{"id":"https://openalex.org/W7155960530","doi":"https://doi.org/10.48550/arxiv.2604.22597","title":"Rethinking Math Reasoning Evaluation: A Robust LLM-as-a-Judge Framework Beyond Symbolic Rigidity","display_name":"Rethinking Math Reasoning Evaluation: A Robust LLM-as-a-Judge Framework Beyond Symbolic Rigidity","publication_year":2026,"publication_date":"2026-04-24","ids":{"openalex":"https://openalex.org/W7155960530","doi":"https://doi.org/10.48550/arxiv.2604.22597"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.22597","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.22597","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":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.2604.22597","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134683083","display_name":"Erez Yosef","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yosef, Erez","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024638180","display_name":"Oron Anschel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anschel, Oron","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037165507","display_name":"Shunit Haviv Hakimi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hakimi, Shunit Haviv","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030879550","display_name":"Asaf Gendler","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gendler, Asaf","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004822803","display_name":"Adam Botach","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Botach, Adam","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134715881","display_name":"Nimrod Berman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Berman, Nimrod","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5040459833","display_name":"Igor Kviatkovsky","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kviatkovsky, Igor","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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.24969999492168427,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.24969999492168427,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.149399995803833,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.05420000106096268,"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/correctness","display_name":"Correctness","score":0.7560999989509583},{"id":"https://openalex.org/keywords/automated-reasoning","display_name":"Automated reasoning","score":0.5390999913215637},{"id":"https://openalex.org/keywords/mathematical-logic","display_name":"Mathematical logic","score":0.41440001130104065},{"id":"https://openalex.org/keywords/mathematical-theory","display_name":"Mathematical theory","score":0.37959998846054077},{"id":"https://openalex.org/keywords/the-symbolic","display_name":"The Symbolic","score":0.3474999964237213},{"id":"https://openalex.org/keywords/symbolic-computation","display_name":"Symbolic computation","score":0.34380000829696655},{"id":"https://openalex.org/keywords/mathematical-structure","display_name":"Mathematical structure","score":0.3391000032424927},{"id":"https://openalex.org/keywords/mathematical-model","display_name":"Mathematical model","score":0.3353999853134155}],"concepts":[{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.7560999989509583},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5812000036239624},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.5390999913215637},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.43779999017715454},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4357999861240387},{"id":"https://openalex.org/C47884741","wikidata":"https://www.wikidata.org/wiki/Q1166618","display_name":"Mathematical logic","level":2,"score":0.41440001130104065},{"id":"https://openalex.org/C2779193601","wikidata":"https://www.wikidata.org/wiki/Q20026918","display_name":"Mathematical theory","level":2,"score":0.37959998846054077},{"id":"https://openalex.org/C2776095079","wikidata":"https://www.wikidata.org/wiki/Q489538","display_name":"The Symbolic","level":2,"score":0.3474999964237213},{"id":"https://openalex.org/C110812573","wikidata":"https://www.wikidata.org/wiki/Q175515","display_name":"Symbolic computation","level":2,"score":0.34380000829696655},{"id":"https://openalex.org/C130327152","wikidata":"https://www.wikidata.org/wiki/Q748349","display_name":"Mathematical structure","level":2,"score":0.3391000032424927},{"id":"https://openalex.org/C76969082","wikidata":"https://www.wikidata.org/wiki/Q486902","display_name":"Mathematical model","level":2,"score":0.3353999853134155},{"id":"https://openalex.org/C172347087","wikidata":"https://www.wikidata.org/wiki/Q3217196","display_name":"Language of mathematics","level":2,"score":0.32499998807907104},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3197999894618988},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.30300000309944153},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C73301696","wikidata":"https://www.wikidata.org/wiki/Q5469984","display_name":"Formalism (music)","level":3,"score":0.2797999978065491},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C66783780","wikidata":"https://www.wikidata.org/wiki/Q1166625","display_name":"Mathematical problem","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2565999925136566},{"id":"https://openalex.org/C65620979","wikidata":"https://www.wikidata.org/wiki/Q7661176","display_name":"Symbolic data analysis","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.22597","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.22597","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.22597","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.22597","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"score":0.43698573112487793,"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":{"Recent":[0],"advancements":[1],"in":[2,24,114],"large":[3],"language":[4],"models":[5],"have":[6],"led":[7],"to":[8,20,63,82,124,143],"significant":[9],"improvements":[10,129],"across":[11,65,100],"various":[12],"tasks,":[13],"including":[14],"mathematical":[15,33,67,102,153],"reasoning,":[16],"which":[17,61,148],"is":[18,55,149],"used":[19,132],"assess":[21],"models'":[22],"intelligence":[23],"logical":[25],"reasoning":[26,34],"and":[27,69,79,104,119,121,140,155],"problem-solving.":[28],"Models":[29],"are":[30],"evaluated":[31],"on":[32,57],"benchmarks":[35],"by":[36],"verifying":[37],"the":[38,41],"correctness":[39],"of":[40,111],"final":[42],"answer":[43,105],"against":[44],"a":[45,77],"ground":[46],"truth":[47],"answer.":[48],"A":[49],"common":[50],"approach":[51],"for":[52,93,151],"this":[53,73],"verification":[54],"based":[56],"symbolic":[58,84,112],"mathematics":[59,85],"comparison,":[60],"fails":[62],"generalize":[64],"diverse":[66,101],"representations":[68,103],"solution":[70],"formats.":[71,106],"In":[72],"work,":[74],"we":[75],"offer":[76],"robust":[78],"flexible":[80],"alternative":[81],"rule-based":[83],"comparison.":[86],"We":[87,107],"propose":[88],"an":[89],"LLM-based":[90],"evaluation":[91,99,113,139],"framework":[92,135],"evaluating":[94],"model-generated":[95],"answers,":[96],"enabling":[97],"accurate":[98,145],"present":[108],"failure":[109],"cases":[110],"two":[115],"popular":[116],"frameworks,":[117],"Lighteval":[118],"SimpleRL,":[120],"compare":[122],"them":[123],"our":[125],"approach,":[126],"demonstrating":[127],"clear":[128],"over":[130],"commonly":[131],"methods.":[133],"Our":[134],"enables":[136],"more":[137,144],"reliable":[138],"benchmarking,":[141],"leading":[142],"performance":[146],"monitoring,":[147],"important":[150],"advancing":[152],"problem-solving":[154],"intelligent":[156],"systems.":[157]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-28T00:00:00"}
