Datum: 23.09.2026 bis 24.09.2026
Ort: Leibniz-Institut für Europäische Geschichte (IEG) | Alte Universitätsstraße 19 | D - 55116 Mainz
Diese Veranstaltung wird organisiert durch das
Format:
Bring-your-own-data-Lab
Build Your Own HistoRAG
Source sovereignty and historical method when working with LLMs
Workshop led by:
Noah Kim-Baumann und Aurel Daugs
Aims and content:
Large language models are changing how researchers work with large source corpora, but the standard Retrieval-Augmented Generation (RAG) systems behind them are built for general-purpose, consumer-facing applications, often centred on factual question-answering. They treat similarity as relevance, obscure how sources are selected, flatten change over time, and present their output as answers rather than as something to be questioned. Those assumptions sit awkwardly with interpretive, source-critical scholarship.
This lab questions those processes and encourages a different kind of engagement. Building on HistoRAG, a framework that embeds historical method into the architecture itself, we treat RAG as a research process the scholar controls rather than a black box. Participants bring their own corpus, sent in advance, and over two days we build small HistoRAG-style applications around it and put them to work live. Together we open up the decisions that shape every result, from source selection and chunking to balancing sources across time, evaluating relevance, and interpretation, and we watch how each choice changes what the system returns. The goal is source-sovereign, source-critical work with LLMs that keeps interpretive control and epistemic agency with the researcher.
Prerequisites:
It is aimed at researchers across the humanities, cultural, and social sciences who work with their own large text corpora. It works from the view that the conveniences LLMs offer (natural-language access, seamless answers, agentic decision-making) quietly hide the decisions that constitute scholarship and outsource the researcher’s epistemic agency. Reclaiming that agency is what this lab is about. The two days combine short impulse talks, hands-on building, and one-to-one mentoring on your own data.
No programming experience is required, and corpora should be machine-readable.
The lab is held in English and limited to 15 participants.
Contact and Registration:
Dr Judit Garzón Rodríguez
hermes@ieg-mainz.de
Please provide the following information when registering:
• Your area of expertise
• What experience do you have with Retrieval-Augmented Generation (RAG) systems?
• What kind of data are you bringing with you?
Registration deadline: 13 September 2026
Vorläufiges Programm
Tag 1:
10:00 Registration
10:30 Welcome, introductions, getting to know each other
11:15 Coffee break
11:30 Impulse 1: RAG fundamentals
11:50 Discussion: the affordance dilemma of AI tools
12:30 Lunch
13:30 Meet your dataset: first exploration
14:00 Impulse 2: retrieval, generation and temporal windowing
14:30 Hands-on: retrieval and temporal windowing
15:00 Coffee break
15:15 Impulse 3: evaluation and pitfalls
15:45 Hands-on: evaluation and curating your corpus
16:45 Closing
18:00 Workshop dinner (at own expense)
Tag 2:
9:30 Welcome
9:45 Impulse 1: interpretation and “Zwischentexte”
10:15 Hands-on: analysis and citations
11:15 Coffee break
11:30 Impulse 2: critical reading and tool criticism
12:00 Hands-on and mentoring
13:00 Lunch
14:00 Plenary: findings and limits
15:30 Local implementation and hosting
16:30 Closing remarks