Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Havin, Miriam, Kleinman, Timna Wharton, Koren, Moran, Dover, Yaniv, Goldstein, Ariel
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2503.01844
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912372246970368
author Havin, Miriam
Kleinman, Timna Wharton
Koren, Moran
Dover, Yaniv
Goldstein, Ariel
author_facet Havin, Miriam
Kleinman, Timna Wharton
Koren, Moran
Dover, Yaniv
Goldstein, Ariel
contents The increasing integration of large language models (LLMs) based conversational agents into everyday life raises critical cognitive and social questions about their potential to influence human opinions. Although previous studies have shown that LLM-based agents can generate persuasive content, these typically involve controlled English-language settings. Addressing this, our preregistered study explored LLMs' persuasive capabilities in more ecological, unconstrained scenarios, examining both static (written paragraphs) and dynamic (conversations via Telegram) interaction types. Conducted entirely in Hebrew with 200 participants, the study assessed the persuasive effects of both LLM and human interlocutors on controversial civil policy topics. Results indicated that participants adopted LLM and human perspectives similarly, with significant opinion changes evident across all conditions, regardless of interlocutor type or interaction mode. Confidence levels increased significantly in most scenarios. These findings demonstrate LLM-based agents' robust persuasive capabilities across diverse sources and settings, highlighting their potential impact on shaping public opinions.
format Preprint
id arxiv_https___arxiv_org_abs_2503_01844
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Can (A)I Change Your Mind?
Havin, Miriam
Kleinman, Timna Wharton
Koren, Moran
Dover, Yaniv
Goldstein, Ariel
Computation and Language
The increasing integration of large language models (LLMs) based conversational agents into everyday life raises critical cognitive and social questions about their potential to influence human opinions. Although previous studies have shown that LLM-based agents can generate persuasive content, these typically involve controlled English-language settings. Addressing this, our preregistered study explored LLMs' persuasive capabilities in more ecological, unconstrained scenarios, examining both static (written paragraphs) and dynamic (conversations via Telegram) interaction types. Conducted entirely in Hebrew with 200 participants, the study assessed the persuasive effects of both LLM and human interlocutors on controversial civil policy topics. Results indicated that participants adopted LLM and human perspectives similarly, with significant opinion changes evident across all conditions, regardless of interlocutor type or interaction mode. Confidence levels increased significantly in most scenarios. These findings demonstrate LLM-based agents' robust persuasive capabilities across diverse sources and settings, highlighting their potential impact on shaping public opinions.
title Can (A)I Change Your Mind?
topic Computation and Language
url https://arxiv.org/abs/2503.01844