Building Trustworthy AI by Addressing its 16+2 Desiderata with Goal-Directed Commonsense Reasoning

TL;DR

This paper introduces s(CASP), a goal-directed reasoning system that addresses key desiderata for trustworthy AI, providing explainability and reliability through commonsense reasoning, demonstrated via diverse applications.

Contribution

The paper presents s(CASP), a novel reasoning framework that supports 16+2 desiderata for trustworthy AI, bridging the gap between sub-symbolic and rule-based approaches.

Findings

s(CASP) effectively supports key trustworthiness desiderata.

Demonstrated applications include chatbot and embodied reasoner.

s(CASP) offers explainable and reliable reasoning capabilities.

Abstract

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.