Related papers: Avoiding Obfuscation with Prover-Estimator Debate
Deceptive agents are a challenge for the safety, trustworthiness, and cooperation of AI systems. We focus on the problem that agents might deceive in order to achieve their goals (for instance, in our experiments with language models, the…
As an epistemic activity, rational debate and discussion requires cooperation, yet involves a tension between collective and individual interests. While all participants benefit from collective outcomes like reaching consensus on true…
Isolated perspectives have often paved the way for great scientific discoveries. However, many breakthroughs only emerged when moving away from singular views towards interactions. Discussions on Artificial Intelligence (AI) typically treat…
When people reason about cause and effect, they often consider many competing "what if" scenarios before deciding which explanation fits best. Analogously, advanced language models capable of causal inference can consider multiple…
With the growing capabilities and pervasiveness of AI systems, societies must collectively choose between reduced human autonomy, endangered democracies and limited human rights, and AI that is aligned to human and social values, nurturing…
Mediation is a process, in which both parties agree to resolve their dispute by negotiating over alternative solutions presented by a mediator. In order to construct such solutions, mediation brings more information and knowledge, and, if…
While natural-language explanations from large language models (LLMs) are widely adopted to improve transparency and trust, their impact on objective human-AI team performance remains poorly understood. We identify a Persuasion Paradox:…
As Large Language Models (LLMs) gain expertise across diverse domains and modalities, scalable oversight becomes increasingly challenging, particularly when their capabilities may surpass human evaluators. Debate has emerged as a promising…
As robots and other intelligent agents move from simple environments and problems to more complex, unstructured settings, manually programming their behavior has become increasingly challenging and expensive. Often, it is easier for a…
In recent years, various machine and deep learning architectures have been successfully introduced to the field of predictive process analytics. Nevertheless, the inherent opacity of these algorithms poses a significant challenge for human…
The rapid evolution of artificial intelligence has led to expectations of transformative impact on science, yet current systems remain fundamentally limited in enabling genuine scientific discovery. This perspective contends that progress…
Large Language Models (LLMs) have shown remarkable reasoning capabilities in mathematical and scientific tasks. To enhance complex reasoning, multi-agent systems have been proposed to harness the collective intelligence of LLM agents.…
Introduction. AI Ethics is framed distinctly across actors and stakeholder groups. We report results from a case study of OpenAI analysing ethical AI discourse. Method. Research addressed: How has OpenAI's public discourse leveraged…
Given the fast rise of increasingly autonomous artificial agents and robots, a key acceptability criterion will be the possible moral implications of their actions. In particular, intelligent persuasive systems (systems designed to…
Argumentation is a central subarea of Artificial Intelligence (AI) for modeling and reasoning about arguments. The semantics of abstract argumentation frameworks (AFs) is given by sets of arguments (extensions) and conditions on the…
Deliberative democracy arguably leads to better collective decisions, but is fundamentally constrained by human attention and bandwidth. While recent AI-mediated deliberations scale participation by synthesizing inputs from many humans,…
OpenAI o1 has shown that applying reinforcement learning to integrate reasoning steps directly during inference can significantly improve a model's reasoning capabilities. This result is exciting as the field transitions from the…
As the use of algorithmic systems in high-stakes decision-making increases, the ability to contest algorithmic decisions is being recognised as an important safeguard for individuals. Yet, there is little guidance on what…
As AI agents surpass human capabilities, scalable oversight -- the problem of effectively supplying human feedback to potentially superhuman AI models -- becomes increasingly critical to ensure alignment. While numerous scalable oversight…
Automated content filtering and moderation is an important tool that allows online platforms to build striving user communities that facilitate cooperation and prevent abuse. Unfortunately, resourceful actors try to bypass automated filters…