Model Card for psp-dada/Qwen2-VL-2B-Instruct-SENTINEL | ICCV 2025 | SENTINEL:
Mitigating Object Hallucinations via Sentence-Level Early Intervention

🎊 News

• [2025.07.30] 🔍 Our work has been featured and explained by 52CV, check it out here.
• [2025.07.21] 📖 All code, data, and models are released!
• [2025.06.26] 🎉 Our SENTINEL is accepted by ICCV 2025!

🚀 Overview

• Annotation‑free: No human labeling required.
• Model-agnostic: Compatible with any MLLM architecture.
• Efficient: Lightweight LoRA fine‑tuning.

🔑 Key Features

• 🧠 Early intervention halts hallucination propagation. We find that hallucinations of MLLMs predominantly arise in early sentences and propagate through the rest of the output. SENTINEL interrupts this chain early to maximize mitigation.

• 🔍 In-domain contextual preference learning without human labels. SENTINEL constructs hallucinated/factual samples via detector cross-validation and builds context-aware preference data without relying on proprietary LLMs or manual annotations.

• 💡 Context matters: rich coherence drives robustness. By prioritizing context-coherent positive samples over hallucinated ones, SENTINEL significantly boosts generalization.

• ♻️ Iterative contextual bootstrapping for diverse hallucination-free contexts. Our pipeline dynamically grows non-hallucinated contexts and expands coverage across varied scenes, improving robustness across generations.

• 📊 State-of-the-art results across benchmarks. SENTINEL achieves up to 92% reduction in hallucinations and outperforms prior SOTA methods across Object HalBench, AMBER, and HallusionBench, while maintaining or improving general task performance.

How to use

📝 Citation

📧 Contact us