AI RESEARCH

LLM-Assisted Causal Structure Disambiguation and Factor Extraction for Legal Judgment Prediction

arXiv CS.CL

ArXi:2603.11446v1 Announce Type: new Mainstream methods for Legal Judgment Prediction (LJP) based on Pre-trained Language Models (PLMs) heavily rely on the statistical correlation between case facts and judgment results. This paradigm lacks explicit modeling of legal constituent elements and underlying causal logic, making models prone to learning spurious correlations and suffering from poor robustness. While