Counterfactual Explanations for Natural Language Interfaces

TL;DR

This paper introduces a method for generating counterfactual explanations in natural language interfaces, helping users understand system capabilities by showing minimal utterance modifications to achieve goals.

Contribution

It presents a novel semantic parsing-based approach for counterfactual explanations, improving user understanding and system transparency in natural language interfaces.

Findings

User performance improved significantly with the approach

Generated explanations closely match user intent

Method outperforms ablation baselines

Abstract

A key challenge facing natural language interfaces is enabling users to understand the capabilities of the underlying system. We propose a novel approach for generating explanations of a natural language interface based on semantic parsing. We focus on counterfactual explanations, which are post-hoc explanations that describe to the user how they could have minimally modified their utterance to achieve their desired goal. In particular, the user provides an utterance along with a demonstration of their desired goal; then, our algorithm synthesizes a paraphrase of their utterance that is guaranteed to achieve their goal. In two user studies, we demonstrate that our approach substantially improves user performance, and that it generates explanations that more closely match the user's intent compared to two ablations.