AI search engines show high error rates in source attribution, study finds

An independent study by the Tow Center for Digital Journalism revealed that eight AI search engines, including Perplexity and ChatGPT, incorrectly attribute sources in over 60% of cases. This inaccuracy persists even with paid subscriptions, as Perplexity Pro showed a higher error rate than its free version. The research also found that ChatGPT frequently fabricates sources rather than admitting it cannot find an answer. While Yandex's Nuro-Alice service appears to have a lower error rate due to its method of relying on existing search results, it may still misinterpret the content of valid links. AI

IMPACT Highlights the unreliability of AI search engines for accurate source citation, impacting research and information integrity.

RANK_REASON Research paper detailing inaccuracies in AI search engine attribution [lever_c_demoted from research: ic=1 ai=1.0]

Read on dev.to — LLM tag →

• Aravind Srinivas
• ChatGPT
• Gemini API
• MOAB
• Nuro-Alice
• OpenAI
• Perplexity
• Perplexity Pro
• Tow Center for Digital Journalism
• Yandex

• product
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →