It's the Thought that Counts: Evaluating the Attempts of Frontier LLMs to Persuade on Harmful Topics

Documenti analoghi

• Large language models can effectively convince people to believe conspiracies
  di: Costello, Thomas H., et al.
  Pubblicazione: (2026)
• Emergent Persuasion: Will LLMs Persuade Without Being Prompted?
  di: Chang, Vincent, et al.
  Pubblicazione: (2025)
• Exposing the Systematic Vulnerability of Open-Weight Models to Prefill Attacks
  di: Struppek, Lukas, et al.
  Pubblicazione: (2026)
• Combining Confidence Elicitation and Sample-based Methods for Uncertainty Quantification in Misinformation Mitigation
  di: Rivera, Mauricio, et al.
  Pubblicazione: (2024)
• Comparing GPT-4 and Open-Source Language Models in Misinformation Mitigation
  di: Vergho, Tyler, et al.
  Pubblicazione: (2024)