Many thanks to @stanfordimpact for their generous support of our research on AI voter guides. With new AI guides popping up this cycle, it feels increasingly important to study the potential risks and benefits of using LLMs to translate and personalize voter information.
Joe Mernyk
Can AI voter guides help voters decide while remaining accurate, nonpartisan, and trustworthy?
Very grateful to @stanfordimpactlabs.bsky.social for a new grant supporting our next work on this (building on work led by Joe Mernyk & Jonne Kamphorst):
bsky.app/profile/robb...
Robb Willer
🚨New WP: Can an AI voter guide (grounded in information from a nonpartisan, fact-checked source) help voters’ decision making? 🚨
We built and evaluated an LLM-based chatbot that provided voting info in CA & TX (N=2,474) right before the 2024 election. 🧵👇
