Saved in:
Bibliographic Details
Main Authors: Wang, Xiting, Jiang, Liming, Hernandez-Orallo, Jose, Stillwell, David, Sun, Luning, Luo, Fang, Xie, Xing
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2310.16379
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909056580452352
author Wang, Xiting
Jiang, Liming
Hernandez-Orallo, Jose
Stillwell, David
Sun, Luning
Luo, Fang
Xie, Xing
author_facet Wang, Xiting
Jiang, Liming
Hernandez-Orallo, Jose
Stillwell, David
Sun, Luning
Luo, Fang
Xie, Xing
contents Comprehensive and accurate evaluation of general-purpose AI systems such as large language models allows for effective mitigation of their risks and deepened understanding of their capabilities. Current evaluation methodology, mostly based on benchmarks of specific tasks, falls short of adequately assessing these versatile AI systems, as present techniques lack a scientific foundation for predicting their performance on unforeseen tasks and explaining their varying performance on specific task items or user inputs. Moreover, existing benchmarks of specific tasks raise growing concerns about their reliability and validity. To tackle these challenges, we suggest transitioning from task-oriented evaluation to construct-oriented evaluation. Psychometrics, the science of psychological measurement, provides a rigorous methodology for identifying and measuring the latent constructs that underlie performance across multiple tasks. We discuss its merits, warn against potential pitfalls, and propose a framework to put it into practice. Finally, we explore future opportunities of integrating psychometrics with the evaluation of general-purpose AI systems.
format Preprint
id arxiv_https___arxiv_org_abs_2310_16379
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Evaluating General-Purpose AI with Psychometrics
Wang, Xiting
Jiang, Liming
Hernandez-Orallo, Jose
Stillwell, David
Sun, Luning
Luo, Fang
Xie, Xing
Artificial Intelligence
Computers and Society
Comprehensive and accurate evaluation of general-purpose AI systems such as large language models allows for effective mitigation of their risks and deepened understanding of their capabilities. Current evaluation methodology, mostly based on benchmarks of specific tasks, falls short of adequately assessing these versatile AI systems, as present techniques lack a scientific foundation for predicting their performance on unforeseen tasks and explaining their varying performance on specific task items or user inputs. Moreover, existing benchmarks of specific tasks raise growing concerns about their reliability and validity. To tackle these challenges, we suggest transitioning from task-oriented evaluation to construct-oriented evaluation. Psychometrics, the science of psychological measurement, provides a rigorous methodology for identifying and measuring the latent constructs that underlie performance across multiple tasks. We discuss its merits, warn against potential pitfalls, and propose a framework to put it into practice. Finally, we explore future opportunities of integrating psychometrics with the evaluation of general-purpose AI systems.
title Evaluating General-Purpose AI with Psychometrics
topic Artificial Intelligence
Computers and Society
url https://arxiv.org/abs/2310.16379