y0news
← Feed
Back to feed
🧠 AI NeutralImportance 6/10

Can Humans Tell? A Dual-Axis Study of Human Perception of LLM-Generated News

arXiv – CS AI|Alexander Loth, Martin Kappes, Marc-Oliver Pahl|
🤖AI Summary

A research study using JudgeGPT platform found that humans cannot reliably distinguish between AI-generated and human-written news articles across 2,318 judgments from 1,054 participants. The study tested six different LLMs and concluded that user-side detection is not viable, suggesting the need for cryptographic content provenance systems.

Key Takeaways
  • Humans cannot reliably distinguish between AI-generated and human-written news content across all tested language models.
  • Even smaller open-weight models with 7B parameters can fool human detection consistently.
  • Domain expertise correlates with better judgment accuracy while political orientation does not affect detection ability.
  • Participants fall into distinct response patterns as either 'Skeptics' or 'Believers' when evaluating content authenticity.
  • Detection accuracy degrades after about 30 sequential evaluations due to cognitive fatigue effects.
Read Original →via arXiv – CS AI
Act on this with AI
Stay ahead of the market.
Connect your wallet to an AI agent. It reads balances, proposes swaps and bridges across 15 chains — you keep full control of your keys.
Connect Wallet to AI →How it works
Related Articles