Improving Compactness and Reducing Ambiguity of CFIRE Rule-Based Explanations
This work addresses transparency needs in sensitive domains by improving explanation clarity, though it is incremental as it builds on the existing CFIRE method.
The paper tackled the problem of ambiguity in CFIRE rule-based explanations for tabular data models by proposing a post-hoc pruning strategy, which reduced rule set size and ambiguity while maintaining predictive fidelity across multiple datasets.
Models trained on tabular data are widely used in sensitive domains, increasing the demand for explanation methods to meet transparency needs. CFIRE is a recent algorithm in this domain that constructs compact surrogate rule models from local explanations. While effective, CFIRE may assign rules associated with different classes to the same sample, introducing ambiguity. We investigate this ambiguity and propose a post-hoc pruning strategy that removes rules with low contribution or conflicting coverage, yielding smaller and less ambiguous models while preserving fidelity. Experiments across multiple datasets confirm these improvements with minimal impact on predictive performance.