|
--- |
|
license: mit |
|
base_model: |
|
- meta-llama/Llama-3.2-3B-Instruct |
|
--- |
|
# DeepRetrieval |
|
## Overview |
|
|
|
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. |
|
## Key Features |
|
|
|
- **No Supervision Required**: Eliminates the need for expensive human-annotated or distilled reference queries |
|
- **RL-Based Framework**: Uses reinforcement learning to optimize query generation directly for retrieval performance |
|
- **State-of-the-Art Performance**: Achieves remarkable results across diverse retrieval tasks |
|
|
|
Please view our [GitHub page](https://github.com/pat-jj/DeepRetrieval) for instructions. |
|
|
|
[DeepRetrieval Paper](arxiv.org/abs/2503.00223) |
|
``` |
|
@article{jiang2025deepretrievalhackingrealsearch, |
|
title={DeepRetrieval: Hacking Real Search Engines and Retrievers with Large Language Models via Reinforcement Learning}, |
|
author={Pengcheng Jiang and Jiacheng Lin and Lang Cao and Runchu Tian and SeongKu Kang and Zifeng Wang and Jimeng Sun and Jiawei Han}, |
|
year={2025}, |
|
journal = {arXiv preprint arXiv: 2503.00223}, |
|
url={https://arxiv.org/abs/2503.00223} |
|
} |
|
``` |
