Salvato in:
Dettagli Bibliografici
Autore principale: Kong, Haein
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2505.12248
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909615030009856
author Kong, Haein
author_facet Kong, Haein
contents As large language models (LLMs) achieve advanced persuasive capabilities, concerns about their potential risks have grown. The EU AI Act prohibits AI systems that use manipulative or deceptive techniques to undermine informed decision-making, highlighting the need to distinguish between rational persuasion, which engages reason, and manipulation, which exploits cognitive biases. My dissertation addresses the lack of empirical studies in this area by developing a taxonomy of persuasive techniques, creating a human-annotated dataset, and evaluating LLMs' ability to distinguish between these methods. This work contributes to AI safety by providing resources to mitigate the risks of persuasive AI and fostering discussions on ethical persuasion in the age of generative AI.
format Preprint
id arxiv_https___arxiv_org_abs_2505_12248
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Persuasion and Safety in the Era of Generative AI
Kong, Haein
Computers and Society
As large language models (LLMs) achieve advanced persuasive capabilities, concerns about their potential risks have grown. The EU AI Act prohibits AI systems that use manipulative or deceptive techniques to undermine informed decision-making, highlighting the need to distinguish between rational persuasion, which engages reason, and manipulation, which exploits cognitive biases. My dissertation addresses the lack of empirical studies in this area by developing a taxonomy of persuasive techniques, creating a human-annotated dataset, and evaluating LLMs' ability to distinguish between these methods. This work contributes to AI safety by providing resources to mitigate the risks of persuasive AI and fostering discussions on ethical persuasion in the age of generative AI.
title Persuasion and Safety in the Era of Generative AI
topic Computers and Society
url https://arxiv.org/abs/2505.12248