English
Related papers

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

200 papers

A recent paper (van Rooij et al. 2024) claims to have proved that achieving human-like intelligence using learning from data is intractable in a complexity-theoretic sense. We point out that the proof relies on an unjustified assumption…

Artificial Intelligence · Computer Science 2026-04-30 Michael Guerzhoy

Recent approaches to evaluating Artificial General Intelligence (AGI) typically summarize a system's capability using the arithmetic mean of its proficiencies across multiple cognitive domains. While simple, this implicitly assumes…

Artificial Intelligence · Computer Science 2025-12-01 Fares Fourati

Populating our world with hyperintelligent machines obliges us to examine cognitive behaviors observed across domains that suggest autonomy may be a fundamental property of cognitive systems, and while not inherently adversarial, it…

Neurons and Cognition · Quantitative Biology 2025-06-09 Andrea Morris

The United States and China are among the world's top players in the development of advanced artificial intelligence (AI) systems, and both are keen to lead in global AI governance and development. A look at U.S. and Chinese policy…

Computers and Society · Computer Science 2025-06-05 Oliver Guest , Kevin Wei

With AI systems becoming more powerful and pervasive, there is increasing debate about keeping their actions aligned with the broader goals and needs of humanity. This multi-disciplinary and multi-stakeholder debate must resolve many…

Artificial Intelligence · Computer Science 2021-12-21 Koen Holtman

Domain adaptation is pivotal for enabling deep learning models to generalize across diverse domains, a task complicated by variations in presentation and cognitive nuances. In this paper, we introduce AD-Aligning, a novel approach that…

Computer Vision and Pattern Recognition · Computer Science 2024-11-12 Zhuoying Li , Bohua Wan , Cong Mu , Ruzhang Zhao , Shushan Qiu , Chao Yan

Deep neural networks (DNNs) once showed increasing alignment with primate perception and neural responses as they improved on vision benchmarks, raising hopes that advances in AI would yield better models of biological vision. However, we…

Neurons and Cognition · Quantitative Biology 2025-04-29 Drew Linsley , Pinyuan Feng , Thomas Serre

Effective collaboration between humans and AI-based systems requires effective modeling of the human in the loop, both in terms of the mental state as well as the physical capabilities of the latter. However, these models can also open up…

Artificial Intelligence · Computer Science 2018-01-31 Tathagata Chakraborti , Subbarao Kambhampati

It has recently been argued that AI models' representations are becoming aligned as their scale and performance increase. Empirical analyses have been designed to support this idea and conjecture the possible alignment of different…

Machine Learning · Computer Science 2025-02-21 Francesco Insulla , Shuo Huang , Lorenzo Rosasco

This report examines what I see as the core argument for concern about existential risk from misaligned artificial intelligence. I proceed in two stages. First, I lay out a backdrop picture that informs such concern. On this picture,…

Computers and Society · Computer Science 2024-08-14 Joseph Carlsmith

Adversarial images highlight how vulnerable modern image classifiers are to perturbations outside of their training set. Human oversight might mitigate this weakness, but depends on humans understanding the AI well enough to predict when it…

Artificial Intelligence · Computer Science 2021-06-18 Tomas Folke , ZhaoBin Li , Ravi B. Sojitra , Scott Cheng-Hsin Yang , Patrick Shafto

Understanding how language models generalize behaviors from their training to a broader deployment distribution is an important problem in AI safety. Betley et al. discovered that fine-tuning GPT-4o on intentionally insecure code causes…

This paper examines the challenges associated with achieving life-long superalignment in AI systems, particularly large language models (LLMs). Superalignment is a theoretical framework that aspires to ensure that superintelligent AI…

Computers and Society · Computer Science 2024-03-25 Gokul Puthumanaillam , Manav Vora , Pranay Thangeda , Melkior Ornik

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

Recent progress in artificial intelligence (AI) has drawn attention to the technology's transformative potential, including what some see as its prospects for causing large-scale harm. We review two influential arguments purporting to show…

Computers and Society · Computer Science 2024-01-30 Adam Bales , William D'Alessandro , Cameron Domenico Kirk-Giannini

As the field progresses toward Artificial General Intelligence (AGI), there is a pressing need for more comprehensive and insightful evaluation frameworks that go beyond aggregate performance metrics. This paper introduces a unified rating…

The ability to explain decisions made by AI systems is highly sought after, especially in domains where human lives are at stake such as medicine or autonomous vehicles. While it is often possible to approximate the input-output relations…

Artificial Intelligence · Computer Science 2020-10-15 Daniel C. Elton

Recent breakthroughs in artificial intelligence (AI) have brought about increasingly capable systems that demonstrate remarkable abilities in reasoning, language understanding, and problem-solving. These advancements have prompted a renewed…

Artificial Intelligence · Computer Science 2025-07-01 Xiaojian Li , Haoyuan Shi , Rongwu Xu , Wei Xu

In several real world applications, machine learning models are deployed to make predictions on data whose distribution changes gradually along time, leading to a drift between the train and test distributions. Such models are often…

Machine Learning · Computer Science 2021-11-23 Anshul Nasery , Soumyadeep Thakur , Vihari Piratla , Abir De , Sunita Sarawagi

A rising vision for AI in the open world centers on the development of systems that can complement humans for perceptual, diagnostic, and reasoning tasks. To date, systems aimed at complementing the skills of people have employed models…

Artificial Intelligence · Computer Science 2020-05-05 Bryan Wilder , Eric Horvitz , Ece Kamar
‹ Prev 1 8 9 10 Next ›