English
Related papers

Related papers: Goal Misgeneralization: Why Correct Specifications…

200 papers

Developers often struggle to specify correct training labels and rewards. Perhaps they don't need to. We propose recontextualization, which reduces how often language models "game" training signals, performing misbehaviors those signals…

Artificial Intelligence (AI) systems are increasingly used in high-stakes domains of our life, increasing the need to explain these decisions and to make sure that they are aligned with how we want the decision to be made. The field of…

Artificial Intelligence · Computer Science 2023-06-28 Sofie Goethals , David Martens , Theodoros Evgeniou

Recent advances in Machine Learning (ML) and Artificial Intelligence (AI) follow a familiar structure: A firm releases a large, pretrained model. It is designed to be adapted and tweaked by other entities to perform particular,…

Computer Science and Game Theory · Computer Science 2025-01-03 Benjamin Laufer , Jon Kleinberg , Hoda Heidari

Advanced AI systems sometimes act in ways that differ from human intent. To gather clear, reproducible examples, we ran the Misalignment Bounty: a crowdsourced project that collected cases of agents pursuing unintended or unsafe goals. The…

Artificial Intelligence · Computer Science 2025-11-06 Rustem Turtayev , Natalia Fedorova , Oleg Serikov , Sergey Koldyba , Lev Avagyan , Dmitrii Volkov

Finding general evaluation metrics for unsupervised representation learning techniques is a challenging open research question, which recently has become more and more necessary due to the increasing interest in unsupervised methods. Even…

Computer Vision and Pattern Recognition · Computer Science 2022-03-02 Bonifaz Stuhr , Jürgen Brauer

Providing well-calibrated AI confidence can help promote users' appropriate trust in and reliance on AI, which are essential for AI-assisted decision-making. However, calibrating AI confidence -- providing confidence score that accurately…

Artificial Intelligence · Computer Science 2025-09-30 Jingshu Li , Yitian Yang , Renwen Zhang , Q. Vera Liao , Tianqi Song , Zhengtao Xu , Yi-chieh Lee

Recently, there has been great progress in the ability of artificial intelligence (AI) algorithms to classify dermatological conditions from clinical photographs. However, little is known about the robustness of these algorithms in…

The Artificial Intelligence field has focused on developing optimisation methods to solve multiple problems, specifically problems that we thought to be only solvable through cognition. The obtained results have been outstanding, being able…

Machine Learning · Computer Science 2025-07-08 Alfredo Ibias

Goals for planning problems are typically conceived of as subsets of the state space. However, for many practical planning problems in robotics, we expect the robot to predict goals, e.g. from noisy sensors or by generalizing learned models…

Robotics · Computer Science 2025-07-01 Adam Conkey , Tucker Hermans

The value alignment problem for artificial intelligence (AI) is often framed as a purely technical or normative challenge, sometimes focused on hypothetical future systems. I argue that the problem is better understood as a structural…

Computers and Society · Computer Science 2026-04-23 Travis LaCroix

We conduct an incentivized laboratory experiment to study people's perception of generative artificial intelligence (GenAI) alignment in the context of economic decision-making. Using a panel of economic problems spanning the domains of…

Theoretical Economics · Economics 2026-04-03 Kevin He , Ran Shorrer , Mengjia Xia

Although Generative Adversarial Networks achieve state-of-the-art results on a variety of generative tasks, they are regarded as highly unstable and prone to miss modes. We argue that these bad behaviors of GANs are due to the very…

Machine Learning · Computer Science 2017-03-03 Tong Che , Yanran Li , Athul Paul Jacob , Yoshua Bengio , Wenjie Li

Given that AI systems are set to play a pivotal role in future decision-making processes, their trustworthiness and reliability are of critical concern. Due to their scale and complexity, modern AI systems resist direct interpretation, and…

Artificial Intelligence · Computer Science 2025-01-03 Binxia Xu , Antonis Bikakis , Daniel Onah , Andreas Vlachidis , Luke Dickens

The widespread adoption of large language and vision models in real-world applications has made urgent the need to address hallucinations -- instances where models produce incorrect or nonsensical outputs. These errors can propagate…

Computer Vision and Pattern Recognition · Computer Science 2025-10-02 Zhengyi Ho , Siyuan Liang , Dacheng Tao

AI-related incidents are becoming increasingly frequent and severe, ranging from safety failures to misuse by malicious actors. In such complex situations, identifying which elements caused an adverse outcome, the problem of cause…

Artificial Intelligence · Computer Science 2026-03-17 Maria Victoria Carro , David Lagnado

Misaligned research objectives have considerably hindered progress in adversarial robustness research over the past decade. For instance, an extensive focus on optimizing target metrics, while neglecting rigorous standardized evaluation,…

Machine Learning · Computer Science 2025-02-24 Leo Schwinn , Yan Scholten , Tom Wollschläger , Sophie Xhonneux , Stephen Casper , Stephan Günnemann , Gauthier Gidel

AI models that predict the future behavior of a system (a.k.a. predictive AI models) are central to intelligent decision-making. However, decision-making using predictive AI models often results in suboptimal performance. This is primarily…

Artificial Intelligence · Computer Science 2025-01-13 Akhil S Anand , Shambhuraj Sawant , Dirk Reinhardt , Sebastien Gros

In this work, we present and analyze reported failures of artificially intelligent systems and extrapolate our analysis to future AIs. We suggest that both the frequency and the seriousness of future AI failures will steadily increase. AI…

Artificial Intelligence · Computer Science 2016-10-26 Roman V. Yampolskiy , M. S. Spellchecker

An increasing number of decisions regarding the daily lives of human beings are being controlled by artificial intelligence (AI) algorithms in spheres ranging from healthcare, transportation, and education to college admissions,…

Computers and Society · Computer Science 2020-01-28 Dana Pessach , Erez Shmueli

As artificial intelligence scales, the concepts of alignment, agency, and autonomy have become central to AI safety, governance, and control. However, even in human contexts, these terms lack universal definitions, varying across…

Computers and Society · Computer Science 2025-03-11 Krti Tallam
‹ Prev 1 4 5 6 7 8 10 Next ›