PruneHal：通过自适应KV缓存剪枝减少多模态大语言模型中的幻觉
PruneHal: Reducing Hallucinations in Multi-modal Large Language Models through Adaptive KV Cache Pruning
AI总结：
针对多模态大语言模型的幻觉问题，提出无需训练的PruneHal方法，通过自适应KV缓存剪枝增强关键视觉信息聚焦，适配多模型与解码策略，在多基准测试中取得优异效果。
摘要：
尽管多模态大语言模型（MLLMs）近年来取得了显著进展，但幻觉问题仍是一项重大挑战。为缓解这一现象，现有解决方案要么引入额外数据进行进一步训练，要么在推理过程中整合外部或内部信息，但这些方法不可避免地会带来额外的计算成本。本文中，我们观察到MLLMs的幻觉与分配给视觉token的注意力不足密切相关。具体而言，冗余视觉token的存在分散了模型的注意力，使其无法聚焦于信息量最大的token，导致关键视觉线索往往得不到充分关注，进而加剧了幻觉的发生。基于这一观察，我们提出了PruneHal，这是一种无需训练、简单且有效的方法，利用自适应KV缓存剪枝增强模型对关键视觉信息的聚焦，从而缓解幻觉。据我们所知，我们是首个将token剪枝应用于MLLMs幻觉缓解的研究。值得注意的是，我们的方法无需额外训练，且几乎不会产生额外推理成本。此外，PruneHal具有模型无关性，可无缝集成不同的解码策略，包括专门为缓解幻觉设计的策略。我们使用四种主流MLLMs在多个广泛使用的幻觉评估基准上测试PruneHal，取得了稳健且优异的结果，彰显了该方法的有效性与优越性。我们的代码将公开可用。
英文摘要：
While multi-modal large language models (MLLMs) have made significant progress in recent years, the issue of hallucinations remains a major challenge. To mitigate this phenomenon, existing solutions either introduce additional data for further training or incorporate external or internal information during inference. However, these approaches inevitably introduce extra computational costs. In this paper, we observe that hallucinations in MLLMs are strongly associated with insufficient attention allocated to visual tokens. In particular, the presence of redundant visual tokens disperses the model's attention, preventing it from focusing on the most informative ones. As a result, critical visual cues are often under-attended, which in turn exacerbates the occurrence of hallucinations. Building on this observation, we propose \textbf{PruneHal}, a training-free, simple yet effective method that leverages adaptive KV cache pruning to enhance the model's focus on critical visual information, thereby mitigating hallucinations. To the best of our knowledge, we are the first to apply token pruning for hallucination mitigation in MLLMs. Notably, our method don't require additional training and incurs nearly no extra inference cost. Moreover, PruneHal is model-agnostic and can be seamlessly integrated with different decoding strategies, including those specifically designed for hallucination mitigation. We evaluate PruneHal on several widely used hallucination evaluation benchmarks using four mainstream MLLMs, achieving robust and outstanding results that highlight the effectiveness and superiority of our method. Our code will be publicly available.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
