Sabine Wehnert

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.

Ha Thanh Nguyen, Wachara Fungwacharakorn, Sabine Wehnert et al.

We study the overall process of automatic formalization of GDPR provisions using large language models, within a human-in-the-loop verification framework. Rather than aiming for full autonomy, we adopt a role-specialized workflow in which LLM-based AI components, operating in a multi-agent setting with iterative feedback, generate legal scenarios, formal rules, and atomic facts. This is coupled with independent verification modules which include human reviewers' assessment of representational, logical, and legal correctness. Using this approach, we construct a high-quality dataset to be used for GDPR auto-formalization, and analyze both successful and problematic cases. Our results show that structured verification and targeted human oversight are essential for reliable legal formalization, especially in the presence of legal nuance and context-sensitive reasoning.

Sabine Wehnert

In this work, I discuss how Large Language Models can be applied in the legal domain, circumventing their current drawbacks. Despite their large success and acceptance, their lack of explainability hinders legal experts to trust in their output, and this happens rightfully so. However, in this paper, I argue in favor of a new view, Justifiable Artificial Intelligence, instead of focusing on Explainable Artificial Intelligence. I discuss in this paper how gaining evidence for and against a Large Language Model's output may make their generated texts more trustworthy - or hold them accountable for misinformation.

May-Myo Zin, Sabine Wehnert, Yuntao Kong et al.

The anticipated positive social impact of regulatory processes requires both the accuracy and efficiency of their application. Modern artificial intelligence technologies, including natural language processing and machine-assisted reasoning, hold great promise for addressing this challenge. We present a framework to address the challenge of tools for regulatory application, based on current state-of-the-art (SOTA) methods for natural language processing (large language models or LLMs) and formalization of legal reasoning (the legal representation system PROLEG). As an example, we focus on Article 6 of the European General Data Protection Regulation (GDPR). In our framework, a single LLM prompt simultaneously transforms legal text into if-then rules and a corresponding PROLEG encoding, which are then validated and refined by legal domain experts. The final output is an executable PROLEG program that can produce human-readable explanations for instances of GDPR decisions. We describe processes to support the end-to-end transformation of a segment of a regulatory document (Article 6 from GDPR), including the prompting frame to guide an LLM to "compile" natural language text to if-then rules, then to further "compile" the vetted if-then rules to PROLEG. Finally, we produce an instance that shows the PROLEG execution. We conclude by summarizing the value of this approach and note observed limitations with suggestions to further develop such technologies for capturing and deploying regulatory frameworks.

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.

Sabine Wehnert, Sayed Anisul Hoque, Wolfram Fenske et al.

Getting an overview over the legal domain has become challenging, especially in a broad, international context. Legal question answering systems have the potential to alleviate this task by automatically retrieving relevant legal texts for a specific statement and checking whether the meaning of the statement can be inferred from the found documents. We investigate a combination of the BM25 scoring method of Elasticsearch with word embeddings trained on English translations of the German and Japanese civil law. For this, we define criteria which select a dynamic number of relevant documents according to threshold scores. Exploiting two deep learning classifiers and their respective prediction bias with a threshold-based answer inclusion criterion has shown to be beneficial for the textual entailment task, when compared to the baseline.