arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2312.09928cs.AI
收藏

神经符号价值启发式AI(为何、是什么与如何实现)

Neurosymbolic Value-Inspired AI (Why, What, and How)

University of South Carolina(南卡罗来纳大学)

Amit Sheth, Kaushik Roy

AI总结:

为使大语言模型系统契合人类价值观并适配高风险场景,本文扩展卡尼曼双系统框架,提出名为VAI的神经符号计算框架以整合多维度人类价值观,并梳理进展、展望未来方向。

摘要:

大语言模型(LLMs)的出现推动了人工智能(AI)系统的快速发展,使其得以在各行各业广泛应用,为人类提供辅助。这一趋势引发了广泛讨论,核心议题是:基于LLM的AI系统愈发需要融入人类社会、与人类共处并共享人类价值观,尤其是当这些系统被部署在医疗、自动驾驶等高风险场景中时。为实现这一目标,神经符号AI系统颇具吸引力,因为它们能够借助对共享价值观的显式表征,打造易于理解、可解释的交互界面,以支持基于价值观的决策。本文对卡尼曼的系统一/系统二框架进行了大幅扩展,提出了名为Value-Inspired AI(VAI,价值启发式AI)的神经符号计算框架,该框架明确了稳健且实用地落地VAI系统所需的核心组件,旨在表征并整合人类价值观的多个维度。最后,本文进一步梳理了该方向的现有研究进展,并展望了该领域未来的潜在发展方向。

英文摘要:

The rapid progression of Artificial Intelligence (AI) systems, facilitated by the advent of Large Language Models (LLMs), has resulted in their widespread application to provide human assistance across diverse industries. This trend has sparked significant discourse centered around the ever-increasing need for LLM-based AI systems to function among humans as part of human society, sharing human values, especially as these systems are deployed in high-stakes settings (e.g., healthcare, autonomous driving, etc.). Towards this end, neurosymbolic AI systems are attractive due to their potential to enable easy-to-understand and interpretable interfaces for facilitating value-based decision-making, by leveraging explicit representations of shared values. In this paper, we introduce substantial extensions to Khaneman's System one/two framework and propose a neurosymbolic computational framework called Value-Inspired AI (VAI). It outlines the crucial components essential for the robust and practical implementation of VAI systems, aiming to represent and integrate various dimensions of human values. Finally, we further offer insights into the current progress made in this direction and outline potential future directions for the field.

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。

↑