{"id":"https://openalex.org/W7166834202","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1982","title":"Rewarding the Rare: Uniqueness-Aware RL for Creative Problem Solving in LLMs","display_name":"Rewarding the Rare: Uniqueness-Aware RL for Creative Problem Solving in LLMs","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166834202","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1982"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1982","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1982","pdf_url":"https://aclanthology.org/2026.findings-acl.1982.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.1982.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139750365","display_name":"Zhiyuan Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiyuan Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139846335","display_name":"Yucheng Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yucheng Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139716680","display_name":"Yufei He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yufei He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139798872","display_name":"Jiaying Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiaying Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139773668","display_name":"Yilun Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yilun Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139770658","display_name":"See-Kiong Ng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"See-Kiong Ng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139752941","display_name":"Cynthia Breazeal","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cynthia Breazeal","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139773614","display_name":"Anh Tuan Luu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anh Tuan Luu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139800636","display_name":"Hae Won Park","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hae Won Park","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139743486","display_name":"Bryan Hooi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bryan Hooi","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":0.82402383,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"39765","last_page":"39790"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.42980000376701355,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.42980000376701355,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.2565999925136566,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.019300000742077827,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.37059998512268066},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.3151000142097473}],"concepts":[{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.37059998512268066},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3587999939918518},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.336899995803833},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.31700000166893005},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.31690001487731934},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3151000142097473},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.26019999384880066},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.25369998812675476},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.2531000077724457},{"id":"https://openalex.org/C39549134","wikidata":"https://www.wikidata.org/wiki/Q133080","display_name":"Public relations","level":1,"score":0.24899999797344208}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1982","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1982","pdf_url":"https://aclanthology.org/2026.findings-acl.1982.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.1982","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1982","pdf_url":"https://aclanthology.org/2026.findings-acl.1982.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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8330815434455872}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166834202.pdf","grobid_xml":"https://content.openalex.org/works/W7166834202.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Zhiyuan":[0],"Hu,":[1],"Yucheng":[2],"Wang,":[3],"Yufei":[4],"He,":[5],"Jiaying":[6],"Wu,":[7],"Yilun":[8],"Zhao,":[9],"See-Kiong":[10],"Ng,":[11],"Cynthia":[12],"Breazeal,":[13],"Anh":[14],"Tuan":[15],"Luu,":[16],"Hae":[17],"Won":[18],"Park,":[19],"Bryan":[20],"Hooi.":[21],"Findings":[22],"of":[23],"the":[24],"Association":[25],"for":[26],"Computational":[27],"Linguistics:":[28],"ACL":[29],"2026.":[30,31]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}
