CIS

ABSTRACT: “Does generative AI infringe copyright?” is an urgent question. It is also a difficult question, for two reasons. First, “generative AI” is not just one product from one company. It is a catch-all name for a massive ecosystem of loosely related technologies. These systems behave differently and raise different legal issues. Second, copyright law […]

ABSTRACT:  Algorithm audits are powerful tools for studying black-box systems without direct knowledge of those systems’ inner workings. While they have been effectively deployed to identify harms and biases in algorithmic content, algorithm audits’ narrow focus on technical components stop short of considering users themselves as integral and dynamic parts of the system, to be […]

ABSTRACT:  Shapley values and similar methods are widely used to explain the importance of features in model predictions. Clarity in the semantics of these feature importances is subtle, but crucial: What do these explanations actually mean? And how are they useful? We illustrate using explanations of predictions in three domains: (a) medical outcomes, (b) image […]

ABSTRACT: As deep learning systems improve, their applicability to critical domains is hampered because of a lack of transparency. Post-hoc explanations attempt to address this concern but they provide no guarantee of faithfulness to the model’s computations. Inherently interpretable models are an alternative but such models are often considered to be too simple to perform […]