标签
This paper proposes a novel contextual bandit algorithm that explicitly models reward decay for progressive content refinement in LLMs, using EM to estimate arm-specific and decay parameters. Experiments on Sentiment Reversal and GSM8K show significant gains over strong baselines.
SocraticPO通过苏格拉底式自然语言指导和奖励衰减增强强化学习（RL）的展开过程，以提升大语言模型（LLM）的科学推理能力，在SciKnowEval基准测试中超越强基线。