Update README.md
Browse files
README.md
CHANGED
|
@@ -14,7 +14,7 @@ It's live at [semblen.com](https://semblen.com), including an index of 2026 Sena
|
|
| 14 |
|
| 15 |
Our technique models are fine-tuned DeBERTa-v3-large multi-label classifiers: 16 technique heads, plus one that estimates whether the charged language belongs to a quoted speaker rather than the outlet. They're the first stage of the pipeline; a language model then explains each flag in plain words.
|
| 16 |
|
| 17 |
-
The models are private. Researchers can request access: email [
|
| 18 |
|
| 19 |
## How we work
|
| 20 |
|
|
@@ -22,4 +22,4 @@ The models are private. Researchers can request access: email [jason@semblen.com
|
|
| 22 |
- We audit flags by hand. In our last blind audit, about 1 in 10 was wrong.
|
| 23 |
- A flag is about how something is worded, not whether it's true or who's right.
|
| 24 |
|
| 25 |
-
Semblen LLC 路 Austin, Texas 路 [
|
|
|
|
| 14 |
|
| 15 |
Our technique models are fine-tuned DeBERTa-v3-large multi-label classifiers: 16 technique heads, plus one that estimates whether the charged language belongs to a quoted speaker rather than the outlet. They're the first stage of the pipeline; a language model then explains each flag in plain words.
|
| 16 |
|
| 17 |
+
The models are private. Researchers can request access: email [hello@semblen.com](mailto:hello@semblen.com).
|
| 18 |
|
| 19 |
## How we work
|
| 20 |
|
|
|
|
| 22 |
- We audit flags by hand. In our last blind audit, about 1 in 10 was wrong.
|
| 23 |
- A flag is about how something is worded, not whether it's true or who's right.
|
| 24 |
|
| 25 |
+
Semblen LLC 路 Austin, Texas 路 [hello@semblen.com](mailto:hello@semblen.com)
|