Leveraging Language Models and Bandit Algorithms to Drive Adoption of Battery-Electric Vehicles

TL;DR

This paper combines large language models and contextual bandit algorithms to create personalized, conversational interventions aimed at increasing adoption of battery-electric vehicles, demonstrating improved persuasion over non-targeted approaches.

Contribution

It introduces a novel method that integrates LLMs with bandit algorithms for personalized behavior change interventions in EV adoption.

Findings

Bandit-enhanced LLM outperforms non-targeted LLM in persuasive effectiveness.

Offline training of bandit algorithms using LLM-generated participant simulations.

Personalized interventions based on demographics increase engagement and effectiveness.

Abstract

Behavior change interventions are important to coordinate societal action across a wide array of important applications, including the adoption of electrified vehicles to reduce emissions. Prior work has demonstrated that interventions for behavior must be personalized, and that the intervention that is most effective on average across a large group can result in a backlash effect that strengthens opposition among some subgroups. Thus, it is important to target interventions to different audiences, and to present them in a natural, conversational style. In this context, an important emerging application domain for large language models (LLMs) is conversational interventions for behavior change. In this work, we leverage prior work on understanding values motivating the adoption of battery electric vehicles. We leverage new advances in LLMs, combined with a contextual bandit, to develop conversational interventions that are personalized to the values of each study participant. We use a contextual bandit algorithm to learn to target values based on the demographics of each participant. To train our bandit algorithm in an offline manner, we leverage LLMs to play the role of study participants. We benchmark the persuasive effectiveness of our bandit-enhanced LLM against an unaided LLM generating conversational interventions without demographic-targeted values.