Robust Interpretation of Historical Documents in Knowledge Graphs Through Query Inference and Execution
2026-07-27 • Information Retrieval
Information RetrievalDigital Libraries
AI summaryⓘ
The authors explore how to use large language models (LLMs) to access historical documents reliably without losing accuracy. They compare a traditional approach called Retrieval-Augmented Generation (RAG) with their new method, GraphRAG, which uses a knowledge graph and word-spotting to handle errors from old document scans. Their system combines text correction and smart search queries to improve finding accurate information despite OCR mistakes. This helps keep the information trustworthy while still using the flexibility of LLMs.
Large Language ModelsRetrieval-Augmented GenerationGraphRAGOCR errorsknowledge graphword spottinghistorical document analysiscode generationinformation retrieval
Authors
Sebastià Nicolau, Adrià Molina, Oriol Ramos Terrades, Josep Lladós
Abstract
The emergence of Large Language Models (LLMs) has redefined how users interact with information in digital environments. However, their widespread and often indiscriminate integration has raised significant concerns regarding reliability and trustworthiness issues that are particularly critical when accessing digital libraries and historical archives. How can one leverage the generalization capacity of an LLM without losing the level of accountability required for an archival institution? In this paper, we present an agentic retrieval system designed to deliver more accurate and verifiable access to historical data while preserving much of the flexibility associated with unconstrained LLMs. As a contribution to historical document analysis, we compare traditional Retrieval-Augmented Generation (RAG) with an agentic GraphRAG architecture in their ability to deliver historical information under realistic conditions, including the presence of OCR and transcription errors. We introduce a semi-symbolic framework that integrates word-spotting techniques for post-OCR correction with a knowledge graph representation that enables the agent to access information through synthesized queries. The interleaved collaboration between word spotting and code generation allows the agent to construct strong retrieval queries that are robust to misinterpretation and hallucination, while still leveraging approximate search when noise and uncertainty, common in historical document analysis, would otherwise hinder precise retrieval.