idw – Informationsdienst Wissenschaft
Nachrichten, Termine, Experten
Nachrichten, Termine, Experten
An international research team involving the University of Bayreuth has, for the first time, analysed 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 one of the world’s leading AI conferences, the International Conference on Machine Learning (ICML 2026) in Seoul, South Korea.
---
Why it matters
AI-supported opinion research is already being used in academia, market research and political consultancy. 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. Analysing the internal representations of AI models helps to 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 analyse attitudes, consumer behaviour 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. A research team from Ludwig Maximilian University of Munich and the University of Bayreuth set out to address this issue.
“Previous research approaches that focused solely on analysing AI-generated answers are rather like looking only at the result displayed by a calculator without understanding how the calculation was performed. In our study, we were effectively able to look over the AI’s shoulder as it was thinking,” says Simeon Allmendinger, doctoral researcher in the University of Bayreuth Information Systems and Human-Centred Artificial Intelligence research group.
In the study, the researchers analysed more than 24 million combinations of factors—including the specific language model used, individual demographic characteristics, party constellations and prompts (so-called configurations)—across seven language models and six national elections. Within these different configurations, they investigated which internal regions of the LLMs were activated, how political parties were associated with particular characteristics within the models and how information such as age and educational background was processed.
“We found that the ‘inner workings’ of language models often contain additional information that is not fully reflected in the final answer. Making this information visible using our new method can provide additional insights and improve forecast accuracy,” says Professor Dr. Niklas Kühl, Chair of Information Systems and Human-Centred Artificial Intelligence at the University of Bayreuth.
For example, if a language model is asked to predict which party a person would vote for and its answer is “Party X”, the model may internally contain indications that the person has an equally strong association with Party Y.
“Our results show that the models learn more about underlying relationships than they ultimately reveal in their final output,” Kühl explains. “It is important to emphasise that this method is intended as a complementary tool and not as a replacement for traditional surveys. Particularly when it comes to underrepresented groups, real-world surveys remain indispensable,” Allmendinger stresses. The study was conducted in collaboration with the Munich Center for Machine Learning (MCML), the Fraunhofer Institute for Applied Information Technology FIT and the University of Maryland.
Professor Dr. Niklas Kühl
Information Systems and Human-Centred Artificial Intelligence
University of Bayreuth
Phone: +49 (0)921 55-4756
E-mail: kuehl@uni-bayreuth.de
Sarah Ball, Simeon Allmendinger, Frauke Kreuter, Niklas Kühl. Reading Between the Tokens: Improving Preference Predictions through Mechanistic Forecasting. ICML (2026)
DOI: https://doi.org/10.48550/arXiv.2602.02882
Criteria of this press release:
Journalists, Scientists and scholars
Information technology, Politics
transregional, national
Research results, Scientific Publications
English
You can combine search terms with and, or and/or not, e.g. Philo not logy.
You can use brackets to separate combinations from each other, e.g. (Philo not logy) or (Psycho and logy).
Coherent groups of words will be located as complete phrases if you put them into quotation marks, e.g. “Federal Republic of Germany”.
You can also use the advanced search without entering search terms. It will then follow the criteria you have selected (e.g. country or subject area).
If you have not selected any criteria in a given category, the entire category will be searched (e.g. all subject areas or all countries).
