Update README.md
Browse files
README.md
CHANGED
|
@@ -1,10 +1,25 @@
|
|
| 1 |
---
|
| 2 |
-
title:
|
| 3 |
-
emoji:
|
| 4 |
-
colorFrom:
|
| 5 |
colorTo: green
|
| 6 |
sdk: static
|
| 7 |
pinned: false
|
| 8 |
---
|
| 9 |
|
| 10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
title: LongLaMP Benchmark
|
| 3 |
+
emoji: 📝
|
| 4 |
+
colorFrom: blue
|
| 5 |
colorTo: green
|
| 6 |
sdk: static
|
| 7 |
pinned: false
|
| 8 |
---
|
| 9 |
|
| 10 |
+
# LongLaMP: A Benchmark for Personalized Long-form Text Generation
|
| 11 |
+
|
| 12 |
+
LongLaMP provides a comprehensive benchmark for evaluating personalized long-text generation across 4 diverse tasks:
|
| 13 |
+
|
| 14 |
+
1. Personalized Email Completion
|
| 15 |
+
2. Personalized Abstract Generation
|
| 16 |
+
3. Personalized Review Writing
|
| 17 |
+
4. Personalized Topic Writing
|
| 18 |
+
|
| 19 |
+
Key features:
|
| 20 |
+
- Focuses on generating longer, more complex personalized text (vs. short text)
|
| 21 |
+
- Includes user and temporal settings for each task
|
| 22 |
+
- Provides datasets, evaluation metrics, and baseline results
|
| 23 |
+
- Open source and extensible
|
| 24 |
+
|
| 25 |
+
Visit http://LongLaMP-benchmark.github.io for more details and to access the benchmark.
|