Course
LLMs for Social Science
Language models are reshaping how social scientists collect, annotate, and analyze text. But treating them as black-box APIs leaves enormous potential on the table, and introduces risks you cannot diagnose without understanding what happens inside.
This course takes you from the mathematical foundations of word embeddings and transformers through to building autonomous research agents, giving you the conceptual depth and hands-on skills to use LLMs critically and creatively in your own work.
What You Will Learn
Module 1
Foundations: From Embeddings to Transformers
How machines represent meaning as geometry, and how the Transformer architecture learns to attend, predict, and scale. The conceptual bedrock everything else builds on.
Module 2
From Models to Tools
Post-training alignment (SFT, RLHF, DPO), prompting strategies from zero-shot to chain-of-thought, and how to evaluate and choose between models for your research questions.
Module 3
Deploying for Research
Fine-tuning with LoRA, serving models with vLLM and APIs, and building rigorous text classification pipelines with proper validation.
Module 4
Social Science Applications
Information extraction and RAG pipelines for working with large corpora, plus using LLMs as simulated agents to study human behavior, and when to trust the results.
Module 5
Agentic Workflows
Building autonomous research agents with tool use, ReAct patterns, and multi-step orchestration: the frontier of what LLMs can do for your research pipeline.
Prerequisites
Beginner-to-intermediate Python. A Google account for Colab. No prior deep learning or NLP experience required; we build from fundamentals.
Preliminary notebooks →Materials
All exercises are open-source Jupyter notebooks. Clone the repo, open in Colab, and follow along.
GitHub Repository →Begin the Course
Start with Module 1: the mathematical and conceptual foundations that everything else builds on.
Begin →2026 Dates & Locations
Oxford
March 23–27, 2026
5-day intensive. DPIR, University of Oxford.
ESSCA Paris
April 7, 2026
1-day workshop.
EUI Florence
April 20–21, 2026
2-day workshop. European University Institute.