Social Contract AI: Aligning AI Assistants with Implicit Group Norms
This addresses the problem of practical AI alignment for developers and researchers, but it is incremental as it presents preliminary results in a simulation framework.
The paper tackled aligning AI assistants with implicit group norms by inverting a model of user preferences from interactions, using simulations in the ultimatum game, and found that the assistant accurately matched known policies but lacked robustness and generalization in out-of-distribution settings.
We explore the idea of aligning an AI assistant by inverting a model of users' (unknown) preferences from observed interactions. To validate our proposal, we run proof-of-concept simulations in the economic ultimatum game, formalizing user preferences as policies that guide the actions of simulated players. We find that the AI assistant accurately aligns its behavior to match standard policies from the economic literature (e.g., selfish, altruistic). However, the assistant's learned policies lack robustness and exhibit limited generalization in an out-of-distribution setting when confronted with a currency (e.g., grams of medicine) that was not included in the assistant's training distribution. Additionally, we find that when there is inconsistency in the relationship between language use and an unknown policy (e.g., an altruistic policy combined with rude language), the assistant's learning of the policy is slowed. Overall, our preliminary results suggest that developing simulation frameworks in which AI assistants need to infer preferences from diverse users can provide a valuable approach for studying practical alignment questions.