Related papers: The Alignment Problem from a Deep Learning Perspec…
We explore the AI2050 "hard problems" that block the promise of AI and cause AI risks: (1) developing general capabilities of the systems; (2) assuring the performance of AI systems and their training processes; (3) aligning system goals…
Human Intelligence (HI) excels at combining basic skills to solve complex tasks. This capability is vital for Artificial Intelligence (AI) and should be embedded in comprehensive AI Agents, enabling them to harness expert models for complex…
Artificial Intelligence (AI) has apparently become one of the most important techniques discovered by humans in history while the human brain is widely recognized as one of the most complex systems in the universe. One fundamental critical…
Recent advances in AI raise the possibility that AI systems will one day be able to do anything humans can do, only better. If artificial general intelligence (AGI) is achieved, AI systems may be able to understand, reason, problem solve,…
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…
Multimodal Large Language Models (MLLMs) are widely regarded as crucial in the exploration of Artificial General Intelligence (AGI). The core of MLLMs lies in their capability to achieve cross-modal alignment. To attain this goal, current…
The project of aligning machine behavior with human values raises a basic problem: whose moral expectations should guide AI decision-making? Much alignment research assumes that the appropriate benchmark is how humans themselves would act…
In AI alignment, extensive latitude must be granted to annotators, either human or algorithmic, to judge which model outputs are `better' or `safer.' We refer to this latitude as alignment discretion. Such discretion remains largely…
Generative adversarial networks (GANs) are a novel approach to generative modelling, a task whose goal it is to learn a distribution of real data points. They have often proved difficult to train: GANs are unlike many techniques in machine…
Deep Generative AI has been a long-standing essential topic in the machine learning community, which can impact a number of application areas like text generation and computer vision. The major paradigm to train a generative model is…
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…
Recent advances in AI research make it increasingly plausible that artificial agents with consequential real-world impact will soon operate beyond tightly controlled environments. Ensuring that these agents are not only safe but that they…
This paper introduces a new metamodel-based knowledge representation that significantly improves autonomous learning and adaptation. While interest in hybrid machine learning / symbolic AI systems leveraging, for example, reasoning and…
Artificial General Intelligence (AGI), widely regarded as the fundamental goal of artificial intelligence, represents the realization of cognitive capabilities that enable the handling of general tasks with human-like proficiency.…
The field of artificial intelligence (AI) is devoted to the creation of artificial decision-makers that can perform (at least) on par with the human counterparts on a domain of interest. Unlike the agents in traditional AI, the agents in…
Discussion of AI alignment (alignment between humans and AI systems) has focused on value alignment, broadly referring to creating AI systems that share human values. We argue that before we can even attempt to align values, it is…
Beneficial societal outcomes cannot be guaranteed by aligning individual AI systems with the intentions of their operators or users. Even an AI system that is perfectly aligned to the intentions of its operating organization can lead to bad…
Artificial Intelligence has the potential to exacerbate societal bias and set back decades of advances in equal rights and civil liberty. Data used to train machine learning algorithms may capture social injustices, inequality or…
The rapid advancement of artificial intelligence systems has brought the challenge of AI alignment to the forefront of research, particularly in complex decision-making and task execution. As these systems surpass human-level performance in…
Big models have achieved revolutionary breakthroughs in the field of AI, but they might also pose potential concerns. Addressing such concerns, alignment technologies were introduced to make these models conform to human preferences and…