LegalCiteTrust
LegalCiteTrust evaluates citation trustworthiness in Chinese long-form legal research reports, assessing coverage, support, and citation-level existence, fidelity, and applicability.
- Released
- 2026-07-23
- Readiness
- Paper only
- Primary field
- General AI
Why it matters
Long-form legal research reports increasingly rely on LLMs, but citation trustworthiness is critical for legal accuracy. This benchmark addresses the gap by measuring whether citations are not only real but also accurate and applicable, providing a more nuanced evaluation than simple existence checks.
Motivation
Long-form legal research reports increasingly rely on LLMs and agentic research systems, but their reliability depends not only on answering the task, but also on whether cited legal authorities are trustworthy.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.