arXiv:2611.17620v1 cs.AI

Safety Side Effects of Preventative Persona Steering: An Empirical Audit

Sabrina Tang, Nikolai Vo, Carson Murillo, Chira Sukumarnpiti, Sarah Wilson

제출 2026-11-13

저자 비고

arXiv Comments

5 pages, 1 figure (6 charts), 1 table, accepted at NeurIPS 2026 Bialign Workshop

원문 초록

High-level behaviors such as sycophancy and hallucination correspond to directions in a model's activation space (Chen et al., 2025). These directions, known as persona vectors, can suppress undesirable traits either at inference time, subtracting the vector during generation, or through preventative steering, adding the vector during fine-tuning, so the optimizer never needs to encode the trait in weights, then removing the vector at evaluation. Chen et al. (2025) recommend preventative steering because it preserves Massive Multitask Language Understanding (MMLU) accuracy, but validations of this recommendation have measured capability alone. We primarily evaluate results on preventative steering of sycophancy and hallucination vectors on three models, measuring three safety benchmarks alongside trait expression, coherence, and MMLU. Our findings show that preventative steering still changes refusal behavior, but by an amount that depends on the trait and does not establish that preventative persona steering is safety-neutral, and steering methods should be evaluated on several safety benchmarks.

제출 이력

확인된 버전만 표시합니다. 전체 제출 이력은 arXiv 원문에서 확인하세요.

  1. arXiv:2611.17620v1

함께 살펴볼 논문

공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.

공통 태그로 연결된 공개 논문이 아직 없습니다.

토론

이 논문과 연결된 포럼 글이 아직 없습니다.