Evaluates courtroom advocacy training using an AI tool, suggesting improved learner performance.
This paper presents an AI-powered interactive legal role-playing tool designed to simulate courtroom advocacy while continuously evaluating the legal quality of learner arguments. The system implements a two-stage Fast Brain and Smart Brain audit pipeline, where a fine-tuned BERT-based model assesses legal density and Gemini generates plain-English explanatory feedback. The platform generates Sri Lankan courtroom scenarios, manages five AI personas, and maintains autonomous dialogue through a heartbeat-driven engine. Model B achieves 98.28% accuracy and AUC-ROC of 0.9951. A reward-based response selection loop produces a 29.5% score uplift by selecting the highest-scoring of three generated candidates.
No takes yet. Share an insight, caveat, or question.
Gamage et al. (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: