Update README.md
Browse files
README.md
CHANGED
|
@@ -17,6 +17,10 @@ We've found the representations to be performant for machine-text detection in p
|
|
| 17 |
We expect to release more performant versions of LUSR in the future.
|
| 18 |
We'll link all such versions here.
|
| 19 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
## Few-Shot Machine-text Detection
|
| 21 |
|
| 22 |
The following table shows machine-text detection performance on the M4 dataset using the same setup as: [Few-Shot Detection of Machine-Generated Text using Style Representations
|
|
|
|
| 17 |
We expect to release more performant versions of LUSR in the future.
|
| 18 |
We'll link all such versions here.
|
| 19 |
|
| 20 |
+
**Update 08/06/2026** - LUSR achieves the **top score** on the STEB-Operational benchmark and the **third-highest score** on the STEB-Definitional benchmark.
|
| 21 |
+
[STEB](https://arxiv.org/abs/2606.31741) is a comprehensive benchmark for style embeddings, spanning **96 datasets across 7 languages**.
|
| 22 |
+
See the STEB [leaderboard](https://rrivera1849.github.io/STEB/leaderboard/) and [codebase](https://github.com/rrivera1849/STEB).
|
| 23 |
+
|
| 24 |
## Few-Shot Machine-text Detection
|
| 25 |
|
| 26 |
The following table shows machine-text detection performance on the M4 dataset using the same setup as: [Few-Shot Detection of Machine-Generated Text using Style Representations
|