no code implementations • 7 Apr 2024 • Andi Zhang, Tim Z. Xiao, Weiyang Liu, Robert Bamler, Damon Wischik
We revisit the likelihood ratio between a pretrained large language model (LLM) and its finetuned variant as a criterion for out-of-distribution (OOD) detection.
no code implementations • 1 Jun 2023 • Andi Zhang, Mingtian Zhang, Damon Wischik
We propose a probabilistic perspective on adversarial examples.
no code implementations • 23 Oct 2022 • Andi Zhang, Damon Wischik
An intuitive way to detect out-of-distribution (OOD) data is via the density function of a fitted probabilistic generative model: points with low density may be classed as OOD.