Towards human-centered explainable ai: A survey of user studies for model explanations
Explainable AI (XAI) is widely viewed as a sine qua non for ever-expanding AI research. A
better understanding of the needs of XAI users, as well as human-centered evaluations of …
better understanding of the needs of XAI users, as well as human-centered evaluations of …
Explainability in ai policies: A critical review of communications, reports, regulations, and standards in the eu, us, and uk
Public attention towards explainability of artificial intelligence (AI) systems has been rising in
recent years to offer methodologies for human oversight. This has translated into the …
recent years to offer methodologies for human oversight. This has translated into the …
The role of human knowledge in explainable AI
A Tocchetti, M Brambilla - Data, 2022 - mdpi.com
As the performance and complexity of machine learning models have grown significantly
over the last years, there has been an increasing need to develop methodologies to …
over the last years, there has been an increasing need to develop methodologies to …
Interpretability is in the eye of the beholder: Human versus artificial classification of image segments generated by humans versus XAI
The evaluation of explainable artificial intelligence is challenging, because automated and
human-centred metrics of explanation quality may diverge. To clarify their relationship, we …
human-centred metrics of explanation quality may diverge. To clarify their relationship, we …
AI robustness: a human-centered perspective on technological challenges and opportunities
Despite the impressive performance of Artificial Intelligence (AI) systems, their robustness
remains elusive and constitutes a key issue that impedes large-scale adoption. Besides …
remains elusive and constitutes a key issue that impedes large-scale adoption. Besides …
Improving human-algorithm collaboration: Causes and mitigation of over-and under-adherence
M Balakrishnan, K Ferreira, J Tong - Available at SSRN 4298669, 2022 - papers.ssrn.com
Even if algorithms make better predictions than humans on average, humans may
sometimes have “private” information which an algorithm does not have access to that can …
sometimes have “private” information which an algorithm does not have access to that can …
It Is Like Finding a Polar Bear in the Savannah! Concept-Level AI Explanations with Analogical Inference from Commonsense Knowledge
With recent advances in explainable artificial intelligence (XAI), researchers have started to
pay attention to concept-level explanations, which explain model predictions with a high …
pay attention to concept-level explanations, which explain model predictions with a high …
Opening the Analogical Portal to Explainability: Can Analogies Help Laypeople in AI-assisted Decision Making?
Abstract Concepts are an important construct in semantics, based on which humans
understand the world with various levels of abstraction. With the recent advances in …
understand the world with various levels of abstraction. With the recent advances in …
OpenHEXAI: An Open-Source Framework for Human-Centered Evaluation of Explainable Machine Learning
Recently, there has been a surge of explainable AI (XAI) methods driven by the need for
understanding machine learning model behaviors in high-stakes scenarios. However …
understanding machine learning model behaviors in high-stakes scenarios. However …
Smart" Error"! Exploring Imperfect AI to Support Creative Ideation
Designers widely accept AI as a partner in the design process for its efficient and intelligent
decision-making. However, AI is often not perfect, and AI error often makes humans …
decision-making. However, AI is often not perfect, and AI error often makes humans …