Papers
arxiv:2606.08077

Support Vector Rubrics: Closing the Gap Between Self-Generated and Human Rubrics

Published on Jun 6
Authors:
,
,
,
,

Abstract

SVR improves LLM evaluation by learning discriminative rubrics via max-margin boundary optimization over preference pairs, closing the gap with human criteria.

Rubric-based evaluation is a promising paradigm for judging large language model (LLM) outputs, yet self-generated rubrics lag human-annotated criteria on hard instances. We argue this discriminative gap reflects an objective mismatch: self-generated rubrics describe good responses, whereas effective criteria must discriminate between close candidates. To close this gap, we introduce SVR (Support Vector Rubrics), a framework that recasts rubric construction as max-margin boundary learning over preference data. SVR mines contrastive features from preference pairs into a rubric bank, learns a prompt-conditioned selector together with global rubric weights, and iteratively refines the bank through support-pair selection and adversarial probing of hard negatives. At inference, given only the prompt, SVR retrieves the top-rubrics from the bank and scores responses. On RubricBench, SVR narrows the gap to human reference rubrics from 24.1 to 0.3 points and outperforms strong self-rubric and judge baselines, and the learned bank transfers across judges without retraining. On RewardBench 1&2, and RM-Bench, it remains competitive with dedicated reward models, demonstrating broader reward modeling capability. Overall, boundary-defining rubrics offer a principled route to closing the discriminative gap in LLM evaluation.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2606.08077
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/2606.08077 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/2606.08077 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/2606.08077 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.