VersionRAG: Version-Aware Retrieval-Augmented Generation for Evolving Documents

2025-10-09

AI Summary

To address the limitation of conventional RAG systems in accurately answering version-sensitive queries over evolving technical documentation—primarily due to neglecting temporal validity of documents—this paper proposes the first version-aware RAG framework. Methodologically, it constructs a hierarchical version graph to model document evolution, employs a query-driven intent classifier for adaptive path selection, and integrates temporal-consistent retrieval with change-tracking mechanisms to detect both explicit and implicit modifications. A lightweight indexing strategy reduces indexing overhead by 97%. Evaluated on the VersionQA benchmark, the framework achieves 90% question-answering accuracy—significantly outperforming baselines—and attains 60% accuracy in implicit change detection (baseline ≈ 0%), enabling, for the first time, effective identification of undocumented semantic drift.

Technology Category

• Data Mining & Knowledge Management: Intelligent Query Processing
• Knowledge Representation and Reasoning: Action, Change, and Causality
• Natural Language Processing: Question Answering

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

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.

Problem

• Addresses RAG failure in versioned document evolution
• Solves temporal validity gaps in retrieval-augmented generation
• Enables version-aware filtering for evolving technical documentation

Innovation

• Models document evolution via hierarchical graph structure
• Routes queries through intent-based specialized paths
• Achieves high accuracy with reduced token requirements