2 papers
cs.CL2025
AI Debaters are More Persuasive when Arguing in Alignment with Their Own Beliefs
MarÃa Victoria Carro, Denise Alejandra Mester, Facundo Nieto +9
The core premise of AI debate as a scalable oversight technique is that it is harder to lie convincingly than to refute a lie, enabling the judge to identify the correct position.…
cs.AI2025
A Conceptual Framework for AI Capability Evaluations
MarÃa Victoria Carro, Denise Alejandra Mester, Francisca Gauna Selasco +7
As AI systems advance and integrate into society, well-designed and transparent evaluations are becoming essential tools in AI governance, informing decisions by providing evidence…