Effectiveness of large language models in political microtargeting assessed in new study

Recent advancements in large language models (LLMs) have raised the prospect of scalable, automated, and fine-grained political microtargeting on a scale previously unseen. By building a custom web application capable of integrating demographic and political data into GPT-4 prompts in real time, the OII researchers generated thousands of unique messages tailored to persuade individual users. Deploying this application in a pre-registered, randomised control experiment, they found that messages generated by GPT-4 were broadly persuasive. Crucially, however, in aggregate, the persuasive impact of microtargeted messages was not statistically different from that of non-microtargeted messages. In contrast, it highlights the persuasiveness of GPT’s ‘best message’ on specific policy issues, without targeting.’The study ‘Evaluating the persuasive influence of political microtargeting with large language models’ is published in PNAS.