We study the problem of retrieval with instructions, where users of a retrieval system explicitly describe their intent along with their queries. We aim to develop a general-purpose task-aware retrieval system using multi-task instruction tuning, which can follow human-written instructions to find the best documents for a given query. We introduce the first large-scale collection of approximately 40 retrieval datasets with instructions, BERRI, and present TART, a multi-task retrieval system trained on BERRI with instructions. TART shows strong capabilities to adapt to a new retrieval task via instructions and advances the state of the art on two zero-shot retrieval benchmarks, BEIR and LOTTE, outperforming models up to three times larger. We further introduce a new evaluation setup, X^2-Retrieval to better reflect real-world scenarios, where diverse domains and tasks are pooled and a system needs to find documents aligning users' intents. In this setup, TART significantly outperforms competitive baselines, further demonstrating the effectiveness of guiding retrieval with instructions.
@article{arxiv.2211.09260,
title = {Task-aware Retrieval with Instructions},
author = {Akari Asai and Timo Schick and Patrick Lewis and Xilun Chen and Gautier Izacard and Sebastian Riedel and Hannaneh Hajishirzi and Wen-tau Yih},
journal= {arXiv preprint arXiv:2211.09260},
year = {2022}
}
Comments
Code, data and pretrained model checkpoints are available at https://github.com/facebookresearch/tart