Related papers: Counterfactual Explanations for Natural Language I…

Visual counterfactual explanations are ideal hypothetical images that change the decision-making of the classifier with high confidence toward the desired class while remaining visually plausible and close to the initial image. In this…

Incorporating natural language rationales in the prompt and In-Context Learning (ICL) have led to a significant improvement of Large Language Models (LLMs) performance. However, generating high-quality rationales require human-annotation or…

Interactive proof assistants are computer programs carefully constructed to check a human-designed proof of a mathematical claim with high confidence in the implementation. However, this only validates truth of a formal claim, which may…

Explainable NLP techniques primarily explain by answering "Which tokens in the input are responsible for this prediction?''. We argue that for NLP models that make predictions by comparing two input texts, it is more useful to explain by…

This work showcases a new approach for causal discovery by leveraging user experiments and recent advances in photo-realistic image editing, demonstrating a potential of identifying causal factors and understanding complex systems…

Deep neural networks and other intricate Artificial Intelligence (AI) models have reached high levels of accuracy on many biomedical natural language processing tasks. However, their applicability in real-world use cases may be limited due…

Explanations accompanied by a recommendation can assist users in understanding the decision made by recommendation systems, which in turn increases a user's confidence and trust in the system. Recently, research has focused on generating…

Negation is a common linguistic phenomenon. Yet language models face challenges with negation in many natural language understanding tasks such as question answering and natural language inference. In this paper, we experiment with seamless…

This position paper defends post-hoc explainability methods as legitimate tools for scientific knowledge production in machine learning. Addressing criticism of these methods' reliability and epistemic status, we develop a philosophical…

Being able to provide counterfactual interventions - sequences of actions we would have had to take for a desirable outcome to happen - is essential to explain how to change an unfavourable decision by a black-box machine learning model…

A fundamental research goal for Explainable AI (XAI) is to build models that are capable of reasoning through the generation of natural language explanations. However, the methodologies to design and evaluate explanation-based inference…

Despite the increasing effectiveness of language models, their reasoning capabilities remain underdeveloped. In particular, causal reasoning through counterfactual question answering is lacking. This work aims to bridge this gap. We first…

For building question answering systems and natural language interfaces, semantic parsing has emerged as an important and powerful paradigm. Semantic parsers map natural language into logical forms, the classic representation for many…

Counterfactual explanations describe how to modify a feature vector in order to flip the outcome of a trained classifier. Obtaining robust counterfactual explanations is essential to provide valid algorithmic recourse and meaningful…

In this paper I argue that the search for explainable models and interpretable decisions in AI must be reformulated in terms of the broader project of offering a pragmatic and naturalistic account of understanding in AI. Intuitively, the…

As the complexity of multi-robot systems grows to incorporate a greater number of robots, more complex tasks, and longer time horizons, the solutions to such problems often become too complex to be fully intelligible to human users. In this…

Explainable AI is an emerging field providing solutions for acquiring insights into automated systems' rationale. It has been put on the AI map by suggesting ways to tackle key ethical and societal issues. Existing explanation techniques…

As machine learning models evolve, maintaining transparency demands more human-centric explainable AI techniques. Counterfactual explanations, with roots in human reasoning, identify the minimal input changes needed to obtain a given output…

Providing personalized explanations for recommendations can help users to understand the underlying insight of the recommendation results, which is helpful to the effectiveness, transparency, persuasiveness and trustworthiness of…

Face Recognition (FR) has advanced significantly with the development of deep learning, achieving high accuracy in several applications. However, the lack of interpretability of these systems raises concerns about their accountability,…