arXiv:2606. 10347v1 Announce Type: new Abstract: Machine learning is increasingly used in critical domains, where both predictions and their associated confidence levels influence important decisions.
The paper proposes an empirical pipeline to estimate the preferences that a large language model (LLM) implicitly optimizes by combining the model’s probability distribution over unknowns with its chosen action, and fitting a discrete choice model to recover the underlying cost function. This revealed-preference framework enables rigorous assessment of whether LLMs act consistently toward a goal, can articulate objectives that align with their decision policy, and can be steered by prompting to follow a user-specified cost function. Experiments across four medical diagnosis domains and various frontier and open-source models show that while many LLMs exhibit internal coherence, they still struggle to accurately report or adopt preferences when guided by users.
arXiv:2606. 18832v1 Announce Type: cross Abstract: Counterfactual explanations are widely used to provide algorithmic recourse in high-stakes decision-making systems.
Counterfactual explanations are widely used to provide algorithmic recourse in high-stakes decision-making systems. Most existing methods seek the smallest change to an input that flips a model's decision.
The paper proposes a framework for making machine‑learning based insurance premiums explainable in a way that is valid, actionable, and reliable. It introduces axioms for each property and develops a method that uses Conformal Prediction to filter out uncertain recommendations, ensuring that suggested changes to controllable characteristics are likely to lower premiums. Experiments on real Florida flood‑insurance claims and synthetic driver‑telematics data show that constrained recommendations are more reliable and predict larger risk reductions than unconstrained ones.
The paper introduces egRUE, an explainable uncertainty estimation method that merges uncertainty quantification with feature‑level explanations for medical AI predictions. egRUE incorporates prediction explanations into its uncertainty calculation and decomposes uncertainty into contributions from individual features. Experiments and a user study with medical experts show that egRUE improves reliability, interpretability, and calibrated trust compared to existing methods.
arXiv:2606. 18418v1 Announce Type: new Abstract: The increasing use of machine learning algorithms in social applications has raised concerns about fairness and transparency, leading to the development of counterfactual explanations.
arXiv:2603. 14894v3 Announce Type: replace-cross Abstract: Trust and ethical concerns due to the widespread deployment of opaque machine learning (ML) models motivating the need for reliable model explanations.
arXiv:2607. 02206v1 Announce Type: cross Abstract: Predictions are increasingly used to guide high-stakes decisions, from treatment selection to policy making.
arXiv:2610.14474v1 Announce Type: cross Abstract: Medication recommendations seek to deliver personalized drug combinations based on patients' clinical information, where ensuring transparent decisio...
arXiv:2602.02639v2 Announce Type: replace-cross Abstract: LLM self-explanations are often presented as a promising tool for AI oversight, yet their faithfulness to the model's true reasoning process...
arXiv:2607. 09502v1 Announce Type: cross Abstract: Explaining machine-learning models is increasingly important for decision-making and consumer trust, yet it is widely believed to come at a cost: existing Explainable AI (XAI) methods suffer from a persistent accuracy-explainability trade-off.