# Conversational Retrieval and On-the-Fly Knowledge Modeling of Historical Penitentiary Repression Records

arXiv: https://arxiv.org/abs/2607.08459 · HTML: https://mlsanity.com/paper/2607.08459/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation.
- Builds on 9 of its 24 references that are in the map.
- First posted on arXiv 9 Jul 2026.

## Placed in

- Retrieval-augmented generation / [RAG pipeline design and evaluation](https://mlsanity.com/rag/rag-pipeline-design-and-evaluation/)

## Builds on (most cited first, 9 of 9)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [Ragas: Automated Evaluation of Retrieval Augmented Generation](https://mlsanity.com/paper/2309.15217/) (2023)
- [TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models](https://mlsanity.com/paper/2109.10282/) (2021)
- [Evaluation of Retrieval-Augmented Generation: A Survey](https://mlsanity.com/paper/2405.07437/) (2024)
- [Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation](https://mlsanity.com/paper/2401.17904/) (2024)
- [Calamari - A High-Performance Tensorflow-based Deep Learning Package for Optical Character Recognition](https://mlsanity.com/paper/1807.02004/) (2018)
- [Historical Document Processing: Historical Document Processing: A Survey of Techniques, Tools, and Trends](https://mlsanity.com/paper/2002.06300/) (2020)

## Abstract (arXiv)

Recent developments in digital libraries increasingly favor conversational and natural language access to information through Retrieval-Augmented Generation (RAG). Although these approaches are effective for extractive tasks grounded in individual records, they remain limited in their ability to interpret document collections holistically and to incorporate expert knowledge dynamically. In this article, we present a document analysis system designed for the management of historical digital libraries that supports on-the-fly knowledge modeling. The system is equipped with the capability to store facts produced either by expert archivists or derived from document retrieval processes within a graph-based structure. Through continuous professional interaction, the system can retrieve information not only from primary sources such as documents, but also from previously modeled knowledge, with the graph-based index acting as a memory for the language model to access. This enables increasingly complex queries involving long-term dependencies across documents, link discovery, and the integration of expert knowledge that may not be explicitly present in the original sources. As a result, the proposed approach facilitates the generation of richer and more comprehensive information.