AI models like ChatGPT have amazed the world with their ability to write poetry, solve equations and even pass medical exams. But they can also churn out harmful content, or promote disinformation.
In a new study, George Washington University researchers have used physics to dissect and explain the attention mechanism at the core of AI systems. The research is published on the arXiv preprint server.
Researchers Neil Johnson and Frank Yingjie Huo looked into why AI repeats itself, why it sometimes makes things up and where harmful or biased content comes from, even when the input seems innocent.
The researchers found that the attention mechanism at the heart of these systems behaves like two spinning tops working together to deliver a response. AI’s responses are shaped not just by the input, but by how the input interacts with everything the AI has ever learned.
This analysis could lead to solutions that would make AI safer, more trustworthy and resistant to manipulation.
More information:
Frank Yingjie Huo et al, Capturing AI’s Attention: Physics of Repetition, Hallucination, Bias and Beyond, arXiv (2025). DOI: 10.48550/arxiv.2504.04600
Citation:
Study cracks the code behind why AI behaves as it does (2025, April 15)
retrieved 15 April 2025
from
This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no
part may be reproduced without the written permission. The content is provided for information purposes only.
