Related papers: Corrigibility Transformation: Constructing Goals T…
AI-enabled capabilities are reaching the requisite level of maturity to be deployed in the real world, yet do not always make correct or safe decisions. One way of addressing these concerns is to leverage AI control systems alongside and in…
Deceptive agents are a challenge for the safety, trustworthiness, and cooperation of AI systems. We focus on the problem that agents might deceive in order to achieve their goals (for instance, in our experiments with language models, the…
Collaborative learning techniques have the potential to enable training machine learning models that are superior to models trained on a single entity's data. However, in many cases, potential participants in such collaborative schemes are…
Achievement goals are frequently used to support behavior change. However, they are often not specifically designed for this purpose nor account for the degree to which a user is already intending to perform the target behavior. In this…
Machine-learning models demand periodic updates to improve their average accuracy, exploiting novel architectures and additional data. However, a newly updated model may commit mistakes the previous model did not make. Such…
This paper studies AI persuasion by distinguishing between two reasons for disagreement: attention differences, where the AI detects features the decision-maker missed, and comprehension differences, where the AI and the decision-maker…
The rapid uptake of generative artificial intelligence (AI) in higher education is reshaping assessment practices and intensifying concerns around academic integrity, fairness, and learning quality. While institutional responses…
Online learning algorithms are designed to learn even when their input is generated by an adversary. The widely-accepted formal definition of an online algorithm's ability to learn is the game-theoretic notion of regret. We argue that the…
Generative AI systems such as ChatGPT have a disruptive effect on learning and assessment. Computer science requires practice to develop skills in problem solving and programming that are traditionally developed using assignments.…
Many meta-learning algorithms can be formulated into an interleaved process, in the sense that task-specific predictors are learned during inner-task adaptation and meta-parameters are updated during meta-update. The normal meta-training…
One strategy in response to pluralistic values in a user population is to personalize an AI system: if the AI can adapt to the specific values of each individual, then we can potentially avoid many of the challenges of pluralism.…
AI systems can take harmful actions and are highly vulnerable to adversarial attacks. We present an approach, inspired by recent advances in representation engineering, that interrupts the models as they respond with harmful outputs with…
With AI systems becoming more powerful and pervasive, there is increasing debate about keeping their actions aligned with the broader goals and needs of humanity. This multi-disciplinary and multi-stakeholder debate must resolve many…
Generative AI is directional: it performs well in some task directions and poorly in others. Knowledge work is directional and endogenous as well: workers can satisfy the same job requirements with different mixes of tasks. We develop a…
Generative AI has the potential to help teachers rapidly create classroom-ready visual materials, particularly in mathematics where diagrams and visual representations must be pedagogically meaningful and instructionally correct. However,…
Reinforcement learning faces significant challenges when applied to tasks characterized by sparse reward structures. Although imitation learning, within the domain of supervised learning, offers faster convergence, it relies heavily on…
It has become commonplace to assert that autonomous agents will have to be built to follow human rules of behavior--social norms and laws. But human laws and norms are complex and culturally varied systems, in many cases agents will have to…
In AI research and practice, rigor remains largely understood in terms of methodological rigor -- such as whether mathematical, statistical, or computational methods are correctly applied. We argue that this narrow conception of rigor has…
Explainable AI provides insight into the "why" for model predictions, offering potential for users to better understand and trust a model, and to recognize and correct AI predictions that are incorrect. Prior research on human and…
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…