Trust The Typical
Abstract
Current approaches to LLM safety fundamentally rely on a brittle cat-and-mouse game of identifying and blocking known threats via guardrails. We argue for a fresh approach: robust safety comes not from enumerating what is harmful, but from deeply understanding what is safe. We introduce Trust The Typical (T3), a framework that operationalizes this principle by treating safety as an out-of-distribution (OOD) detection problem. T3 learns the distribution of acceptable prompts in a semantic space and flags any significant deviation as a potential threat. Unlike prior methods, it requires no training on harmful examples, yet achieves state-of-the-art performance across 18 benchmarks spanning toxicity, hate speech, jailbreaking, multilingual harms, and over-refusal, reducing false positive rates by up to 40x relative to specialized safety models. A single model trained only on safe English text transfers effectively to diverse domains and over 14 languages without retraining. Finally, we demonstrate production readiness by integrating a GPU-optimized version into vLLM, enabling continuous guardrailing during token generation with less than 6% overhead even under dense evaluation intervals on large-scale workloads.
Cite
@article{arxiv.2602.04581,
title = {Trust The Typical},
author = {Debargha Ganguly and Sreehari Sankar and Biyao Zhang and Vikash Singh and Kanan Gupta and Harshini Kavuru and Alan Luo and Weicong Chen and Warren Morningstar and Raghu Machiraju and Vipin Chaudhary},
journal= {arXiv preprint arXiv:2602.04581},
year = {2026}
}