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
¿Cómo podemos supervisar eficazmente los sistemas de IA que superan la inteligencia humana? AI Security via Debate propone que dos sistemas de IA argumenten posiciones opuestas y un juez, ya sea un modelo humano o un modelo más débil, decida cuál es el correcto. Al facilitar a los supervisores el suministro de señales de capacitación de alta calidad, el debate tiene como objetivo alentar el comportamiento verdadero y seguro de los sistemas de IA cuyas capacidades exceden las nuestras propias. Sin embargo, el juicio humano no es neutral: las personas a menudo confían en los vicios que los sistemas avanzados de IA pueden aprender a explotar.
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