超越事后解释：通过概率中介迈向玻璃箱AI
Beyond Post-hoc Explanation: Toward Glassbox AI via Probabilistic Mediation
AI总结：
针对大语言模型在关键领域的不透明性，提出玻璃箱框架，利用贝叶斯网络作为事前中介层，实现可审计推理、不确定性量化和可争议输出。
摘要：
大型语言模型正迅速成为高风险机构设置中的基础设施组件，包括公共管理、法律推理和医疗保健，在这些领域中，不透明性不仅不方便，而且在制度和法律上不可接受。现有的可解释性方法主要是事后性的，提供不稳定、不可争议的解释，这些解释与产生输出的推理过程没有正式关系。我们认为问题不在于缺乏解释，而在于首先缺乏结构化推理。本文提出了一种根本不同的架构，我们称之为玻璃箱框架，其中贝叶斯网络作为生成模型的透明事前中介层。贝叶斯网络在推理之前编码领域知识、因果假设和概率依赖性，从而实现可审计的推理轨迹、不确定性量化和可争议的输出。我们描述了该框架的架构，并将其置于一个福利资格场景中，确定了必须解决的基础性挑战，包括语义对齐、动态模型构建、概率基础以及人类治理，以便大规模实现它。通过从事后解释转向事前概率中介，本文勾勒出一条原则性路径，通往不仅强大而且根本上可问责的AI系统。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
