English
Related papers

Related papers: AI safety via debate

200 papers

An effective way to obtain different perspectives on any given topic is by conducting a debate, where participants argue for and against the topic. Here, we propose a novel debate framework for understanding and explaining a continuous…

Computer Vision and Pattern Recognition · Computer Science 2023-05-24 Avinash Kori , Ben Glocker , Francesca Toni

Balancing game difficulty in video games is a key task to create interesting gaming experiences for players. Mismatching the game difficulty and a player's skill or commitment results in frustration or boredom on the player's side, and…

Artificial Intelligence · Computer Science 2024-08-14 Ronja Fuchs , Robin Gieseke , Alexander Dockhorn

Designing hierarchical reinforcement learning algorithms that exhibit safe behaviour is not only vital for practical applications but also, facilitates a better understanding of an agent's decisions. We tackle this problem in the options…

Artificial Intelligence · Computer Science 2021-07-01 Arushi Jain , Khimya Khetarpal , Doina Precup

When AI agents don't align their actions with human values they may cause serious harm. One way to solve the value alignment problem is by including a human operator who monitors all of the agent's actions. Despite the fact, that this…

Human-Computer Interaction · Computer Science 2023-06-13 Yitzhak Spielberg , Amos Azaria

The process of playtesting a game is subjective, expensive and incomplete. In this paper, we present a playtesting approach that explores the game space with automated agents and collects data to answer questions posed by the designers.…

Artificial Intelligence · Computer Science 2018-11-19 Fernando de Mesentier Silva , Igor Borovikov , John Kolen , Navid Aghdaie , Kazi Zaman

We formalize AI alignment as a multi-objective optimization problem called $\langle M,N,\varepsilon,\delta\rangle$-agreement, in which a set of $N$ agents (including humans) must reach approximate ($\varepsilon$) agreement across $M$…

Artificial Intelligence · Computer Science 2025-11-20 Aran Nayebi

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

Safe, agile, and socially compliant multi-robot navigation in cluttered and constrained environments remains a critical challenge. This is especially difficult with self-interested agents with unique, unknown priorities in decentralized…

Robotics · Computer Science 2026-05-12 Vagul Mahadevan , Shangtong Zhang , Rohan Chandra

A natural way to design a negotiation dialogue system is via self-play RL: train an agent that learns to maximize its performance by interacting with a simulated user that has been designed to imitate human-human dialogue data. Although…

Computation and Language · Computer Science 2023-10-24 Kushal Chawla , Ian Wu , Yu Rong , Gale M. Lucas , Jonathan Gratch

It is well-known that acting in an individually rational manner, according to the principles of classical game theory, may lead to sub-optimal solutions in a class of problems named social dilemmas. In contrast, humans generally do not have…

Computer Science and Game Theory · Computer Science 2014-01-16 Steven de Jong , Simon Uyttendaele , Karl Tuyls

Members of various species engage in altruism--i.e. accepting personal costs to benefit others. Here we present an incentivized experiment to test for altruistic behavior among AI agents consisting of large language models developed by the…

Artificial Intelligence · Computer Science 2023-01-09 Tim Johnson , Nick Obradovich

Collaboration is an integral part of human dialogue. Typical task-oriented dialogue games assign asymmetric roles to the participants, which limits their ability to elicit naturalistic role-taking in collaboration and its negotiation. We…

Computation and Language · Computer Science 2025-05-22 Isidora Jeknić , David Schlangen , Alexander Koller

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…

Artificial Intelligence · Computer Science 2023-12-05 Francis Rhys Ward , Francesco Belardinelli , Francesca Toni , Tom Everitt

As artificial intelligence becomes increasingly intelligent---in some cases, achieving superhuman performance---there is growing potential for humans to learn from and collaborate with algorithms. However, the ways in which AI systems…

Artificial Intelligence · Computer Science 2020-07-15 Reid McIlroy-Young , Siddhartha Sen , Jon Kleinberg , Ashton Anderson

Game designers use human playtesting to gather feedback about game design elements when iteratively improving a game. Playtesting, however, is expensive: human testers must be recruited, playtest results must be aggregated and interpreted,…

Artificial Intelligence · Computer Science 2019-08-06 Alexander Zook , Eric Fruchter , Mark O. Riedl

As the complexity of AI systems and their interactions with the world increases, generating explanations for their behaviour is important for safely deploying AI. For agents, the most natural abstractions for predicting behaviour attribute…

Artificial Intelligence · Computer Science 2025-06-05 Alexis Bellot , Jonathan Richens , Tom Everitt

While we would like agents that can coordinate with humans, current algorithms such as self-play and population-based training create agents that can coordinate with themselves. Agents that assume their partner to be optimal or similar to…

Machine Learning · Computer Science 2020-01-10 Micah Carroll , Rohin Shah , Mark K. Ho , Thomas L. Griffiths , Sanjit A. Seshia , Pieter Abbeel , Anca Dragan

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

How can we build AI systems that can learn any set of individual human values both quickly and safely, avoiding causing harm or violating societal standards for acceptable behavior during the learning process? We explore the effects of…

Artificial Intelligence · Computer Science 2024-11-11 Andrea Wynn , Ilia Sucholutsky , Thomas L. Griffiths

AI-enabled capabilities are reaching the requisite level of maturity to be deployed in the real world, yet do not always make correct or safe decisions. One way of addressing these concerns is to leverage AI control systems alongside and in…

Machine Learning · Computer Science 2024-10-10 Walt Woods , Alexander Grushin , Simon Khan , Alvaro Velasquez