OPPO is an evidence-aware preference optimization that contrasts faithful responses under varying visual evidence strengths to reduce hallucinations in MLLMs.
Andesvl technical report: An efficient mobile-side multimodal large language model.arXiv preprint arXiv:2510.11496, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Clearer Sight, Fewer Lies: Oriented Pickup Preference Optimization for Multimodal Hallucination Mitigation
OPPO is an evidence-aware preference optimization that contrasts faithful responses under varying visual evidence strengths to reduce hallucinations in MLLMs.