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
AI Safety via Debate では、二つのAIシステムが対立した立場を論じ、人間か弱いモデルである裁判官がどちらが正しいかを決定することを提案します。高品質のトレーニングシグナルを提供する監督者を容易にすることにより、討論は、AIシステムの能力が我々の能力を上回る真実で安全な行動を奨励することを目指しています。しかし、人間の判断は中立ではありません:人々はしばしば先進的なAIシステムが利用することを学ぶ偏見に頼ります。
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