Effective Explanations Support Planning Under Uncertainty

TL;DR

This paper introduces a computational model that converts explanations into action plans to improve navigation under uncertainty, demonstrating that higher-quality explanations enhance performance and helpfulness.

Contribution

The authors propose a novel method translating explanations into executable plans using large language models, evaluated through experiments on navigation tasks.

Findings

Higher-scored explanations are judged more helpful.

Participants with explanations outperform those without.

High-scoring explanations significantly improve navigation.

Abstract

Explaining how to get from A to B can be challenging. It requires mentally simulating what the listener will do based on what they are told. To capture this process, we propose a computational model that converts utterances into action plans: a large language model translates an explanation into program-like guidance (a policy prior and value map), and a planning agent executes it under partial observability. We score explanations by the efficiency and reliability of the resulting paths, penalizing replanning. Across four preregistered experiments, we collect a corpus of 1,200 explanations over 24 maps, elicit helpfulness judgments, measure baseline navigation, and test behavior with explanations of differing quality. Higher-scored explanations are judged more helpful and improve navigation: participants with explanations outperform those without, and high-scoring explanations help more than low-scoring ones. Together, these results show procedural explanation as utility-guided communication shaped by how language can be grounded into action under uncertainty.