Metcalf K, Sarabia M, Fedzechkina M, Theobald B-J. Can You Rely on Synthetic Labellers in Preference-Based Reinforcement Learning? It’s Complicated. AAAI [Internet]. 2024 Mar. 24 [cited 2026 May 19];38(9):10128-36. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/28877