用可组合模块构建透明可控的交互式AI系统
Composable Building Blocks for Controllable and Transparent Interactive AI Systems
- 将交互系统拆解为可解释的结构化模块
- 通过可视化组件实现系统流程与API的显式呈现
- 适合需要可解释性的AI系统设计者与协作团队
随着AI技术在交互系统中的深度集成，系统能解决的任务数量持续增加，但其整体仍面临黑箱问题。尽管可解释AI（XAI）技术可通过事后分析或采用内在可解释模型提升单个AI模块的透明度，系统级架构依然不透明。为此，我们提出将交互系统表示为一系列结构化模块的序列，如文献中已有的AI模型和控制机制。这些模块可通过配套的可视化组件（如XAI技术）进行解释，模块间的流程与API形成系统的显式概览。这为人类与自动化代理（如大语言模型）提供了统一的沟通基础，实现人机对齐的可解释性。本文讨论了若干模块选择，并在架构层面实现了基于流程的系统原型。
原文摘要 · Abstract (English)
While the increased integration of AI technologies into interactive systems enables them to solve an equally increasing number of tasks, the black box problem of AI models continues to spread throughout the interactive system as a whole. Explainable AI (XAI) techniques can make AI models more accessible by employing post-hoc methods or transitioning to inherently interpretable models. While this makes individual AI models clearer, the overarching system architecture remains opaque. To this end, we propose an approach to represent interactive systems as sequences of structural building blocks, such as AI models and control mechanisms grounded in the literature. These can then be explained through accompanying visual building blocks, such as XAI techniques. The flow and APIs of the structural building blocks form an explicit overview of the system. This serves as a communication basis for both humans and automated agents like LLMs, aligning human and machine interpretability of AI models. We discuss a selection of building blocks and concretize our flow-based approach in an architecture and accompanying prototype interactive system.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。