Designing effective reward signals for open-domain question answering is challenging because high-quality responses must simultaneously satisfy multiple aspects of answer quality that are difficult to capture with a holistic scalar objective. This paper introduces a rubric-based reward framework that generates query-specific rubrics grounded in retrieved evidence and decomposed into multiple quality dimensions, providing fine-grained supervision during post-training.

Averaged across three evaluation axes (composition, grounding, and instruction-following), the approach improves over the instruction-tuned baseline by 6.5% and over flat rubric variants by 4%, with consistent gains across all evaluation datasets. Conditioning rubrics on retrieved evidence improves factual support, while decomposing rubrics into quality-specific dimensions further improves coherence, organization, and adherence to query requirements.

The results show that grounded, multi-dimensional rubrics provide more effective reward supervision for complex open-domain question answering, offering a principled alternative to holistic reward signals.