English
Related papers

Related papers: The Hot Mess of AI: How Does Misalignment Scale Wi…

200 papers

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

We study \emph{Human Projection} (HP): people's tendency to evaluate AI using the same frameworks they use for humans -- treating features such as task difficulty and the reasonableness of mistakes as diagnostic of overall ability. We…

General Economics · Economics 2026-05-12 Bnaya Dreyfuss , Raphaël Raux

Artificial intelligence (AI) systems attempt to imitate human behavior. How well they do this imitation is often used to assess their utility and to attribute human-like (or artificial) intelligence to them. However, most work on AI refers…

Computers and Society · Computer Science 2022-11-24 Vinodkumar Prabhakaran , Rida Qadri , Ben Hutchinson

Although AI has become increasingly smart, its wisdom has not kept pace. In this article, we examine what is known about human wisdom and sketch a vision of its AI counterpart. We analyze human wisdom as a set of strategies for solving…

. It is typically assumed that for the successful use of machine learning algorithms, these algorithms should have a higher accuracy than a human expert. Moreover, if the average accuracy of ML algorithms is lower than that of a human…

Human-Computer Interaction · Computer Science 2024-11-19 Saveli Goldberg , Lev Salnikov , Noor Kaiser , Tushar Srivastava , Eugene Pinsky

As AI technologies increase in capability and ubiquity, AI accidents are becoming more common. Based on normal accident theory, high reliability theory, and open systems theory, we create a framework for understanding the risks associated…

Computers and Society · Computer Science 2024-03-13 Heather M. Williams , Roman V. Yampolskiy

AI alignment research aims to develop techniques to ensure that AI systems do not cause harm. However, every alignment technique has failure modes, which are conditions in which there is a non-negligible chance that the technique fails to…

Artificial Intelligence · Computer Science 2025-10-14 Leonard Dung , Florian Mai

Assured AI in unrestricted settings is a critical problem. Our framework addresses AI assurance challenges lying at the intersection of domain adaptation, fairness, and counterfactuals analysis, operating via the discovery and intervention…

Machine Learning · Computer Science 2021-11-19 William Paul , Philippe Burlina

The understanding of bias in AI is currently undergoing a revolution. Initially understood as errors or flaws, biases are increasingly recognized as integral to AI systems and sometimes preferable to less biased alternatives. In this paper,…

Computers and Society · Computer Science 2025-03-11 Gabriella Waters , Phillip Honenberger

AI systems are often used to make or contribute to important decisions in a growing range of applications, including criminal justice, hiring, and medicine. Since these decisions impact human lives, it is important that the AI systems act…

Artificial Intelligence · Computer Science 2021-03-16 Duncan C McElfresh , Lok Chan , Kenzie Doyle , Walter Sinnott-Armstrong , Vincent Conitzer , Jana Schaich Borg , John P Dickerson

We have witnessed superhuman intelligence thanks to the fast development of large language models and multimodal language models. As the application of such superhuman models becomes more and more popular, a critical question arises here:…

Computation and Language · Computer Science 2024-12-24 Minlie Huang , Yingkang Wang , Shiyao Cui , Pei Ke , Jie Tang

A significant element of human cooperative intelligence lies in our ability to identify opportunities for fruitful collaboration; and conversely to recognise when the task at hand is better pursued alone. Research on flexible cooperation in…

Multiagent Systems · Computer Science 2026-03-10 Max Taylor-Davies , Neil Bramley , Christopher G. Lucas

As autonomous AI agents are increasingly deployed in high-stakes environments, ensuring their safety and alignment with human values is becoming a practical deployment concern. Current benchmarks for AI agents primarily evaluate refusal of…

Artificial Intelligence · Computer Science 2026-05-12 Miles Q. Li , Benjamin C. M. Fung , Martin Weiss , Pulei Xiong , Khalil Al-Hussaeni , Claude Fachkha

In decision making tasks under uncertainty, humans display characteristic biases in seeking, integrating, and acting upon information relevant to the task. Here, we reexamine data from previous carefully designed experiments, collected at…

Artificial Intelligence · Computer Science 2021-02-05 Soumya Chatterjee , Pradeep Shenoy

Highly capable AI systems could secretly pursue misaligned goals -- what we call "scheming". Because a scheming AI would deliberately try to hide its misaligned goals and actions, measuring and mitigating scheming requires different…

Active automata learning (AAL) algorithms can learn a behavioral model of a system from interacting with it. The primary challenge remains scaling to larger models, in particular in the presence of many possible inputs to the system. Modern…

Machine Learning · Computer Science 2026-02-26 Loes Kruger , Sebastian Junges , Jurriaan Rot

Models trained on different datasets can be merged by a weighted-averaging of their parameters, but why does it work and when can it fail? Here, we connect the inaccuracy of weighted-averaging to mismatches in the gradients and propose a…

Machine Learning · Computer Science 2024-08-26 Nico Daheim , Thomas Möllenhoff , Edoardo Maria Ponti , Iryna Gurevych , Mohammad Emtiyaz Khan

Recent human-computer interaction (HCI) research has revealed a widespread misalignment between how developers design workplace artificial intelligence (AI) systems, and what workers actually need from them. Yet, little research has…

Human-Computer Interaction · Computer Science 2026-05-21 Julia De Miguel Velázquez , Sanja Šćepanović , Andrés Gvirtz , Daniele Quercia

Recent work has advocated for training AI models on ever-larger datasets, arguing that as the size of a dataset increases, the performance of a model trained on that dataset will correspondingly increase (referred to as "scaling laws"). In…

Machine Learning · Computer Science 2024-07-30 Fernando Diaz , Michael Madaio

Work on scaling laws has found that large language models (LMs) show predictable improvements to overall loss with increased scale (model size, training data, and compute). Here, we present evidence for the claim that LMs may show inverse…

‹ Prev 1 3 4 5 6 7 10 Next ›