{"id":"https://openalex.org/W4403566260","doi":"https://doi.org/10.48550/arxiv.2410.09528","title":"Boosting Deductive Reasoning with Step Signals In RLHF","display_name":"Boosting Deductive Reasoning with Step Signals In RLHF","publication_year":2024,"publication_date":"2024-10-12","ids":{"openalex":"https://openalex.org/W4403566260","doi":"https://doi.org/10.48550/arxiv.2410.09528"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2410.09528","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.09528","pdf_url":"https://arxiv.org/pdf/2410.09528","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2410.09528","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102730595","display_name":"Jialian Li","orcid":"https://orcid.org/0000-0003-4927-2202"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Li, Jialian","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114169627","display_name":"Yipin Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yipin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100673085","display_name":"Wei Shen","orcid":"https://orcid.org/0009-0000-1221-5330"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Wei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yan, Yuzi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Yuzi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102637896","display_name":"Jian Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Jian","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5080233678","display_name":"Dong Yan","orcid":"https://orcid.org/0000-0003-4549-9469"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Dong","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5102730595"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T11010","display_name":"Logic, Reasoning, and Knowledge","score":0.8222000002861023,"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":0.8222000002861023,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.7307999730110168,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.715499997138977,"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/boosting","display_name":"Boosting (machine learning)","score":0.8048815727233887},{"id":"https://openalex.org/keywords/deductive-reasoning","display_name":"Deductive reasoning","score":0.7422888875007629},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.470117449760437},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3689553141593933}],"concepts":[{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.8048815727233887},{"id":"https://openalex.org/C97364631","wikidata":"https://www.wikidata.org/wiki/Q484284","display_name":"Deductive reasoning","level":2,"score":0.7422888875007629},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.470117449760437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3689553141593933}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2410.09528","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.09528","pdf_url":"https://arxiv.org/pdf/2410.09528","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2410.09528","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2410.09528","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:oai:arXiv.org:2410.09528","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.09528","pdf_url":"https://arxiv.org/pdf/2410.09528","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4403566260.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2125652721","https://openalex.org/W1540371141","https://openalex.org/W4231274751","https://openalex.org/W1549363203","https://openalex.org/W2154063878","https://openalex.org/W2556012038","https://openalex.org/W1489772951"],"abstract_inverted_index":{"Logical":[0],"reasoning":[1,18,21,44,99,110],"is":[2],"a":[3,23],"crucial":[4],"task":[5],"for":[6,42,56,94],"Large":[7],"Language":[8],"Models":[9],"(LLMs),":[10],"enabling":[11],"them":[12],"to":[13,50,106],"tackle":[14],"complex":[15],"problems.":[16],"Among":[17],"tasks,":[19],"multi-step":[20,57,109],"poses":[22],"particular":[24],"challenge.":[25],"Grounded":[26],"in":[27,91],"the":[28,65,68,108],"theory":[29],"of":[30,67,75,97,112],"formal":[31],"logic,":[32],"we":[33,102],"have":[34,103],"developed":[35],"an":[36],"automated":[37],"method,":[38],"Multi-step":[39],"Deduction":[40],"(MuseD),":[41],"deductive":[43],"data.":[45],"MuseD":[46],"has":[47,87],"allowed":[48],"us":[49],"create":[51],"training":[52,72,85],"and":[53,73],"testing":[54],"datasets":[55],"reasoning.":[58],"Our":[59],"generation":[60],"method":[61],"enables":[62],"control":[63],"over":[64],"complexity":[66],"generated":[69],"instructions,":[70],"facilitating":[71],"evaluation":[74],"models":[76],"across":[77],"different":[78],"difficulty":[79],"levels.":[80],"Through":[81],"RLHF":[82],"training,":[83],"our":[84],"data":[86],"demonstrated":[88],"significant":[89],"improvements":[90],"logical":[92],"capabilities":[93],"both":[95],"in-domain":[96],"out-of-domain":[98],"tasks.":[100],"Additionally,":[101],"conducted":[104],"tests":[105],"assess":[107],"abilities":[111],"various":[113],"models.":[114]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}