{"id":"https://openalex.org/W4416035937","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.186","title":"SafeConf: A Confidence-Calibrated Safety Self-Evaluation Method for Large Language Models","display_name":"SafeConf: A Confidence-Calibrated Safety Self-Evaluation Method for Large Language Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416035937","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.186"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.186","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.186","pdf_url":"https://aclanthology.org/2025.findings-emnlp.186.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: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.186.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101440426","display_name":"Bo Zhang","orcid":"https://orcid.org/0009-0007-7302-4627"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bo Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100653319","display_name":"Cong Gao","orcid":"https://orcid.org/0000-0001-9829-8025"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cong Gao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039888657","display_name":"Linkang Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Linkang Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029019386","display_name":"B Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bingxu Han","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101814775","display_name":"Minghao Hu","orcid":"https://orcid.org/0000-0002-8573-7110"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minghao Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101037209","display_name":"Zhunchen Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhunchen Luo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070742322","display_name":"Guotong Geng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guotong Geng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062486535","display_name":"Xiaoying Bai","orcid":"https://orcid.org/0000-0003-3989-4075"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoying Bai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108046750","display_name":"Junwen Zhang","orcid":"https://orcid.org/0000-0001-8041-1608"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089866078","display_name":"Wen Yao","orcid":"https://orcid.org/0000-0001-5224-9834"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wen Yao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100435269","display_name":"Zhong Wang","orcid":"https://orcid.org/0000-0002-2254-7723"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhong Wang","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":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3483","last_page":"3495"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.2728999853134155,"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":0.2728999853134155,"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":0.07320000231266022,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.05119999870657921,"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/natural-language","display_name":"Natural language","score":0.3301999866962433},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.29170000553131104},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.2847999930381775},{"id":"https://openalex.org/keywords/computational-model","display_name":"Computational model","score":0.2791999876499176},{"id":"https://openalex.org/keywords/modeling-language","display_name":"Modeling language","score":0.26649999618530273}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5996999740600586},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4065000116825104},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4056999981403351},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3301999866962433},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.26649999618530273},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.186","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.186","pdf_url":"https://aclanthology.org/2025.findings-emnlp.186.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: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.186","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.186","pdf_url":"https://aclanthology.org/2025.findings-emnlp.186.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: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416035937.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Bo":[0],"Zhang,":[1,17],"Cong":[2],"Gao,":[3],"Linkang":[4],"Yang,":[5],"Bingxu":[6],"Han,":[7],"Minghao":[8],"Hu,":[9],"Zhunchen":[10],"Luo,":[11],"Guotong":[12],"Geng,":[13],"Xiaoying":[14],"Bai,":[15],"Jun":[16],"Wen":[18],"Yao,":[19],"Zhong":[20],"Wang.":[21],"Findings":[22],"of":[23],"the":[24],"Association":[25],"for":[26],"Computational":[27],"Linguistics:":[28],"EMNLP":[29],"2025.":[30,31]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}
