注意力重分配：迈向多模态大语言模型零成本且可控的幻觉缓解
Attention Reallocation: Towards Zero-cost and Controllable Hallucination Mitigation of MLLMs
AI总结：
本文提出注意力重分配方法AttnReal，通过回收输出token的过量注意力并重新分配给视觉token，以近零额外成本缓解多模态大语言模型的幻觉，并可通过控制强度实现响应忠实度与整体性能之间的可控权衡。
摘要：
多模态大语言模型（MLLMs）在各类任务中表现突出，但仍受到幻觉问题的困扰。近期免训练的缓解方法大多通过回溯策略和对比解码引入额外的推理开销，而我们提出注意力重分配（AttnReal），以几乎零额外成本缓解幻觉。我们的方法源于以下关键观察：MLLM不合理的注意力分布导致特征被历史输出token主导，而不同token类型之间的分布差距进一步加剧了幻觉响应。基于这些观察，AttnReal回收输出token上的过量注意力，并将其重新分配给视觉token，从而降低MLLM对语言先验的依赖，确保解码过程更多地依赖视觉输入。更有趣的是，我们发现通过控制AttnReal的强度，可以在响应忠实度与整体性能之间实现大范围的权衡。来自不同基准的综合结果验证了AttnReal在六个开源MLLM和三种解码策略上的有效性。
英文摘要：
Multi-Modal Large Language Models (MLLMs) stand out in various tasks but still struggle with hallucinations. While recent training-free mitigation methods mostly introduce additional inference overhead via retrospection strategy and contrastive decoding, we propose attention reallocation (AttnReal) to mitigate hallucinations with nearly zero extra cost. Our approach is motivated by the key observations that, MLLM's unreasonable attention distribution causes features to be dominated by historical output tokens, which further contributes to hallucinated responses because of the distribution gap between different token types. Based on the observations, AttnReal recycles excessive attention from output tokens and reallocates it to visual tokens, which reduces MLLM's reliance on language priors and ensures the decoding process depends more on the visual inputs. More interestingly, we find that, by controlling the intensity of AttnReal, we can achieve a wide-range trade-off between the response faithfulness and overall performance. Comprehensive results from different benchmarks validate the effectiveness of AttnReal across six open-source MLLMs and three decoding strategies.
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。
