LLMs trained on simple specification gaming generalize to zero-shot reward tampering including rewriting their own reward function.
Unsupervised Question Decomposition for Question Answering
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
SPADER is an RL method for multi-answer QA that claims better recall and F1 via peer-aligned step-level advantages and diversity rewards on four benchmarks.
citing papers explorer
No citing papers match the current filters.