floriancafiero/lrec2026-llm-as-annotator-tutorial

Materials for the LREC-COLING 2026 tutorial “Under-Resourced Studies of Under-Resourced Languages”: practical, reproducible LLM-as-annotator pipelines for low-resource languages, non-Latin scripts, and historical/OCR corpora, with notebooks, datasets, and ethical guidelines. # lrec2026: llm as annotator tutorial Materials for the LREC-COLING 2026 tutorial “Under-Resourced Studies of Under-Resourced Languages”: practical, reproducible LLM-as-annotator pipelines for low-resource languages, non-Latin scripts, and historical/OCR corpora, with notebooks, datasets, and ethical guidelines. ## Hands-on notebooks The practical sessions use five Colab-ready notebooks. They are designed to run in order and include a fallback mode without API keys. | # | Notebook | Open in Colab | |---|---|---| | 00 | Setup and data | Open in Colab | | 01 | Zero-shot and few-shot prompting | Open in Colab | | 02 | Structured outputs and validation | Open in Colab | | 03 | Evaluation and error analysis | Open in Colab | | 04 | Sampling and bootstrapping | Open in Colab | | Full | Full lesson | Open in Colab