发表机构
Seoul National University（首尔大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出Sieve和Sage框架，通过分解检索失败为不可回答和分心状态，用轻量模块筛选干扰证据，再调用LLM生成与弃权，显著提升准确率、F1并加速。
AI 中文摘要
正如苏格拉底认识到自己知识的局限，检索增强语言模型（RALMs）也应学会在检索到的证据无法支持可靠回答时弃权（不执行）。现有方法主要依赖单一的大型语言模型（LLM）在单一步骤中处理异构的检索失败，导致弃权性能有限且计算成本高昂。我们转而将检索失败分解为两种不同状态：（i）不可回答状态，即所需证据缺失；（ii）分心状态，即相关证据与冲突、否定或对抗性信息混杂。基于这一分解，我们引入一个轻量级模块（Sieve），在调用昂贵的LLM（Sage）进行基于证据的生成和弃权之前，对检索到的文档集进行干扰证据筛选。在通用领域和高风险专家领域的评估中，我们的Sieve和Sage框架能够预先检测干扰噪声，与单阶段基线相比，系统准确率最高提升69.4个百分点，Macro-F1最高提升55.2个百分点。此外，它实现了高达1.99倍的加速，为带弃权的RALM建立了一个高效且可靠的弃权流水线。
英文摘要
Just as Socrates recognized the limits of his own knowledge, Retrieval-Augmented Language Models (RALMs) should learn to abstain when the retrieved evidence cannot support a reliable response. Existing approaches largely rely on monolithic LLMs to handle heterogeneous retrieval failures in a single step, resulting in limited abstention performance and high computational costs. We instead decompose retrieval failures into two distinct states: (i) the unanswerable state, where the required evidence is absent, and (ii) the distracted state, where relevant evidence is mixed with conflicting, negated, or adversarial information. Based on this decomposition, we introduce a lightweight module (Sieve) that screens retrieved document sets for distracting evidence before invoking a costly LLM (Sage) for grounded generation and abstention. Evaluated across both general and high-stakes expert domains, our Sieve and Sage framework preemptively detects distracting noise, improving system accuracy by up to 69.4 percentage points and Macro-F1 by 55.2 percentage points compared to one-stage baselines. Furthermore, it achieves up to a 1.99x speedup, establishing a highly efficient and reliable abstention pipeline for RALM with abstention.
Comments20 pages, 6 figures, accepted at EMNLP 2026 Findings
