Introduces the first benchmark for over-refusal in large audio language models using 3,000 pseudo-harmful audio samples and evaluates 12 models across six families, finding widespread over-refusal.
Safety Alignment for Vision Language Models
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
AP-Test identifies deployed guardrails in LLMs via adversarial prompt testing and a match score metric, reporting perfect accuracy on four open-source guardrails.
WARD is a guard model trained on 177K web samples and adversarially hardened via attacker-guard co-evolution to achieve high recall on prompt injections with low false positives and no added latency.
Synthetic clinical demonstrations at inference time improve safety of Med-VLMs against visual and textual jailbreaks while preserving general performance on medical tasks.
citing papers explorer
-
AOR-Bench: Do Large Audio Language Models Over-Refuse Pseudo-Harmful Queries?
Introduces the first benchmark for over-refusal in large audio language models using 3,000 pseudo-harmful audio samples and evaluates 12 models across six families, finding widespread over-refusal.
-
Peering Behind the Shield: Guardrail Identification in Large Language Models
AP-Test identifies deployed guardrails in LLMs via adversarial prompt testing and a match score metric, reporting perfect accuracy on four open-source guardrails.
-
WARD: Adversarially Robust Defense of Web Agents Against Prompt Injections
WARD is a guard model trained on 177K web samples and adversarially hardened via attacker-guard co-evolution to achieve high recall on prompt injections with low false positives and no added latency.
-
Enhancing the Safety of Medical Vision-Language Models by Synthetic Demonstrations
Synthetic clinical demonstrations at inference time improve safety of Med-VLMs against visual and textual jailbreaks while preserving general performance on medical tasks.