arXiv cs.LG
· Papers
Safe responses matter: Output-aware safety guardrail mitigate over-refusal in MLLMs
arXiv:2607.09697v1 Announce Type: new Abstract: Existing safety mechanisms for multimodal large language models (MLLMs) face a fundamental trade-off between safety and utility. Model fine-tuning achieves robust safety but compromises general utility. Input-side safety guardrails offer a lightweight alternative, yet the