Designing Human-AI System for Legal Research: A Case Study of Precedent Search in Chinese Law

2025-04-11

AI Summary

Current AI-powered legal tools for case retrieval in China suffer from low efficacy and ethical risks due to their “end-to-end black-box” architecture, which renders intermediate reasoning steps uncontrollable and precludes meaningful human-AI collaboration. Method: Through in-depth interviews, task observation, and contextual analysis with five legal practitioners, this study systematically identifies pain points across the entire Chinese case retrieval workflow. Contribution/Results: We propose a human-AI collaboration framework centered on “controllable intermediate steps,” repositioning AI as an interpretable, auditable, and intervenable collaborator. Six critical intervention points—including cause-of-action calibration and statutory provision tracing—are formally defined. We further develop the first interactive prototype tailored to Chinese case retrieval, which demonstrates strong usability and trustworthiness, earning high recognition from legal practitioners.

Technology Category

• Humans and AI: Intelligent User Interfaces
• Philosophy and Ethics of AI: AI & Law, Justice, Regulation & Governance
• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy

Application Category

• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Economics, Online Markets and Human Computation: Fairness and ethical considerations in crowd work and in human-in-the-loop AI systems

Abstract

Recent advancements in AI technology have seen researchers and industry professionals actively exploring the application of AI tools in legal workflows. Despite this prevailing trend, legal practitioners found that AI tools had limited effectiveness in supporting everyday tasks, which can be partly attributed to their design. Typically, AI legal tools only offer end-to-end interaction: practitioners can only manipulate the input and output but have no control over the intermediate steps, raising concerns about AI tools' performance and ethical use. To design an effective AI legal tool, as a first step, we explore users' needs with one specific use case: precedent search. Through a qualitative study with five legal practitioners, we uncovered the precedent search workflow, the challenges they face using current systems, and their concerns and expectations regarding AI tools. We conclude our exploration with an initial prototype to reflect the design implications derived from our findings.

Problem

• Designing effective Human-AI system for legal research
• Addressing limited AI tool effectiveness in legal workflows
• Improving control over intermediate steps in AI legal tools

Innovation

• Human-AI system for legal research
• Qualitative study with legal practitioners
• Initial prototype reflecting design implications