LADE extracts cross-model safety signals from first-token dark knowledge, lowering jailbreak success while preserving the safety-utility balance
LADE extracts model-agnostic latent safety signals from dark knowledge in the first-token output probability distribution by contrasting harmful and benign queries, maps the selected tokens across tokenizers, and filters harmful queries via kNN distance before generation; across Llama-2-7B-Chat, Llama-3-8B-Instruct, Qwen2-7B-Instruct, Qwen3-8B, Gemma-7B-it, and Mistral-7B-Instruct-v0.3, it attains the lowest or near-lowest average compliance under multiple jailbreak attacks and the best safety-utility average on six of eight models.