Search Results for author:
Found 2 papers, 0 papers with code
Axioms for AI Alignment from Human Feedback
The problem of learning a reward function is one of preference aggregation that, we argue, largely falls within the scope of social choice theory.
Learning Linear Utility Functions From Pairwise Comparison Queries
Our results thus exhibit a qualitative learnability gap between passive and active learning from pairwise preference queries, demonstrating the value of the ability to select pairwise queries for utility learning.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
