Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Keiichi Namikoshi, David A. Shamma, Rumen Iliev, Jingchao Fang, Alexandre Filipowicz, Candice L Hogan, Charlene Wu, Nikos Arechiga

TL;DR

This work uses new advances in LLMs, combined with a contextual bandit, to develop conversational interventions that are personalized to the values of each study participant, and uses a contextual bandit algorithm to learn to target values based on the demographics of each participant.

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.

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

TL;DR

This work uses new advances in LLMs, combined with a contextual bandit, to develop conversational interventions that are personalized to the values of each study participant, and uses a contextual bandit algorithm to learn to target values based on the demographics of each participant.

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.

Paper Structure

This paper contains 18 sections, 1 equation, 5 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Related work
  3. Contextual multi-armed bandit problem
  4. Problem setting: Preferences for BEVs
  5. Method
  6. Intervention system architecture
  7. Virtual participants implementation
  8. Measuring preferences for battery-electric vehicles
  9. PeaR-RL: Learning values of survey participants
  10. Wizard: LLM-based intervention generation
  11. Intervention learning with virtual participants
  12. Experimental settings
  13. Results
  14. Comparison to human data on fixed interventions
  15. Experiment settings
  16. ...and 3 more sections

Figures (5)

  • Figure 1: Architecture of intervention system
  • Figure 2: Accumulated preference shifts. Line and areas indicate mean and standard deviation between difference random seed experiments.
  • Figure 3: Estimated mean of preference shifts. Left: UCB policy. Right: random policy. Each results are calculated to average with all steps on one random seed experiment.
  • Figure 4: Survey response comparisons. Upper: Initial preference distribution. Lower: Preference shift distribution.
  • Figure 5: Mean of preference shifts per intervention.