Scoring Higher, Answering Worse: Mitigating Reward Hacking in Rubric-Based RL via Protocol-Level Rubrics
Scoring Higher, Answering Worse: Mitigating Reward Hacking in Rubric-Based RL via Protocol-Level Rubrics
研究指出,基於評分規準的強化學習以加權總和匯總各項評分時,模型可能透過不相關建議補回關鍵決策失誤的分數,出現評分提高、回答品質下降。研究提出 Protocol-Level Rubrics(ProRubric),將評分項目分組,只有同組條件全部符合且未觸發失敗條款才計分。ProRubric 提高回答適切度 10.8 分而不損失覆蓋率,並在兩種規模下取得七項基準的最高平均分。
Published on Sep 30
·
on Oct 14
Authors:
,
,
,
,
,
,
Abstract
Rubric-based reinforcement learning (Rubric-RL) trains language models where no verifier exists. A judge checks each criterion of a rubric, and the verdicts are aggregated into a reward, most often by a weighted sum. We show that this additive aggregation is the weak point. Under a sum, criteria compensate for one another: a policy that misses the one decision that matters can buy the points back with advice nobody asked for. On clinical consultation, such a policy scores higher and answers worse. Rubric coverage rises while appropriateness on held-out physician criteria falls below the untrained model. The medical criteria are not to blame. Grouped so that they must hold together, the same criteria, unchanged to the word, recover a third of the loss; shorter answers recover almost none. We therefore propose Protocol-level Rubrics (ProRubric), which keeps what the criteria ask for and changes how they are aggregated. It groups a checklist into a few protocol-level dimensions. A dimension counts only when all of its criteria hold and its failure clause does not fire. The grouping is done once, offline, and leaves the optimizer unchanged. ProRubric raises appropriateness by 10.8 points without losing coverage and has the best seven-benchmark average at both scales. Reward validity is set not only by what a rubric verifies, but by how it aggregates. Code is available at https://github.com/Estrellajer/ProRubric
View arXiv page View PDF Add to collection
Get this paper in your agent:
hf papers read 2609.38847
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2609.38847 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2609.38847 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2609.38847 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co