Beyond Post-hoc Explanation: Toward Glassbox AI via Probabilistic Mediation

• URL: http://arxiv.org/abs/2606.07113v1
• Date: Fri, 05 Jun 2026 10:08:56 GMT
• Title: Beyond Post-hoc Explanation: Toward Glassbox AI via Probabilistic Mediation
• Abstract summary: We argue that the problem is not the absence of explanation but the absence of structured reasoning in the first place.<n>This paper makes the case for the Glassbox Framework, in which Bayesian networks serve as transparent, ante-hoc mediation layers for generative models.
• Score: 0.7614628596146601
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models are rapidly becoming infrastructural components in high-stakes institutional settings, including public administration, legal reasoning, and healthcare, where opacity is not merely inconvenient but institutionally and legally untenable. Existing approaches to explainability are predominantly post-hoc, offering unstable, non-contestable accounts that have no formal relationship to the reasoning process that produced the output. We argue that the problem is not the absence of explanation but the absence of structured reasoning in the first place. This paper makes the case for a fundamentally different architecture, which we call the Glassbox Framework, in which Bayesian networks serve as transparent, ante-hoc mediation layers for generative models. Bayesian networks encode domain knowledge, causal assumptions, and probabilistic dependencies before inference occurs, enabling auditable reasoning traces, uncertainty quantification, and contestable outputs. We characterise the architecture of this framework and ground it in a benefit eligibility scenario, identifying the foundational challenges spanning semantic alignment, dynamic model construction, probabilistic grounding, and human governance that must be solved to realise it at scale. By shifting from post-hoc explanation to ante-hoc probabilistic mediation, this work outlines a principled path toward AI systems that are not only powerful but fundamentally accountable.

Related papers

• Interpreting Object-Dependent Concept Brittleness in Text-to-Image Diffusion Models [105.53190946111586]
  We term this phenomenon object-dependent concept brittleness.<n>We present an interpretability-oriented framework to audit and minimally correct these failures.<n>We evaluate the proposed framework on style and attribute failure cases across multiple diffusion backbones.
  arXiv  Detail & Related papers  (2026-09-09T09:07:40Z)
• Provably Secure Agent Guardrail [89.79561918065122]
  Existing defense architectures rely on empirical semantic guardrails and probabilistic large model adjudicators.<n>This paper proposes a new security paradigm for agents based on the fundamental limitations of logical reasoning.
  arXiv  Detail & Related papers  (2026-05-28T02:12:41Z)
• Trustworthy AI Suffers from Invariance Conflicts and Causality is The Solution [80.98492754957466]
  Core trustworthy AI objectives, such as fairness, robustness, privacy, and explainability, are hard to achieve simultaneously.<n>This paper argues that causality is necessary to understand and balance trade-offs in performance and multiple objectives of trustworthy AI.
  arXiv  Detail & Related papers  (2026-05-04T14:26:28Z)
• A Survey of Reasoning in Autonomous Driving Systems: Open Challenges and Emerging Paradigms [49.66022971508878]
  We argue that reasoning should be elevated from a modular component to the system's cognitive core.<n>We derive and systematize seven core reasoning challenges, such as the responsiveness-reasoning trade-off and social-game reasoning.<n>We identify a fundamental and unresolved tension between the high-latency, deliberative nature of LLM-based reasoning and the millisecond-scale, safety-critical demands of vehicle control.
  arXiv  Detail & Related papers  (2026-03-11T07:40:53Z)
• Semantic Laundering in AI Agent Architectures: Why Tool Boundaries Do Not Confer Epistemic Warrant [0.0]
  We show that semantic laundering constitutes an architectural realization of the Gettier problem.<n>Unlike classical Gettier cases, this effect is not accidental; it is architecturally determined and systematically reproducible.<n>We introduce the Warrant Erosion Principle as the fundamental explanation for this effect and show that scaling, model improvement, and LLM-as-judge schemes are structurally incapable of eliminating a problem that exists at the type level.
  arXiv  Detail & Related papers  (2026-01-13T08:45:17Z)
• Non-Resolution Reasoning (NRR): A Computational Framework for Contextual Identity and Ambiguity Preservation [0.0]
  Current artificial intelligence systems exhibit a fundamental architectural limitation: they resolve ambiguity prematurely.<n>This premature semantic collapse stems from classical identity assumptions embedded in standard neural architectures.<n>We propose Non-Resolution Reasoning (NRR), a computational framework that treats ambiguity retention as a valid reasoning mode.
  arXiv  Detail & Related papers  (2025-12-15T16:14:32Z)
• All You Need for Counterfactual Explainability Is Principled and Reliable Estimate of Aleatoric and Epistemic Uncertainty [27.344785490275864]
  We argue that transparency research overlooks many foundational concepts of artificial intelligence.<n>Inherently transparent models can benefit from human-centred explanatory insights.<n>At a higher level, integrating artificial intelligence fundamentals into transparency research promises to yield more reliable, robust and understandable predictive models.
  arXiv  Detail & Related papers  (2025-02-24T09:38:31Z)
• Hierarchical Invariance for Robust and Interpretable Vision Tasks at Larger Scales [54.78115855552886]
  We show how to construct over-complete invariants with a Convolutional Neural Networks (CNN)-like hierarchical architecture. With the over-completeness, discriminative features w.r.t. the task can be adaptively formed in a Neural Architecture Search (NAS)-like manner. For robust and interpretable vision tasks at larger scales, hierarchical invariant representation can be considered as an effective alternative to traditional CNN and invariants.
  arXiv  Detail & Related papers  (2024-02-23T16:50:07Z)
• Advancing Counterfactual Inference through Nonlinear Quantile Regression [77.28323341329461]
  We propose a framework for efficient and effective counterfactual inference implemented with neural networks. The proposed approach enhances the capacity to generalize estimated counterfactual outcomes to unseen data. Empirical results conducted on multiple datasets offer compelling support for our theoretical assertions.
  arXiv  Detail & Related papers  (2023-06-09T08:30:51Z)
• (Un)reasonable Allure of Ante-hoc Interpretability for High-stakes Domains: Transparency Is Necessary but Insufficient for Comprehensibility [25.542848590851758]
  Ante-hoc interpretability has become the holy grail of explainable artificial intelligence for high-stakes domains such as healthcare. It can refer to predictive models whose structure adheres to domain-specific constraints, or ones that are inherently transparent. We unpack this concept to better understand what is needed for its safe adoption across high-stakes domains.
  arXiv  Detail & Related papers  (2023-06-04T09:34:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.