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 proposes step-wise peer advantage and diversity-aware exploration rewards in RL for multi-answer QA, reporting improved recall and F1 on QAMPARI, Mintaka, WebQSP, and QUEST.
citing papers explorer
-
SPADER: Step-wise Peer Advantage with Diversity-Aware Exploration Rewards for Multi-Answer Question Answering
SPADER proposes step-wise peer advantage and diversity-aware exploration rewards in RL for multi-answer QA, reporting improved recall and F1 on QAMPARI, Mintaka, WebQSP, and QUEST.