LLM INDEX / FIELD NOTES

A quieter place to explore language models.

Notes on model evaluation, open research, and the practical details of working with language.

RESEARCH METHODS

Start with the question, then choose a benchmark.

A useful evaluation begins with a clear task, a representative dataset, and a baseline that can be reproduced. Record limitations alongside results.

READING LIST

From papers to practice.

Explore open research at arXiv: Computation and Language and datasets at Hugging Face.