Chatbots Are Surprisingly Effective at Debunking Conspiracy Theories

Why It Matters

The findings prove that AI‑driven, evidence‑based debunking can reliably shift entrenched false beliefs, offering a scalable tool for platforms and policymakers to combat misinformation and mitigate the societal impact of conspiracy theories.

Summary

Researchers deployed DebunkBot, a GPT‑4 Turbo‑based chatbot, in three‑round, eight‑minute conversations with over 2,000 self‑identified conspiracy believers. The interaction cut participants' confidence in the targeted conspiracy by 20% and led roughly one‑quarter to abandon the belief entirely, with effects lasting at least two months. The effect held for both classic conspiracies (e.g., JFK, moon landing) and recent political ones (e.g., 2020 election, COVID‑19), and persisted when users thought they were speaking to a human expert. Independent fact‑checking found over 99% of the bot’s claims accurate, showing AI can deliver reliable evidence at scale.