Influence of Solution Efficiency and Valence of Instruction on Additive and Subtractive Solution Strategies in Humans and GPT-4

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Uhler, Lydia, Jordan, Verena, Buder, Jürgen, Huff, Markus, Papenmeier, Frank
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912856066228224
author Uhler, Lydia
Jordan, Verena
Buder, Jürgen
Huff, Markus
Papenmeier, Frank
author_facet Uhler, Lydia
Jordan, Verena
Buder, Jürgen
Huff, Markus
Papenmeier, Frank
contents Generative artificial intelligences, particularly large language models (LLMs), play an increasingly prominent role in human decision-making contexts, necessitating transparency about their capabilities. While prior studies have shown addition biases in humans (Adams et al., 2021) and OpenAI's GPT-3 (Winter et al., 2023), this study extends the research by comparing human and GPT-4 problem-solving across both spatial and linguistic tasks, with variations in solution efficiency and valence of task instruction. Four preregistered experiments with 588 participants from the U.S. and 680 GPT-4 iterations revealed a stronger tendency towards additive transformations in GPT-4 than in humans. Human participants were less likely to use additive strategies when subtraction was relatively more efficient than when addition and subtraction were equally efficient. GPT-4 exhibited the opposite behavior, with a strong addition bias when subtraction was more efficient. In terms of valence of task instruction, GPT-4's use of additive strategies increased when instructed to "improve" (positive) rather than "edit" (neutral). These findings demonstrate that biases in human problem-solving are amplified in GPT-4, and that LLM behavior differs from human efficiency-based strategies. This highlights the limitations of LLMs and the need for caution when using them in real-world applications.
format Preprint
id arxiv_https___arxiv_org_abs_2404_16692
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Influence of Solution Efficiency and Valence of Instruction on Additive and Subtractive Solution Strategies in Humans and GPT-4
Uhler, Lydia
Jordan, Verena
Buder, Jürgen
Huff, Markus
Papenmeier, Frank
Computation and Language
Artificial Intelligence
Generative artificial intelligences, particularly large language models (LLMs), play an increasingly prominent role in human decision-making contexts, necessitating transparency about their capabilities. While prior studies have shown addition biases in humans (Adams et al., 2021) and OpenAI's GPT-3 (Winter et al., 2023), this study extends the research by comparing human and GPT-4 problem-solving across both spatial and linguistic tasks, with variations in solution efficiency and valence of task instruction. Four preregistered experiments with 588 participants from the U.S. and 680 GPT-4 iterations revealed a stronger tendency towards additive transformations in GPT-4 than in humans. Human participants were less likely to use additive strategies when subtraction was relatively more efficient than when addition and subtraction were equally efficient. GPT-4 exhibited the opposite behavior, with a strong addition bias when subtraction was more efficient. In terms of valence of task instruction, GPT-4's use of additive strategies increased when instructed to "improve" (positive) rather than "edit" (neutral). These findings demonstrate that biases in human problem-solving are amplified in GPT-4, and that LLM behavior differs from human efficiency-based strategies. This highlights the limitations of LLMs and the need for caution when using them in real-world applications.
title Influence of Solution Efficiency and Valence of Instruction on Additive and Subtractive Solution Strategies in Humans and GPT-4
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2404.16692