Interpretive Blindness
Artificial Intelligence
2021-11-02 v1 Computation and Language
Abstract
We model here an epistemic bias we call \textit{interpretive blindness} (IB). IB is a special problem for learning from testimony, in which one acquires information only from text or conversation. We show that IB follows from a co-dependence between background beliefs and interpretation in a Bayesian setting and the nature of contemporary testimony. We argue that a particular characteristic contemporary testimony, \textit{argumentative completeness}, can preclude learning in hierarchical Bayesian settings, even in the presence of constraints that are designed to promote good epistemic practices.
Keywords
Cite
@article{arxiv.2111.00867,
title = {Interpretive Blindness},
author = {Nicholas Asher and Julie Hunter},
journal= {arXiv preprint arXiv:2111.00867},
year = {2021}
}