Safety
Rubric Judgments Lack Uncertainty: Conformal Weighting for LLM Evaluation
arXiv:2610.21214v1 Announce Type: new Abstract: Rubric-based evaluation is widely used to assess large language model (LLM) outputs by decomposing quality into multiple criteria and assigning each a b
arXiv:2610.21214v1 Announce Type: new Abstract: Rubric-based evaluation is widely used to assess large language model (LLM) outputs by decomposing quality into multiple criteria and assigning each a binary judgment from an LLM verifier. However, judgment certainty varies substantially across criteria. Existing methods uniformly aggregate these judgments into a final score, implicitly treating every criterion as equally certain and overlooking this heterogeneity. As a result, uncertain judgments remain incorporated into reward estimation without distinction, potentially yielding misleading training signals for downstream reinforcement learning (RL). To address this limitation, we propose Uncertainty-aware Rubric Weighting (URW), a training-free framework that quantifies criterion-level judgment uncertainty via conformal calibration. Specifically, URW elicits a soft uncertainty signal from a fixed pool of paraphrased judgment templates and converts it into a per-criterion weight using split-conformal p-values with provable coverage guarantees. Extensive experiments demonstrate that URW consistently improves pairwise preference accuracy and delivers stronger downstream RL alignment.
Related
- CoRT: Counterfactual Replay for Token-Level Rubric-Guided Policy Optimization
- Mubric: Mutation Testing-Guided Rubric Generation for LLM Evaluation
- Reliable to Expressive: A Curriculum for Rubric-Following Safety Judges
- SCOPE: Selective Conformal Optimized Pairwise LLM Judging
Source: arXiv cs.AI | 2026-10-16