{"id":"https://openalex.org/W7126210969","doi":"https://doi.org/10.48550/arxiv.2601.21464","title":"Conversation for Non-verifiable Learning: Self-Evolving LLMs through Meta-Evaluation","display_name":"Conversation for Non-verifiable Learning: Self-Evolving LLMs through Meta-Evaluation","publication_year":2026,"publication_date":"2026-01-29","ids":{"openalex":"https://openalex.org/W7126210969","doi":"https://doi.org/10.48550/arxiv.2601.21464"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2601.21464","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124399338","display_name":"Yuan Sui","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sui, Yuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5124418976","display_name":"Bryan Hooi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hooi, Bryan","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5124399338"],"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":0.23800000548362732,"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":0.23800000548362732,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.19990000128746033,"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":0.1551000028848648,"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/conversation","display_name":"Conversation","score":0.7297000288963318},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5961999893188477},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5608999729156494},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5076000094413757},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.47679999470710754},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.3763999938964844}],"concepts":[{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.7297000288963318},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5961999893188477},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5608999729156494},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5282999873161316},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5076000094413757},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.47679999470710754},{"id":"https://openalex.org/C39549134","wikidata":"https://www.wikidata.org/wiki/Q133080","display_name":"Public relations","level":1,"score":0.4465999901294708},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.40070000290870667},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3763999938964844},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.3698999881744385},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.36079999804496765},{"id":"https://openalex.org/C2780829048","wikidata":"https://www.wikidata.org/wiki/Q1624720","display_name":"Conversation analysis","level":3,"score":0.33009999990463257},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3269999921321869},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.32690000534057617},{"id":"https://openalex.org/C55587333","wikidata":"https://www.wikidata.org/wiki/Q1133029","display_name":"Engineering ethics","level":1,"score":0.31119999289512634},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.3041999936103821},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.30219998955726624},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.29100000858306885},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.29100000858306885},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.2800999879837036},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.27869999408721924},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2784999907016754},{"id":"https://openalex.org/C2777877512","wikidata":"https://www.wikidata.org/wiki/Q1116097","display_name":"Common ground","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.266400009393692},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2612000107765198},{"id":"https://openalex.org/C109986646","wikidata":"https://www.wikidata.org/wiki/Q546113","display_name":"Public policy","level":2,"score":0.2574999928474426}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2601.21464","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2601.21464","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.21464","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2601.21464","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8156652450561523}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Training":[0],"large":[1],"language":[2],"models":[3],"(LLMs)":[4],"for":[5,143],"non-verifiable":[6],"tasks,":[7],"such":[8],"as":[9],"creative":[10],"writing,":[11],"dialogue,":[12],"and":[13,61,78,92,128,145,151],"ethical":[14],"reasoning,":[15],"remains":[16],"challenging":[17],"due":[18],"to":[19,32,76,125],"the":[20,44,49,74,80,118],"absence":[21],"of":[22,149],"ground-truth":[23],"labels.":[24],"While":[25],"LLM-as-Judge":[26],"approaches":[27],"offer":[28],"a":[29,37,86,137],"scalable":[30],"alternative":[31],"human":[33],"feedback,":[34],"they":[35],"face":[36],"fundamental":[38],"limitation:":[39],"performance":[40],"is":[41],"constrained":[42],"by":[43,105],"evaluator's":[45],"own":[46],"quality.":[47],"If":[48],"judge":[50],"cannot":[51,56],"recognize":[52],"good":[53],"solutions,":[54],"it":[55,107],"provide":[57],"useful":[58],"training":[59],"signals,":[60],"evaluation":[62],"biases":[63],"(e.g.,":[64],"favoring":[65],"verbosity":[66],"over":[67,172],"quality)":[68],"remain":[69],"unaddressed.":[70],"This":[71],"motivates":[72],"meta-evaluation:":[73],"ability":[75],"evaluate":[77],"improve":[79,110],"evaluator":[81],"itself.":[82],"We":[83],"introduce":[84],"CoNL,":[85,114],"framework":[87],"that":[88,132,167],"unifies":[89],"generation,":[90],"evaluation,":[91],"meta-evaluation":[93,144],"through":[94,154],"multi-agent":[95],"self-play.":[96],"Our":[97],"key":[98],"insight:":[99],"critique":[100],"quality":[101],"can":[102],"be":[103],"measured":[104],"whether":[106],"helps":[108],"others":[109],"their":[111],"solutions.":[112,130],"In":[113],"multiple":[115],"agents":[116],"sharing":[117],"same":[119],"policy":[120],"engage":[121],"in":[122],"structured":[123],"conversations":[124],"propose,":[126],"critique,":[127],"revise":[129],"Critiques":[131],"enable":[133],"solution":[134],"improvements":[135,171],"earn":[136],"diagnostic":[138],"reward,":[139],"creating":[140],"explicit":[141],"supervision":[142],"enabling":[146],"joint":[147],"optimization":[148],"generation":[150],"judging":[152],"capabilities":[153],"self-play,":[155],"without":[156],"external":[157],"judges":[158],"or":[159],"ground":[160],"truth.":[161],"Experiments":[162],"on":[163],"five":[164],"benchmarks":[165],"show":[166],"CoNL":[168],"achieves":[169],"consistent":[170],"self-rewarding":[173],"baselines":[174],"while":[175],"maintaining":[176],"stable":[177],"training.":[178]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-02-01T00:00:00"}