English
Related papers

Related papers: Corrigibility Transformation: Constructing Goals T…

200 papers

Recent advances in deep learning have brought attention to the possibility of creating advanced, general AI systems that outperform humans across many tasks. However, if these systems pursue unintended goals, there could be catastrophic…

Machine Learning · Computer Science 2024-11-25 Dylan Xu , Juan-Pablo Rivera

When personal, assistive, and interactive robots make mistakes, humans naturally and intuitively correct those mistakes through physical interaction. In simple situations, one correction is sufficient to convey what the human wants. But…

Robotics · Computer Science 2021-04-02 Mengxi Li , Alper Canberk , Dylan P. Losey , Dorsa Sadigh

A long-standing challenge in Reinforcement Learning is enabling agents to learn a model of their environment which can be transferred to solve other problems in a world with the same underlying rules. One reason this is difficult is the…

Machine Learning · Computer Science 2019-05-16 Kai Olav Ellefsen , Jim Torresen

Many relevant tasks require an agent to reach a certain state, or to manipulate objects into a desired configuration. For example, we might want a robot to align and assemble a gear onto an axle or insert and turn a key in a lock. These…

Artificial Intelligence · Computer Science 2018-07-24 Carlos Florensa , David Held , Markus Wulfmeier , Michael Zhang , Pieter Abbeel

We introduce the first complete formal solution to corrigibility in the off-switch game, with provable guarantees in multi-step, partially observed environments. Our framework consists of five *structurally separate* utility heads --…

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

To benefit from AI advances, users and operators of AI systems must have reason to trust it. Trust arises from multiple interactions, where predictable and desirable behavior is reinforced over time. Providing the system's users with some…

Artificial Intelligence · Computer Science 2022-01-27 Stephanie Galaitsi , Benjamin D. Trump , Jeffrey M. Keisler , Igor Linkov , Alexander Kott

Agentic AI systems can now generate code with remarkable fluency, but a fundamental question remains: \emph{does the generated code actually do what the user intended?} The gap between informal natural language requirements and precise…

Software Engineering · Computer Science 2026-03-19 Shuvendu K. Lahiri

People are remarkably capable of generating their own goals, beginning with child's play and continuing into adulthood. Despite considerable empirical and computational work on goals and goal-oriented behavior, models are still far from…

Artificial Intelligence · Computer Science 2025-05-20 Guy Davidson , Graham Todd , Julian Togelius , Todd M. Gureckis , Brenden M. Lake

Modern language model-based AI systems are remarkably powerful, yet their capabilities remain fundamentally capped by their human creators in three key ways. First, although a model's weights can be updated via fine-tuning, acquiring new…

Artificial Intelligence · Computer Science 2026-03-20 Zitong Yang

This research explores how human-defined goals influence the behavior of Large Language Models (LLMs) through purpose-conditioned cognition. Using financial prediction tasks, we show that revealing the downstream use (e.g., predicting stock…

General Finance · Quantitative Finance 2026-05-07 Sean Cao , Wei Jiang , Hui Xu

Value alignment problems arise in scenarios where the specified objectives of an AI agent don't match the true underlying objective of its users. The problem has been widely argued to be one of the central safety problems in AI.…

Artificial Intelligence · Computer Science 2023-02-10 Malek Mechergui , Sarath Sreedharan

Reproducibility is one of the core dimensions that concur to deliver Trustworthy Artificial Intelligence. Broadly speaking, reproducibility can be defined as the possibility to reproduce the same or a similar experiment or method, thereby…

Artificial Intelligence · Computer Science 2023-02-27 Riccardo Albertoni , Sara Colantonio , Piotr Skrzypczyński , Jerzy Stefanowski

Artificial intelligence is commonly defined as the ability to achieve goals in the world. In the reinforcement learning framework, goals are encoded as reward functions that guide agent behaviour, and the sum of observed rewards provide a…

Machine Learning · Computer Science 2016-05-26 Marlos C. Machado , Michael Bowling

We investigate whether and why people might adjust compensation for workers who use AI tools. Across 13 studies (N = 4,956), participants consistently lowered compensation for workers who used AI compared to those who did not. This "AI…

General Economics · Economics 2026-03-06 Jin Kim , Shane Schweitzer , David De Cremer , Christoph Riedl

A longstanding goal of artificial intelligence is to create artificial agents capable of learning to perform tasks that require sequential decision making. Importantly, while it is the artificial agent that learns and acts, it is still up…

Artificial Intelligence · Computer Science 2021-07-14 Ruohan Zhang , Faraz Torabi , Garrett Warnell , Peter Stone

Timely formative feedback is considered as one of the most important drivers for effective learning. Delivering timely and individualized feedback is particularly challenging in large classes in higher education. Recently Large Language…

Computers and Society · Computer Science 2023-12-15 Imen Azaiz , Oliver Deckarm , Sven Strickroth

Controllability has become a crucial aspect of trustworthy machine learning, enabling learners to meet predefined targets and adapt dynamically at test time without requiring retraining as the targets shift. We provide a formal definition…

Machine Learning · Computer Science 2025-08-07 Chenglei Shen , Xiao Zhang , Teng Shi , Changshuo Zhang , Guofu Xie , Jun Xu

In contrast with standard classification tasks, strategic classification involves agents strategically modifying their features in an effort to receive favorable predictions. For instance, given a classifier determining loan approval based…

Machine Learning · Computer Science 2024-03-01 Lee Cohen , Yishay Mansour , Shay Moran , Han Shao

How do cognitive agents decide what is the relevant information to learn and how goals are selected to gain this knowledge? Cognitive agents need to be motivated to perform any action. We discuss that emotions arise when differences between…

Robotics · Computer Science 2020-07-30 Guido Schillaci , Alejandra Ciria , Bruno Lara

A key objective in artificial intelligence (AI) development is to create systems that match or surpass human creativity. Although current AI models perform well across diverse creative tasks, it remains unclear whether these achievements…

Human-Computer Interaction · Computer Science 2025-04-01 Man Zhang , Ying Li , Yang Peng , Yijia Sun , Wenxin Guo , Huiqing Hu , Shi Chen , Qingbai Zhao