让AI读懂文档版本更新，精准回答随时间变化的问题。
VersionRAG: Version-Aware Retrieval-Augmented Generation for Evolving Documents
- 构建分层图结构追踪文档版本演化路径与内容变更
- 在版本问答测试中准确率达90%，显著超越现有方法
- 适合需要处理持续更新的技术文档的场景
检索增强生成（RAG）系统在文档版本演进场景下表现不佳——这是技术文档的普遍特性。现有方法在敏感版本问题上仅达到58%-64%的准确率，因未能进行时间有效性校验而检索到语义相似但过时的内容。我们提出VersionRAG，一种显式建模文档演化的版本感知RAG框架，通过分层图结构捕捉版本序列、内容边界及状态间变更。检索时，根据查询意图引导至特定路径，实现精准的版本感知过滤与变更追踪。在自建的VersionQA基准测试（覆盖34份版本化技术文档的100个精标问题）中，VersionRAG达到90%准确率，远超朴素RAG（58%）和GraphRAG（64%）。在隐式变更检测任务中，其准确率达60%，而基线模型仅为0-10%，展现出对未记录修改的追踪能力。此外，VersionRAG索引阶段仅需GraphRAG 3%的令牌量，具备大规模部署可行性。本工作确立了版本化文档问答为独立任务，并提供了方法与基准供后续研究。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation (RAG) systems fail when documents evolve through versioning-a ubiquitous characteristic of technical documentation. Existing approaches achieve only 58-64% accuracy on version-sensitive questions, retrieving semantically similar content without temporal validity checks. We present VersionRAG, a version-aware RAG framework that explicitly models document evolution through a hierarchical graph structure capturing version sequences, content boundaries, and changes between document states. During retrieval, VersionRAG routes queries through specialized paths based on intent classification, enabling precise version-aware filtering and change tracking. On our VersionQA benchmark-100 manually curated questions across 34 versioned technical documents-VersionRAG achieves 90% accuracy, outperforming naive RAG (58%) and GraphRAG (64%). VersionRAG reaches 60% accuracy on implicit change detection where baselines fail (0-10%), demonstrating its ability to track undocumented modifications. Additionally, VersionRAG requires 97% fewer tokens during indexing than GraphRAG, making it practical for large-scale deployment. Our work establishes versioned document QA as a distinct task and provides both a solution and benchmark for future research.
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。