English
Related papers

Related papers: Scalable AI Safety via Doubly-Efficient Debate

200 papers

If AI systems match or exceed human capabilities on a wide range of tasks, it may become difficult for humans to efficiently judge their actions -- making it hard to use human feedback to steer them towards desirable traits. One proposed…

Artificial Intelligence · Computer Science 2025-05-26 Marie Davidsen Buhl , Jacob Pfau , Benjamin Hilton , Geoffrey Irving

Training powerful AI systems to exhibit desired behaviors hinges on the ability to provide accurate human supervision on increasingly complex tasks. A promising approach to this problem is to amplify human judgement by leveraging the power…

Artificial Intelligence · Computer Science 2025-06-17 Jonah Brown-Cohen , Geoffrey Irving , Georgios Piliouras

To make AI systems broadly useful for challenging real-world tasks, we need them to learn complex human goals and preferences. One approach to specifying complex goals asks humans to judge during training which agent behaviors are safe and…

Machine Learning · Statistics 2018-10-23 Geoffrey Irving , Paul Christiano , Dario Amodei

As AI grows more powerful, it will increasingly shape how we understand the world. But with this influence comes the risk of amplifying misinformation and deepening social divides-especially on consequential topics where factual accuracy…

For some problems, humans may not be able to accurately judge the goodness of AI-proposed solutions. Irving et al. (2018) propose that in such cases, we may use a debate between two AI systems to amplify the problem-solving capabilities of…

Artificial Intelligence · Computer Science 2021-03-17 Vojtěch Kovařík , Ryan Carey

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. Yet, existing debate experiments have relied on datasets…

Ensuring responsible use of artificial intelligence (AI) has become imperative as autonomous systems increasingly influence critical societal domains. However, the concept of trustworthy AI remains broad and multi-faceted. This thesis…

Artificial Intelligence · Computer Science 2025-10-28 Filip Cano

As AI systems are used to answer more difficult questions and potentially help create new knowledge, judging the truthfulness of their outputs becomes more difficult and more important. How can we supervise unreliable experts, which have…

Artificial Intelligence · Computer Science 2023-11-16 Julian Michael , Salsabila Mahdi , David Rein , Jackson Petty , Julien Dirani , Vishakh Padmakumar , Samuel R. Bowman

As AI systems become prevalent in high stakes domains such as surveillance and healthcare, researchers now examine how to design and implement them in a safe manner. However, the potential harms caused by systems to stakeholders in complex…

Artificial Intelligence · Computer Science 2019-11-21 Roel Dobbe , Thomas Krendl Gilbert , Yonatan Mintz

AI safety via debate and reinforcement learning from AI feedback (RLAIF) are both proposed methods for scalable oversight of advanced AI systems, yet no formal framework relates them or characterizes when debate offers an advantage. We…

Machine Learning · Computer Science 2026-03-06 Robin Young

Embodied AI systems, comprising AI models and physical plants, are increasingly prevalent across various applications. Due to the rarity of system failures, ensuring their safety in complex operating environments remains a major challenge,…

As AI systems are integrated into high stakes social domains, researchers now examine how to design and operate them in a safe and ethical manner. However, the criteria for identifying and diagnosing safety risks in complex social contexts…

Computers and Society · Computer Science 2021-06-22 Roel Dobbe , Thomas Krendl Gilbert , Yonatan Mintz

Common methods for aligning already-capable models with desired behavior rely on the ability of humans to provide supervision. However, future superhuman models will surpass the capability of humans. Therefore, humans will only be able to…

Computation and Language · Computer Science 2025-01-24 Hao Lang , Fei Huang , Yongbin Li

Artificial Intelligence (AI) is being increasingly deployed in practical applications. However, there is a major concern whether AI systems will be trusted by humans. In order to establish trust in AI systems, there is a need for users to…

Artificial Intelligence · Computer Science 2021-02-16 Quratul-ain Mahesar , Simon Parsons

It is well recognised that ensuring fair AI systems is a complex sociotechnical challenge, which requires careful deliberation and continuous oversight across all stages of a system's lifecycle, from defining requirements to model…

Human-Computer Interaction · Computer Science 2025-05-14 Alpay Sabuncuoglu , Christopher Burr , Carsten Maple

AI systems are increasingly tasked to complete responsibilities with decreasing oversight. This delegation requires users to accept certain risks, typically mitigated by perceived or actual alignment of values between humans and AI, leading…

Computers and Society · Computer Science 2025-01-29 Jennifer Chien , David Danks

Emerging Distributed AI systems are revolutionizing big data computing and data processing capabilities with growing economic and societal impact. However, recent studies have identified new attack surfaces and risks caused by security,…

Machine Learning · Computer Science 2024-02-05 Wenqi Wei , Ling Liu

In the current era, people and society have grown increasingly reliant on artificial intelligence (AI) technologies. AI has the potential to drive us towards a future in which all of humanity flourishes. It also comes with substantial risks…

Computers and Society · Computer Science 2021-08-24 Lu Cheng , Kush R. Varshney , Huan Liu

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…

Human-Computer Interaction · Computer Science 2021-02-23 Henrietta Lyons , Eduardo Velloso , Tim Miller

The rapid development of Artificial Intelligence (AI) technology has enabled the deployment of various systems based on it. However, many current AI systems are found vulnerable to imperceptible attacks, biased against underrepresented…

Artificial Intelligence · Computer Science 2022-05-27 Bo Li , Peng Qi , Bo Liu , Shuai Di , Jingen Liu , Jiquan Pei , Jinfeng Yi , Bowen Zhou
‹ Prev 1 2 3 10 Next ›