Reducing belief in conspiracy theories as they unfold using large language models

The emergence of conspiracy theories in the wake of major events is a significant societal challenge. Here we test whether conversational dialogues with a large language model (LLM) can reduce belief in immediately unfolding conspiracies. In experiments conducted in the days following the July 2024 assassination attempt on Donald Trump and the September 2025 assassination of Charlie Kirk, U.S. adults (Experiment 1: N = 472; Experiment 2: N = 1035) holding conspiratorial views about the crisis event engaged in a multi-turn conversation with an LLM prompted to reduce their conspiracy belief. Compared to control participants who either discussed an irrelevant topic with an LLM or viewed a static fact sheet, participants in the LLM treatment showed significantly reduced conspiracy beliefs in both experiments. We also found evidence of downstream effects of the LLM treatment, observing reduced belief in different conspiracies one to two months later in the wake of subsequent crisis events. These results shed light on the psychology of emerging conspiracies and highlight the potential for scalable, cognitively-focused interventions to counteract misinformation in the immediate aftermath of high-profile societal events.

Introduction. Many of the best-known unsubstantiated conspiracy theories are historical, having circulated for decades (e.g., JFK assassination, government UFO cover-up) or centuries (e.g., Illuminati, Jewish control of finance). As a result, large bodies of evidence debunking these theories have accumulated. Recent work has shown that large language model (LLM) AI systems, which functionally serve as a means of querying humanity’s collective knowledge,1 can leverage evidence from their training data to substantially and durably reduce conspiracy beliefs via brief human-AI dialogues.2 While many previous interventions meant to reduce belief in conspiracy theories are largely ineffective,3 AI models can quickly, legibly provide compelling rebuttals to any given conspiracy topic, a task which is extremely challenging and time-consuming for even the most experienced human would-be debunkers.

Discussion / Conclusion. Our results indicate that the “debunkbot” LLM was, perhaps surprisingly, quite effective at reducing beliefs in conspiracy theories that emerge in the immediate aftermath of two consequential crisis events. In addition to decreasing confidence in the stated conspiracy beliefs of the participants, the dialogue—which was relatively short (M = 6.9 minutes)—reduced suspicions of a cover-up and concerns about hidden factors. Importantly, we also find some carry-over influence of the increased skepticism that was adopted by the participants. Participants who received the AI debunking about the first Trump assassination attempt subsequently had less conspiratorial views about the second assassination attempt on Trump two months later; and participants who received the AI debunking about the Kirk assassination were less generally conspiratorial one month later, with also some evidence of treatment persistence when examining conspiratorial beliefs about a subsequent mass shooting incident.