arXiv · 2611.19388
SARGO: Agreement-Gated Reinforcement and Suppression via On-Policy Self-Guidance for Visual Hallucination Mitigation
Abstract
Vision-language models remain susceptible to visual hallucinations, often mixing grounded information with unsupported claims in the same response. Response-level reinforcement learning assigns a shared advantage to all tokens in a response, causing negative updates to suppress correct information alongside unsupported claims. To reduce hallucination while preserving useful visual information, we introduce SARGO (Self-guided Advantage-Routed Grounding Optimization), a post-training framework for selective reinforcement and suppression through on-policy self-guidance. Direct and reciprocal weighting gives better-supported tokens stronger reinforcement on positive updates and weaker penalties on negative updates. Agreement between overall and hallucination-specific advantages selects when to apply this guidance. At the response level, a reference-calibrated reward couples factuality with the retention and expansion of grounded information, discouraging lower hallucination scores obtained through omission. Experiments on Qwen3-VL-4B, Qwen3-VL-8B, and Gemma3-4B demonstrate that SARGO outperforms the evaluated mitigation baselines across Obj-Hal, AMBER, THRONE, and SHR evaluations. SARGO achieves these gains while preserving useful visual information and general multimodal capabilities.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Jinyu Li, Zhiming Zhang, Hao Fang, Hongyao Yu, Bin Chen, Albert Ma, Shu-Tao Xia. 2026-11-14. SARGO: Agreement-Gated Reinforcement and Suppression via On-Policy Self-Guidance for Visual Hallucination Mitigation. https://searcharxiv.com/abs/2611.19388
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.