English
Related papers

Related papers: The Alignment Problem from a Deep Learning Perspec…

200 papers

It's widely expected that humanity will someday create AI systems vastly more intelligent than us, leading to the unsolved alignment problem of "how to control superintelligence." However, this commonly expressed problem is not only…

Artificial Intelligence · Computer Science 2024-12-02 James M. Mazzu

We stress-tested 16 leading models from multiple developers in hypothetical corporate environments to identify potentially risky agentic behaviors before they cause real harm. In the scenarios, we allowed models to autonomously send emails…

Cryptography and Security · Computer Science 2025-10-17 Aengus Lynch , Benjamin Wright , Caleb Larson , Stuart J. Ritchie , Soren Mindermann , Evan Hubinger , Ethan Perez , Kevin Troy

Recent progress in artificial intelligence (AI) has renewed interest in building systems that learn and think like people. Many advances have come from using deep neural networks trained end-to-end in tasks such as object recognition, video…

Artificial Intelligence · Computer Science 2016-11-03 Brenden M. Lake , Tomer D. Ullman , Joshua B. Tenenbaum , Samuel J. Gershman

Artificial Intelligence (AI) increasingly shows its potential to outperform predicate logic algorithms and human control alike. In automatically deriving a system model, AI algorithms learn relations in data that are not detectable for…

Artificial Intelligence · Computer Science 2022-10-12 Simon Daniel Duque Anton , Daniel Schneider , Hans Dieter Schotten

The overarching problem in artificial intelligence (AI) is that we do not understand the intelligence process well enough to enable the development of adequate computational models. Much work has been done in AI over the years at lower…

Artificial Intelligence · Computer Science 2018-11-16 Paul Yaworsky

Advances in artificial intelligence (AI) have great potential to help address societal challenges that are both collective in nature and present at national or trans-national scale. Pressing challenges in healthcare, finance, infrastructure…

In many real-life settings, algorithms play the role of assistants, while humans ultimately make the final decision. Often, algorithms specifically act as curators, narrowing down a wide range of options into a smaller subset that the human…

Computer Science and Game Theory · Computer Science 2025-11-06 Jiaxin Song , Parnian Shahkar , Kate Donahue , Bhaskar Ray Chaudhury

Recent years have witnessed remarkable progress made in large language models (LLMs). Such advancements, while garnering significant attention, have concurrently elicited various concerns. The potential of these models is undeniably vast;…

Computation and Language · Computer Science 2023-09-27 Tianhao Shen , Renren Jin , Yufei Huang , Chuang Liu , Weilong Dong , Zishan Guo , Xinwei Wu , Yan Liu , Deyi Xiong

Deep learning networks have been trained to recognize speech, caption photographs and translate text between languages at high levels of performance. Although applications of deep learning networks to real world problems have become…

Neurons and Cognition · Quantitative Biology 2020-02-13 Terrence J. Sejnowski

Alignment of artificial intelligence (AI) encompasses the normative problem of specifying how AI systems should act and the technical problem of ensuring AI systems comply with those specifications. To date, AI alignment has generally…

Artificial and biological systems may evolve similar computational solutions despite fundamental differences in architecture and learning mechanisms -- a form of convergent evolution. We demonstrate this phenomenon through large-scale…

Neurons and Cognition · Quantitative Biology 2025-07-04 Guobin Shen , Dongcheng Zhao , Yiting Dong , Qian Zhang , Yi Zeng

Deep neural networks (DNNs) have shown huge superiority over humans in image recognition, speech processing, autonomous vehicles and medical diagnosis. However, recent studies indicate that DNNs are vulnerable to adversarial examples (AEs),…

Machine Learning · Computer Science 2019-09-24 Jiliang Zhang , Chen Li

As AI systems become increasingly capable and influential, ensuring their alignment with human values, preferences, and goals has become a critical research focus. Current alignment methods primarily focus on designing algorithms and loss…

Computation and Language · Computer Science 2025-05-02 Min-Hsuan Yeh , Jeffrey Wang , Xuefeng Du , Seongheon Park , Leitian Tao , Shawn Im , Yixuan Li

Artificial Intelligence has made remarkable advancements in recent years, primarily driven by increasingly large deep learning models. However, achieving true Artificial General Intelligence (AGI) demands fundamentally new architectures…

Artificial Intelligence · Computer Science 2025-04-30 Rajeev Gupta , Suhani Gupta , Ronak Parikh , Divya Gupta , Amir Javaheri , Jairaj Singh Shaktawat

Two core challenges of alignment are 1) scalable oversight and 2) accounting for the dynamic nature of human values. While solutions like recursive reward modeling address 1), they do not simultaneously account for 2). We sketch a roadmap…

Artificial Intelligence · Computer Science 2025-03-19 Florian Mai , David Kaczér , Nicholas Kluge Corrêa , Lucie Flek

Dramatic advances in artificial intelligence over the past decade (for narrow-purpose AI) and the last several years (for general-purpose AI) have transformed AI from a niche academic field to the core business strategy of many of the…

Computers and Society · Computer Science 2025-03-10 Anthony Aguirre

Algorithmic systems, particularly social media recommenders, have achieved remarkable success in predicting behavior. By optimizing for observable signals such as clicks, views, and engagement, these systems effectively capture user…

Computers and Society · Computer Science 2026-04-14 Kristina Lerman

The solution methods used to realize artificial general intelligence (AGI) may not contain the formalism needed to adequately model and characterize AGI. In particular, current approaches to learning hold notions of problem domain and…

Artificial Intelligence · Computer Science 2021-11-30 Tyler Cody

During the evolution of large models, performance evaluation is necessarily performed to assess their capabilities and ensure safety before practical application. However, current model evaluations mainly rely on specific tasks and…

Artificial Intelligence · Computer Science 2024-03-07 Youzhi Qu , Chen Wei , Penghui Du , Wenxin Che , Chi Zhang , Wanli Ouyang , Yatao Bian , Feiyang Xu , Bin Hu , Kai Du , Haiyan Wu , Jia Liu , Quanying Liu

Autonomous Artificial Intelligence (AI) has many benefits. It also has many risks. In this work, we identify the 3 levels of autonomous AI. We are of the position that AI must not be fully autonomous because of the many risks, especially as…

Artificial Intelligence · Computer Science 2025-08-01 Tosin Adewumi , Lama Alkhaled , Florent Imbert , Hui Han , Nudrat Habib , Karl Löwenmark