Published inTDS ArchiveThe Art of Prompt Design: Prompt Boundaries and Token HealingLearn how standard greedy tokenization introduces a subtle and powerful bias that can have all kinds of unintended consequences.May 8, 20234May 8, 20234
Published inTDS ArchiveThe Art of Prompt Design: Use Clear SyntaxExplore how clear syntax can enable you to communicate intent to language models, and also help ensure that outputs are easy to parseMay 2, 20236May 2, 20236
Published inTDS ArchiveBe Careful When Interpreting Predictive Models in Search of Causal InsightsA careful exploration of the pitfalls of trying to extract causal insights from modern predictive machine learning models.May 17, 202122May 17, 202122
Published inTDS ArchiveExplaining Measures of FairnessAvoid the black-box use of fairness metrics in machine learning by applying modern explainable AI methods to measures of fairness.Mar 2, 20204Mar 2, 20204
Published inTDS ArchiveInterpretable Machine Learning with XGBoostThis is a story about the danger of interpreting your machine learning model incorrectly, and the value of interpreting it correctly…Apr 17, 201849Apr 17, 201849
