适应性引导的检索增强掩码扩散模型
Adaptive Guidance for Retrieval-Augmented Masked Diffusion Models
AI总结：
本文提出ARAM框架，通过动态校准引导尺度提升检索增强扩散模型在知识密集型问答中的性能。
摘要：
检索增强生成（RAG）通过整合外部知识增强语言模型的事实性。然而，当检索到的上下文噪声、不可靠或与模型参数知识不一致时，会引入检索先验冲突，影响生成质量。本文提出适应性检索增强掩码扩散模型（ARAM），为检索增强设置下的掩码扩散模型（MDMs）提供无训练的适应性引导框架。ARAM根据检索上下文引起的分布偏移的信噪比动态校准引导尺度。直观上，当检索上下文提供可靠的纠正证据时，模型加强引导；当上下文信号噪声或不支持时，抑制引导。在多个知识密集型问答基准上的广泛实验表明，ARAM在问答性能上优于竞争性的RAG基线。
英文摘要：
Retrieval-Augmented Generation (RAG) improves factual grounding by incorporating external knowledge into language model generation. However, when retrieved context is noisy, unreliable, or inconsistent with the model's parametric knowledge, it introduces retrieval-prior conflicts that can degrade generation quality. While this problem has been studied in autoregressive language models, it remains largely unexplored in diffusion-based language models, where the iterative denoising process introduces unique challenges for integrating retrieved context. In this work, we propose Adaptive Retrieval-Augmented Masked Diffusion (ARAM), a training-free adaptive guidance framework for Masked Diffusion Models (MDMs) in RAG settings. ARAM dynamically calibrates the guidance scale during denoising according to the Signal-to-Noise Ratio (SNR) of the distributional shift induced by retrieved context. Intuitively, the model strengthens guidance when the retrieved context provides reliable corrective evidence and suppresses it when the contextual signal is noisy or non-supportive. Extensive experiments on multiple knowledge-intensive QA benchmarks show that ARAM improves overall QA performance over competitive RAG baselines.
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。
