Multi-task Retrieval for Knowledge-Intensive Tasks
This work is significant for researchers and practitioners working on knowledge-intensive tasks, as it provides a more robust and universal neural retrieval model that performs well across various domains, addressing the common problem of performance degradation on out-of-domain data.
The paper addresses the problem of neural retrieval models degrading on out-of-domain data by proposing a multi-task trained model. This model outperforms previous methods in few-shot settings and rivals specialized neural retrievers even with abundant in-domain data, leading to improved state-of-the-art performance on multiple benchmarks for downstream tasks.
Retrieving relevant contexts from a large corpus is a crucial step for tasks such as open-domain question answering and fact checking. Although neural retrieval outperforms traditional methods like tf-idf and BM25, its performance degrades considerably when applied to out-of-domain data. Driven by the question of whether a neural retrieval model can be universal and perform robustly on a wide variety of problems, we propose a multi-task trained model. Our approach not only outperforms previous methods in the few-shot setting, but also rivals specialised neural retrievers, even when in-domain training data is abundant. With the help of our retriever, we improve existing models for downstream tasks and closely match or improve the state of the art on multiple benchmarks.