2023/10/17 by David Ilić, Gilles E. Gignac · 1 voice · 3 citations
Computer Science · Psychology · #Child and Animal Learning Development #Cognitive Abilities and Testing #Cognitive Science and Mapping #cs.AI #cs.CL
paper · pdf · doi:10.1016/j.intell.2024.101858
arxiv published 2023/10/17 · openalex publication_date 2024/08/29 · arxiv updated 2024/09/10 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/30
Large language models (LLMs) are advanced artificial intelligence (AI) systems that can perform a variety of tasks commonly found in human intelligence tests, such as defining words, performing calculations, and engaging in verbal reasoning. There are also substantial individual differences in LLM capacities. Given the consistent observation of a positive manifold and general intelligence factor in human samples, along with group-level factors (e.g., crystallised intelligence), we hypothesized that LLM test scores may also exhibit positive inter-correlations, which could potentially give rise to an artificial general ability (AGA) factor and one or more group-level factors. Based on a sample of 591 LLMs and scores from 12 tests aligned with fluid reasoning ( Gf ), domain-specific knowledge ( Gkn ), reading/writing ( Grw ), and quantitative knowledge ( Gq ), we found strong empirical evidence for a positive manifold and a general factor of ability. Additionally, we identified a combined Gkn / Grw group-level factor. Finally, the number of LLM parameters correlated positively with both general factor of ability and Gkn / Grw factor scores, although the effects showed diminishing returns. We interpreted our results to suggest that LLMs, like human cognitive abilities, may share a common underlying efficiency in processing information and solving problems, though whether LLMs manifest primarily achievement/expertise rather than intelligence remains to be determined. Finally, while models with greater numbers of parameters exhibit greater general cognitive-like abilities, akin to the connection between greater neuronal density and human general intelligence, other characteristics must also be involved. • Test performance from a sample of 591 large language models (LLMs). • Very strong positive manifold identified (mean r = 0.73). • Artificial general ability (AGA) tested via factor analysis. • Very strong AGA factor identified (66% of test variance). • Number of parameters associated positively with AGA ( r ≈ 0.6).