arXiv cs.AI· Yeonjun Choi, Seyeon Jeong, Jong Wook Kim, Beakcheol Jang·· 14 小时前AI 评分26
DuQUAD：面向多文档问答的双视角与质量感知证据剪枝框架
DuQUAD: A Dual-View Framework with Quality-Aware Evidence Pruning for Multi-Document Question Answering
AI 导读
DuQUAD 是一个缓解多文档问答中 Lost in the Middle 问题的框架，通过由 Structural Fusion Score 引导的 Local Agent 与全局推理的 Global Agent 构成双视角机制，并用显式质量评分和句子级精炼过滤候选证据。其准确率平均比最强基线高 3.0%，黄金证据召回率提升 9.4%，计算成本显著低于现有多智能体框架。
正文 · 原文
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 still obscure useful evidence in central positions. We propose DuQUAD, a multi-document QA framework that mitigates positional bias through dual-view reasoning and quality-aware evidence pruning. DuQUAD combines a Local Agent guided by a Structural Fusion Score with a Global Agent that reasons over the full document set, providing both targeted evidence recovery and broad contextual understanding. The framework further filters candidate evidence using explicit quality scoring and refines it at the sentence level to reduce noise. DuQUAD consistently outperforms strong Lost-in-the-Middle mitigation baselines, including hybrid retrieval and reranking, multi-agent reasoning, and context optimization methods, improving accuracy by 3.0% on average over the strongest competing baseline and gold evidence recall by 9.4%, while substantially reducing computational cost compared to existing multi-agent frameworks.
| Subjects: | Information Retrieval (cs.IR); Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.37701 [cs.IR] |
| (or arXiv:2610.37701v1 [cs.IR] for this version) | |
| https://doi.org/10.48550/arXiv.2610.37701 arXiv-issued DOI via DataCite |
Submission history
From: Yeonjun Choi [view email]
[v1]
Sun, 25 Oct 2026 14:14:11 UTC (484 KB)
来源：arXiv cs.AI · arxiv.org