| ---
|
| license: mit
|
| base_model:
|
| - Qwen/Qwen2.5-3B-Instruct
|
| language:
|
| - zho
|
| - eng
|
| - fra
|
| - spa
|
| - por
|
| - deu
|
| - ita
|
| - rus
|
| - jpn
|
| - kor
|
| - vie
|
| - tha
|
| - ara
|
| ---
|
| # 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}
|
| }
|
| ``` |
