通过调控得分函数平滑度，显著减少扩散模型的幻觉问题。
Score-Control for Hallucination Reduction in Diffusion Models
- 基于得分函数的Lipschitz常数设计变分引导得分调制策略
- 在真实与合成数据上降低幻觉率最高达25%，保持图像保真度与多样性
- 适用于需高可信生成结果的视觉生成场景，如医疗图像、安全关键应用
扩散模型已成为现代生成式AI的核心，推动了视觉、语言、音频等多模态的发展。尽管取得成功，其仍存在幻觉问题——即生成样本偏离真实数据分布，影响可靠性与可信度。本文首次实证验证了得分平滑性导致图像生成中幻觉的假设，并从密度角度加以解释。进一步，我们形式化地将幻觉概率质量与学习到的得分函数的Lipschitz常数关联。受此启发，提出变分引导得分调制（VSM）策略，通过控制得分雅可比矩阵来降低得分平滑性，更贴近真实得分，从而减少幻觉。在合成与真实数据集上的实验表明，该方法可降低幻觉（最高约25%），同时维持高保真度与多样性。此外，我们构建了两个具有极端语义差异的基准数据集，用于系统评估幻觉。代码与数据集已公开于 https://github.com/bhosalems/VSM。
原文摘要 · Abstract (English)
Diffusion models have emerged as the backbone of modern generative AI, powering advances in vision, language, audio and other modalities. Despite their success, they suffer from hallucinations, implausible samples that lie outside the support of true data distribution, which degrade reliability and trust. In this work, we first empirically confirm previously proposed hypothesis that score smoothness causes hallucinations in Image Generation diffusion models and provide a density-based perspective. We further formalize this notion by linking the hallucinations probability mass to lipschitz constant of the learned score function. Motivated by this, we introduce a Variance-Guided Score Modulation (VSM) strategy that controls the score Jacobian, in turn reducing score smoothness and better approximating the ground truth score that decreases hallucinations. Empirical results on synthetic and real-world datasets demonstrate that our approach reduces hallucinations (up to ~25%) while maintaining high fidelity and diversity, providing a principled step toward more reliable diffusion-based image generation. We also propose two benchmark datasets with extreme semantic variation for systematic hallucination evaluation. Code and Datasets are publicly available at https://github.com/bhosalems/VSM.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。