A framework for redesigning RAG systems around historical methodology — preserving source sovereignty, interpretive transparency, and temporal sensitivity where standard architectures undermine them.
RAG systems are designed for factual question-answering — find the relevant passages, generate the answer. Historical scholarship demands something different: source criticism before interpretation, temporal sensitivity across decades of discourse, and transparent collaborative reasoning rather than seamless answers.
Query → retrieval → generation in one step. Source selection is a technical optimisation hidden from the researcher. Similarity-based ranking favours recent vocabulary. No built-in space for source criticism. Output presented as answers.
Two separated phases restore the historian's workflow: a Heuristik phase for source discovery and evaluation, followed by an Analyse phase for interpretation. The researcher curates what enters computational reading. Outputs are Zwischentexte (interpretive proposals, not conclusions).
Drawing on Agre's Critical Technical Practice, we embed disciplinary values into system architecture rather than accepting computational defaults as neutral.
Formally decouples corpus construction from interpretation. Researchers examine, critique, and curate retrieved sources before any computational "reading" begins, thus restoring the heuristic phase that standard RAG eliminates.
Enforces proportional retrieval across time periods. Left unchecked, similarity-based search embeds presentist bias, privileging sources whose vocabulary matches modern query terms while suppressing formative periods where concepts emerged.
Post-retrieval evaluation against researcher-defined criteria. Turns algorithmic selection from a black box into a transparent, argumentative process with scored justifications that can be reviewed and contested.
HistoRAG separates the RAG pipeline into distinct phases, each with explicit researcher control points. The architecture is transferable with specific implementations configuring chunking, embedding, and evaluation criteria as well as further features for unique use-cases.
HistoRAG generates what we term Zwischentexte (intermediate texts). These are not answers but interpretive proposals: they lie between retrieved sources and historical argument, offering first proposals for interpretation that the historian can verify, contest, and develop.
"The central question for LLMs in digital humanities is not whether machines can 'read' but how we design systems that make their interpretive interventions visible and contestable, thereby preserving the scholar's epistemic agency throughout."
Our first implementation of HistoRAG, applied to computerisation discourse in Der Spiegel (1950–1979). Tracking how West German society's understanding of automation evolved — from "Elektronenhirn" to "Computer" to "EDV," and from euphoria to anxiety.
Public anxiety about automation crystallised fourteen years before the canonical 1978 "Computer-Revolution" — surfaced through reader letters that keyword searches missed.
The same term carried opposed meanings depending on speaker position — efficiency for management, existential threat for workers — a pattern visible only at corpus scale.
Technological anxiety migrated upward through the class structure over time, becoming socially explosive only when it reached the discourse-producing classes.
HistoRAG is a transferable framework. Each instance configures the architecture for a specific corpus and research context.
Computerisation discourse in Der Spiegel. 102,189 articles, nomic-embed embeddings, ChromaDB vector store. Primary case study for the HistoRAG paper.
UN General Assembly General Speeches, 1946–2024. Semantic search across decades of diplomatic discourse with temporal windowing and Qwen3 embeddings. Primary use case for upcoming DH26 Workshop.
Cypherpunk mailing list archive. Email corpus with thread-aware retrieval, FastText semantic expansion, and ChromaDB vector store.
Access to live instances is currently restricted to the internal team for testing. If you are interested, please get in touch.
HistoRAG: Designing a Methodologically Informed Retrieval-Augmented Generation System for Historical Research — Demonstrated through a Case Study of Der Spiegel (1950–1979) and the Computerisation of the Early Federal Republic.
Noah J. Kim-Baumann & Torsten Hiltmann · 2026
Currently under review at the Journal for Digital History. Published as an executable notebook article (Jupyter).
Kim-Baumann, N. J. & Hiltmann, T. (2026). HistoRAG: Designing a Methodologically Informed Retrieval-Augmented Generation System for Historical Research — Demonstrated through a Case Study of Der Spiegel (1950–1979) and the Computerisation of the Early Federal Republic. [Venue TBD].