LegalCiteBench: A Benchmark for Citation Reliability in Legal Language Models

LegalCiteBench is a benchmark dataset for evaluating citation reliability in legal language models. It covers tasks including closed-book citation retrieval, citation completion, citation error detection, case matching, and case verification and correction. The dataset was created by 'legalcitebench' and was last updated on 2026-05-06.

Use Cases

• Evaluating closed-book citation retrieval capabilities of legal language models.
• Benchmarking citation completion and error detection tasks.
• Testing case matching and verification algorithms.
• Training or fine-tuning models for legal document analysis.

Strengths

• Designed for multiple specific evaluation tasks (citation retrieval, completion, error detection, case matching, verification).
• Last updated on 2026-05-06, indicating recent maintenance.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Description metadata is limited; actual data quality requires manual inspection after download.

Provenance

Source

huggingface

Freshness

Last updated 2026-05-06 21:11:52