Interpretable ML
ML: Machine Learning
Overview
Interpretable machine learning aims to make predictions understandable enough for people to inspect, challenge, and use, especially in high-stakes decisions and scientific discovery. Approaches include inherently transparent decision trees, rule sets, additive models, and symbolic formulas, as well as concept- and prototype-based models that connect predictions to human-readable ideas or examples. Other methods explain complex models after training with feature attributions, local surrogates, or analyses of internal representations, while newer work also builds in uncertainty, domain knowledge, and opportunities for human intervention. A central challenge is balancing predictive accuracy with explanations that are faithful, stable under changes in data, and meaningful to the people relying on them; evaluation increasingly tests these qualities rather than treating a plausible explanation as sufficient.
Latest papers
329 papers22 papers in the last four weeks, down 19% on the four weeks before. 0.2% of all new papers.