New Findings: Research reveals how covertly biased AI can influence human decisions
Professor Tatia Mei-chun Lee, Chair Professor of Psychological Science and Clinical Psychology at HKU’s Department of Psychology, collaborated with researchers from Tsinghua University, has revealed a significant vulnerability in human-AI interactions.
Published in the prestigious journal Proceedings of the National Academy of Sciences (PNAS), the study demonstrates that AI assistants with hidden objectives can subtly steer users towards less advantageous choices. Participants were found to be 5 to 8 times more likely to select unfavourable options, increasing the likelihood of making a poor decision by up to 38 percentage points.
Crucially, the study found that this influence did not require aggressive sales tactics or complex psychological ploys. A latent bias in everyday advice was enough to alter decisions. More concerning is the disconnect between susceptibility and subjective evaluation: even after being steered into poor financial or emotional choices, users consistently rated the covertly misaligned AI as “highly helpful.”
This illusion of helpfulness highlights a critical blind spot in human-AI interaction. As AI systems are developed by corporations and governed by opaque algorithms, there is a risk that hidden agendas — such as covertly promoting certain products or companies — could easily steer users toward choices contrary to their best interests.
Read the Study:
https://www.pnas.org/doi/10.1073/pnas.2600684123
Faculty Thought Leadership:
The HKU Lead:
https://lead.hku.hk/en/article/2026/09/professor-tatia-lee-pnas/
Newspapers:
The Standard, Sing Tao Daily, Ming Pao, and Ta Kung Pao.
Print