Prerequisites
Beginner-to-intermediate Python. A Google account for Colab. No prior deep learning or NLP experience required, though comfort with basic linear algebra and probability will help.
Preliminary notebooks →LLMs for Social Science
From embeddings
to agents.
Language models are reshaping how social scientists collect, annotate, and analyze text. This course builds the conceptual depth and hands-on skills to use them critically. Beginner Python required; everything else is taught from first principles.
Five weeks of material
What you will learn.
The course runs from how text becomes data to autonomous research agents. Each module builds on the last; start at Module 1.
Module 1 Module 2 Module 3 Module 4 Module 5
Foundations
From bag-of-words to embeddings and tokenization, then contextual representations, language modeling, the Transformer, scaling laws, and how this stack shows up in social science workflows. The conceptual spine for everything that follows.
Open module →From Models to Tools
Post-training alignment (SFT, RLHF, DPO), prompting from zero-shot to chain-of-thought, reasoning techniques, and how to evaluate models and choose one that fits your task.
Open module →Deploying for Research
Fine-tuning (including LoRA-style adaptation and encoder heads), moving from notebooks to APIs and self-hosted inference, and rigorous validation — so a classifier works as a measurement instrument you can defend in publication.
Open module →Extraction, Summarization, and RAG
Faithful extraction and summarization (hallucination, omission, and distortion), then retrieval-augmented generation: chunking, embeddings, retrieval, and grounded answers with provenance checks over your own corpora.
Open module →Agentic Workflows
Building autonomous research agents with tool use, ReAct patterns, and multi-step orchestration. The frontier of what language models can do for your research pipeline.
Open module →From the intensive
Advanced lectures.
Explore a topic in depth with a guest researcher. Guided notes and original slides connect each lecture to the foundations you have learned here.
LLM Agents and Evaluation
Tatiana Shavrina on human preference, scientific research agents, and what makes an evaluation credible.
Explore the lecture →Getting started
Open access. No registration required.
Materials
All exercises are open-source Jupyter notebooks. Clone the repository, open in Colab, and follow along at your own pace.
GitHub repository →Start here
Begin with Module 1: the mathematical and conceptual foundations that everything else builds on.
Begin Module 1 →Spring 2026
Three institutions across Europe.
The course was delivered in person at three institutions in spring 2026. All materials remain freely available online.
Oxford
23–27 March 2026
5-day intensive · DPIR, University of Oxford
ESSCA Paris
7 April 2026
1-day workshop
EUI Florence
20–21 April 2026
2-day workshop · European University Institute