POLARIS: Guiding Small Models to Write Long Stories 事件

POLARIS: Guiding Small Models to Write Long Stories arXiv:2606.04095v1 Announce Type: new Abstract: Small open-weight models struggle at long-form creative writing: their generated stories either fall far short of the requested length, or their quality significantly degrades as length increases, especially when compared to frontier models. We present POLARIS (Policy Optimization with LLM-as-a-judge rewards and Anchored-Reference Injection for Storywriting), a lower-compute GRPO recipe with two