用可管理的原子单元提升RAG系统维护性与准确性
NuggetIndex: Governed Atomic Retrieval for Maintainable RAG
- 将信息拆分为带时间区间和状态的原子记录，实现精准检索
- 相比基线，原子召回率提升42%，时间正确率提高9个百分点
- 适合需长期维护、对抗过时信息的问答系统开发者
检索增强生成（RAG）系统常以事实类指标评估，但标准实现仅检索段落或静态命题，评估对象与检索单元不匹配，导致数据演化时难以维护，也无法捕捉过时信息或来源冲突。本文提出NuggetIndex，将原子信息单元作为受控记录存储，称为nugget。每个记录包含证据链接、时间有效性区间及生命周期状态。通过在排序前过滤无效或废弃的nugget，系统避免引入过时信息。我们在nugget化的MS MARCO子集、时间型维基百科问答数据集及多跳问答任务上评估该方法。相较于段落和未管理命题的基线，NuggetIndex提升原子召回率42%，时间正确率提高9个百分点，且无时间过滤基线常见的召回率下降问题，冲突率降低55%。紧凑的nugget格式使生成器输入长度减少64%，并支持浏览器端和资源受限环境的轻量索引部署。我们开源了实现、数据集与评估脚本。
原文摘要 · Abstract (English)
Retrieval-augmented generation (RAG) systems are frequently evaluated via fact-based metrics, yet standard implementations retrieve passages or static propositions. This unit mismatch between evaluation and retrieval objects hinders maintenance when corpora evolve and fails to capture superseded facts or source disagreements. We propose NuggetIndex, a retrieval system that stores atomic information units as managed records, so called nuggets. Each record maintains links to evidence, a temporal validity interval, and a lifecycle state. By filtering invalid or deprecated nuggets prior to ranking, the system prevents the inclusion of outdated information. We evaluate the approach using a nuggetized MS MARCO subset, a temporal Wikipedia QA dataset, and a multi-hop QA task. Against passage and unmanaged proposition retrieval baselines, NuggetIndex improves nugget recall by 42%, increases temporal correctness by 9 percentage points without the recall collapse observed in time-filtered baselines, and reduces conflict rates by 55%. The compact nugget format reduces generator input length by 64% while enabling lightweight index structures suitable for browser-based and resource-constrained deployment. We release our implementation, datasets, and evaluation scripts
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。