Robust Interpretation of Historical Documents in Knowledge Graphs Through Query Inference and Execution

2026-07-27

AI Summary

This work addresses the susceptibility of large language models to noise and their limited verifiability when retrieving information from historical archives containing OCR and transcription errors. To tackle this challenge, the authors propose a semi-symbolic intelligent retrieval framework that integrates word-spotting techniques with knowledge graphs to generate and execute synthetic queries. This approach preserves the flexibility of large language models while enabling precise anchoring to original documents. Built upon a GraphRAG architecture, the system jointly performs post-OCR correction, query reasoning, and verifiable answer generation. Experimental results demonstrate that, compared to conventional RAG methods, the proposed framework significantly improves retrieval accuracy and result verifiability in real-world historical document settings, effectively mitigating hallucination issues.

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 As a contribution to historical document analysis, we compare traditional Retrieval-Augmented Generation (RAG) with an agentic GraphRAG architecture in their ability to deliver historical information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.

Problem

• historical documents
• knowledge graphs
• reliability
• OCR errors
• accountability

Innovation

• GraphRAG
• word spotting
• knowledge graph
• OCR correction
• agentic retrieval