Research map / Large language models / Language, safety and interpretability
CUAD: An Expert-Annotated NLP Dataset for Legal Contract Review
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| domain-specific MLM pretraining on 8GB of contracts | RoBERTa-base · CUAD | AUPR: 42.6 -> 45.2 | Helped |
| scale BERT-base to BERT-large | BERT · CUAD | AUPR: 32.4 -> 32.3 | No clear effect |
| scale ALBERT-base to ALBERT-xxlarge | ALBERT · CUAD | AUPR: 35.3 -> 38.4 | Helped |
| scale RoBERTa-base to RoBERTa-large | RoBERTa · CUAD | AUPR: 42.6 -> 48.2 | Helped |
| increase training data by 10x | RoBERTa-base · CUAD | AUPR: 27.6% -> 42.6% | Helped |
| DeBERTa-xlarge instead of BERT-base | contract review model · CUAD | Precision@80% Recall: 8.2 -> 44.0 | Helped |
| downweight features without labels to balance training | all models · CUAD | AUPR | Helped |
Closest papers by meaning
- Lawma: The Power of Specialization for Legal Annotation (ICLR 2025 · similarity 0.85)
- LexEval: A Comprehensive Chinese Legal Benchmark for Evaluating Large Language Models (NeurIPS 2024 · similarity 0.82)
- The SEC Filings Dataset: Reconstructing U.S. Corporate and Financial Disclosures into Layout-Faithful and Token-Efficient Pretraining Data (NeurIPS 2026 · similarity 0.81)
- Neither Valid nor Reliable? Investigating the Use of LLMs as Judges (NeurIPS 2025 · similarity 0.81)
- Interpretable Long-Form Legal Question Answering with Retrieval-Augmented Large Language Models (AAAI 2024 · similarity 0.81)
- SaulLM-54B & SaulLM-141B: Scaling Up Domain Adaptation for the Legal Domain (NeurIPS 2024 · similarity 0.81)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.