Neuro-symbolic model helps assess Dutch bankruptcy fraud claims
Machina Pauliana: A neuro-symbolic approach to the actio pauliana in Dutch insolvency law
Artificial IntelligenceComputation and Language
Summary
Figuring out if a transaction in bankruptcy unfairly hurts creditors can be tricky, as the law uses clear rules along with open-ended words explained by past cases. The authors built a system that combines clear logical rules with AI that understands legal language to decide if such rules apply. Their AI reads court decisions and breaks down complex terms based on similar past judgments, helping the system stay grounded in real legal precedent. While the model performs well on many points, it has some trouble fully capturing the idea of required knowledge in these cases.
What this means in practice
- •For legal tech developers: Build tools that automate analyzing bankruptcy law cases by combining rule-based checks with AI understanding of complex legal terms from prior court judgments.
- •For civil law software teams: Integrate case-law grounded AI routines to assist with interpreting vague legal requirements in civil procedure automation.
Authors
Daan Boven, Gregor Behnke, David Graus
Abstract
Applying a legal provision frequently requires both structured rule-based reasoning and sensitivity to open-textured terms developed in case law. The actio pauliana of Article 42 of the Dutch Bankruptcy Act (Faillissementswet, Fw), which allows an insolvency practitioner to avoid transactions that prejudice creditors, requires both. We present a neuro-symbolic model of Article 42 Fw. Its symbolic core is written in Catala in a literate style that keeps statute and formalisation aligned and was developed through pair programming, with open-textured terms represented as boolean inputs where neural components couple to the symbolic solver. A neural routine structures a case's natural-language facts into boolean and date inputs. Neural subroutines resolve the open-textured terms through case-based reasoning over Dutch civil judgments, retrieved through a pipeline that filters on the requirement being resolved and expands along the procedural chain of a case. Segmenting and labelling those judgments attains high precision and recall against a manually annotated gold standard of 100 judgments. On ten hand-annotated cases the neuro-symbolic model handles most criteria reasonably but struggles with the knowledge requirement. Retrieval depth shows no clear quantitative effect, although retrieved judgments provide explicit grounding in prior case law.