POLARIS: Guiding Small Models to Write Long Stories
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 key ingredients: a frontier LLM judge with a structured Story Quality rubric as the online reward, and human-reference injection (HRI), where a teacher-forced human-written story serves as a high-reward anchor within each GRPO group. By applying our training recipe to Qwen3.5-9B, using a dataset o...
| Authors | Rishanth Rajendhran, Jenna Russell, Mohit Iyyer et al. |
|---|---|
| Primary category | cs.CL |
| Published | 2 June 2026 |
| Last updated at source | 30 August 2026 |
Connected in the knowledge graph
- rishanthrajendhran/POLARIS-9BModel · cited by
- rishanthrajendhran/POLARISDataset · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.