JudgmentLens helps non-experts understand complex legal judgments faster
JudgmentLens: Human-AI Sensemaking of Complex Legal Judgments
Human-Computer Interaction
Summary
Legal judgments are often hard for people without legal training to understand because they are written in complicated language and have many connected parts. The authors studied how non-experts in China tried to make sense of these judgments and found several common difficulties. They created JudgmentLens, a reading system that uses AI to provide clear explanations and shows exactly where the explanations come from in the text. People using JudgmentLens completed understanding tasks faster and felt less mental effort than reading normal PDFs, though their measured comprehension was about the same.
What this means in practice
- •For legal technology developers: Build AI-enhanced tools that help non-experts navigate and understand complex legal documents through linked explanations and source references.$Commercial implications: Enables creation of user-friendly legal document readers for consumers and professionals needing accessible interpretations.
- •For consumer legal aid organizations: Provide accessible digital aids that help laypeople interpret court rulings and better understand their rights and obligations.
Authors
Xinyi Chen, Ruijie Li, Yuelu Li, Chen Liang
Abstract
Judicial judgments are increasingly available, yet dense language and distributed relationships among facts, evidence, reasoning, and rulings remain difficult for non-experts to interpret. Through a mixed-methods formative study with Chinese non-expert readers (survey N=34; interviews N=6), we identified structural, interpretive, verification, and action breakdowns. We developed JudgmentLens, an AI-augmented reading system combining persistent case representations, adaptive explanations, and traceable links from generated interpretations to judgment passages. In a counterbalanced within-subject evaluation (N=16), participants completed tasks faster with JudgmentLens than with conventional PDF reading and reported lower workload and greater self-reported decision understanding, while rubric-scored comprehension did not differ reliably. An exploratory PDF+DeepSeek probe suggested that conversational AI supported formulated questions while leaving question formulation, answer integration, and source checking largely to users. We contribute an empirical account of non-expert judgment sensemaking and design strategies for inspectable, source-grounded AI mediation.