ABSTRACT Measuring semantic similarity between words or phrases is central to natural language processing, information retrieval and computational linguistics. Despite their importance, similarity and distance measures are typically chosen by default (e.g., cosine similarity) or in an ad hoc fashion, with little empirical justification. This lack of systematic evaluation creates two gaps: first, the absence of a comprehensive taxonomy of measures that spans set‐based, vector‐based and information‐theoretic approaches; second, the lack of task‐aware benchmarking that quantifies how these measures perform across different models and applications. In this paper, we address these gaps by comparing 15 similarity and distance measures on four NLP tasks (sentence similarity, kNN classification, correlation analysis and visualisation) using multiple benchmark datasets and embedding models. Our results reveal that the effectiveness of similarity measures varies substantially depending on the task and model, challenging the assumption that cosine similarity is universally optimal. These findings highlight the practical risk of relying on default measures and provide a principled basis for selecting similarity functions in NLP, information retrieval and related fields.

Synthetic Data Generation (SDG) is expanding rapidly, yet existing surveys differ widely in scope and methodological quality. This tertiary study systematically searched four major scholarly databases (2015-2025) and, after PRISMA screening and DARE-4 appraisal, 1 identified 17 eligible secondary studies. The evidence reveals a strong concentration in healthcare (58.8% of surveys), limited coverage of non-health domains, and inconsistent reporting of evaluation protocols (e.g., incomplete specification of metrics, data splits, baselines, or evaluation scripts). Fidelity and downstream utility dominate assessment practices, whereas privacy and diversity remain under-examined. Only 4 of 17 surveys provide any reproducibility artefacts. By consolidating these findings, we propose a compact, domain-agnostic evaluation baseline and highlight structural gaps in transparency, domain breadth, and methodological consistency. The study offers actionable guidance for strengthening reproducibility and broadening the evidential foundations of SDG research.

In the last few years, we have been witnessing the increasing deployment of machine learning-based systems, which act as black boxes whose behaviour is hidden to end-users. As a side-effect, this contributes to increasing the need for explainable methods and tools to support the coordination between humans and ML models towards collaborative decision-making. In this paper, we demonstrate ContrXT, a novel tool that computes the differences in the classification logic of two distinct trained models, reasoning on their symbolic representation through Binary Decision Diagrams. ContrXT is available as a pip package and API.

While word embeddings have been showing their effectiveness in capturing semantic and lexical similarities in a large number of domains, in case the corpus used to generate embeddings is associated with a taxonomy (i.e., classification tasks over standard de-jure taxonomies) the common intrinsic and extrinsic evaluation tasks cannot guarantee that the generated embeddings are consistent with the taxonomy. This, as a consequence sharply limits the use of distributional semantics in those domains. To address this issue, we design and implement MEET, which proposes a new measure -HSS- that allows evaluating embeddings from a text corpus preserving the semantic similarity relations of the taxonomy.

Over the past two decades, academia has witnessed numerous tools and search engines which facilitate the retrieval procedure in the literature review process and aid researchers to review the literature with more ease and accuracy. These tools mostly work based on a simple textual input which supposedly encapsulates the primary keywords in the desired research areas. Such tools mainly suffer from the following shortcomings: (i) they rely on textual search queries that are expected to reflect all the desired keywords and concepts, and (ii) shallow results which makes following a paper through time via citations a cumbersome task. In this paper, we introduce GRASP, a search engine that retrieves scientific papers starting from a sub-graph query provided by the user, offering (i) a list of time papers based on the query and (ii) a graph with papers and authors as vertices and edges being cited and published-by. GRASPhas been created using a Neo4j graph database, based on DBLP and AMiner corpora provided by their API. Acting performance evaluation by asking ten computer science experts, we demonstrate how GRASPcan efficiently retrieve and rank the most related papers based on the user's input.

Explainable Artificial Intelligence (XAI) is gaining interests in both academia and industry, mainly thanks to the proliferation of darker more complex black-box solutions which are replacing their more transparent ancestors. Believing that the overall performance of an XAI system can be augmented by considering the end-user as a human being, we are studying the ways we can improve the explanations by making them more informative and easier to use from one hand, and interactive and customisable from the other hand.