AutoRubric generates rubric-based process rewards from self-aggregated successful trajectories to improve faithful multimodal reasoning in MLLMs under RLVR without human annotation or teacher models.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
AutoRubric: Rubric-Based Generative Rewards for Faithful Multimodal Reasoning
AutoRubric generates rubric-based process rewards from self-aggregated successful trajectories to improve faithful multimodal reasoning in MLLMs under RLVR without human annotation or teacher models.