Situated Natural Language Explanations

TL;DR

This paper introduces situated natural language explanations (NLE), emphasizing audience needs and preferences, and proposes new evaluation metrics and prompt engineering techniques to improve explanation generation by large pretrained language models.

Contribution

It presents a novel perspective on NLE focusing on audience context, along with automated evaluation scores and prompt techniques for better explanation generation.

Findings

Automated evaluation scores cover lexical, semantic, and pragmatic properties.

Three prompt engineering techniques are assessed for situational NLE generation.

Situated NLE facilitates targeted explanation generation and evaluation.

Abstract

Natural language is among the most accessible tools for explaining decisions to humans, and large pretrained language models (PLMs) have demonstrated impressive abilities to generate coherent natural language explanations (NLE). The existing NLE research perspectives do not take the audience into account. An NLE can have high textual quality, but it might not accommodate audiences' needs and preference. To address this limitation, we propose an alternative perspective, \textit{situated} NLE. On the evaluation side, we set up automated evaluation scores. These scores describe the properties of NLEs in lexical, semantic, and pragmatic categories. On the generation side, we identify three prompt engineering techniques and assess their applicability on the situations. Situated NLE provides a perspective and facilitates further research on the generation and evaluation of explanations.