Democratizing Reward Design for Personal and Representative Value-Alignment

TL;DR

This paper presents a novel interactive method for aligning AI with individual human values by engaging users in reflective dialogue, capturing diverse preferences, and constructing personalized reward models for better value alignment.

Contribution

It introduces Interactive-Reflective Dialogue Alignment, a new approach that learns individual value definitions through language models, enabling personalized and more representative AI alignment.

Findings

Successfully captured diverse value definitions from participants.

Accurately modeled individual preferences for ethical decision-making.

Demonstrated potential for personalized and collective value alignment strategies.

Abstract

Aligning AI agents with human values is challenging due to diverse and subjective notions of values. Standard alignment methods often aggregate crowd feedback, which can result in the suppression of unique or minority preferences. We introduce Interactive-Reflective Dialogue Alignment, a method that iteratively engages users in reflecting on and specifying their subjective value definitions. This system learns individual value definitions through language-model-based preference elicitation and constructs personalized reward models that can be used to align AI behaviour. We evaluated our system through two studies with 30 participants, one focusing on "respect" and the other on ethical decision-making in autonomous vehicles. Our findings demonstrate diverse definitions of value-aligned behaviour and show that our system can accurately capture each person's unique understanding. This approach enables personalized alignment and can inform more representative and interpretable collective alignment strategies.