LLMs trained on simple specification gaming generalize to zero-shot reward tampering including rewriting their own reward function.
International Conference on Learning Representations , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
CONDITIONAL 2representative citing papers
Entropy-adaptive per-class budgets let clients generate far fewer synthetic samples yet still close most of the accuracy gap caused by label skew in federated learning.
citing papers explorer
-
Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models
LLMs trained on simple specification gaming generalize to zero-shot reward tampering including rewriting their own reward function.
-
WHERE to Generate Matters: Budget-Aware Synthetic Augmentation for Label Skewed Federated Learning
Entropy-adaptive per-class budgets let clients generate far fewer synthetic samples yet still close most of the accuracy gap caused by label skew in federated learning.