Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Reimagining Legal Fact Verification with GenAI: Toward Effective Human-AI Collaboration

Sirui Han, Yuyao Zhang, Yidan Huang, Xueyan Li, Chengzhong Liu, Yike Guo

TL;DR

This paper investigates how Generative AI (GenAI) can support legal fact verification in non-litigation practice, a high-stakes, interpretive task demanding defensible conclusions and tight accountability. Through semi-structured interviews with 18 lawyers, the study shows GenAI offers efficiency gains for orientation, drafting, and early-stage structuring but cannot replace professional judgment due to accuracy, confidentiality, and liability concerns. It argues for auditable, transparent, and specialized AI designs that surface provenance, provide layered reasoning, and preserve human oversight—seeing automation as a way to reorganize cognitive labor rather than replace expertise. The work contributes design insights for trustworthy human–AI collaboration in legal fact verification and highlights epistemic risks that must be managed for responsible deployment in high-stakes domains.

Abstract

Fact verification is a critical yet underexplored component of non-litigation legal practice. While existing research has examined automation in legal workflow and human-AI collaboration in high-stakes domains, little is known about how GenAI can support fact verification, a task that demands prudent judgment and strict accountability. To address this, we conducted semi-structured interviews with 18 lawyers to understand their current verification practices, attitudes toward GenAI adoption, and expectations for future systems. We found that while lawyers use GenAI for low-risk tasks like drafting and language optimization, concerns over accuracy, confidentiality, and liability are currently limiting its adoption for fact verification. These concerns translate into core design requirements for AI systems that are trustworthy and accountable. Based on these, we contribute design insights for human-AI collaboration in legal fact verification, emphasizing the development of auditable systems that balance efficiency with professional judgment and uphold ethical and legal accountability in high-stakes practice.

Reimagining Legal Fact Verification with GenAI: Toward Effective Human-AI Collaboration

TL;DR

This paper investigates how Generative AI (GenAI) can support legal fact verification in non-litigation practice, a high-stakes, interpretive task demanding defensible conclusions and tight accountability. Through semi-structured interviews with 18 lawyers, the study shows GenAI offers efficiency gains for orientation, drafting, and early-stage structuring but cannot replace professional judgment due to accuracy, confidentiality, and liability concerns. It argues for auditable, transparent, and specialized AI designs that surface provenance, provide layered reasoning, and preserve human oversight—seeing automation as a way to reorganize cognitive labor rather than replace expertise. The work contributes design insights for trustworthy human–AI collaboration in legal fact verification and highlights epistemic risks that must be managed for responsible deployment in high-stakes domains.

Abstract

Fact verification is a critical yet underexplored component of non-litigation legal practice. While existing research has examined automation in legal workflow and human-AI collaboration in high-stakes domains, little is known about how GenAI can support fact verification, a task that demands prudent judgment and strict accountability. To address this, we conducted semi-structured interviews with 18 lawyers to understand their current verification practices, attitudes toward GenAI adoption, and expectations for future systems. We found that while lawyers use GenAI for low-risk tasks like drafting and language optimization, concerns over accuracy, confidentiality, and liability are currently limiting its adoption for fact verification. These concerns translate into core design requirements for AI systems that are trustworthy and accountable. Based on these, we contribute design insights for human-AI collaboration in legal fact verification, emphasizing the development of auditable systems that balance efficiency with professional judgment and uphold ethical and legal accountability in high-stakes practice.
Paper Structure (30 sections, 1 figure, 1 table)

This paper contains 30 sections, 1 figure, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. Legal Technology for Fact Verification
  4. GenAI for Legal Practice
  5. Human-AI Collaboration in High-stakes Work
  6. Methodology
  7. Participants and Recruitment
  8. Data Collection
  9. Data Analysis
  10. Findings
  11. Current Practices
  12. Workflow of Fact Verification.
  13. Complexities in Fact Verification.
  14. GenAI Can Reduce Uncertainty and Burden in Fact Verification.
  15. Challenges Shaping GenAI Adoption
  16. ...and 15 more sections

Figures (1)

  • Figure 1: A Common Fact Verification Workflow Summarized from 18 Participants.