arXiv:2601. 12913v4 Announce Type: replace Abstract: This paper argues that interpretability research in Artificial Intelligence (AI) is fundamentally ill-posed as existing definitions of interpretability fail to describe how interpretability can be formally tested or designed for.
arXiv:2606. 26523v1 Announce Type: new Abstract: We develop a framework for interpreting AI systems as agents, drawing on the philosophical tradition of radical interpretation and the tools of mechanistic interpretability.
arXiv:2606. 12289v1 Announce Type: cross Abstract: As Artificial Intelligence models grow in complexity, interpretability has become an indispensable tool for understanding, debugging, and controlling their computations.
arXiv:2606. 26228v1 Announce Type: cross Abstract: We review the concepts of interpretability and explainability as they apply to machine learning in physics.
The paper argues that explainable AI for computer vision has focused too much on developing interpretability methods rather than assessing how interpretable the models themselves are. It proposes a shift toward model-centric evaluation, using existing tools to compare what different models represent and compute, and emphasizes the need to measure whether humans can truly understand these models. The authors review the current toolbox, survey limited model comparison work, draw parallels to systems neuroscience, and outline a future agenda for model-focused XAI.
arXiv:2606. 11769v1 Announce Type: new Abstract: The European AI Act is the first comprehensive regulation of artificial intelligence (AI), setting out extensive obligations, particularly for so-called high-risk and general-purpose AI systems.
arXiv:2605. 27618v2 Announce Type: replace Abstract: Despite the wide use of explainability techniques to attempt to understand the behavior of Artificial Intelligence (AI), the generated explanations may not always be reliable.
The paper argues that as Large Language Models transition from chatbots to agentic systems, the current post-hoc interpretability paradigm is insufficient for safe deployment because it cannot audit or intervene before an output is produced. It proposes a shift to generative interpretability, where a model’s inference process inherently exposes semantically meaningful checkpoints that are human-understandable and can be causally intervened upon. The authors illustrate the advantages of this approach and introduce Neuro‑Symbolic Models as a concrete implementation.
arXiv:2608. 02238v1 Announce Type: cross Abstract: Ensuring trust in AI systems is essential for the safe and ethical integration of machine learning systems into high-stakes domains such as digital health.
arXiv:2607. 07229v1 Announce Type: new Abstract: Prior work has shown that chain-of-thought (CoT) reasoning is often unfaithful: a model's stated reasoning does not reliably reflect the process that produced its output.
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:2607. 21209v1 Announce Type: cross Abstract: In the field of Artificial Intelligence, an agent is a system which is able to autonomously make decisions in order to reach a desired goal.
The paper introduces TRACE, a Transparent Reasoning Architecture for Credible Execution, which provides an explainable AI-based decision framework for autonomous robots. TRACE structures decision-making into four auditable layers—Semantic Perception, Belief Reasoning, Action Synthesis, and Execution Verification—to ensure every action can be traced back to sensor evidence through documented causal chains. Experimental results on warehouse robot navigation show high evidence traceability (98.6%), temporal continuity (99.0%), and decision reconstructability (98.1%) across 500 simulated decision cycles.