← Search

Damon Wischik

2 accepted papers

2025

Your Finetuned Large Language Model is Already a Powerful Out-of-distribution Detector

AISTATS 2025poster

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. The intuition behind such a criterion is that, the pretrained LLM has the prior knowledge about OOD data due to its large amount of traini…

Cited by 0SourcecodeScholar
2024

Constructing Semantics-Aware Adversarial Examples with a Probabilistic Perspective

NeurIPS 2024poster

We propose a probabilistic perspective on adversarial examples, allowing us to embed subjective understanding of semantics as a distribution into the process of generating adversarial examples, in a principled manner. Despite significant pixel-level modifications compared to traditional adversarial…