Ai helps nonexperts understand complex legal decisions faster
JudgmentLens: Human-AI Sensemaking of Complex Legal Judgments
Human-Computer Interaction
Summary
Legal judgments can be very hard for ordinary people to understand because they use complicated language and link many pieces of information together. The authors studied how non-expert readers struggle with understanding these judgments and built a tool called JudgmentLens to help. This tool uses AI to show clear explanations and links parts of the judgment text to its interpretations, making it easier and quicker to read. People who tested JudgmentLens worked faster and felt less tired, although their tested understanding didn’t improve much. The authors also explored how conversational AI can help with asking questions but still needs users to check answers carefully.
legal judgmentshuman-AI interactionsensemakingAI augmentationexplainable AItext comprehensionsource verificationconversational AI
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.