Supratik Chakraborty","orcid":"https://orcid.org/0000-0002-7527-7675"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chakraborty, Supratik","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137343183","display_name":"Partha Pratim Das","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Das, Partha Pratim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102724695","display_name":"Lipika Dey","orcid":"https://orcid.org/0000-0003-3831-5545"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dey, Lipika","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137336911","display_name":"Richa Singh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Singh, Richa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5050521702","display_name":"Mayank Vatsa","orcid":"https://orcid.org/0000-0001-5952-2274"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vatsa, Mayank","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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.19830000400543213,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.19830000400543213,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.14589999616146088,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.0885000005364418,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5314000248908997},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4277999997138977},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4104999899864197},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.3896999955177307},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.38510000705718994},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.36000001430511475},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.33820000290870667},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.31709998846054077},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.3156999945640564}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7218999862670898},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5870000123977661},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5439000129699707},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5314000248908997},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4277999997138977},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4104999899864197},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.3896999955177307},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3864000141620636},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.38510000705718994},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.36000001430511475},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.33820000290870667},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.31709998846054077},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3156999945640564},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3140000104904175},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.28839999437332153},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2863999903202057},{"id":"https://openalex.org/C65965080","wikidata":"https://www.wikidata.org/wiki/Q1806885","display_name":"Latent variable model","level":3,"score":0.2775000035762787},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C2779714256","wikidata":"https://www.wikidata.org/wiki/Q25305062","display_name":"Multiple Models","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C3020493868","wikidata":"https://www.wikidata.org/wiki/Q55631277","display_name":"Real world data","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.25459998846054077},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.25440001487731934}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.30018","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.30018","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2605.30018","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.30018","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[{"id":"https://metadata.un.org/sdg/16","score":0.5924307107925415,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2,147,167],"(LLMs)":[3],"frequently":[4],"achieve":[5],"impressive":[6],"scores":[7,171],"on":[8,56,119],"standardized":[9],"benchmarks,":[10],"yet":[11],"accuracy":[12,139],"alone":[13],"offers":[14],"a":[15,53,77,83,100,114,120,159,215],"limited":[16],"view":[17],"of":[18,88,116,148,162,219],"their":[19],"capabilities.":[20],"Evaluating":[21],"open-source":[22],"LLMs":[23],"through":[24],"leaderboards":[25],"faces":[26],"persistent":[27],"issues":[28],"like":[29],"data":[30],"contamination,":[31],"narrow":[32],"task":[33],"scope,":[34],"and":[35,109,124,133,194,229],"weak":[36],"alignment":[37],"with":[38,168,199],"real-world":[39],"reliability.":[40],"Benchmark-based":[41],"evaluations":[42],"such":[43,177],"as":[44,178],"MMLU":[45],"PRO,":[46],"BBH,":[47],"or":[48,67,182],"IFEval":[49],"primarily":[50],"capture":[51],"what":[52],"model":[54,220,225],"outputs":[55],"fixed":[57],"test":[58],"sets,":[59],"not":[60],"how":[61],"it":[62],"processes":[63],"information,":[64],"calibrates":[65],"uncertainty,":[66],"structures":[68],"internal":[69],"knowledge.":[70],"In":[71],"this":[72,91],"article,":[73],"we":[74,93,164,188],"advocate":[75],"for":[76,192],"shift":[78],"from":[79,106,204],"benchmark-centric":[80],"evaluation":[81,230],"toward":[82],"complementary,":[84],"state-centered":[85],"intrinsic":[86,200],"assessment":[87],"LLMs.":[89],"To":[90],"end,":[92],"introduce":[94],"Latent":[95],"Performance":[96],"Profiling":[97],"(LPP)":[98],"--":[99],"framework":[101],"that":[102,129,166,197,209],"derives":[103],"task-agnostic":[104],"diagnostics":[105],"hidden":[107,135],"activations":[108],"output":[110],"distributions.":[111],"LPP":[112,141,211],"defines":[113],"set":[115],"scalar":[117],"metrics":[118,201],"model's":[121],"latent":[122,175],"representations":[123],"dynamics,":[125],"revealing":[126],"scale-independent":[127],"traits":[128],"enable":[130],"interpretable":[131,217],"comparisons":[132],"uncover":[134],"vulnerabilities.":[136],"Unlike":[137],"static":[138],"scores,":[140],"provides":[142,214],"stable,":[143],"architecture-sensitive":[144],"signatures":[145],"across":[146,155],"similar":[149,169],"size.":[150],"With":[151],"extensive":[152],"empirical":[153],"analyses":[154],"eight":[156],"LLMs,":[157],"spanning":[158],"size":[160],"range":[161],"0.5B-14B,":[163],"demonstrate":[165],"benchmark":[170],"can":[172],"exhibit":[173],"contrasting":[174],"profiles,":[176],"differences":[179],"in":[180],"entropy":[181],"adaptability.":[183],"Guided":[184],"by":[185],"these":[186],"insights,":[187],"design":[189],"synthetic":[190],"probes":[191],"uncertainty":[193],"symbolic":[195],"reasoning":[196],"align":[198],"while":[202],"decoupling":[203],"leaderboard":[205],"bias.":[206],"We":[207],"recommend":[208],"reporting":[210],"alongside":[212],"benchmarks":[213],"deeper,":[216],"understanding":[218],"behavior,":[221],"enabling":[222],"more":[223],"reliable":[224],"selection,":[226],"safety":[227],"assessment,":[228],"beyond":[231],"surface-level":[232],"accuracy.":[233]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-30T00:00:00"}