Related papers: Are we measuring trust correctly in explainability…
Interpretable classification models are built with the purpose of providing a comprehensible description of the decision logic to an external oversight agent. When considered in isolation, a decision tree, a set of classification rules, or…
Although measuring intrinsic quality has been a key factor in the advancement of Machine Translation (MT), successfully deploying MT requires considering not just intrinsic quality but also the user experience, including aspects such as…
People's trust in prediction models can be affected by many factors, including domain expertise like knowledge about the application domain and experience with predictive modelling. However, to what extent and why domain expertise impacts…
A myriad of explainability methods have been proposed in recent years, but there is little consensus on how to evaluate them. While automatic metrics allow for quick benchmarking, it isn't clear how such metrics reflect human interaction…
Auditors demand financial models be transparent yet no consensus exists on what that means precisely. Without a clear modeling transparency definition we cannot know when our models are "transparent". The financial modeling community…
The use of models, even if efficient, must be accompanied by an understanding at all levels of the process that transforms data (upstream and downstream). Thus, needs increase to define the relationships between individual data and the…
How does the extent to which a model is open or closed impact the scientific inferences that can be drawn from research that involves it? In this paper, we analyze how restrictions on information about model construction and deployment…
As artificial intelligence systems increasingly inform high-stakes decisions across sectors, transparency has become foundational to responsible and trustworthy AI implementation. Leveraging our role as a leading institute in advancing AI…
After the tremendous advances of deep learning and other AI methods, more attention is flowing into other properties of modern approaches, such as interpretability, fairness, etc. combined in frameworks like Responsible AI. Two research…
Mathematical models of complex social systems can enrich social scientific theory, inform interventions, and shape policy. From voting behavior to economic inequality and urban development, such models influence decisions that affect…
One of the risks involved in multi agent community is in the identification of trustworthy agent partners for transaction. In this paper we aim to describe a trust model for measuring trust in the interacting agents. The trust metric model…
Systems relying on ML have become ubiquitous, but so has biased behavior within them. Research shows that bias significantly affects stakeholders' trust in systems and how they use them. Further, stakeholders of different backgrounds view…
The increasing adoption of machine learning tools has led to calls for accountability via model interpretability. But what does it mean for a machine learning model to be interpretable by humans, and how can this be assessed? We focus on…
Perceived trustworthiness underpins how users navigate online information, yet it remains unclear whether large language models (LLMs),increasingly embedded in search, recommendation, and conversational systems, represent this construct in…
A significant challenge to measuring human-automation trust is the amount of construct proliferation, models, and questionnaires with highly variable validation. However, all agree that trust is a crucial element of technological…
Since trust measures in human-robot interaction are often subjective or not possible to implement real-time, we propose to use speech cues (on what, when and how the user talks) as an objective real-time measure of trust. This could be…
While recent years have witnessed the emergence of various explainable methods in machine learning, to what degree the explanations really represent the reasoning process behind the model prediction -- namely, the faithfulness of…
Model interpretations are often used in practice to extract real world insights from machine learning models. These interpretations have a wide range of applications; they can be presented as business recommendations or used to evaluate…
Transparency is often deemed critical to enable effective real-world deployment of intelligent systems. Yet the motivations for and benefits of different types of transparency can vary significantly depending on context, and objective…
Trusting machine learning algorithms requires having confidence in their outputs. Confidence is typically interpreted in terms of model reliability, where a model is reliable if it produces a high proportion of correct outputs. However,…