Ernesto William De Luca

Sabine Wehnert, Harikrishnan Changaramkulath, Ivan Habernal

PDF parsers have recently improved on page-level layout understanding. However, recovering a document-global section hierarchy with reliable boundaries remains brittle for deeply structured books: many systems expose only page-local heading roles, assume shallow depth, or rely on high-quality PDF tags or Table of Contents (TOC) metadata, and public gold-standard data for deep book hierarchies is scarce. We present HiPS for hierarchical PDF segmentation of doctrinal legal books and make two main contributions. First, we release a gold-standard benchmark of 49 open-access law books with 9,812 manually curated headings, hierarchy levels, and page anchors, enabling evaluation of title detection, hierarchy reconstruction, and section boundary assignment. Second, we introduce complementary segmentation pipelines: a TOC-based parser for books with reliable outline metadata and a TOC-free LLM-refined pipeline that combines OCR whitespace cues, XML typography, and local context. Across a broad comparison against open-source parsers and multimodal/LLM baselines, the TOC-based pipeline is strongest when metadata is complete, while the LLM-refined pipeline improves heading precision, deep-level recovery, and boundary quality when metadata is missing or noisy.

Erasmo Purificato, Ludovico Boratto, Ernesto William De Luca

The integration of artificial intelligence (AI) into daily life, particularly through information retrieval and recommender systems, has necessitated advanced user modeling and profiling techniques to deliver personalized experiences. These techniques aim to construct accurate user representations based on the rich amounts of data generated through interactions with these systems. This paper presents a comprehensive survey of the current state, evolution, and future directions of user modeling and profiling research. We provide a historical overview, tracing the development from early stereotype models to the latest deep learning techniques, and propose a novel taxonomy that encompasses all active topics in this research area, including recent trends. Our survey highlights the paradigm shifts towards more sophisticated user profiling methods, emphasizing implicit data collection, multi-behavior modeling, and the integration of graph data structures. We also address the critical need for privacy-preserving techniques and the push towards explainability and fairness in user modeling approaches. By examining the definitions of core terminology, we aim to clarify ambiguities and foster a clearer understanding of the field by proposing two novel encyclopedic definitions of the main terms. Furthermore, we explore the application of user modeling in various domains, such as fake news detection, cybersecurity, and personalized education. This survey serves as a comprehensive resource for researchers and practitioners, offering insights into the evolution of user modeling and profiling and guiding the development of more personalized, ethical, and effective AI systems.

Sabine Wehnert, Muhammet Ertas, Ernesto William De Luca

Natural Language Processing (NLP) is vital for computers to process and respond accurately to human language. However, biases in training data can introduce unfairness, especially in predicting legal judgment. This study focuses on analyzing biases within the Swiss Judgment Prediction Dataset (SJP-Dataset). Our aim is to ensure unbiased factual descriptions essential for fair decision making by NLP models in legal contexts. We analyze the dataset using social bias descriptors from the Holistic Bias dataset and employ advanced NLP techniques, including attention visualization, to explore the impact of dispreferred descriptors on model predictions. The study identifies biases and examines their influence on model behavior. Challenges include dataset imbalance and token limits affecting model performance.