{"id":"https://openalex.org/W4412886755","doi":"https://doi.org/10.18653/v1/2025.acl-long.158","title":"Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training","display_name":"Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412886755","doi":"https://doi.org/10.18653/v1/2025.acl-long.158"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.158","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.158","pdf_url":"https://aclanthology.org/2025.acl-long.158.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.158.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101287548","display_name":"Youliang Yuan","orcid":null},"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/A5023250445","display_name":"Wenxiang Jiao","orcid":"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":"middle","author":{"id":"https://openalex.org/A5100755181","display_name":"Wenxuan Wang","orcid":"https://orcid.org/0000-0001-7172-8662"},"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/A5047584018","display_name":"Jen-tse Huang","orcid":"https://orcid.org/0000-0003-3446-0083"},"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/A5101622578","display_name":"Jiahao Xu","orcid":"https://orcid.org/0000-0001-9894-228X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiahao Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034614141","display_name":"Liang Tian","orcid":"https://orcid.org/0000-0002-6595-445X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tian Liang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101941950","display_name":"Pinjia He","orcid":"https://orcid.org/0000-0003-3377-8129"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pinjia He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5110579339","display_name":"Zhaopeng Tu","orcid":"https://orcid.org/0000-0002-7900-6055"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhaopeng Tu","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":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3149","last_page":"3167"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13295","display_name":"Safety Systems Engineering in Autonomy","score":0.9465000033378601,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13295","display_name":"Safety Systems Engineering in Autonomy","score":0.9465000033378601,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12423","display_name":"Software Reliability and Analysis Research","score":0.9243000149726868,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/training","display_name":"Training (meteorology)","score":0.6096226572990417},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.535769522190094},{"id":"https://openalex.org/keywords/internet-privacy","display_name":"Internet privacy","score":0.4610111117362976},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.44410091638565063},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3743387460708618},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3516082167625427}],"concepts":[{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6096226572990417},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.535769522190094},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.4610111117362976},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.44410091638565063},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3743387460708618},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3516082167625427},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.158","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.158","pdf_url":"https://aclanthology.org/2025.acl-long.158.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.158","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.158","pdf_url":"https://aclanthology.org/2025.acl-long.158.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7609782405","display_name":null,"funder_award_id":"2024A1515010145","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412886755.pdf","grobid_xml":"https://content.openalex.org/works/W4412886755.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W4412817058","https://openalex.org/W3216976533","https://openalex.org/W100620283"],"abstract_inverted_index":{"Youliang":[0],"Yuan,":[1],"Wenxiang":[2],"Jiao,":[3],"Wenxuan":[4],"Wang,":[5],"Jen-tse":[6],"Huang,":[7],"Jiahao":[8],"Xu,":[9],"Tian":[10],"Liang,":[11],"Pinjia":[12],"He,":[13],"Zhaopeng":[14],"Tu.":[15],"Proceedings":[16],"of":[17,22],"the":[18,23],"63rd":[19],"Annual":[20],"Meeting":[21],"Association":[24],"for":[25],"Computational":[26],"Linguistics":[27],"(Volume":[28],"1:":[29],"Long":[30],"Papers).":[31],"2025.":[32]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
