La Trobe
- No file added yet -

A Reasoning and Value Alignment Test to Assess Advanced GPT Reasoning

Download (3.25 MB)
journal contribution
posted on 2024-09-01, 23:53 authored by Timothy McIntoshTimothy McIntosh, Tong Liu, Teo Susnjak, Paul WattersPaul Watters, Malka N Halgamuge
In response to diverse perspectives on artificial general intelligence (AGI), ranging from potential safety and ethical concerns to more extreme views about the threats it poses to humanity, this research presents a generic method to gauge the reasoning capabilities of artificial intelligence (AI) models as a foundational step in evaluating safety measures. Recognizing that AI reasoning measures cannot be wholly automated, due to factors such as cultural complexity, we conducted an extensive examination of five commercial generative pre-trained transformers (GPTs), focusing on their comprehension and interpretation of culturally intricate contexts. Utilizing our novel “Reasoning and Value Alignment Test,” we assessed the GPT models’ ability to reason in complex situations and grasp local cultural subtleties. Our findings have indicated that, although the models have exhibited high levels of human-like reasoning, significant limitations remained, especially concerning the interpretation of cultural contexts. This article also explored potential applications and use-cases of our Test, underlining its significance in AI training, ethics compliance, sensitivity auditing, and AI-driven cultural consultation. We concluded by emphasizing its broader implications in the AGI domain, highlighting the necessity for interdisciplinary approaches, wider accessibility to various GPT models, and a profound understanding of the interplay between GPT reasoning and cultural sensitivity.

History

Publication Date

2024-09-01

Journal

ACM Transactions on Interactive Intelligent Systems

Volume

14

Issue

3

Article Number

17

Pagination

37p.

Publisher

Association for Computing Machinery (ACM)

ISSN

2160-6455

Rights Statement

© 2024 Copyright held by the owner/author(s). This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike International 4.0 License.