Safe responses matter: Output-aware safety guardrail mitigate over-refusal in MLLMs
英文标题：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
打开原文相关 2.4 · 机会 0
2.6 KB
2.1 KB
640 B
612 B
380 B
9.1 KB
32.7 KB
22.8 KB
24.2 KB
34.7 KB
中文
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
中文全文翻译正在补齐，可先查看下方英文原文。
English / 原文
BibTeX formatted citation
×