相关论文: Constitutional AI: Harmlessness from AI Feedback

As Artificial Intelligence (AI) technologies continue to advance, protecting human autonomy and promoting ethical decision-making are essential to fostering trust and accountability. Human agency (the capacity of individuals to make…

When interacting with people, AI agents do not just influence the state of the world -- they also influence the actions people take in response to the agent, and even their underlying intentions and strategies. Accounting for and leveraging…

Model-free reinforcement learning (RL) is inherently a reactive method, operating under the assumption that it starts with no prior knowledge of the system and entirely depends on trial-and-error for learning. This approach faces several…

Safety is an essential component for deploying reinforcement learning (RL) algorithms in real-world scenarios, and is critical during the learning process itself. A natural first approach toward safe RL is to manually specify constraints on…

Residual reinforcement learning (RL) has been proposed as a way to solve challenging robotic tasks by adapting control actions from a conventional feedback controller to maximize a reward signal. We extend the residual formulation to learn…

The use of Artificial Intelligence (AI), or more generally data-driven algorithms, has become ubiquitous in today's society. Yet, in many cases and especially when stakes are high, humans still make final decisions. The critical question,…

Reinforcement Learning from Human Feedback (RLHF) has emerged as a popular paradigm for aligning models with human intent. Typically RLHF algorithms operate in two phases: first, use human preferences to learn a reward function and second,…

The rise of reinforcement learning (RL) in critical real-world applications demands a fundamental rethinking of privacy in AI systems. Traditional privacy frameworks, designed to protect isolated data points, fall short for sequential…

When people receive advice while making difficult decisions, they often make better decisions in the moment and also increase their knowledge in the process. However, such incidental learning can only occur when people cognitively engage…

Efforts furthering the advancement of Artificial Intelligence (AI) will increasingly encompass AI Legal Reasoning (AILR) as a crucial element in the practice of law. It is argued in this research paper that the infusion of AI into existing…

To achieve desirable performance, current AI systems often require huge amounts of training data. This is especially problematic in domains where collecting data is both expensive and time-consuming, e.g., where AI systems require having…

We formalize Prescriptive Artificial Intelligence as a distinct paradigm for human-AI decision collaboration in high-stakes environments. Unlike predictive systems optimized for outcome accuracy, prescriptive systems are designed to…

Artificial intelligence (AI) is increasingly being considered to assist human decision-making in high-stake domains (e.g. health). However, researchers have discussed an issue that humans can over-rely on wrong suggestions of the AI model…

Reinforcement Learning (RL), a subfield of Artificial Intelligence (AI), focuses on training agents to make decisions by interacting with their environment to maximize cumulative rewards. This paper provides an overview of RL, covering its…

AI methods are used in societally important settings, ranging from credit to employment to housing, and it is crucial to provide fairness in regard to algorithmic decision making. Moreover, many settings are dynamic, with populations…

Autonomous AI agents powered by Large Language Models can reason, plan, and execute complex tasks, but their ability to autonomously retrieve information and run code introduces significant security risks. Existing approaches attempt to…

Large Multimodal Models (LMMs) excel at comprehending human instructions and demonstrate remarkable results across a broad spectrum of tasks. Reinforcement Learning from Human Feedback (RLHF) and AI Feedback (RLAIF) further refine LLMs by…

Humans rely more and more on systems with AI components. The AI community typically treats human inputs as a given and optimizes AI models only. This thinking is one-sided and it neglects the fact that humans can learn, too. In this work,…

In offline reinforcement learning (RL) agents are trained using a logged dataset. It appears to be the most natural route to attack real-life applications because in domains such as healthcare and robotics interactions with the environment…

While AI algorithms have shown remarkable success in various fields, their lack of transparency hinders their application to real-life tasks. Although explanations targeted at non-experts are necessary for user trust and human-AI…