Geometry-Adaptive Explainer for Faithful Dictionary-Based Interpretability under Distribution Shift
Researchers have developed a Geometry-Adaptive Explainer (GAE) to improve the faithfulness of dictionary-based interpretability methods when models encounter out-of-distribution data. The GAE addresses the misalignment caused by distribution shifts, which can rotate the active subspace of model activations and thus misalign explainer dictionaries. By realigning the dictionary with the OOD-active subspace using only unlabeled OOD data, GAE enhances causal faithfulness without requiring gradient updates, matching or exceeding existing training-based methods. AI
IMPACT Enhances the reliability of AI model explanations when encountering new, unseen data, crucial for safety and debugging.