Are UFOs Driving Innovation? The Illusion of Causality in Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Carro, María Victoria, Selasco, Francisca Gauna, Mester, Denise Alejandra, Leiva, Mario Alejandro
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910651550531584
author Carro, María Victoria
Selasco, Francisca Gauna
Mester, Denise Alejandra
Leiva, Mario Alejandro
author_facet Carro, María Victoria
Selasco, Francisca Gauna
Mester, Denise Alejandra
Leiva, Mario Alejandro
contents Illusions of causality occur when people develop the belief that there is a causal connection between two variables with no supporting evidence. This cognitive bias has been proposed to underlie many societal problems including social prejudice, stereotype formation, misinformation and superstitious thinking. In this research we investigate whether large language models develop the illusion of causality in real-world settings. We evaluated and compared news headlines generated by GPT-4o-Mini, Claude-3.5-Sonnet, and Gemini-1.5-Pro to determine whether the models incorrectly framed correlations as causal relationships. In order to also measure sycophantic behavior, which occurs when a model aligns with a user's beliefs in order to look favorable even if it is not objectively correct, we additionally incorporated the bias into the prompts, observing if this manipulation increases the likelihood of the models exhibiting the illusion of causality. We found that Claude-3.5-Sonnet is the model that presents the lowest degree of causal illusion aligned with experiments on Correlation-to-Causation Exaggeration in human-written press releases. On the other hand, our findings suggest that while mimicry sycophancy increases the likelihood of causal illusions in these models, especially in GPT-4o-Mini, Claude-3.5-Sonnet remains the most robust against this cognitive bias.
format Preprint
id arxiv_https___arxiv_org_abs_2410_11684
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Are UFOs Driving Innovation? The Illusion of Causality in Large Language Models
Carro, María Victoria
Selasco, Francisca Gauna
Mester, Denise Alejandra
Leiva, Mario Alejandro
Artificial Intelligence
Computation and Language
Machine Learning
Illusions of causality occur when people develop the belief that there is a causal connection between two variables with no supporting evidence. This cognitive bias has been proposed to underlie many societal problems including social prejudice, stereotype formation, misinformation and superstitious thinking. In this research we investigate whether large language models develop the illusion of causality in real-world settings. We evaluated and compared news headlines generated by GPT-4o-Mini, Claude-3.5-Sonnet, and Gemini-1.5-Pro to determine whether the models incorrectly framed correlations as causal relationships. In order to also measure sycophantic behavior, which occurs when a model aligns with a user's beliefs in order to look favorable even if it is not objectively correct, we additionally incorporated the bias into the prompts, observing if this manipulation increases the likelihood of the models exhibiting the illusion of causality. We found that Claude-3.5-Sonnet is the model that presents the lowest degree of causal illusion aligned with experiments on Correlation-to-Causation Exaggeration in human-written press releases. On the other hand, our findings suggest that while mimicry sycophancy increases the likelihood of causal illusions in these models, especially in GPT-4o-Mini, Claude-3.5-Sonnet remains the most robust against this cognitive bias.
title Are UFOs Driving Innovation? The Illusion of Causality in Large Language Models
topic Artificial Intelligence
Computation and Language
Machine Learning
url https://arxiv.org/abs/2410.11684