{"id":"https://openalex.org/W7161031192","doi":"https://doi.org/10.48550/arxiv.2605.11978","title":"On Predicting the Post-training Potential of Pre-trained LLMs","display_name":"On Predicting the Post-training Potential of Pre-trained LLMs","publication_year":2026,"publication_date":"2026-05-12","ids":{"openalex":"https://openalex.org/W7161031192","doi":"https://doi.org/10.48550/arxiv.2605.11978"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.11978","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.11978","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.11978","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100603568","display_name":"Xiaoyuan Li","orcid":"https://orcid.org/0000-0003-3305-936X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xiaoyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136070580","display_name":"Yubo Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Yubo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136003959","display_name":"Kexin Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Kexin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136045004","display_name":"Moxin Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Moxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013954858","display_name":"Keqin Bao","orcid":"https://orcid.org/0009-0001-5910-0204"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bao, Keqin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136079928","display_name":"Wenie Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Wenie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136072755","display_name":"Fuli Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Fuli","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136005038","display_name":"Dayiheng Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Dayiheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"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/T10028","display_name":"Topic Modeling","score":0.3472000062465668,"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":0.3472000062465668,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.10620000213384628,"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/T13629","display_name":"Text Readability and Simplification","score":0.08980000019073486,"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/rubric","display_name":"Rubric","score":0.8317999839782715},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6969000101089478},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5590999722480774},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5042999982833862},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.46459999680519104},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.44589999318122864},{"id":"https://openalex.org/keywords/unified-model","display_name":"Unified Model","score":0.41429999470710754},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.3977999985218048}],"concepts":[{"id":"https://openalex.org/C111640148","wikidata":"https://www.wikidata.org/wiki/Q847349","display_name":"Rubric","level":2,"score":0.8317999839782715},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6969000101089478},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6549999713897705},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5590999722480774},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5281000137329102},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5042999982833862},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48429998755455017},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.46459999680519104},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.44589999318122864},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.41429999470710754},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3977999985218048},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.3961000144481659},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.36059999465942383},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33399999141693115},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.32330000400543213},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.30790001153945923},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.29350000619888306},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.2897999882698059},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.28290000557899475},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2718000113964081},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.11978","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.11978","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.11978","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.11978","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":"article"},"sustainable_development_goals":[{"score":0.7025418281555176,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"performance":[1,58],"of":[2,49,75],"Large":[3],"Language":[4],"Models":[5],"(LLMs)":[6],"on":[7],"downstream":[8],"tasks":[9],"is":[10],"fundamentally":[11],"constrained":[12],"by":[13,44,78,83,96],"the":[14,72],"capabilities":[15],"acquired":[16],"during":[17],"pre-training.":[18],"However,":[19],"traditional":[20],"benchmarks":[21],"like":[22],"MMLU":[23],"often":[24],"fail":[25],"to":[26,37],"reflect":[27],"a":[28,46,55,67,103,130],"base":[29,56,76],"model's":[30,57],"plasticity":[31],"in":[32],"complex":[33],"open-ended":[34],"scenarios,":[35],"leading":[36],"inefficient":[38],"model":[39,135],"selection.":[40],"We":[41,61],"address":[42],"this":[43],"introducing":[45],"new":[47],"task":[48],"predicting":[50],"post-training":[51,109],"potential":[52],"-":[53],"forecasting":[54],"before":[59],"post-training.":[60],"propose":[62],"RuDE":[63,88,119],"(Rubric-based":[64],"Discriminative":[65],"Evaluation),":[66],"unified":[68],"framework":[69],"that":[70,118,125],"bypasses":[71],"generation":[73],"gap":[74],"models":[77,124],"leveraging":[79],"response":[80],"discrimination.":[81],"Guided":[82],"our":[84],"systematic":[85],"4C":[86],"Taxonomy,":[87],"constructs":[89],"controlled":[90],"contrastive":[91],"pairs":[92],"across":[93],"diverse":[94],"domains":[95],"fine-grained":[97],"rubric":[98],"violations.":[99],"Extensive":[100],"experiments":[101],"demonstrate":[102],"correlation":[104],"greater":[105],"than":[106],"90%":[107],"with":[108],"performance.":[110],"Crucially,":[111],"validation":[112],"via":[113],"Reinforcement":[114],"Learning":[115],"(RL)":[116],"confirms":[117],"effectively":[120],"identifies":[121],"high-potential":[122],"smaller":[123],"outperform":[126],"larger":[127],"counterparts,":[128],"offering":[129],"compute-efficient":[131],"mechanism":[132],"for":[133],"foundation":[134],"development.":[136]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-14T00:00:00"}