Update README.md
Browse files
README.md
CHANGED
|
@@ -7,7 +7,8 @@ sdk: static
|
|
| 7 |
pinned: false
|
| 8 |
---
|
| 9 |
|
| 10 |
-
[Project page](https://mj-bench.github.io/)
|
|
|
|
| 11 |
Multimodal judges reward models play a pivotal role in Reinforcement Learning from Human Feedback (RLHF) and Reinforcement Learning from AI Feedback (RLAIF). They serve as judges, providing crucial feedback to align foundation models (FMs) with desired behaviors. However, the evaluation of these multimodal judges often lacks thoroughness, leading to potential misalignment and unsafe fine-tuning outcomes.
|
| 12 |
|
| 13 |
To address this, we introduce **MJ-Bench**, a novel benchmark designed to evaluate multimodal judges using a comprehensive preference dataset. MJ-Bench assesses feedback for image generation models across four key perspectives: ***alignment***, ***safety***, ***image quality***, and ***bias***.
|
|
|
|
| 7 |
pinned: false
|
| 8 |
---
|
| 9 |
|
| 10 |
+
[Project page](https://mj-bench.github.io/)
|
| 11 |
+
|
| 12 |
Multimodal judges reward models play a pivotal role in Reinforcement Learning from Human Feedback (RLHF) and Reinforcement Learning from AI Feedback (RLAIF). They serve as judges, providing crucial feedback to align foundation models (FMs) with desired behaviors. However, the evaluation of these multimodal judges often lacks thoroughness, leading to potential misalignment and unsafe fine-tuning outcomes.
|
| 13 |
|
| 14 |
To address this, we introduce **MJ-Bench**, a novel benchmark designed to evaluate multimodal judges using a comprehensive preference dataset. MJ-Bench assesses feedback for image generation models across four key perspectives: ***alignment***, ***safety***, ***image quality***, and ***bias***.
|