arXiv:2607. 16652v1 Announce Type: cross Abstract: This position paper argues that claims about explanation stability are scientifically invalid without cross method validation.
arXiv:2609.06173v1 Announce Type: new Abstract: Post-deployment drift poses a critical risk to algorithmic accountability, particularly when ground truth labels are delayed and performance degradatio...
arXiv:2603. 25251v2 Announce Type: replace-cross Abstract: Explainable AI (XAI) methods are commonly evaluated using functional correctness metrics, sometimes termed faithfulness or fidelity, which estimate how closely an explanation reflects the model's reasoning.
arXiv:2608. 19807v1 Announce Type: new Abstract: Vision-language models (VLMs) can estimate physical quantities such as duration, speed, and acceleration from visual observations, but existing benchmarks primarily assess overall model performance against annotated ground truth.
The paper introduces a formal auditing framework to evaluate the robustness and fidelity of post‑hoc explainers such as SHAP and LIME. It defines a Trust Score that combines how stable an explanation is under small input perturbations with how well the highlighted features actually influence the model’s prediction. Experiments on a Madagascar malnutrition dataset show that even highly accurate models can produce unreliable explanations, and that fidelity scores degrade when models overfit.
arXiv:2607. 29614v1 Announce Type: cross Abstract: The rapid adoption of deep learning models in high-risk domains has intensified the need for trustworthy Explainable Artificial Intelligence (XAI).
The paper evaluates uncertainty estimation (UE) methods for clinical vision‑language models (VLMs) on visual question answering (VQA). Across 8 UE techniques and 12 VLMs, UE quality tracks model accuracy, degrading where performance is weakest, and fails to signal uncertainty when models are stressed by hiding the correct answer (NOTA perturbations). However, UE on unperturbed inputs reliably predicts which predictions will collapse under NOTA, suggesting UE can diagnose model fragility.
arXiv:2503. 13445v3 Announce Type: replace-cross Abstract: When asked to explain their decisions, LLMs can often give explanations which sound plausible to humans.
The paper argues that prediction‑based certifications—such as accuracy, calibration, and conformal coverage—are insufficient to guarantee trustworthy AI. It proves a separation theorem showing that a model can appear reliable under all prediction‑side certificates yet differ arbitrarily in explanation fidelity and deployment behaviour. The authors propose a competence envelope framework that combines both prediction and explanation certification to detect such hidden failures.
arXiv:2608. 02665v1 Announce Type: cross Abstract: A benchmark score is a measurement instrument, yet most benchmarks read each item at a single canonical surface form.
The paper investigates whether giving AI monitors access to the final answer improves their ability to verify reasoning. Using 237 step‑by‑step solutions to physics exam questions, the authors found that answer access mainly helps monitors detect inconsistencies with the final answer rather than independently checking the reasoning. Certification of the answer increased overall accuracy and error localization but reduced the ability to flag critical traces where the answer was correct but the reasoning was flawed.
arXiv:2607. 23804v1 Announce Type: cross Abstract: Context attribution methods for large language models (LLMs) identify which input context contributes to the model response.
arXiv:2608.23313v1 Announce Type: new Abstract: Vision-language model safety benchmarks typically evaluate only final responses: whether a model refuses, warns, or complies. This outcome-level view c...