V-Rubrics: Visual Faithfulness via Rubric-Based Reinforcement Learning
Vision-language models can produce fluent answers that are insufficiently grounded in the visual evidence: a single unsupported object, chart value, or intermediate inference can undermine an otherwise plausible response. We argue that this is a credit-assignment failure in multimodal post-training. Scalar outcome rewards indicate whether an answer is acceptable, but do not identify which visual facts are grounded, which reasoning steps are valid, or which instruction constraints are missed. We introduce Visual Rubrics-Based Reinforcement Learning, which decomposes reference responses into atomic propositions and scores generated answers along Visual Faithfulness (VF), Reasoning Consisten...
| Authors | Shulin Tian, Minglun Li, Yuhao Dong et al. |
|---|---|
| Primary category | cs.CV |
| Published | 26 August 2026 |
| Last updated at source | 26 August 2026 |
Popularity, last 2 days
0 now. Counts as reported by the source, snapshotted daily by Silytics.
Connected in the knowledge graph
- v-rubrics/v-rubrics-50kDataset · cited by
Models and datasets referencing this paper
- v-rubrics/v-rubrics-50kDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 18 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.