LLM Cognitive Judgements Differ From Human

Sotiris Lamprinidis
7/20/2023
cs.CLcs.AIcs.LG

Official code: sotlampr/llm-cognitive-judgements (10 stars, last commit 2023-07-25).

Abstract

Large Language Models (LLMs) have lately been on the spotlight of researchers, businesses, and consumers alike. While the linguistic capabilities of such models have been studied extensively, there is growing interest in investigating them as cognitive subjects. In the present work I examine GPT-3 and ChatGPT capabilities on an limited-data inductive reasoning task from the cognitive science literature. The results suggest that these models' cognitive judgements are not human-like.

View on arXivView PDF

Code Implementations(1)

sotlampr/llm-cognitive-judgementsOfficial100%

Code and Data for the paper 'LLM Cognitive Judgements Differ From Human'

100PythonJul 25, 20233 years ago

Similar Papers

Human-Like Intuitive Behavior and Reasoning Biases Emerged in Language Models -- and Disappeared in GPT-4

88% match2023

Judgment of Learning: A Human Ability Beyond Generative Artificial Intelligence

85% match2024

Humanlike Cognitive Patterns as Emergent Phenomena in Large Language Models

84% match2024

Towards a Psychology of Machines: Large Language Models Predict Human Memory

84% match2024

Studying and improving reasoning in humans and machines

84% match2023

A Perspective on Large Language Models, Intelligent Machines, and Knowledge Acquisition

83% match2024

Cite this paper

@article{lamprinidis2023cognitive,
  title  = {LLM Cognitive Judgements Differ From Human},
  author = {Sotiris Lamprinidis},
  year   = {2023},
  eprint = {2307.11787},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2307.11787v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2307.11787.svg)](https://codeofpaper.com/paper/2307.11787)

Discussion