{"id":"https://openalex.org/W7166803163","doi":"https://doi.org/10.18653/v1/2026.findings-acl.865","title":"SPS: Steering Probability Squeezing for Better Exploration in Reinforcement Learning for Large Language Models","display_name":"SPS: Steering Probability Squeezing for Better Exploration in Reinforcement Learning for Large Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166803163","doi":"https://doi.org/10.18653/v1/2026.findings-acl.865"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.865","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.865","pdf_url":"https://aclanthology.org/2026.findings-acl.865.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.865.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101231782","display_name":"Yifu Huo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yifu Huo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139764690","display_name":"Chenglong Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenglong Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139769134","display_name":"Ziming Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziming Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134111884","display_name":"Shunjie Xing","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shunjie Xing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101318537","display_name":"Peinan Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peinan Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012126405","display_name":"Tongran Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tongran Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139803444","display_name":"Qiaozhi He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiaozhi He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5118899156","display_name":"Tian Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tian Hua Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139835951","display_name":"Changxiaojia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Changxiaojia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139767941","display_name":"JingBo Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"JingBo Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139844812","display_name":"Zhengtao Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhengtao Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139769527","display_name":"Tong Xiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tong Xiao","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":0.79258432,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"17472","last_page":"17489"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.29269999265670776,"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":0.29269999265670776,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.07429999858140945,"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":0.052299998700618744,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.475600004196167},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.35190001130104065},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.334199994802475},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3124000132083893},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.29989999532699585},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.2768999934196472}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5424000024795532},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5135999917984009},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.475600004196167},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.35190001130104065},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.334199994802475},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3183000087738037},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3124000132083893},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.29989999532699585},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.27160000801086426},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2676999866962433},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C2982736386","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Statistical learning","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.25519999861717224}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.865","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.865","pdf_url":"https://aclanthology.org/2026.findings-acl.865.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.865","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.865","pdf_url":"https://aclanthology.org/2026.findings-acl.865.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6716360449790955,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335785","display_name":"Project 211","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166803163.pdf","grobid_xml":"https://content.openalex.org/works/W7166803163.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Yifu":[0],"Huo,":[1],"Chenglong":[2],"Wang,":[3],"Ziming":[4],"Zhu,":[5,19],"Shunjie":[6],"Xing,":[7],"Peinan":[8],"Feng,":[9],"Tongran":[10],"Liu,":[11],"Qiaozhi":[12],"He,":[13],"Tian":[14],"Hua":[15],"Zhou,":[16],"Changxiaojia,":[17],"JingBo":[18],"Zhengtao":[20],"Yu,":[21],"Tong":[22],"Xiao.":[23],"Findings":[24],"of":[25],"the":[26],"Association":[27],"for":[28],"Computational":[29],"Linguistics:":[30],"ACL":[31],"2026.":[32,33]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}