CED adds a counterfactual evidence margin to GRPO so that correct answers are rewarded only when their likelihood drops more when the evidence region is neutralized than when matched non-evidence regions are neutralized.
Evaluating object hallucination in large vision-language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
Evidence-RL: Towards Evidence-intensive Visual Reasoning
CED adds a counterfactual evidence margin to GRPO so that correct answers are rewarded only when their likelihood drops more when the evidence region is neutralized than when matched non-evidence regions are neutralized.