VERDICT verifies each reasoning step of a multimodal LLM by combining scores from three frozen judges through a closed-form consensus, reporting up to +5.95 accuracy points across six benchmarks.
In: The Thirty-ninth Annual Conference on Neural Information Processing Systems (2025),https:// openreview.net/forum?id=ZyiBk1ZinG4, 10
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
VERDICT: Training-Free Step-Wise Verification of Multimodal Reasoning via Disagreement-Aware Consensus
VERDICT verifies each reasoning step of a multimodal LLM by combining scores from three frozen judges through a closed-form consensus, reporting up to +5.95 accuracy points across six benchmarks.