通过投影到幻觉空间零空间，有效减少视觉语言模型的物体幻觉。
Nullu: Mitigating Object Hallucinations in Large Vision-Language Models via HalluSpace Projection
- 基于幻觉嵌入特征识别幻觉空间，通过权重正交化实现输入投影
- 在多个视觉语言模型上显著降低幻觉率，且推理无额外开销
- 适合关注模型可信度与输出准确性的研究者和应用开发者
近期研究表明，大型视觉语言模型（LVLM）常出现物体幻觉（OH）问题。本文提出一种高效方法，通过修改模型权重来缓解该问题。我们定义了一个不安全子空间，称为霍卢空间（HalluSpace），利用真实与幻觉文本提示伴随视觉内容输入，提取幻觉嵌入特征并剔除真实表示，从而识别出霍卢空间。通过正交化模型权重，使输入特征投影至霍卢空间的零空间，抑制由大语言模型（LLMs）先验知识引发的幻觉生成，提升输出上下文准确性。实验表明，该方法在不同LVLM家族中均能有效缓解幻觉，且无需额外推理成本，在通用LVLM基准测试中表现优异。代码已开源：https://github.com/Ziwei-Zheng/Nullu。
原文摘要 · Abstract (English)
Recent studies have shown that large vision-language models (LVLMs) often suffer from the issue of object hallucinations (OH). To mitigate this issue, we introduce an efficient method that edits the model weights based on an unsafe subspace, which we call HalluSpace in this paper. With truthful and hallucinated text prompts accompanying the visual content as inputs, the HalluSpace can be identified by extracting the hallucinated embedding features and removing the truthful representations in LVLMs. By orthogonalizing the model weights, input features will be projected into the Null space of the HalluSpace to reduce OH, based on which we name our method Nullu. We reveal that HalluSpaces generally contain prior information in the large language models (LLMs) applied to build LVLMs, which have been shown as essential causes of OH in previous studies. Therefore, null space projection suppresses the LLMs' priors to filter out the hallucinated features, resulting in contextually accurate outputs. Experiments show that our method can effectively mitigate OH across different LVLM families without extra inference costs and also show strong performance in general LVLM benchmarks. Code is released at https://github.com/Ziwei-Zheng/Nullu.
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。