arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2512.04822cs.AI
收藏

实现道德AI:利用本体上下文进行合理化智能体决策的案例研究

Enabling Ethical AI: A case study in using Ontological Context for Justified Agentic AI Decisions

Kaiasm Ltd(Kaiasm有限公司);Avantra;The Alan Turing Institute(艾伦·图灵研究所)

Liam McGee, James Harvey, Lucy Cull, Andreas Vermeulen, Bart-Floris Visscher, Malvika Sharan

AI总结:

本文提出一种协作人机AI方法,通过本体上下文构建可检查语义层,提升智能体决策的合理性和透明度。

摘要:

在本文预印本中,我们提出了一种协作的人机AI方法,用于构建可检查的语义层。AI代理首先从多样化的数据源中提出候选知识结构;领域专家随后验证、纠正和扩展这些结构,其反馈用于改进后续模型。作者展示了这一过程如何捕捉隐性制度知识,提高响应质量和效率,并缓解制度性遗忘。我们主张从事后解释转向合理化的智能体AI,其中决策基于明确、可检查的证据和推理,使专家和非专业人士都能理解。

英文摘要:

In this preprint, we present A collaborative human-AI approach to building an inspectable semantic layer for Agentic AI. AI agents first propose candidate knowledge structures from diverse data sources; domain experts then validate, correct, and extend these structures, with their feedback used to improve subsequent models. Authors show how this process captures tacit institutional knowledge, improves response quality and efficiency, and mitigates institutional amnesia. We argue for a shift from post-hoc explanation to justifiable Agentic AI, where decisions are grounded in explicit, inspectable evidence and reasoning accessible to both experts and non-specialists.

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。

↑