通过重分配注意力，零成本减少多模态大模型幻觉
Attention Reallocation: Towards Zero-cost and Controllable Hallucination Mitigation of MLLMs
- 将输出令牌过多注意力重分配给视觉令牌，降低语言先验依赖
- 在多个基准上提升回答忠实度，且不增加推理开销
- 可调节强度实现忠实度与性能的灵活权衡，适合部署优化
多模态大语言模型（MLLMs）在各类任务中表现优异，但仍存在幻觉问题。现有无需训练的缓解方法大多通过回溯策略和对比解码引入额外推理开销。本文提出注意力重分配（AttnReal），以近乎零成本缓解幻觉。其核心观察是：MLLM中不合理注意力分布导致特征被历史输出令牌主导，加剧了不同令牌类型间的分布差异，从而引发幻觉。AttnReal将输出令牌的冗余注意力回收并重新分配给视觉令牌，降低对语言先验的依赖，使解码更依赖视觉输入。更有趣的是，通过控制AttnReal强度，可在响应忠实度与整体性能间实现广泛权衡。在六种开源MLLM和三种解码策略下的全面实验验证了该方法的有效性。
原文摘要 · Abstract (English)
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.
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。