相关论文: Dice in the Black Box: User Experiences with an In…

As technology become more advanced, those who design, use and are otherwise affected by it want to know that it will perform correctly, and understand why it does what it does, and how to use it appropriately. In essence they want to be…

What should regulators of complex algorithms regulate? We propose a model of oversight over 'black-box' algorithms used in high-stakes applications such as lending, medical testing, or hiring. In our model, a regulator is limited in how…

Machine learning models are becoming increasingly popular in different types of settings. This is mainly caused by their ability to achieve a level of predictive performance that is hard to match by human experts in this new era of big…

Cybersecurity vendors consistently apply AI (Artificial Intelligence) to their solutions and many cybersecurity domains can benefit from AI technology. However, black-box AI techniques present some difficulties in comprehension and adoption…

With the long term accumulation of high quality educational data, artificial intelligence has shown excellent performance in knowledge tracing. However, due to the lack of interpretability and transparency of some algorithms, this approach…

With dramatic improvements in optimization software, the solution of large-scale problems that seemed intractable decades ago are now a routine task. This puts even more real-world applications into the reach of optimizers. At the same…

Recommender systems are used to provide relevant suggestions on various matters. Although these systems are a classical research topic, knowledge is still limited regarding the public opinion about these systems. Public opinion is also…

Artificial Intelligence systems are rapidly evolving, integrating extrinsic and intrinsic motivations. While these frameworks offer benefits, they risk misalignment at the algorithmic level while appearing superficially aligned with human…

This paper investigates the prospect of developing human-interpretable, explainable artificial intelligence (AI) systems based on active inference and the free energy principle. We first provide a brief overview of active inference, and in…

In this paper, we introduce and evaluate a tool for researchers and practitioners to assess the actionability of information provided to users to support algorithmic recourse. While there are clear benefits of recourse from the user's…

Algorithmic audits are essential tools for examining systems for properties required by regulators or desired by operators. Current audits of large language models (LLMs) primarily rely on black-box evaluations that assess model behavior…

Internet of Things (IoT) devices are typically designed to function in a secure, closed environment, making it difficult for users to comprehend devices' behaviors. This paper shows that a user can leverage side-channel information to…

In recent years, the use of sophisticated statistical models that influence decisions in domains of high societal relevance is on the rise. Although these models can often bring substantial improvements in the accuracy and efficiency of…

Recent work in model-agnostic explanations of black-box machine learning has demonstrated that interpretability of complex models does not have to come at the cost of accuracy or model flexibility. However, it is not clear what kind of…

Algorithmic fairness for artificial intelligence has become increasingly relevant as these systems become more pervasive in society. One realm of AI, recommender systems, presents unique challenges for fairness due to trade offs between…

A test oracle determines whether a system behaves correctly for a given input. Automatic testing techniques rely on an automated test oracle to test the system without user interaction. Important families of automated test oracles include…

As algorithms are increasingly used to make important decisions that affect human lives, ranging from social benefit assignment to predicting risk of criminal recidivism, concerns have been raised about the fairness of algorithmic decision…

What does it mean for an algorithm to be fair? Different papers use different notions of algorithmic fairness, and although these appear internally consistent, they also seem mutually incompatible. We present a mathematical setting in which…

We survey concepts at the frontier of research connecting artificial, animal and human cognition to computation and information processing---from the Turing test to Searle's Chinese Room argument, from Integrated Information Theory to…

Technologies increasingly mimic human-like social behaviours. Beyond prototypical conversational agents like chatbots, this also applies to basic automated systems like app notifications or self-checkout machines that address or 'talk to'…