Mathematical statements written in natural language are usually composed of two different
modalities: mathematical elements and natural language. These two modalities have …

Disentangling the encodings of neural models is a fundamental aspect for improving
interpretability, semantic control, and understanding downstream task performance in …

An emerging line of research in Explainable NLP is the creation of datasets enriched with
human-annotated explanations and rationales, used to build and evaluate models with step …

The amount of unstructured scientific data in the form of documents, reports, papers, patents,
and the like is exponentially increasing each year. Technological advances and their …

Interpreting the predictions of existing Question Answering (QA) models is critical to many
real-world intelligent applications, such as QA systems for healthcare, education, and …

Abstract Explainable Multi-Hop Question Answering (MHQA) requires an ability to reason
explicitly across facts to arrive at the answer. The majority of multi-hop reasoning methods …

Traditionally, Question Answering (QA) has been an important task in the field of Artificial
Intelligence (AI) and a substantial amount of research has been done in the past proposing …

Transformer-based large language models (LLM) s are effective at scoring a wide range of
short, constructed response (SCR) items, as evidenced by high levels of interrater reliability …

Building systems that can explain and understand the world is a long-standing goal for
Artificial Intelligence (AI). The ability to explain, in fact, constitutes an archetypal feature of …

The EnnCore project addresses the fundamental security problem of guaranteeing safety,
transparency, and robustness in neural-based architectures. Specifically, EnnCore aims at …