APS
2025 APS Annual Convention · 2025
Large Language Models Reinforce Positivity Bias Toward Personal Future in Humans
- Ya-Jie Tai
National Taiwan University - Yu Ching Chen
National Taiwan University - Tsung-Ren Huang
National Taiwan University - Suparna Rajaram
Stony Brook University, The State University of New York
Abstract
This study investigates emotional tendencies in popular human queries and the corresponding responses from three Large Language Models (LLMs). Regression analyses reveal that humans show a positivity bias toward personal future events (n=60), and LLMs align emotionally with prompts (n=300). These emotional tendencies may reinforce unrealistic optimism during human-LLM interactions.
Other
