Large Language Models (LLMs) as Agents for Augmented Democracy

arXiv:2405.03452v1 Announce Type: cross
Abstract: We explore the capabilities of an augmented democracy system built on off-the-shelf LLMs fine-tuned on data summarizing individual preferences across 67 policy proposals collected during the 2022 Brazilian presidential elections. We use a train-test cross-validation setup to estimate the accuracy with which the LLMs predict both: a subject's individual political choices and the aggregate preferences of the full sample of participants. At the individual level, the accuracy of the out of sample predictions lie in …

abstract accuracy agents arxiv capabilities cs.ai cs.cl cs.cy data democracy elections explore language language models large language large language models llms policy proposals setup summarizing test train type validation