相关论文: Human-to-AI Coach: Improving Human Inputs to AI Sy…

Human-Computer Interaction has been shown to lead to improvements in machine learning systems by boosting model performance, accelerating learning and building user confidence. In this work, we aim to alleviate the expectation that human…

Data-driven algorithmic matching systems promise to help human decision makers make better matching decisions in a wide variety of high-stakes application domains, such as healthcare and social service provision. However, existing systems…

For an AI's training process to successfully impart a desired goal, it is important that the AI does not attempt to resist the training. However, partially learned goals will often incentivize an AI to avoid further goal updates, as most…

When working with generative artificial intelligence (AI), users may see productivity gains, but the AI-generated content may not match their preferences exactly. To study this effect, we introduce a Bayesian framework in which…

AI agents are continually optimized for tasks related to human work, such as software engineering and professional writing, signaling a pressing trend with significant impacts on the human workforce. However, these agent developments have…

Deepfake detection is widely framed as a machine learning problem, yet how humans and AI detectors compare under realistic conditions remains poorly understood. We evaluate 200 human participants and 95 state-of-the-art AI detectors across…

In decision support applications of AI, the AI algorithm's output is framed as a suggestion to a human user. The user may ignore this advice or take it into consideration to modify their decision. With the increasing prevalence of such…

Automated scoring (AS) systems used in large-scale assessment have traditionally used small statistical models that require a large quantity of hand-scored data to make accurate predictions, which can be time-consuming and costly.…

Human intelligence, the most evident and accessible form of source of reasoning, hosted by biological hardware, has evolved and been refined over thousands of years, positioning itself today to create new artificial forms and preparing to…

Artificial intelligence (AI) systems are increasingly used for providing advice to facilitate human decision making in a wide range of domains, such as healthcare, criminal justice, and finance. Motivated by limitations of the current…

In recent years, the utilization of Artificial Intelligence (AI) in the contact center industry is on the rise. One area where AI can have a significant impact is in the coaching of contact center agents. By analyzing call transcripts using…

Human feedback is commonly utilized to finetune AI assistants. But human feedback may also encourage model responses that match user beliefs over truthful ones, a behaviour known as sycophancy. We investigate the prevalence of sycophancy in…

When machine predictors can achieve higher performance than the human decision-makers they support, improving the performance of human decision-makers is often conflated with improving machine accuracy. Here we propose a framework to…

AI systems are increasingly applied to complex tasks that involve interaction with humans. During training, such systems are potentially dangerous, as they haven't yet learned to avoid actions that could cause serious harm. How can an AI…

Assistive agents should make humans' lives easier. Classically, such assistance is studied through the lens of inverse reinforcement learning, where an assistive agent (e.g., a chatbot, a robot) infers a human's intention and then selects…

AI predictive systems are increasingly embedded in decision making pipelines, shaping high stakes choices once made solely by humans. Yet robust decisions under uncertainty still rely on capabilities that current AI lacks: domain knowledge…

Today, most large-scale conversational AI agents (e.g. Alexa, Siri, or Google Assistant) are built using manually annotated data to train the different components of the system. Typically, the accuracy of the ML models in these components…

As environments involving both robots and humans become increasingly common, so does the need to account for people during planning. To plan effectively, robots must be able to respond to and sometimes influence what humans do. This…

This paper argues that a range of current AI systems have learned how to deceive humans. We define deception as the systematic inducement of false beliefs in the pursuit of some outcome other than the truth. We first survey empirical…

Artificial intelligence (AI) is transforming education, offering unprecedented opportunities to personalize learning, enhance assessment, and support educators. Yet these opportunities also introduce risks related to equity, privacy, and…