Spaces:
Running
Running
Update README.md
Browse files
README.md
CHANGED
@@ -1,15 +1,9 @@
|
|
1 |
# DeepRetrieval
|
2 |
-
|
3 |
## Overview
|
4 |
|
5 |
DeepRetrieval is a novel approach that uses reinforcement learning (RL) to train Large Language Models (LLMs) for query generation without requiring supervised data. Instead of relying on expensive human-annotated or distilled reference queries, DeepRetrieval enables LLMs to learn through direct trial and error, using retrieval metrics as rewards.
|
6 |
-
|
7 |
## Key Features
|
8 |
|
9 |
- **No Supervision Required**: Eliminates the need for expensive human-annotated or distilled reference queries
|
10 |
- **RL-Based Framework**: Uses reinforcement learning to optimize query generation directly for retrieval performance
|
11 |
-
- **State-of-the-Art Performance**: Achieves remarkable results across diverse retrieval tasks
|
12 |
-
-
|
13 |
-
## About
|
14 |
-
|
15 |
-
DeepRetrieval was developed by researchers from the UIUC CS. For more information, visit the [GitHub repository](https://github.com/pat-jj/DeepRetrieval).
|
|
|
1 |
# DeepRetrieval
|
|
|
2 |
## Overview
|
3 |
|
4 |
DeepRetrieval is a novel approach that uses reinforcement learning (RL) to train Large Language Models (LLMs) for query generation without requiring supervised data. Instead of relying on expensive human-annotated or distilled reference queries, DeepRetrieval enables LLMs to learn through direct trial and error, using retrieval metrics as rewards.
|
|
|
5 |
## Key Features
|
6 |
|
7 |
- **No Supervision Required**: Eliminates the need for expensive human-annotated or distilled reference queries
|
8 |
- **RL-Based Framework**: Uses reinforcement learning to optimize query generation directly for retrieval performance
|
9 |
+
- **State-of-the-Art Performance**: Achieves remarkable results across diverse retrieval tasks
|
|
|
|
|
|
|
|