Linguistic Data Analysis II
Applying Large Language Models for Linguistic Analysis
Welcome
Linguistic Data Analysis II is a five-day intensive master-level graduate course on critically evaluating Large Language Models (LLMs) for linguistic analysis, offered at the Graduate School of International Cultural Studies, Tohoku University, in Summer 2026.
Among broad applications of LLMs, we cover topics that allows one to empirically evaluate LLMs performance on tasks at hand. To this end, we explore annotation scheme design, gold-standard dataset construction, prompt design/tuning, and evaluation.
Given the intensive nature of the 5-day course, we focus on the core concepts, methodology, and hands-on applications, instead of helping you to fully develop your own research agenda in this domain. However, the course aims to equip the students to explore further issues in LLM through applied linguistics lens, and plan and execute research studies of their own if they are interested.
- 📋 Course info — syllabus, grading, policies, and required materials (ready)
- 📚 Readings — assigned readings by day (ready)
- 🛠️ Setup guides — get Google Colab and your Gemini API key ready before Day 1 (ready)
- 📅 Sessions — the daily schedule and per-session pages (being finalized)
- 🎓 Final Project — the group mini-research project (being finalized)
- 🛠️ Resources — corpora, datasets, and notebooks (being finalized)