Explainability 2 items

Everything Explainability

📑 arXiv 2d ago

Towards Rigorous Explainability by Feature Attribution

Advocates for rigorous symbolic XAI methods over non-symbolic approaches like SHAP and Shapley values, which provably lack rigor and can mislead in high-stakes decisions. The paper overviews symbolic methods for assigning relative feature importance that provide formal guarantees instead of heuristic explanations.

Interpretability Explainability Theory

📑 arXiv 3d ago

Agentic Explainability at Scale: Between Corporate Fears and XAI Needs

Examines explainability requirements for agentic AI in enterprise settings where low-code agent proliferation ("Agent Sprawl") outpaces governance capabilities. Proposes design-time and runtime explainability techniques from AI governance experts to address corporate concerns about autonomous agent decision-making and inter-agent communication.

Agents Safety Explainability Governance

Towards Rigorous Explainability by Feature Attribution ↗

Agentic Explainability at Scale: Between Corporate Fears and XAI Needs ↗

Towards Rigorous Explainability by Feature Attribution

Agentic Explainability at Scale: Between Corporate Fears and XAI Needs