Machine Learning Law

  • February 5, 2026

    Robust Generalizable Heterogeneous Legal Link Prediction

    Authors: Lorenz Wendlinger, Simon Alexander Nonn, Abdullah Al Zubaer, Michael Granitzer
    Institution: Universität Passau, Germany
    arXiv: 2602.04812v1 | PDF
    Published: February 4, 2026
    Keywords: Link Prediction, Legal Tech, Graph Neural Networks

    This paper improves legal citation link prediction using Graph Neural Networks (GNNs). The authors introduce R-HGE (Robust Heterogeneous Graph Enrichment), which predicts missing citations between legal cases and laws more accurately than previous methods.

  • January 24, 2026

    Unintended Memorization of Sensitive Information in Fine-Tuned Language Models

    Authors: Marton Szep, Jorge Marin Ruiz, Georgios Kaissis, Paulina Seidl, Rüdiger von Eisenhart-Rothe, Florian Hinterwimmer, Daniel Rueckert (Technical University of Munich, Imperial College London)
    arXiv: 2601.17480v1
    Published: January 24, 2026
    Keywords: PII memorization, LLM privacy, differential privacy, machine unlearning, fine-tuning

    This paper investigates a critical privacy vulnerability: LLMs can memorize and leak personally identifiable information (PII) that appears only in training inputs, not in the training targets. Even when PII is irrelevant to the downstream task, fine-tuned models can be tricked into revealing names, addresses, and other sensitive data.