# Improving Access to Historical Archives with Real-time RAG-based Systems Source: [Improving Access to Historical Archives with Real-time RAG-based Systems]() Collection index: [llms.txt]() Data updated: 2026-07-08T05:00:13.057Z Authors: Stergios Konstantinidis, Hayman Lotfy, Alexis Erne, Faruk Zahiragic, Min-Yen Kan, Michalis Vlachos Published: 2026-07-03T15:53:12.000Z ## Abstract Digitized historical archives are large, heterogeneous cultural heritage repositories, but access methods for such archives face challenges such as noisy optical character recognition (OCR) output and rigid keyword-based retrieval, which limit retrieval quality. In this work, we present an end-to-end archival processing and retrieval framework that integrates large language models (LLMs) into the archival pipeline. Our system introduces two core components: (i) an LLM-based OCR refinement module that improves text quality, and (ii) a semantic retrieval and cross-encoder reranking pipeline supporting natural-language question answering via retrieval-augmented generation (RAG). Our evaluations are done on a historical archival dataset of 500,000 Swiss newspaper segments spanning over three centuries (1762 to 2001). Experiments are conducted across 384 natural-language test queries. Our results highlight that LLM refinements reduce OCR errors by up to 44.52% (CER) and 60.95% (WER). More importantly, this is accompanied by downstream information retrieval improvements. Compared to traditional keyword baselines, our reranking pipeline increases NDCG@10 by 31.9% (from 65.99% to 87.05%) and achieves statistically significant gains in both answer correctness and context relevance. These results demonstrate that integrating LLMs with established document processing and retrieval pipelines can elevate digital libraries from static repositories to interactive, semantically searchable archival systems. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Retrieval-Augmented Generation on Historical Newspaper Archives 384 queries k=5](): Retrieval-Augmented Generation; Historical Newspaper Archives 384 queries k=5; Context Relevance: 86.72. - [Retrieval-Augmented Generation on Historical Newspaper Archives 384 queries k=10](): Retrieval-Augmented Generation; Historical Newspaper Archives 384 queries k=10; Context Relevance: 87.63. - [Retrieval-Augmented Generation on Historical Newspaper Archives 384 queries k=25](): Retrieval-Augmented Generation; Historical Newspaper Archives 384 queries k=25; Context Relevance: 87.17. ## Original sources and implementation [Original paper]() [PDF]()