相关论文: Surprise: Youve got some explaining to do

As machine learning and algorithmic decision making systems are increasingly being leveraged in high-stakes human-in-the-loop settings, there is a pressing need to understand the rationale of their predictions. Researchers have responded to…

Push notifications are brief messages that users frequently encounter in their daily lives. However, the volume of notifications can lead to information overload, making it challenging for users to engage effectively. This study…

Although living organisms are affected by many interrelated and unidentified variables, this complexity does not automatically impose a fundamental limitation on statistical inference. Nor need one invoke such complexity as an explanation…

Men and women systematically differ in their beliefs about their performance relative to others; in particular, men tend to be more overconfident. This paper provides support for one explanation for gender differences in overconfidence,…

We introduce an information order on experiments based on weighted garbling, a generalization of the standard notion of garbling. In this order, an experiment is more informative than another if the latter is a weighted garbling of the…

Ensuring fairness of machine learning systems is a human-in-the-loop process. It relies on developers, users, and the general public to identify fairness problems and make improvements. To facilitate the process we need effective, unbiased,…

Background. From information theory, surprisal is a measurement of how unexpected an event is. Statistical language models provide a probabilistic approximation of natural languages, and because surprisal is constructed with the probability…

Recent years have seen a boom in interest in machine learning systems that can provide a human-understandable rationale for their predictions or decisions. However, exactly what kinds of explanation are truly human-interpretable remains…

Explainable AI has brought transparency into complex ML blackboxes, enabling, in particular, to identify which features these models use for their predictions. So far, the question of explaining predictive uncertainty, i.e. why a model…

How predictable a word is can be quantified in two ways: using human responses to the cloze task or using probabilities from language models (LMs).When used as predictors of processing effort, LM probabilities outperform probabilities…

Explaining to users why some items are recommended is critical, as it can help users to make better decisions, increase their satisfaction, and gain their trust in recommender systems (RS). However, existing explainable RS usually consider…

Language is not only used to transmit neutral information; we often seek to persuade by arguing in favor of a particular view. Persuasion raises a number of challenges for classical accounts of belief updating, as information cannot be…

Prior work has proposed effective methods to learn event representations that can capture syntactic and semantic information over text corpus, demonstrating their effectiveness for downstream tasks such as script event prediction. On the…

How do incentive levels affect strategic behaviour? We address this with an experiment that separately identifies own- and opponent-incentive effects in two dominance-solvable games that differ in strategic complexity. Higher own incentives…

We designed and ran an experiment to test how often people's choices are reversed by others' recommendations when facing different levels of confirmation and conformity pressures. In our experiment participants were first asked to provide…

Context and Motivation: The increasing complexity of modern software systems often challenges users' abilities to interact with them. Taking established quality attributes such as usability and transparency into account can mitigate this…

We explore whether the human ratings of open ended responses can be explained with non-content related features, and if such effects vary across different mathematics-related items. When scoring is rigorously defined and rooted in a…

Reward schemes may affect not only agents' effort, but also their incentives to gather information to reduce the riskiness of the productive activity. In a laboratory experiment using a novel task, we find that the relationship between…

Nowadays, interactive technologies are used almost everywhere. As a result, designers need to increasingly make them "socially acceptable". Previous work recommends "subtle" forms of interaction to increase social acceptability and avoid…

Machine Learning explainability techniques have been proposed as a means of `explaining' or interrogating a model in order to understand why a particular decision or prediction has been made. Such an ability is especially important at a…