@inproceedings{811d4d60cb8b482b9af6b631ee82df45,
title = "Kiss up, Kick down: Exploring Behavioral Changes in Multi-modal Large Language Models with Assigned Visual Personas",
abstract = "This study is the first to explore whether multi-modal large language models (LLMs) can align their behaviors with visual personas, addressing a significant gap in the literature that predominantly focuses on text-based personas. We developed a novel dataset of 5K fictional avatar images for assignment as visual personas to LLMs, and analyzed their negotiation behaviors based on the visual traits depicted in these images, with a particular focus on aggressiveness. The results indicate that LLMs assess the aggressiveness of images in a manner similar to humans and output more aggressive negotiation behaviors when prompted with an aggressive visual persona. Interestingly, the LLM exhibited more aggressive negotiation behaviors when the opponent's image appeared less aggressive than their own, and less aggressive behaviors when the opponent's image appeared more aggressive.",
author = "Seungjong Sun and Eungu Lee and Baek, {Seo Yeon} and Seunghyun Hwang and Wonbyung Lee and Dongyan Nan and Jansen, {Bernard J.} and Kim, {Jang Hyun}",
note = "Publisher Copyright: {\textcopyright} 2024 Association for Computational Linguistics.; 2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024 ; Conference date: 12-11-2024 Through 16-11-2024",
year = "2024",
doi = "10.18653/v1/2024.emnlp-main.609",
language = "English",
series = "EMNLP 2024 - 2024 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference",
publisher = "Association for Computational Linguistics (ACL)",
pages = "10888--10901",
editor = "Yaser Al-Onaizan and Mohit Bansal and Yun-Nung Chen",
booktitle = "EMNLP 2024 - 2024 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference",
address = "United States",
}