Maria Victoria Carro, Denise Alejandra Mester, Facundo Nieto, Oscar Agustin Stanchi, Guido Ernesto Bergman, Giovanni Franco Gabriel Marrafini, Trinidad Borrell, Guido Freire · 2026 · arXiv
DOI: 10.48550/arXiv.2610.28539 · open-access PDF
Bagaimana kita dapat secara efektif mengawasi sistem AI yang melampaui kecerdasan manusia? AI Safety via Debate mengusulkan bahwa dua sistem AI membantah posisi yang berlawanan dan seorang hakim, baik manusia atau model yang lebih lemah, memutuskan mana yang benar. Dengan memfasilitasi pengawas dalam memberikan sinyal pelatihan berkualitas tinggi, perdebatan bertujuan untuk mendorong perilaku yang benar dan aman dari sistem AI yang kemampuan melampaui kita sendiri.
Machine translation (Meta M2M100); the English original follows.
How can we effectively oversee AI systems that surpass human intelligence? AI Safety via Debate proposes that two AI systems argue opposing positions and a judge, either a human or a weaker model, decides which is correct. By facilitating supervisors in providing high-quality training signals, debate aims to encourage truthful and safe behavior from AI systems whose capabilities exceed our own. However, human judgment is not neutral: people often rely on biases which advanced AI systems may learn to exploit. Drawing on insights from collective intelligence and social cognition, this paper inve
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.28539, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange