相关论文: Debate Helps Supervise Unreliable Experts

Expert workers make non-trivial decisions with significant implications. Experts' decision accuracy is thus a fundamental aspect of their judgment quality, key to both management and consumers of experts' services. Yet, in many important…

Automated decision systems (ADS) are increasingly used for consequential decision-making. These systems often rely on sophisticated yet opaque machine learning models, which do not allow for understanding how a given decision was arrived…

Large Language Models (LLMs) have advanced autonomous agents' planning and decision-making, yet they struggle with complex tasks requiring diverse expertise and multi-step reasoning. Multi-Agent Debate (MAD) systems, introduced in NLP…

Current literature and public discourse on "trust in AI" are often focused on the principles underlying trustworthy AI, with insufficient attention paid to how people develop trust. Given that AI systems differ in their level of…

Explainability and its emerging counterpart contestability have become important normative and design principles for trustworthy AI as they enable users and subjects to understand and challenge AI decisions. However, realizing these…

The promise of human-AI teaming lies in humans and AI working together to achieve performance levels neither could accomplish alone. Effective communication between AI and humans is crucial for teamwork, enabling users to efficiently…

A growing literature studies how humans incorporate advice from algorithms. This study examines an algorithm with millions of daily users: ChatGPT. In a preregistered study, 118 student participants answer 2,828 multiple-choice questions…

In the face of rapidly advancing AI technology, individuals will increasingly rely on AI agents to navigate life's growing complexities, raising critical concerns about maintaining both human agency and autonomy. This paper addresses a…

As the use of artificial intelligence (AI) in high-stakes decision-making increases, the ability to contest such decisions is being recognised in AI ethics guidelines as an important safeguard for individuals. Yet, there is little guidance…

Scalable oversight protocols aim to empower evaluators to accurately verify AI models more capable than themselves. However, human evaluators are subject to biases that can lead to systematic errors. We conduct two studies examining the…

The spread of online misinformation poses serious threats to democratic societies. Traditionally, expert fact-checkers verify the truthfulness of information through investigative processes. However, the volume and immediacy of online…

Artificial Intelligence (AI) is increasingly becoming a trusted advisor in people's lives. A new concern arises if AI persuades people to break ethical rules for profit. Employing a large-scale behavioural experiment (N = 1,572), we test…

Prior research demonstrates that performance of language models on reasoning tasks can be influenced by suggestions, hints and endorsements. However, the influence of endorsement source credibility remains underexplored. We investigate…

While we have witnessed a rapid growth of ethics documents meant to guide AI development, the promotion of AI ethics has nonetheless proceeded with little input from AI practitioners themselves. Given the proliferation of AI for Social Good…

Humans engage in informal debates on a daily basis. By expressing their opinions and ideas in an argumentative fashion, they are able to gain a deeper understanding of a given problem and in some cases, find the best possible course of…

Large Language Models (LLMs) have shown impressive capabilities in various applications, but they still face various inconsistency issues. Existing works primarily focus on the inconsistency issues within a single LLM, while we…

Much of the success of multi-agent debates depends on carefully choosing the right parameters. The decision-making protocol stands out as it can highly impact final model answers, depending on how decisions are reached. Systematic…

Customers' emotions play a vital role in the service industry. The better frontline personnel understand the customer, the better the service they can provide. As human emotions generate certain (unintentional) bodily reactions, such as…

Trust biases how users rely on AI recommendations in AI-assisted decision-making tasks, with low and high levels of trust resulting in increased under- and over-reliance, respectively. We propose that AI assistants should adapt their…

Multi-agent AI systems can be used for simulating collective decision-making in scientific and practical applications. They can also be used to introduce a diverse group discussion step in chatbot pipelines, enhancing the cultural…