Improving Interpersonal Communication by Simulating Audiences with Large Language Models

How do we communicate with others to achieve our goals? We use our prior experience or advice from others, or construct a candidate utterance by predicting how it will be received. However, our experiences are limited and biased, and reasoning about potential outcomes can be difficult and cognitively challenging. In this paper, we explore how we can leverage Large Language Model (LLM) simulations to help us communicate better. Based on ideas from cognitive science such as the Rational Speech Act model, we propose the Explore-Generate-Simulate (EGS) framework, which takes as input any scenario where an individual is communicating to an audience with a goal they want to achieve. EGS (1) explores the solution space by producing a diverse set of advice relevant to the scenario, (2) generates communication candidates conditioned on subsets of the advice, and (3) simulates the reactions from various audiences to determine both the best candidate and advice to use. We evaluate this framework on eight scenarios spanning a range of interpersonal communication settings. For each scenario, we collect a dataset of human evaluations across candidates and baselines, and show that our framework's chosen candidate is significantly preferred over popular generation mechanisms for LLMs. Finally, we demonstrate the generality of our framework by applying it to real-world scenarios described by users on web forums.