Update README.md
Browse files
README.md
CHANGED
|
@@ -217,7 +217,7 @@ This is the text-only baseline configuration in the paper (no LIWC or context fe
|
|
| 217 |
## Performance (paper reference)
|
| 218 |
|
| 219 |
On the English ValueEval’24 sentence-level splits used in the paper, this baseline DeBERTa model achieves:
|
| 220 |
-
- Macro–F₁ (
|
| 221 |
|
| 222 |
The paper reports comparisons with:
|
| 223 |
- Presence-gated hierarchies
|
|
|
|
| 217 |
## Performance (paper reference)
|
| 218 |
|
| 219 |
On the English ValueEval’24 sentence-level splits used in the paper, this baseline DeBERTa model achieves:
|
| 220 |
+
- Macro–F₁ (2 values, test): ~0.58
|
| 221 |
|
| 222 |
The paper reports comparisons with:
|
| 223 |
- Presence-gated hierarchies
|