Related papers: Flexible Instance-Specific Rationalization of NLP …

Machine learning solutions for pattern classification problems are nowadays widely deployed in society and industry. However, the lack of transparency and accountability of most accurate models often hinders their safe use. Thus, there is a…

Recent advances in language models have substantially improved Natural Language Understanding (NLU). Although widely used benchmarks suggest that Large Language Models (LLMs) can effectively disambiguate, their practical applicability in…

Although deep models achieve high predictive performance, it is difficult for humans to understand the predictions they made. Explainability is important for real-world applications to justify their reliability. Many example-based…

Most of the work on interpretable machine learning has focused on designing either inherently interpretable models, which typically trade-off accuracy for interpretability, or post-hoc explanation systems, which lack guarantees about their…

This paper presents an automated approach for interpretable feature recommendation for solving signal data analytics problems. The method has been tested by performing experiments on datasets in the domain of prognostics where…

Feature attribution methods, such as SHAP and LIME, explain machine learning model predictions by quantifying the influence of each input component. When applying feature attributions to explain language models, a basic question is defining…

Natural Language Processing (NLP) systems often make use of machine learning techniques that are unfamiliar to end-users who are interested in analyzing clinical records. Although NLP has been widely used in extracting information from…

Text summarization has been one of the most challenging areas of research in NLP. Much effort has been made to overcome this challenge by using either the abstractive or extractive methods. Extractive methods are more popular, due to their…

Prototype-based interpretability methods provide intuitive explanations of model prediction by comparing samples to a reference set of memorized exemplars or typical representatives in terms of similarity. In the field of sequential data…

Most existing interpretable methods explain a black-box model in a post-hoc manner, which uses simpler models or data analysis techniques to interpret the predictions after the model is learned. However, they (a) may derive contradictory…

With the growing popularity of general-purpose Large Language Models (LLMs), comes a need for more global explanations of model behaviors. Concept-based explanations arise as a promising avenue for explaining high-level patterns learned by…

Evaluation of Large Language Models (LLMs) is challenging because instruction-following necessitates alignment with human values and the required set of skills varies depending on the instruction. However, previous studies have mainly…

Clustering serves as a vital tool for uncovering latent data structures, and achieving both high accuracy and interpretability is essential. To this end, existing methods typically construct binary decision trees by solving mixed-integer…

Large Language Models (LLMs) have demonstrated exceptional abilities across a broad range of language-related tasks, including generating solutions to complex reasoning problems. An effective technique to enhance LLM performance is…

Large Multimodal Models (LMMs), or Vision-Language Models (VLMs), have shown impressive capabilities in a wide range of visual tasks. However, they often struggle with fine-grained visual reasoning, failing to identify domain-specific…

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…

Automatic mean opinion score (MOS) prediction provides a more perceptual alternative to objective metrics, offering deeper insights into the evaluated models. With the rapid progress of multimodal large language models (MLLMs), their…

Understanding why a model makes a certain prediction can be as crucial as the prediction's accuracy in many applications. However, the highest accuracy for large modern datasets is often achieved by complex models that even experts struggle…

Interpretable machine learning is essential in high-stakes domains where decision-making requires accountability, transparency, and trust. While rule-based models offer global and exact interpretability, learning rule sets that…

Current approaches to explaining the decisions of deep learning systems for medical tasks have focused on visualising the elements that have contributed to each decision. We argue that such approaches are not enough to "open the black box"…