Get started
Keyword

AI alignment

Description: AI alignment is the research area concerned with designing artificial intelligence systems whose behavior accords with human goals, preferences, and ethical principles.
Wikidata ID: wiki/Q24882728
OpenAlex ID: keywords/ai-alignment
BNAI, NO-TOKEN, and MIND-UNITY: Pillars of a Systemic Revolution in Artificial Intelligence
2022 · Wei, Jason, Wang, Xuezhi, et al. · arXiv (Cornell University) · 4,203
PDF
Artificial Intelligence, Values, and Alignment
2020 · Iason Gabriel · Minds and Machines · 876
PDF
Research Priorities for Robust and Beneficial Artificial Intelligence
2015 · Stuart Russell, Daniel Dewey, et al. · AI Magazine · 637
PDF
Direct Preference Optimization: Your Language Model is Secretly a Reward Model
2023 · Rafailov, Rafael, Sharma, Archit, et al. · arXiv (Cornell University) · 293
PDF
Artificial Intelligence
2020 · Stuart Russell · 285
The Superintelligent Will: Motivation and Instrumental Rationality in Advanced Artificial Agents
2012 · Nick Bostrom · Minds and Machines · 254
User Experience Design Professionals’ Perceptions of Generative Artificial Intelligence
2024 · Jie Li, Hancheng Cao, et al. · CHI Conference on Human Factors in Computing Systems · 167
PDF
Aligning AI With Shared Human Values
2020 · Hendrycks, Dan, Burns, Collin, et al. · arXiv (Cornell University) · 166
PDF
Visual Adversarial Examples Jailbreak Aligned Large Language Models
2024 · Xiangyu Qi, Kaixuan Huang, et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 148
PDF
Thinking Inside the Box: Controlling and Using an Oracle AI
2012 · Stuart Armstrong, Anders Sandberg, et al. · Minds and Machines · 144
Mapping the Ethics of Generative AI: A Comprehensive Scoping Review
2024 · Thilo Hagendorff · Minds and Machines · 137
PDF
Human/AI relationships: challenges, downsides, and impacts on human/human relationships
2023 · Anne Zimmerman, Joel Janhonen, et al. · AI and Ethics · 124
Accelerating the integration of ChatGPT and other large‐scale AI models into biomedical research and healthcare
2023 · Ding‐Qiao Wang, Long‐Yu Feng, et al. · MedComm – Future Medicine · 121
PDF
Responses to catastrophic AGI risk: a survey
2014 · Kaj Sotala, Roman V Yampolskiy · Physica Scripta · 120
PDF
Classification of global catastrophic risks connected with artificial intelligence
2018 · Alexey Turchin, David Denkenberger · AI & Society · 112
Human-aligned artificial intelligence is a multiobjective problem
2017 · Peter Vamplew, Richard Dazeley, et al. · Ethics and Information Technology · 112
PDF
On the Promotion of Safe and Socially Beneficial Artificial Intelligence
2016 · Seth D. Baum · AI & Society · 112
Deception abilities emerged in large language models
2024 · Thilo Hagendorff · Proceedings of the National Academy of Sciences · 97
Human-Compatible Artificial Intelligence
2021 · Stuart Russell · Oxford University Press eBooks · 95
Sycophancy in Large Language Models: Causes and Mitigations
2025 · Lars Malmqvist · Lecture notes in networks and systems · 94
PDF
Open Problems in Cooperative AI
2020 · Dafoe, Allan, Hughes, Edward, et al. · arXiv (Cornell University) · 93
PDF
AI Alignment: A Comprehensive Survey
2023 · Ji, Jiaming, Qiu, Tianyi, et al. · arXiv (Cornell University) · 86
PDF
How do we assess the trustworthiness of AI? Introducing the trustworthiness assessment model (TrAM)
2025 · Nadine Schlicker, Kevin Baum, et al. · Computers in Human Behavior · 79
Emergent social conventions and collective bias in LLM populations
2025 · Ariel Flint Ashery, Luca Maria Aiello, et al. · Science Advances · 78
Preference Ranking Optimization for Human Alignment
2024 · Feifan Song, Bowen Yu, et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 77
PDF
Works count: 6,608
Citation count: 15,080
Year
Topic
Type