LARAG: Link-Aware Retrieval Strategy for RAG Systems in Hyperlinked Technical Documentation

2026-05-08

AI Summary

Standard RAG systems disregard the inherent hyperlink structure of technical documentation, leading to retrieval results misaligned with users’ navigational intent. This work proposes a lightweight, link-aware retrieval strategy that incorporates HTML hyperlink relationships as metadata into text chunk representations, enabling implicit graph-structured local relevance without explicitly constructing a graph. By jointly leveraging embedding-based retrieval and hyperlink topology, the method achieves substantially improved answer faithfulness and efficiency on Rulex platform documentation, requiring fewer retrieved chunks and generated tokens while attaining the highest BERTScore F1 value.

Abstract

Retrieval-Augmented Generation (RAG) enhances the factual grounding of Large Language Models by conditioning their outputs on external documents. However, standard embedding-based retrievers treat naturally structured corpora, such as technical manuals, as flat collections of passages, thereby overlooking the hyperlink topology that users rely on when navigating such content. We introduce LARAG (Link-Aware RAG): a lightweight, link-aware retrieval strategy that leverages the author-defined hyperlink structure already present in HTML documentation, encoding hyperlink relations as metadata in the chunk representations and exploiting them to perform a form of graph-like retrieval of locally relevant content. In a benchmark of twenty expert-designed queries over Rulex Platform technical documentation and four prompting strategies, LARAG consistently improves answer quality, achieving the highest BERTScore F1, while retrieving fewer chunks and generating fewer tokens than a baseline RAG architecture used for comparison. These results show that directly leveraging the existing hyperlink topology of technical documentation, even without explicit graph construction or inference, enables an implicit form of graph-like retrieval that yields a more faithful and efficient RAG pipeline, providing better grounding at lower cost.

Problem

• Retrieval-Augmented Generation
• hyperlinked documentation
• link-aware retrieval
• technical manuals
• document topology

Innovation

• Link-Aware Retrieval
• Retrieval-Augmented Generation
• Hyperlinked Documentation
• Graph-like Retrieval
• Technical Documentation