Study exposes limits of majority-vote labels in test-time learning
Researchers analyse majority-vote pseudo-labels in test-time reinforcement learning, where models adapt to unlabeled data using self-generated labels. They decompose error into population-majority bias and finite-rollout variation, and propose a prompt-conditional distributional method to mitigate…
Read the full story at DEV Community — Machine Learning ↗
Timeline · 1 report
- 2026-11-09 07:03 · DEV Community — Machine Learning
Study exposes limits of majority-vote labels in test-time learning