Counterfactual Explanations for Natural Language Interfaces
This addresses the problem of user comprehension in natural language interfaces, offering a practical solution for improving usability, though it is incremental as it builds on existing semantic parsing techniques.
The paper tackles the challenge of helping users understand natural language interfaces by proposing a method for generating counterfactual explanations based on semantic parsing, which synthesizes minimal utterance modifications to achieve user goals, and shows in user studies that it substantially improves user performance and better matches user intent compared to ablations.
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.