Explore how clear syntax can enable you to communicate intent to language models, and also help ensure that outputs are easy to parse — This is the first installment of a series on how to use guidance to control large language models (LLMs), written jointly with Marco Tulio Ribeiro. We’ll start from the basics and work our way up to more advanced topics. In this post, we’ll show that having clear syntax enables you…

A careful exploration of the pitfalls of trying to extract causal insights from modern predictive machine learning models. — A joint article about causality and interpretable machine learning with Eleanor Dillon, Jacob LaRiviere, Jonathan Roth, and Vasilis Syrgkanis from Microsoft. Predictive machine learning models like XGBoost become even more powerful when paired with interpretability tools like SHAP. These tools identify the most informative relationships between the input features and…

Avoid the black-box use of fairness metrics in machine learning by applying modern explainable AI methods to measures of fairness. — This hands-on article connects explainable AI with fairness measures and shows how modern explainability methods can enhance the usefulness of quantitative fairness metrics. By using SHAP (a popular explainable AI tool) we can decompose measures of fairness and allocate responsibility for any observed disparity among each of the model’s input…

This is a story about the danger of interpreting your machine learning model incorrectly, and the value of interpreting it correctly. …