指令锚点:解构模态仲裁的机理动态
Instruction Anchor: Dissecting the Mechanistic Dynamics of Modality Arbitration
AI总结:
本文通过信息流视角研究模态跟随机制,揭示指令令牌作为模态仲裁的结构锚点,浅层注意力层负责多模态信息聚合,深层注意力层则根据指令意图选择性强化子空间,实验验证了注意力头的特定功能。
摘要:
模态跟随是指根据用户指令选择性利用多模态上下文的能力,对多模态大语言模型(MLLMs)的实际部署安全性和可靠性至关重要。然而,这一决策过程的内部机制尚不明确。本文通过信息流视角研究模态跟随的机制,发现指令令牌作为结构锚点:浅层注意力层执行非区分性信息传输,将多模态线索聚合到指令令牌作为潜在缓冲区;相比之下,深层注意力层则选择性强化符合指令的子空间,并根据指令指定的意图解决模态仲裁,由少量注意力头驱动。针对性的注意力头干预进一步验证了这些头的特定功能:仅阻断5%的识别头会显著降低模态跟随性能,同时保持通用视觉和语言能力;而针对性增强可将失败的模态跟随样本恢复至约60%。本文为模态跟随提供了机理解释,并指导未来改进MLLMs在用户指令下整合和利用多模态证据的方法。
英文摘要:
Modality following is the ability to selectively leverage multimodal contexts based on user instructions. It is fundamental to the safety and reliability of multimodal large language models (MLLMs) in real-world deployments. However, the internal mechanisms governing this decision-making process remain largely under-explored. In this work, we investigate the mechanism underlying modality following through an information flow perspective. Our findings reveal that instruction tokens serve as structural anchor for modality arbitration: Shallow attention layers perform undifferentiated information transfer, aggregating multimodal cues to instruction tokens as a latent buffer; in contrast, deep attention layers selectively strengthen the instruction-compliant subspace and resolve modality arbitration according to the instruction-specified intent, with a sparse subset of attention heads driving this process. Targeted attention-head interventions further validate the functional specificity of these heads: blocking only $5\%$ of the identified heads substantially degrades modality following while preserving general visual and language capabilities, whereas targeted amplification can restore failed modality-following samples by up to approximately $60\%$. Together, this work provides a mechanistic account of modality following and informs future efforts to improve how MLLMs integrate and utilize multimodal evidence under user instructions.
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。