Andreas Haupt
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
AI×1
Frequent co-authors
Research Timeline
2026
Reward Bias Substitution: Single-Axis Bias Mitigations Redirect Optimization Pressure
The paper introduces 'reward bias substitution,' demonstrating that single-axis mitigations of reward model biases merely shift optimization pressure to correlated proxies, and proposes augmenting evaluation with policy-induced distributions to accurately detect this failure mode.
Highlighted terms show continued research focus across papers
Papers
cs.AIRecentMay 27, 2026
Reward Bias Substitution: Single-Axis Bias Mitigations Redirect Optimization Pressure
Max Lamparth, Daniel Fein, Andreas Haupt, Marcel Hussing +1 more
The paper introduces 'reward bias substitution,' demonstrating that single-axis mitigations of reward model biases merely shift optimization pressure to correlated proxies, and proposes augmenting eva…
View →