AI Debaters are More Persuasive when Arguing in Alignment with Their Own Beliefs

This is experimental HTML to improve accessibility. We invite you to report rendering errors. Use Alt+Y to toggle on accessible reporting links and Alt+Shift+Y to toggle off. Learn more about this project and help improve conversions.

\workshoptitle Multi-Turn Interactions in Large Language Models AI Debaters are More Persuasive when Arguing in Alignment with Their Own Beliefs María Victoria Carro 1,2 , Denise Alejandra Mester 1 1 1 footnotemark: 1 , Facundo Nieto 1,3 , Oscar Agustín Stanchi 5 , Guido Ernesto Bergman 4 , Mario Alejandro Leiva 6 , Eitan Sprejer 4 , Luca Nicolás Forziati Gangi 1 , Francisca Gauna Selasco 1 , Juan Gustavo Corvalán 1 , Gerardo I. Simari 6 , María Vanina Martinez 7 2 2 footnotemark: 2 1 FAIR, IALAB, Universidad de Buenos Aires, AR 2 Università degli Studi di Genova, IT 3 Universidad Nacional de

related reading

• Modifying LLM Beliefs with Synthetic Document Finetuningalignment.anthropic.com
• Believe It or Not: How Deeply do LLMs Believe Implanted Facts?alignment.anthropic.com
• [2303.17548] Whose Opinions Do Language Models Reflect?arxiv.org
• [2306.13000] Apolitical Intelligence? Auditing Delphi's responses on controversial political issues in the USarxiv.org
• LMCA_dataset.pdfandrew.cmu.edu
• 2308.03958arxiv.org
• Alignment faking in large language modelsarxiv.org
• The limits of AI safety via debate — LessWronglesswrong.com
• [2506.13609] Avoiding Obfuscation with Prover-Estimator Debatearxiv.org
• [2503.03750] The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systemsarxiv.org
• [2601.10160] Alignment Pretraining: AI Discourse Causes Self-Fulfilling (Mis)alignmentarxiv.org
• [2510.17941] Believe It or Not: How Deeply do LLMs Believe Implanted Facts?arxiv.org