中文
相关论文

相关论文: Aligned with Whom? Direct and social goals for AI …

200 篇论文

As LLM-based systems increasingly operate as agents embedded within human social and technical systems, alignment can no longer be treated as a property of an isolated model, but must be understood in relation to the environments in which…

Aligning AI systems with organizational decision-making is typically framed as a single-target problem: make the model behave like the organization. We argue this framing obscures a deeper pluralistic challenge. We rely on a decision-policy…

人工智能 · 计算机科学 2026-05-26 Niklas Weller , Emilio Barkett

The critical inquiry pervading the realm of Philosophy, and perhaps extending its influence across all Humanities disciplines, revolves around the intricacies of morality and normativity. Surprisingly, in recent years, this thematic thread…

人工智能 · 计算机科学 2024-06-19 Nicholas Kluge Corrêa

Recent advances in AI -- including generative approaches -- have resulted in technology that can support humans in scientific discovery and forming decisions, but may also disrupt democracies and target individuals. The responsible use of…

In coming years or decades, artificial general intelligence (AGI) may surpass human capabilities across many critical domains. We argue that, without substantial effort to prevent it, AGIs could learn to pursue goals that are in conflict…

人工智能 · 计算机科学 2025-05-06 Richard Ngo , Lawrence Chan , Sören Mindermann

Modern AI assistants are trained to follow instructions, implicitly assuming that users can clearly articulate their goals and the kind of assistance they need. Decades of behavioral research, however, show that people often engage with AI…

人工智能 · 计算机科学 2026-04-24 Nathanael Jo , Zoe De Simone , Mitchell Gordon , Ashia Wilson

AI alignment research is the field of study dedicated to ensuring that artificial intelligence (AI) benefits humans. As machine intelligence gets more advanced, this research is becoming increasingly important. Researchers in the field…

计算机与社会 · 计算机科学 2022-06-08 Jan H. Kirchner , Logan Smith , Jacques Thibodeau , Kyle McDonell , Laria Reynolds

As artificial intelligence (AI) becomes deeply integrated into critical infrastructures and everyday life, ensuring its safe deployment is one of humanity's most urgent challenges. Current AI models prioritize task optimization over safety,…

人工智能 · 计算机科学 2024-11-08 Joshua T. S. Hewson

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…

人工智能 · 计算机科学 2025-10-14 Leonard Dung , Florian Mai

Large language model-based AI companions are increasingly viewed by users as friends or romantic partners, leading to deep emotional bonds. However, they can generate biased, discriminatory, and harmful outputs. Recently, users are taking…

人机交互 · 计算机科学 2025-02-14 Xianzhe Fan , Qing Xiao , Xuhui Zhou , Jiaxin Pei , Maarten Sap , Zhicong Lu , Hong Shen

In the current era, people and society have grown increasingly reliant on artificial intelligence (AI) technologies. AI has the potential to drive us towards a future in which all of humanity flourishes. It also comes with substantial risks…

计算机与社会 · 计算机科学 2021-08-24 Lu Cheng , Kush R. Varshney , Huan Liu

The field of AI alignment is concerned with AI systems that pursue unintended goals. One commonly studied mechanism by which an unintended goal might arise is specification gaming, in which the designer-provided specification is flawed in a…

机器学习 · 计算机科学 2022-11-03 Rohin Shah , Vikrant Varma , Ramana Kumar , Mary Phuong , Victoria Krakovna , Jonathan Uesato , Zac Kenton

A leading proposal for aligning artificial superintelligence (ASI) is to use AI agents to automate an increasing fraction of alignment research as capabilities improve. We argue that, even when research agents are not scheming to…

人工智能 · 计算机科学 2026-05-18 Aleksandr Bowkis , Marie Davidsen Buhl , Jacob Pfau , Geoffrey Irving

Artificial General Intelligence (AGI) is increasingly being discussed not only as a tool, but also as a potential subject with personal and therefore moral status. In our opinion, the currently dominant alignment strategies, which focus on…

人工智能 · 计算机科学 2026-04-17 Till Mossakowski , Helena Esther Grass

The issues of AI risk and AI safety are becoming critical as the prospect of artificial general intelligence (AGI) looms larger. The emergence of extremely large and capable generative models has led to alarming predictions and created a…

人工智能 · 计算机科学 2025-05-20 Ali A. Minai

As AI agents increasingly operate in multi-agent environments, understanding their collective behavior becomes critical for predicting the dynamics of artificial societies. This study examines conformity, the tendency to align with group…

人工智能 · 计算机科学 2026-01-12 Alessandro Bellina , Giordano De Marzo , David Garcia

With increasing digitalization, Artificial Intelligence (AI) is becoming ubiquitous. AI-based systems to identify, optimize, automate, and scale solutions to complex economic and societal problems are being proposed and implemented. This…

Research on human self-regulation has shown that people hold many goals simultaneously and have complex self-regulation mechanisms to deal with this goal conflict. Artificial autonomous systems may also need to find ways to cope with…

人工智能 · 计算机科学 2017-03-21 Mark Muraven

As the real-world impact of Artificial Intelligence (AI) systems has been steadily growing, so too have these systems come under increasing scrutiny. In response, the study of AI fairness has rapidly developed into a rich field of research…

计算机与社会 · 计算机科学 2023-09-19 Maarten Buyl , Tijl De Bie

With the widespread and pervasive use of Artificial Intelligence (AI) for automated decision-making systems, AI bias is becoming more apparent and problematic. One of its negative consequences is discrimination: the unfair, or unequal…

计算机与社会 · 计算机科学 2021-06-07 Xavier Ferrer , Tom van Nuenen , Jose M. Such , Mark Coté , Natalia Criado