Timezone: »

 
Pragmatic AI Explanations
Shi Feng · Chenhao Tan

@
in HCAI@NeurIPS 2022, Human Centered AI »
Event URL: https://openreview.net/forum?id=tOk8eiMv5Lx »

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.

Keywords: interpretability · pragmatics

Author Information

Shi Feng (University of Chicago)
Chenhao Tan (University of Chicago)

More from the Same Authors