Explaining Agent Behavior with Large Language Models

TL;DR

This paper introduces a method for generating natural language explanations for agent behavior using large language models, enabling interpretability and user interaction without revealing underlying model details.

Contribution

The approach learns a compact behavior representation to produce plausible explanations from observations, facilitating interpretability of complex agents.

Findings

Generated explanations are as helpful as human experts'

Enables user interactions like clarification and counterfactual queries

Produces minimal hallucination in explanations

Abstract

Intelligent agents such as robots are increasingly deployed in real-world, safety-critical settings. It is vital that these agents are able to explain the reasoning behind their decisions to human counterparts, however, their behavior is often produced by uninterpretable models such as deep neural networks. We propose an approach to generate natural language explanations for an agent's behavior based only on observations of states and actions, agnostic to the underlying model representation. We show how a compact representation of the agent's behavior can be learned and used to produce plausible explanations with minimal hallucination while affording user interaction with a pre-trained large language model. Through user studies and empirical experiments, we show that our approach generates explanations as helpful as those generated by a human domain expert while enabling beneficial interactions such as clarification and counterfactual queries.