Related papers: Objective Metrics for Human-Subjects Evaluation in…

We take inspiration from the study of human explanation to inform the design and evaluation of interpretability methods in machine learning. First, we survey the literature on human explanation in philosophy, cognitive science, and the…

This paper proposes a set of criteria to evaluate the objectiveness of explanation methods of neural networks, which is crucial for the development of explainable AI, but it also presents significant challenges. The core challenge is that…

The successful application of machine learning (ML) methods becomes increasingly dependent on their interpretability or explainability. Designing explainable ML systems is instrumental to ensuring transparency of automated decision-making…

The challenge of creating interpretable models has been taken up by two main research communities: ML researchers primarily focused on lower-level explainability methods that suit the needs of engineers, and HCI researchers who have more…

A multitude of explainability methods and associated fidelity performance metrics have been proposed to help better understand how modern AI systems make decisions. However, much of the current work has remained theoretical -- without much…

Explainable Recommender Systems (XRS) aim to provide users with understandable reasons for the recommendations generated by these systems, representing a crucial research direction in artificial intelligence (AI). Recent research has…

Interactive reinforcement learning proposes the use of externally-sourced information in order to speed up the learning process. When interacting with a learner agent, humans may provide either evaluative or informative advice. Prior…

A major challenge of Reinforcement Learning is that agents often learn undesired behaviors that seem to defy the reward structure they were given. Explainable Reinforcement Learning (XRL) methods can answer queries such as "explain this…

Interpretability provides a means for humans to verify aspects of machine learning (ML) models and empower human+ML teaming in situations where the task cannot be fully automated. Different contexts require explanations with different…

Machine learning models are increasingly integrated into societally critical applications such as recidivism prediction and medical diagnosis, thanks to their superior predictive power. In these applications, however, full automation is…

Subjective tests are the gold standard for evaluating speech quality and intelligibility; however, they are time-consuming and expensive. Thus, objective measures that align with human perceptions are crucial. This study evaluates the…

Recently many efforts have been devoted to interpreting the black-box NMT models, but little progress has been made on metrics to evaluate explanation methods. Word Alignment Error Rate can be used as such a metric that matches human…

During a research project in which we developed a machine learning (ML) driven visualization system for non-ML experts, we reflected on interpretability research in ML, computer-supported collaborative work and human-computer interaction.…

The overarching goal of this work is to efficiently enable end-users to correctly anticipate a robot's behavior in novel situations. Since a robot's behavior is often a direct result of its underlying objective function, our insight is that…

Explainable artificial intelligence is proposed to provide explanations for reasoning performed by an Artificial Intelligence. There is no consensus on how to evaluate the quality of these explanations, since even the definition of…

Reinforcement learning (RL) has experienced a second wind in the past decade. While incredibly successful in images and videos, these systems still operate within the realm of propositional tasks ignoring the inherent structure that exists…

A central goal of cognitive modeling is to develop models that not only predict human behavior but also provide insight into the underlying cognitive mechanisms. While neural network models trained on large-scale behavioral data often…

Reliable evaluation protocols are of utmost importance for reproducible NLP research. In this work, we show that sometimes neither metric nor conventional human evaluation is sufficient to draw conclusions about system performance. Using…

To collaborate well with robots, we must be able to understand their decision making. Humans naturally infer other agents' beliefs and desires by reasoning about their observable behavior in a way that resembles inverse reinforcement…

Large Language Models (LLMs) have achieved remarkable success across diverse natural language tasks, yet the reward models employed for aligning LLMs often encounter challenges of reward hacking, where the approaches predominantly rely on…