SWSabine Wehnert

Sabine Wehnert

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Sabine Wehnert has a total of 24 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Exploration and Visualization of a Legal Knowledge Graph: A Human-Centered Approach

    by Sabine Wehnert, Pramod Kumar Bontha, Kilian Lüders, Huu Huong Giang Nguyen, Ernesto William De Luca


  • Open Access

    HiPS: Hierarchical PDF Segmentation of Textbooks

    by Sabine Wehnert, Harikrishnan Changaramkulath, Ernesto William De Luca

    The growing demand for effective tools to parse PDF-formatted texts, particularly structured documents such as textbooks, reveals the limitations of current methods developed mainly for research paper segmentation. This work addresses the challenge of hierarchical segmentation in complex structured documents, with a focus on legal textbooks that contain layered knowledge essential for interpreting and applying legal norms. We examine a Table of Contents (TOC)-based technique and approaches that rely on open-source structural parsing tools or Large Language Models (LLMs) operating without explicit TOC input. To enhance parsing accuracy, we incorporate preprocessing strategies such as OCR-based title detection, XML-derived features, and contextual text features. These strategies are evaluated based on their ability to identify section titles, allocate hierarchy levels, and determine section boundaries. Our findings show that combining LLMs with structure-aware preprocessing substantially reduces false positives and improves extraction quality. We also find that when the metadata quality of headings in the PDF is high, TOC-based techniques perform particularly well. All code and data are publicly available to support replication. We conclude with a comparative evaluation of the methods, outlining their respective strengths and limitations.

  • Open Access

    Analyzing Bias in Swiss Federal Supreme Court Judgments Using Facebook's Holistic Bias Dataset: Implications for Language Model Training

    by 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.

  • Open Access

    LUMI: Legal Understanding and Matching Through Interactive Highlighting

    by Sabine Wehnert, Visakh Padmanabhan, Ernesto William De Luca

    In this paper, we present LUMI, a system that explains document retrieval through span highlighting. LUMI allows users to select a query span and highlights the most relevant part of a retrieved document using transformer-based retrieval, improving transparency in legal and technical analysis.

  • Open Access

    Building Applications with Purpose: Bridging Human-Centered Design and Human-Centered Artificial Intelligence in Legal Tech with the Double Diamond

    by Sabine Wehnert, Ernesto William De Luca

    The concept of human-centeredness exists in the fields of software ergonomics and artificial intelligence. In this work, we propose how key principles from both disciplines can be applied together in a unified software design process. While the research community for legal artificial intelligence is well-aware of common requirements, such as explainability and privacy, work on Human-Centered Design focusing on creating and evaluating the user experience is rare. We contribute a blueprint for future legal system design optimized for user experience and common requirements of legal artificial intelligence applications.


  • Open Access

    Hybrid Legal Norm Retrieval: Leveraging Knowledge Graphs and Textual Representations

    by Sabine Wehnert, Visakh Padmanabhan, Ernesto William De Luca

    In this work, we propose a hybrid approach for legal norm retrieval that combines the structural information modeled in knowledge graphs with the textual content of legal documents. Our method utilizes the intricate relationships within the Japanese Civil Code, supplemented by relevant precedents, references, commentary, and mentions in legal textbooks on Japanese law. We assess the effectiveness of our approach in Task 3 of the Competition on Legal Information Extraction/Entailment (COLIEE), using both a transformer model and BM25 as a more explainable retrieval model. In our experiments, we examine the contributions of the different legal document types, showing the positive impact of the knowledge graph and auxiliary information.


  • Open Access

    TENJI: A Textbook Entity Network and Jurisprudence Interface

    by Sabine Wehnert, Pramod Kumar Bontha, Kilian Lüders, Bent Stohlmann, Ernesto William De Luca

    This paper presents TENJI, a system for exploring a knowledge graph based on legal textbooks, norms, and court decisions. TENJI reveals relationships between legal documents by enabling traversal of citation graphs and references extracted from textbooks. Since textbooks provide contextual legal knowledge that is not always explicit in the norms, TENJI uncovers hidden connections. We followed Human-Centered Design principles to ensure a user-friendly experience.


  • Open Access

    LIRAI'24: 2nd Workshop on Legal Information Retrieval meets Artificial Intelligence

    by Sabine Wehnert, Manuel Fiorelli, Davide Picca, Ernesto William De Luca, Armando Stellato

    LIRAI is a workshop series on Legal Information Retrieval and Legal Artificial Intelligence. It provides a forum for discussing current trends and challenges in legal artificial intelligence, specifically related to the hypertext nature of legal documents and retrieval tasks. The second edition of LIRAI focuses on three main directions: explainable / justifiable artificial intelligence, hybrid systems that combine formal approaches and machine learning-based methods, including deep learning-based methods, and finally generative artificial intelligence. We call for contributions on these topics in the form of short and long papers, and we aim to publish them as open-access proceedings on CEUR-WS.org once again.


  • Improving Robustness in Language Models for Legal Textual Entailment Through Artifact-Aware Training

    by Sabine Wehnert, Venkatesh Murugadas, Preetam Vinod Naik, Ernesto William De Luca


  • Open Access

    A dynamic approach for visualizing and exploring concept hierarchies from textbooks

    by Sabine Wehnert, Praneeth Chedella, Jonas Asche, Ernesto William De Luca

    In this study, we propose a visualization technique to explore and visualize concept hierarchies generated from a textbook in the legal domain. Through a human-centered design process, we developed a tool that allows users to effectively navigate through and explore complex hierarchical concepts in three kinds of traversal techniques: top-down, middle-out, and bottom-up. Our concept hierarchies offer an overview over a given domain, with increasing level of detail toward the bottom of the hierarchy which is consisting of entities. In the legal use case we considered, the concepts were adapted from section headings in a legal textbook, whereas references to law or legal cases inside the textbook became entities. The design of this tool is refined following various steps such as gathering user needs, pain points of an existing visualization, prototyping, testing, and refining. The resulting interface offers users several key features such as dynamic search and filter, explorable concept nodes, and a preview of leaf nodes at every stage. A high-fidelity prototype was created to test our theory and design. To test our concept, we used the System Usability Scale as a way to measure the prototype's usability, a task-based survey to asses the tool's ability in assisting users in gathering information and interacting with the prototype, and finally mouse tracking to understand user interaction patterns. Along with this, we gathered audio and video footage of users when participating in the study. This footage also helped us in getting feedback when the survey responses required further information. The data collected provided valuable insights to set the directions for extending this study. As a result, we have accounted for varying hierarchy depths, longer text spans than only one to two words in the elements of the hierarchy, searchability, and exploration of the hierarchies. At the same time, we aimed for minimizing visual clutter and cognitive overload. We show that existing approaches are not suitable to visualize the type of data which we support with our visualization.