Prosocial Persuasion at Scale? Large Language Models Outperform Humans in Donation Appeals Across Levels of Personalization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Caffier, John, Stavrova, Olga, Kleinberg, Bennett
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908935046299648
author Caffier, John
Stavrova, Olga
Kleinberg, Bennett
author_facet Caffier, John
Stavrova, Olga
Kleinberg, Bennett
contents Large Language Models (LLMs) are increasingly regarded as having the potential to generate persuasive content at scale. While previous studies have focused on the risks associated with LLM-generated misinformation, the role of LLMs in enabling prosocial persuasion is still underexplored. We investigate whether donation appeals authored by LLMs are as effective as those written by humans across degrees of personalization. Two preregistered online experiments (Study 1: N = 658; Study 2: N = 642) manipulated Personalization (generic vs. personalized vs. falsely personalized) and Content source (human vs. LLM) and presented participants with donation appeals for charities. We assessed how participants distributed their bonus money across the charities, how they engaged with the donation appeals, and how persuasive they found them. In both experiments, LLM-generated content yielded more donations, resulted in higher engagement, and was rated as more persuasive than human-authored content. There was a gain associated with personalization (Study 2) and a penalty for false personalization (Study 1). Our results suggest that LLMs may be a suitable technology for generating content that can encourage prosocial behavior.
format Preprint
id arxiv_https___arxiv_org_abs_2604_03202
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Prosocial Persuasion at Scale? Large Language Models Outperform Humans in Donation Appeals Across Levels of Personalization
Caffier, John
Stavrova, Olga
Kleinberg, Bennett
Computers and Society
Large Language Models (LLMs) are increasingly regarded as having the potential to generate persuasive content at scale. While previous studies have focused on the risks associated with LLM-generated misinformation, the role of LLMs in enabling prosocial persuasion is still underexplored. We investigate whether donation appeals authored by LLMs are as effective as those written by humans across degrees of personalization. Two preregistered online experiments (Study 1: N = 658; Study 2: N = 642) manipulated Personalization (generic vs. personalized vs. falsely personalized) and Content source (human vs. LLM) and presented participants with donation appeals for charities. We assessed how participants distributed their bonus money across the charities, how they engaged with the donation appeals, and how persuasive they found them. In both experiments, LLM-generated content yielded more donations, resulted in higher engagement, and was rated as more persuasive than human-authored content. There was a gain associated with personalization (Study 2) and a penalty for false personalization (Study 1). Our results suggest that LLMs may be a suitable technology for generating content that can encourage prosocial behavior.
title Prosocial Persuasion at Scale? Large Language Models Outperform Humans in Donation Appeals Across Levels of Personalization
topic Computers and Society
url https://arxiv.org/abs/2604.03202