擴散模型中減少幻覺的分數控制

摘要

擴散模型已成為現代生成式AI的基石，驅動著視覺、語言、音訊等多模態領域的進展。儘管取得巨大成功，此類模型仍會產生幻覺——即落在真實數據分布支撐集之外、不合理的樣本——進而降低可靠度與信任度。本研究首先透過實驗驗證先前提出的假說：在影像生成擴散模型中，分數平滑性會導致幻覺，並提出基於密度的觀點。我們進一步將此概念形式化，將幻覺機率質量與學習所得分數函數的利普希茨常數相互連結。受此啟發，我們提出一種變異數引導的分數調變（VSM）策略，透過控制分數雅可比矩陣，降低分數平滑性，從而更逼近真實分數，進而減少幻覺。在合成數據集與真實世界數據集上的實證結果顯示，我們的方法能有效降低高達約25%的幻覺，同時維持高保真度與多樣性，為建立更可靠的擴散式影像生成提供了嚴謹的方法論基礎。此外，我們也提出兩個具有極端語義變異的評測基準，用於系統性評估幻覺現象。程式碼與數據集已公開於 https://github.com/bhosalems/VSM。

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.