{"id":"https://openalex.org/W4415798372","doi":"https://doi.org/10.52202/079017-0740","title":"Neuro-Symbolic Data Generation for Math Reasoning","display_name":"Neuro-Symbolic Data Generation for Math Reasoning","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4415798372","doi":"https://doi.org/10.52202/079017-0740"},"language":"en","primary_location":{"id":"doi:10.52202/079017-0740","doi":"https://doi.org/10.52202/079017-0740","is_oa":false,"landing_page_url":"https://doi.org/10.52202/079017-0740","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 37","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2412.04857","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009560003","display_name":"Zenan Li","orcid":"https://orcid.org/0000-0003-2432-1776","observed_orcids":["https://orcid.org/0000-0003-2432-1776"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zenan Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069910503","display_name":"Zhi Quan Zhou","orcid":"https://orcid.org/0000-0003-1769-9367","observed_orcids":["https://orcid.org/0000-0003-1769-9367"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhi Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068643894","display_name":"Yuan Yao","orcid":"https://orcid.org/0000-0002-6913-6542","observed_orcids":["https://orcid.org/0000-0002-6913-6542"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan Yao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yu-Feng Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu-Feng Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Chun Cao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chun Cao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113303177","display_name":"Fan Yang","orcid":"https://orcid.org/0000-0002-5767-6461","observed_orcids":["https://orcid.org/0000-0002-5767-6461"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100438847","display_name":"Xian Zhang","orcid":"https://orcid.org/0000-0002-5203-5251","observed_orcids":["https://orcid.org/0000-0002-5203-5251"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xian Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5041674680","display_name":"Xiaoxing Ma","orcid":"https://orcid.org/0000-0001-7970-1384","observed_orcids":["https://orcid.org/0000-0001-7970-1384"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoxing Ma","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":0.8662,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.77195018,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"23488","last_page":"23515"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11010","display_name":"Logic, Reasoning, and Knowledge","score":0.26510000228881836,"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/T11010","display_name":"Logic, Reasoning, and Knowledge","score":0.26510000228881836,"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.1469999998807907,"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":0.10490000247955322,"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/neuro-symbolic-learning","display_name":"neuro-symbolic learning","score":0.8140000104904175},{"id":"https://openalex.org/keywords/synthetic-data-generation","display_name":"synthetic data generation","score":0.8299999833106995},{"id":"https://openalex.org/keywords/mathematical-reasoning","display_name":"mathematical reasoning","score":0.7160000205039978},{"id":"https://openalex.org/keywords/symbolic-reasoning","display_name":"symbolic reasoning","score":0.42800000309944153}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6568999886512756},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5659999847412109},{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.5548999905586243},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.47540000081062317},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43650001287460327},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.42149999737739563},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4097999930381775},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3772999942302704},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.3598000109195709},{"id":"https://openalex.org/C47884741","wikidata":"https://www.wikidata.org/wiki/Q1166618","display_name":"Mathematical logic","level":2,"score":0.3361999988555908},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33379998803138733},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.313400000333786},{"id":"https://openalex.org/C2776095079","wikidata":"https://www.wikidata.org/wiki/Q489538","display_name":"The Symbolic","level":2,"score":0.3116999864578247},{"id":"https://openalex.org/C167324811","wikidata":"https://www.wikidata.org/wiki/Q12207781","display_name":"Symbolic-numeric computation","level":3,"score":0.30889999866485596},{"id":"https://openalex.org/C206654554","wikidata":"https://www.wikidata.org/wiki/Q5374247","display_name":"Empirical measure","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.28769999742507935},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28369998931884766},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C76969082","wikidata":"https://www.wikidata.org/wiki/Q486902","display_name":"Mathematical model","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C172347087","wikidata":"https://www.wikidata.org/wiki/Q3217196","display_name":"Language of mathematics","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.52202/079017-0740","doi":"https://doi.org/10.52202/079017-0740","is_oa":false,"landing_page_url":"https://doi.org/10.52202/079017-0740","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 37","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2412.04857","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.04857","pdf_url":"https://arxiv.org/pdf/2412.04857","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2412.04857","doi":"https://doi.org/10.48550/arxiv.2412.04857","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.04857","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2412.04857","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.04857","pdf_url":"https://arxiv.org/pdf/2412.04857","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G7268762225","display_name":null,"funder_award_id":"62025202","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415798372.pdf","grobid_xml":"https://content.openalex.org/works/W4415798372.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4416246779","https://openalex.org/W4416017259","https://openalex.org/W4417307891","https://openalex.org/W4404990680","https://openalex.org/W4392222438","https://openalex.org/W4403928588","https://openalex.org/W7166817036","https://openalex.org/W4392538380","https://openalex.org/W4412945228","https://openalex.org/W4402670720"],"abstract_inverted_index":{"A":[0],"critical":[1],"question":[2],"about":[3],"Large":[4],"Language":[5],"Models":[6],"(LLMs)":[7],"is":[8,16,61],"whether":[9],"their":[10,125],"apparent":[11],"deficiency":[12],"in":[13,92],"mathematical":[14,27,41],"reasoning":[15,80],"inherent,":[17],"or":[18],"merely":[19],"a":[20,64],"result":[21],"of":[22,55,74,81,103],"insufficient":[23],"exposure":[24],"to":[25],"high-quality":[26],"data.":[28],"To":[29],"explore":[30],"this,":[31],"we":[32],"developed":[33],"an":[34],"automated":[35],"method":[36,44],"for":[37],"generating":[38],"high-quality,":[39],"supervised":[40],"datasets.":[42],"The":[43],"carefully":[45],"mutates":[46],"existing":[47],"math":[48,82],"problems,":[49],"ensuring":[50],"both":[51],"diversity":[52],"and":[53,76,110,116],"validity":[54],"the":[56,70,77,93,100,107,112,121],"newly":[57],"generated":[58,105,122],"problems.":[59],"This":[60],"achieved":[62],"by":[63,106],"neuro-symbolic":[65],"data":[66,104],"generation":[67],"framework":[68],"combining":[69],"intuitive":[71],"informalization":[72],"strengths":[73],"LLMs,":[75,113],"precise":[78],"symbolic":[79,95],"solvers":[83],"along":[84],"with":[85,120],"projected":[86],"Markov":[87],"chain":[88],"Monte":[89],"Carlo":[90],"sampling":[91],"highly-irregular":[94],"space.":[96],"Empirical":[97],"experiments":[98],"demonstrate":[99],"high":[101],"quality":[102],"proposed":[108],"method,":[109],"that":[111],"specifically":[114],"LLaMA-2":[115],"Mistral,":[117],"when":[118],"realigned":[119],"data,":[123],"surpass":[124],"state-of-the-art":[126],"counterparts.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2025-11-03T00:00:00"}