The Confident Liar Measuring and Governing Assertive Falsehoods in Persona-Conditioned LLMs

제목
The Confident Liar Measuring and Governing Assertive Falsehoods in Persona-Conditioned LLMs
저자
이세영; 권석재
발행일
2025-12-17
학회명
International Conference on Mobile Internet Security 2025 (MobiSec’25)
개최국가
일본
학회 개최일
2025-12-17 ~ 2025-12-17