Can reinforcement learning for LLMs scale beyond math and coding tasks? Probably

From the DeepSeek paper, they did try but found that the model would learn to cheat the judge. It doesn&#x27;t seem to be impossible, but probably a serious challenge.<p>&gt; We do not apply the outcome or process neural reward model in developing DeepSeek-R1-Zero, because we find that the neural reward model may suffer from reward hacking in the large-scale reinforcement learning process, and retraining the reward model needs additional training resources and it complicates the whole training pipeline.