Related papers: Diagnostics-Guided Explanation Generation
Neural predictive models have achieved remarkable performance improvements in various natural language processing tasks. However, most neural predictive models suffer from the lack of explainability of predictions, limiting their practical…
Explanations of model behavior are commonly evaluated via proxy properties weakly tied to the purposes explanations serve in practice. We contribute a decision theoretic framework that treats explanations as information signals valued by…
Building explainable systems is a critical problem in the field of Natural Language Processing (NLP), since most machine learning models provide no explanations for the predictions. Existing approaches for explainable machine learning…
Integrating free-text explanations to in-context learning of large language models (LLM) is shown to elicit strong reasoning capabilities along with reasonable explanations. In this paper, we consider the problem of leveraging the…
We examine whether data generated by explanation techniques, which promote a process of self-reflection, can improve classifier performance. Our work is based on the idea that humans have the ability to make quick, intuitive decisions as…
Modern machine learning models are opaque, and as a result there is a burgeoning academic subfield on methods that explain these models' behavior. However, what is the precise goal of providing such explanations, and how can we demonstrate…
Generating explanation to explain its behavior is an essential capability for a robotic teammate. Explanations help human partners better understand the situation and maintain trust of their teammates. Prior work on robot generating…
LLM self-explanations are often presented as a promising tool for AI oversight, yet their faithfulness to the model's true reasoning process is poorly understood. Existing faithfulness metrics have critical limitations, typically relying on…
Neural networks are among the most accurate supervised learning methods in use today. However, their opacity makes them difficult to trust in critical applications, especially when conditions in training may differ from those in practice.…
There is a broad consensus on the importance of deep learning models in tasks involving complex data. Often, an adequate understanding of these models is required when focusing on the transparency of decisions in human-critical…
Explanations in interactive machine-learning systems facilitate debugging and improving prediction models. However, the effectiveness of various global model-centric and data-centric explanations in aiding domain experts to detect and…
The black-box nature of neural models has motivated a line of research that aims to generate natural language rationales to explain why a model made certain predictions. Such rationale generation models, to date, have been trained on…
Work on "learning with rationales" shows that humans providing explanations to a machine learning system can improve the system's predictive accuracy. However, this work has not been connected to work in "explainable AI" which concerns…
As the field of healthcare increasingly adopts artificial intelligence, it becomes important to understand which types of explanations increase transparency and empower users to develop confidence and trust in the predictions made by…
Prediction without justification has limited applicability. As a remedy, we learn to extract pieces of input text as justifications -- rationales -- that are tailored to be short and coherent, yet sufficient for making the same prediction.…
With the growing pervasiveness of artificial intelligence, the ability to explain the inferences made by machine learning models has become increasingly important. Numerous techniques for model explainability have been proposed, with…
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…
Most recent work on interpretability of complex machine learning models has focused on estimating $\textit{a posteriori}$ explanations for previously trained models around specific predictions. $\textit{Self-explaining}$ models where…
The main objective of explanations is to transmit knowledge to humans. This work proposes to construct informative explanations for predictions made from machine learning models. Motivated by the observations from social sciences, our…
To increase trust in artificial intelligence systems, a promising research direction consists of designing neural models capable of generating natural language explanations for their predictions. In this work, we show that such models are…