用轻量推理框架实现可解释、可信的AI，解决大模型幻觉问题。
Building Trustworthy AI by Addressing its 16+2 Desiderata with Goal-Directed Commonsense Reasoning
- 采用目标导向的约束逻辑编程，模拟人类常识推理
- 支持16项可信AI标准及新增的矛盾检测与多世界假设能力
- 适用于对话机器人等需要透明决策的场景
当前人工智能的发展凸显了确保其可信性的迫切需求，涉及法律、伦理及商业层面。子符号机器学习算法（如大语言模型）虽能模拟推理，但存在幻觉且决策过程不可解释、难审计，影响可信性；而基于规则的推理系统（如Cyc）虽可提供推理链，却结构复杂、需大量规则。本文提出一种轻量级方案s(CASP)，即目标导向的约束答案集编程推理器，仅用少量机制即可模拟可靠、可解释的人类式常识推理。论文说明s(CASP)如何满足杜格·莱纳特与加里·马库斯（2023）提出的16项可信AI理想特性，并额外涵盖不一致检测与假设替代世界两项能力。通过多种应用实例，包括对话聊天机器人和虚拟具身推理器，验证了s(CASP)的可行性与协同效应。
原文摘要 · Abstract (English)
Current advances in AI and its applicability have highlighted the need to ensure its trustworthiness for legal, ethical, and even commercial reasons. Sub-symbolic machine learning algorithms, such as the LLMs, simulate reasoning but hallucinate and their decisions cannot be explained or audited (crucial aspects for trustworthiness). On the other hand, rule-based reasoners, such as Cyc, are able to provide the chain of reasoning steps but are complex and use a large number of reasoners. We propose a middle ground using s(CASP), a goal-directed constraint-based answer set programming reasoner that employs a small number of mechanisms to emulate reliable and explainable human-style commonsense reasoning. In this paper, we explain how s(CASP) supports the 16 desiderata for trustworthy AI introduced by Doug Lenat and Gary Marcus (2023), and two additional ones: inconsistency detection and the assumption of alternative worlds. To illustrate the feasibility and synergies of s(CASP), we present a range of diverse applications, including a conversational chatbot and a virtually embodied reasoner.
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。