The paper proposes treating leaf values of a gradient‑boosted ensemble as coordinates in ℝ^M, turning the model into a linear function over these coordinates. This perspective allows exact contrastive explanations: the difference between two instances is a vector that is zero wherever they share a leaf, so the gap is attributed to a few coordinates linked to specific tree splits. The authors build a recourse method based on this representation, achieving near‑perfect reconstruction of the model’s decision and demonstrating competitive performance on tabular datasets, especially when recommendations are limited to actionable changes.
arXiv:2608. 08126v1 Announce Type: new Abstract: Credit scoring increasingly relies on models whose decision logic cannot be read off their parameters, in tension with supervisory expectations that adverse decisions be explainable.
arXiv:2608. 15725v1 Announce Type: new Abstract: Predictive models in clinical and regulated settings must be accurate and fully auditable.
arXiv:2608.24582v1 Announce Type: cross Abstract: Credit risk models increasingly need to combine predictive accuracy with transparent explanations and auditable fairness constraints. Logistic regres...
arXiv:2602. 07453v2 Announce Type: replace Abstract: Decision tree ensembles are widely used in critical domains, making robustness and sensitivity analysis essential to their trustworthiness.
arXiv:2607. 27027v1 Announce Type: new Abstract: Gradient-boosted trees dominate tabular machine learning, yet canonical correlation analysis has always relied on linear or neural encoders.
Credit risk models increasingly need to combine predictive accuracy with transparent explanations and auditable fairness constraints. Logistic regression remains attractive because its coefficients ar...
arXiv:2609.39229v1 Announce Type: cross Abstract: Automatic evaluation of faithfulness increasingly relies on a large language model acting as a judge, yet the most reliable judges are proprietary fr...
arXiv:2607. 13874v1 Announce Type: new Abstract: Decision trees generate interpretable if--then rules, yet they contain irrelevant conditions (IRCs).
arXiv:2602. 22432v2 Announce Type: replace-cross Abstract: Gradient-boosted decision trees are among the strongest off-the-shelf predictors for tabular regression, but point predictions alone do not quantify uncertainty.
Decision trees generate interpretable if--then rules, yet they contain irrelevant conditions (IRCs). These IRCs arise from the structural mechanism of tree splitting and persist even in modern optimal sparse tree induction algorithms.
arXiv:2608. 14509v1 Announce Type: new Abstract: Systems that ask a language model to reach a conclusion from many sources usually concatenate them into one prompt.
The paper introduces a new consistency criterion for auditing decision systems that combines ensemble margin with local prediction variability to address predictive multiplicity, or the Rashomon effect. It shows that finite ensembles converge to the expected model’s consistency score as ensemble size and sample count grow, and demonstrates that ensembling models from the Rashomon set reduces unchecked incorrect predictions while keeping diversions moderate. Experiments on transformer and fine‑tuned language models for NLP and tabular classification confirm the method’s effectiveness and stronger alignment with existing multiplicity metrics.