Commit
•
a31d0f4
1
Parent(s):
d48bb7a
Update README.md
Browse files
README.md
CHANGED
|
@@ -27,7 +27,7 @@ The General Preference Representation Model (GPM) improves preference-based rewa
|
|
| 27 |
|
| 28 |
## Evaluation
|
| 29 |
|
| 30 |
-
The GPM is evaluated using the [RewardBench](https://github.com/allenai/reward-bench) leaderboard, showing significant improvements over the BT model, with a performance margin of up to
|
| 31 |
|
| 32 |
## Usage
|
| 33 |
|
|
|
|
| 27 |
|
| 28 |
## Evaluation
|
| 29 |
|
| 30 |
+
The GPM is evaluated using the [RewardBench](https://github.com/allenai/reward-bench) leaderboard, showing significant improvements over the BT model, with a performance margin of up to 0.87%. GPM also excels in modeling cyclic preferences, achieving 100% accuracy on cyclic datasets.
|
| 31 |
|
| 32 |
## Usage
|
| 33 |
|