ContractNLI
by Koreeda & Manning / Stanford NLP · open-source · Last verified 2026-03-17
ContractNLI is a natural language inference dataset for contract understanding. Given a contract and a hypothesis statement about the contract's content, models must classify the relationship as entailment, contradiction, or not-mentioned — simulating practical contract review tasks.
https://stanfordnlp.github.io/contract-nli/ ↗B
B—Above Average
Adoption: BQuality: AFreshness: BCitations: B+Engagement: F
Specifications
- License
- Apache-2.0
- Pricing
- open-source
- Capabilities
- evaluation, natural-language-inference, contract-analysis
- Integrations
- Use Cases
- model-evaluation, legal-ai, contract-review
- API Available
- No
- Evaluated Models
- gpt-4o, claude-opus-4, deberta-v3-large, roberta-large
- Metrics
- accuracy, f1-score
- Methodology
- 17 hypothesis templates tested against 607 non-disclosure agreements. Three-way classification (entailment / contradiction / not-mentioned) evaluated at the span level. Models are fine-tuned or prompted zero-shot.
- Last Run
- 2025-11-05
- Tags
- legal, nli, contract, document-understanding, classification
- Added
- 2026-03-17
- Completeness
- 100%
Index Score
60.8Adoption
63
Quality
84
Freshness
65
Citations
75
Engagement
0