Poster
in
Workshop: HCAI@NeurIPS 2022, Human Centered AI

Pragmatic AI Explanations

Shi Feng · Chenhao Tan

Keywords: [ interpretability ] [ pragmatics ]

Abstract:

We use the Rational Speech Act framework to examine AI explanations as a pragmatic inference process. This reveals fatal flaws in how we currently train and deploy AI explainers. To evolve from level-0 explanations to level-1, we present two proposals for data collection and training: learning from L1 feedback, and learning from S1 supervision.

Chat is not available.