Related papers: Challenges in Explanation Quality Evaluation

In the rapidly growing literature on explanation algorithms, it often remains unclear what precisely these algorithms are for and how they should be used. In this position paper, we argue for a novel and pragmatic perspective: Explainable…

While a lot of research in explainable AI focuses on producing effective explanations, less work is devoted to the question of how people understand and interpret the explanation. In this work, we focus on this question through a study of…

Training data influence estimation methods quantify the contribution of training documents to a model's output, making them a promising source of information for example-based explanations. As humans cannot interpret thousands of documents,…

When answering a question, humans utilize the information available across different modalities to synthesize a consistent and complete chain of thought (CoT). This process is normally a black box in the case of deep learning models like…

In sensitive contexts, providers of machine learning algorithms are increasingly required to give explanations for their algorithms' decisions. However, explanation receivers might not trust the provider, who potentially could output…

This paper presents a comprehensive analysis of explainable fact-checking through a series of experiments, focusing on the ability of large language models to verify public health claims and provide explanations or justifications for their…

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…

Many computer scientists use the aggregated answers of online workers to represent ground truth. Prior work has shown that aggregation methods such as majority voting are effective for measuring relatively objective features. For subjective…

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…

This article reviews the empirical evidence on the use of patent citations as a proxy for invention importance. It distinguishes between technical merit, private economic value, and social value, and surveys validation studies using expert…

Machine learning methods are being increasingly applied in sensitive societal contexts, where decisions impact human lives. Hence it has become necessary to build capabilities for providing easily-interpretable explanations of models'…

Logic-based approaches to AI have the advantage that their behavior can in principle be explained to a user. If, for instance, a Description Logic reasoner derives a consequence that triggers some action of the overall system, then one can…

This paper addresses a significant gap in explainable AI: the necessity of interpreting epistemic uncertainty in model explanations. Although current methods mainly focus on explaining predictions, with some including uncertainty, they fail…

Manual evaluation is essential to judge progress on automatic text summarization. However, we conduct a survey on recent summarization system papers that reveals little agreement on how to perform such evaluation studies. We conduct two…

Many methods now exist for conditioning model outputs on task instructions, retrieved documents, and user-provided explanations and feedback. Rather than relying solely on examples of task inputs and outputs, these approaches use valuable…

Recent developments in machine learning have introduced models that approach human performance at the cost of increased architectural complexity. Efforts to make the rationales behind the models' predictions transparent have inspired an…

Argumentation is one of society's foundational pillars, and, sparked by advances in NLP and the vast availability of text data, automated mining of arguments receives increasing attention. A decisive property of arguments is their strength…

Understanding the decisions made and actions taken by increasingly complex AI system remains a key challenge. This has led to an expanding field of research in explainable artificial intelligence (XAI), highlighting the potential of…

As probabilistic systems gain popularity and are coming into wider use, the need for a mechanism that explains the system's findings and recommendations becomes more critical. The system will also need a mechanism for ordering competing…

Evaluating the efficiency of human-AI interactions is challenging, including subjective and objective quality aspects. With the focus on the human experience of the explanations, evaluations of explanation methods have become mostly…