Frontier models still show greediness and frequency bias, researchers say

m_wulfmeier · x · 2026-07-21

The author says frontier models still show two decision biases: greediness, where the model collapses onto the highest-prior answer, and frequency bias, where salient context outweighs evidence.

They add that some training recipes can reduce these biases over the long term, including RL fine-tuning on self-generated rationales, as shown in their greedy agents paper.

Related event: Study Reveals Persistent Decision Biases in Frontier and Vision-Language Models(3 posts)→

Original post →

More from Research

Research channel →