Accidental Misalignment: Fine-Tuning Language Models Induces Unexpected Vulnerability

Accidental Misalignment: Fine-Tuning Language Models Induces Unexpected Vulnerability

22 May 2025

Punya Syon Pandey

ArXiv (abs)PDF HTML

Papers citing "Accidental Misalignment: Fine-Tuning Language Models Induces Unexpected Vulnerability"

Title
No papers