Newest papers

Humans Correct Their Judgments Through Debate, but Weaker AI Models Do Not

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

Arabic

كيف يمكننا التحكم بشكل فعال في أنظمة الذكاء الاصطناعي التي تتجاوز الذكاء الاصطناعي البشرية؟ يهدف الحوار إلى تعزيز سلوك الذكاء الاصطناعي من خلال الحوار إلى أنظمة الذكاء الاصطناعي تتناول موقفين متناقضين، ويقرر محاكمة، أو شخصية أو نموذج أقل ضعفاً، ما هو صحيح. من خلال مساعدة المراقبين في توفير إشارات تدريبية ذات جودة عالية، يهدف الحوار إلى تعزيز السلوك الصحيح والسلامة من أنظمة الذكاء الاصطناعي التي تتجاوز القدرات الخاصة بنا.

Machine translation (Meta M2M100); the English original follows.

Abstract

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

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: 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.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange