Luis Kalckstein commited on
Add readme
Browse files
README.md
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
title: LLM PII Detection Leaderboard
|
| 3 |
+
emoji: 🔒
|
| 4 |
+
colorFrom: green
|
| 5 |
+
colorTo: indigo
|
| 6 |
+
sdk: gradio
|
| 7 |
+
sdk_version: "5.19.0"
|
| 8 |
+
app_file: app.py
|
| 9 |
+
pinned: false
|
| 10 |
+
license: apache-2.0
|
| 11 |
+
short_description: Comprehensive benchmark for PII detection performance
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
# LLM PII Detection Leaderboard
|
| 15 |
+
|
| 16 |
+
A comprehensive benchmark for evaluating language models' performance in detecting and handling personally identifiable information (PII) across various document types and scenarios.
|
| 17 |
+
|
| 18 |
+
## Features
|
| 19 |
+
|
| 20 |
+
- Interactive leaderboard with performance metrics
|
| 21 |
+
- Domain-specific analysis across Healthcare, Financial, Government, Legal, and Personal documents
|
| 22 |
+
- Model performance comparison and filtering
|
| 23 |
+
- Professional performance cards for presentations
|
| 24 |
+
|
| 25 |
+
## Usage
|
| 26 |
+
|
| 27 |
+
The leaderboard displays various metrics including:
|
| 28 |
+
- Overall Accuracy
|
| 29 |
+
- Precision and Recall
|
| 30 |
+
- F1 Score
|
| 31 |
+
- Over-detection Rate
|
| 32 |
+
- Processing Time and Cost
|
| 33 |
+
|
| 34 |
+
Filter by document type and model access to explore performance across different scenarios.
|
| 35 |
+
|
| 36 |
+
## Contributing
|
| 37 |
+
|
| 38 |
+
Contributions are welcome! Submit your results with a Google Colab notebook demonstrating your approach in the Community section.
|