{"id":"https://openalex.org/W4412888657","doi":"https://doi.org/10.18653/v1/2025.findings-acl.311","title":"Tell Me What You Don\u2019t Know: Enhancing Refusal Capabilities of Role-Playing Agents via Representation Space Analysis and Editing","display_name":"Tell Me What You Don\u2019t Know: Enhancing Refusal Capabilities of Role-Playing Agents via Representation Space Analysis and Editing","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888657","doi":"https://doi.org/10.18653/v1/2025.findings-acl.311"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.311","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.311","pdf_url":"https://aclanthology.org/2025.findings-acl.311.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 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.311.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100429106","display_name":"Wenhao Liu","orcid":"https://orcid.org/0000-0001-9757-1077"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenhao Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057579366","display_name":"Siyu An","orcid":"https://orcid.org/0009-0008-6004-7325"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Siyu An","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090635327","display_name":"Junru Lu","orcid":"https://orcid.org/0009-0004-9588-8766"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junru Lu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111333871","display_name":"Muling Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Muling Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020841033","display_name":"Tianlong Li","orcid":"https://orcid.org/0000-0002-9483-457X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianlong Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100438586","display_name":"Xiaohua Wang","orcid":"https://orcid.org/0000-0002-6551-151X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaohua Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113112983","display_name":"Changze Lv","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Changze Lv","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017835517","display_name":"Xiaoqing Zheng","orcid":"https://orcid.org/0000-0003-4430-5036"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoqing Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100758011","display_name":"Di Yin","orcid":"https://orcid.org/0000-0002-3272-9643"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Di Yin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004402130","display_name":"Xing Sun","orcid":"https://orcid.org/0000-0001-8132-9083"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xing Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5111113722","display_name":"Xuanjing Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuanjing Huang","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":0.09266994,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5983","last_page":"6005"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.792900025844574,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.792900025844574,"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":0.7443000078201294,"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/T10028","display_name":"Topic Modeling","score":0.7378000020980835,"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/representation","display_name":"Representation (politics)","score":0.6373270750045776},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6243525743484497},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5984522104263306},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.39130714535713196},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.36247387528419495},{"id":"https://openalex.org/keywords/internet-privacy","display_name":"Internet privacy","score":0.33333897590637207},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10251650214195251},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.09653863310813904},{"id":"https://openalex.org/keywords/politics","display_name":"Politics","score":0.08144214749336243}],"concepts":[{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6373270750045776},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6243525743484497},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5984522104263306},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39130714535713196},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.36247387528419495},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.33333897590637207},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10251650214195251},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.09653863310813904},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.08144214749336243},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.311","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.311","pdf_url":"https://aclanthology.org/2025.findings-acl.311.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 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.311","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.311","pdf_url":"https://aclanthology.org/2025.findings-acl.311.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 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.6000000238418579,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G3612180917","display_name":null,"funder_award_id":"62076068","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888657.pdf","grobid_xml":"https://content.openalex.org/works/W4412888657.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2062195135","https://openalex.org/W2795079307","https://openalex.org/W2793058541","https://openalex.org/W1983629434","https://openalex.org/W2055929693","https://openalex.org/W4324271173","https://openalex.org/W2352227742","https://openalex.org/W4390679071","https://openalex.org/W1967645776"],"abstract_inverted_index":{"Wenhao":[0],"Liu,":[1],"Siyu":[2],"An,":[3],"Junru":[4],"Lu,":[5],"Muling":[6],"Wu,":[7],"Tianlong":[8],"Li,":[9],"Xiaohua":[10],"Wang,":[11],"Changze":[12],"Lv,":[13],"Xiaoqing":[14],"Zheng,":[15],"Di":[16],"Yin,":[17],"Xing":[18],"Sun,":[19],"Xuanjing":[20],"Huang.":[21],"Findings":[22],"of":[23],"the":[24],"Association":[25],"for":[26],"Computational":[27],"Linguistics:":[28],"ACL":[29],"2025.":[30,31]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
