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-supported opinion research is already being used in academia, market research and political consulting. As such forecasts become increasingly integrated into decision-making processes, it is becoming ever more important to understand the basis on which these predictions are generated.
Analyzing the internal representations of AI models helps shed light on the AI "black box" and reveals what information is actually stored within the models and how it is used. This makes AI forecasts more transparent and accurate, facilitates the identification of forecasting errors and helps uncover potential biases.
Large language models (LLMs) are increasingly being used to analyze attitudes, consumer behavior and political preferences, as well as to forecast future developments. However, previous studies of preference prediction have focused primarily on the final responses generated by LLMs rather than on the process by which those responses are produced.
