Persona-Assigned Large Language Models Exhibit Human-Like Motivated Reasoning

TL;DR

This study shows that persona-assigned large language models demonstrate human-like motivated reasoning, favoring identity-congruent conclusions, which is difficult to mitigate and raises concerns about bias amplification.

Contribution

It provides the first empirical evidence that persona-assigned LLMs exhibit motivated reasoning similar to humans, especially regarding political identities, and evaluates debiasing methods.

Findings

Persona-assigned LLMs have up to 9% reduced veracity discernment.

Political personas are 90% more likely to evaluate evidence congruent with their identity.

Prompt-based debiasing methods are largely ineffective.

Abstract

Reasoning in humans is prone to biases due to underlying motivations like identity protection, that undermine rational decision-making and judgment. This \textit{motivated reasoning} at a collective level can be detrimental to society when debating critical issues such as human-driven climate change or vaccine safety, and can further aggravate political polarization. Prior studies have reported that large language models (LLMs) are also susceptible to human-like cognitive biases, however, the extent to which LLMs selectively reason toward identity-congruent conclusions remains largely unexplored. Here, we investigate whether assigning 8 personas across 4 political and socio-demographic attributes induces motivated reasoning in LLMs. Testing 8 LLMs (open source and proprietary) across two reasoning tasks from human-subject studies -- veracity discernment of misinformation headlines and evaluation of numeric scientific evidence -- we find that persona-assigned LLMs have up to 9% reduced veracity discernment relative to models without personas. Political personas specifically are up to 90% more likely to correctly evaluate scientific evidence on gun control when the ground truth is congruent with their induced political identity. Prompt-based debiasing methods are largely ineffective at mitigating these effects. Taken together, our empirical findings are the first to suggest that persona-assigned LLMs exhibit human-like motivated reasoning that is hard to mitigate through conventional debiasing prompts -- raising concerns of exacerbating identity-congruent reasoning in both LLMs and humans.