Do LLM Agents Mirror Socio-Cognitive Effects in Power-Asymmetric Conversations?
This work examines whether large language models exhibit similar behaviors when assigned high or low status personas, and shows that LLMs show key socio-cognitive effects of power, albeit with nuances and variability, linking simulated interactions to both desirable and unsafe behaviors.
Anvesh Rao Vijjini, S. Manjunath, Snigdha Chaturvedi
· Annual Meeting of the Associ... · 0 citations