NDA non-compliance clause detection on Macro-average 5 NDAs (Avg)
93.4AccuracyPolicyGuard
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| PolicyGuardBackbone=GPT-4.1, Zero-shot protocol=true2026.06 | 93.4 | 73.7 | |
| Majority ClassBackbone=GPT-4.1, Zero-shot protocol=true2026.06 | 86.5 | — | |
| Direct PromptingBackbone=GPT-4.1, Zero-shot protocol=true2026.06 | 75.8 | 42.2 | |
| Chain-of-ThoughtBackbone=GPT-4.1, Zero-shot protocol=true2026.06 | 75.1 | 42.4 | |
| Legal SyllogismBackbone=GPT-4.1, Zero-shot protocol=true2026.06 | 73.3 | 42.9 | |
| Legal ReasoningBackbone=GPT-4.1, Zero-shot protocol=true2026.06 | 73.2 | 42.9 |