DuQUAD：面向多文档问答的双视角与质量感知证据剪枝框架
原标题：DuQUAD: A Dual-View Framework with Quality-Aware Evidence Pruning for Multi-Document Question Answering
AI 摘要
该论文提出DuQUAD框架，用于缓解大语言模型在多文档问答中的“Lost in the Middle”位置偏差问题。DuQUAD通过双视角推理（局部Agent与全局Agent）结合质量感知的证据剪枝，并引入结构融合分数（SFS）来优先选择金标文档。实验表明，该方法在三个多文档问答基准上平均准确率比最强基线提升3.0%，金标证据召回率提升9.4%，同时相比现有多智能体框架显著降低计算成本。
正文节选
DuQUAD: A Dual-View Framework with Quality-Aware Evidence Pruning for Multi-Document Question Answering Abstract Large language models with retrieval-augmented generation systematically underutilize evidence in the middle of multi-document contexts, a phenomenon known as Lost in the Middle. Existing mitigation strategies, such as document reordering and attention steering, can reduce boundary bias but remain brittle in noisy settings, where inaccurate relevance estimation and spurious documents