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

2026-08-06

AI Summary

Major societal crises often give rise to conspiracy theories, exacerbating social fragmentation and cognitive biases. This study investigates the efficacy of cognitive interventions delivered via a large language model (LLM)-based multi-turn dialogue system, administered within days of a real-world high-profile crisis to individuals endorsing emergent conspiracy beliefs. Employing a behavioral experiment with longitudinal tracking, the research demonstrates for the first time in a naturalistic setting that LLM-mediated conversations can significantly and durably attenuate nascent conspiracy beliefs. The effect remains robust over a one- to two-month follow-up period and generalizes to distinct conspiracy narratives emerging from subsequent events, indicating cross-event inhibitory transfer.

Abstract

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.

Problem

• conspiracy theories
• belief reduction
• large language models
• misinformation
• crisis events

Innovation

• large language models
• conspiracy belief reduction
• multi-turn dialogue intervention
• real-time misinformation counteraction
• downstream cognitive effects