An international research team involving the University of Bayreuth has, for the first time, analyzed the “inner workings” of AI language models when predicting political voting decisions. To do so, the researchers examined six national elections and AI-based election forecasts and developed a new method for making more precise predictions. They presented their findings at the International Conference on Machine Learning (ICML 2026) in Seoul, South Korea.
AI-powered election forecasts reveal hidden preferences inside language models
Reader’s Picks
-
There are two lighthouses on Lady Elliot Island, at the southernmost tip of Australia’s Great Barrier Reef. The first was [...]
-
Stories of wandering spirits and the restless dead were common in the Middle Ages. These ghostly encounters were recorded in [...]
-
More than half (52.5%) of Americans ages 13 to 27 reported gambling in the past year, including 42.7% of teens [...]
