{"id":"https://openalex.org/W4416615461","doi":"https://doi.org/10.18653/v1/2026.acl-long.844","title":"Curing Miracle Steps in LLM Mathematical Reasoning with Rubric Rewards","display_name":"Curing Miracle Steps in LLM Mathematical Reasoning with Rubric Rewards","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4416615461","doi":"https://doi.org/10.18653/v1/2026.acl-long.844"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.acl-long.844","doi":"https://doi.org/10.18653/v1/2026.acl-long.844","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.844","pdf_url":null,"source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.18653/v1/2026.acl-long.844","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101935567","display_name":"Yanhua Yuan","orcid":"https://orcid.org/0000-0003-4820-3758","observed_orcids":["https://orcid.org/0000-0003-4820-3758"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Youliang Yuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092838030","display_name":"Qiuyang Mang","orcid":"https://orcid.org/0009-0000-4462-8527","observed_orcids":["https://orcid.org/0009-0000-4462-8527"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiuyang Mang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jingbang Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingbang Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008921942","display_name":"Hong Wan","orcid":"https://orcid.org/0009-0003-4523-7263","observed_orcids":["https://orcid.org/0009-0003-4523-7263","https://orcid.org/0000-0002-1119-2955"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hong Wan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100605609","display_name":"Xiaoyuan Liu","orcid":"https://orcid.org/0000-0003-1084-9713","observed_orcids":["https://orcid.org/0000-0003-1084-9713"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoyuan Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Junjielong Xu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junjielong Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jen-tse Huang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jen-tse Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106746626","display_name":"Wenxuan Wang","orcid":"https://orcid.org/0000-0002-9803-8204","observed_orcids":["https://orcid.org/0000-0002-9803-8204"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenxuan Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023250445","display_name":"Wenxiang Jiao","orcid":"https://orcid.org/0000-0003-4951-9420","observed_orcids":["https://orcid.org/0000-0003-4951-9420"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenxiang Jiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101941950","display_name":"Pinjia He","orcid":"https://orcid.org/0000-0003-3377-8129","observed_orcids":["https://orcid.org/0000-0003-3377-8129"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pinjia He","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01909329,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"18556","last_page":"18577"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.7035999894142151,"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":0.7035999894142151,"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":0.12630000710487366,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.034699998795986176,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/large-language-models","display_name":"large language models","score":0.9509999752044678},{"id":"https://openalex.org/keywords/mathematical-reasoning","display_name":"mathematical reasoning","score":0.9950000047683716},{"id":"https://openalex.org/keywords/reward-modeling","display_name":"reward modeling","score":0.43299999833106995},{"id":"https://openalex.org/keywords/curriculum-learning","display_name":"curriculum learning","score":0.31299999356269836},{"id":"https://openalex.org/keywords/step-by-step-reasoning","display_name":"step-by-step reasoning","score":0.46000000834465027}],"concepts":[{"id":"https://openalex.org/C111640148","wikidata":"https://www.wikidata.org/wiki/Q847349","display_name":"Rubric","level":2,"score":0.6890000104904175},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5819000005722046},{"id":"https://openalex.org/C2778875440","wikidata":"https://www.wikidata.org/wiki/Q170774","display_name":"Miracle","level":2,"score":0.5263000130653381},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.522599995136261},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4968000054359436},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4374000132083893},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.39980000257492065},{"id":"https://openalex.org/C21847791","wikidata":"https://www.wikidata.org/wiki/Q191081","display_name":"Logical conjunction","level":2,"score":0.38830000162124634},{"id":"https://openalex.org/C43971567","wikidata":"https://www.wikidata.org/wiki/Q3142865","display_name":"Logical reasoning","level":2,"score":0.3871999979019165},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.37630000710487366},{"id":"https://openalex.org/C174998907","wikidata":"https://www.wikidata.org/wiki/Q357662","display_name":"Work in process","level":2,"score":0.36250001192092896},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.3562999963760376},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3513999879360199},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.34610000252723694},{"id":"https://openalex.org/C2776473838","wikidata":"https://www.wikidata.org/wiki/Q174165","display_name":"Innovator","level":3,"score":0.3361000120639801},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3206000030040741},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.29840001463890076},{"id":"https://openalex.org/C2778023277","wikidata":"https://www.wikidata.org/wiki/Q321703","display_name":"Premise","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2549000084400177},{"id":"https://openalex.org/C192328126","wikidata":"https://www.wikidata.org/wiki/Q4514647","display_name":"Schematic","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.844","doi":"https://doi.org/10.18653/v1/2026.acl-long.844","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.844","pdf_url":null,"source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.07774","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2510.07774","pdf_url":"https://arxiv.org/pdf/2510.07774","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.2510.07774","doi":"https://doi.org/10.48550/arxiv.2510.07774","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.07774","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":"doi:10.18653/v1/2026.acl-long.844","doi":"https://doi.org/10.18653/v1/2026.acl-long.844","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.844","pdf_url":null,"source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7161712591","https://openalex.org/W7166825725","https://openalex.org/W7136091443","https://openalex.org/W4385572906","https://openalex.org/W4411638692","https://openalex.org/W4416034534","https://openalex.org/W7138076159","https://openalex.org/W4417531489","https://openalex.org/W7160155543","https://openalex.org/W7124559526"],"abstract_inverted_index":{"Youliang":[0],"Yuan,":[1],"Qiuyang":[2],"Mang,":[3],"Jingbang":[4],"Chen,":[5],"Hong":[6],"Wan,":[7],"Xiaoyuan":[8],"Liu,":[9],"Junjielong":[10],"Xu,":[11],"Jen-tse":[12],"Huang,":[13],"Wenxuan":[14],"Wang,":[15],"Wenxiang":[16],"Jiao,":[17],"Pinjia":[18],"He.":[19],"Proceedings":[20],"of":[21,26],"the":[22,27],"64th":[23],"Annual":[24],"Meeting":[25],"Association":[28],"for":[29],"Computational":[30],"Linguistics":[31],"(Volume":[32],"1:":[33],"Long":[34],"Papers).":[35],"2026.":[36]},"counts_by_year":[],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2025-10-11T00:00:00"}
