MaNtLE: Model-agnostic Natural Language Explainer
It addresses the need for interpretable AI by providing natural language explanations for practitioners, though it is incremental as it builds on existing explanation methods.
The paper tackles the problem of explaining machine learning predictions by introducing MaNtLE, a model-agnostic natural language explainer that generates faithful explanations for structured classification tasks, achieving at least 11% higher faithfulness compared to LIME and Anchors in simulated studies.
Understanding the internal reasoning behind the predictions of machine learning systems is increasingly vital, given their rising adoption and acceptance. While previous approaches, such as LIME, generate algorithmic explanations by attributing importance to input features for individual examples, recent research indicates that practitioners prefer examining language explanations that explain sub-groups of examples. In this paper, we introduce MaNtLE, a model-agnostic natural language explainer that analyzes multiple classifier predictions and generates faithful natural language explanations of classifier rationale for structured classification tasks. MaNtLE uses multi-task training on thousands of synthetic classification tasks to generate faithful explanations. Simulated user studies indicate that, on average, MaNtLE-generated explanations are at least 11% more faithful compared to LIME and Anchors explanations across three tasks. Human evaluations demonstrate that users can better predict model behavior using explanations from MaNtLE compared to other techniques