Narrow Multimodal Fine-Tuning Can Induce Emergent Misalignment
The findings suggest that multimodal EM reflects a behavioral shift rather than a general loss of capability, extending beyond text to the visual modality.
We have 2 of 12 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
The findings suggest that multimodal EM reflects a behavioral shift rather than a general loss of capability, extending beyond text to the visual modality.
P RO A CT represents an orthogonal defense strategy that serves as an additional guardrail to enhance LLM safety against the most effective attacks.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.