Referral Augmentation for Zero-Shot Information Retrieval
This addresses the challenge of improving retrieval performance without training for researchers and practitioners in information retrieval, though it is incremental as it builds on existing indexing techniques.
The paper tackled the problem of zero-shot information retrieval by proposing Referral-Augmented Retrieval (RAR), which concatenates document indices with referrals from other documents, resulting in a 37% and 21% absolute improvement in Recall@10 on ACL paper retrieval compared to existing methods.
We propose Referral-Augmented Retrieval (RAR), a simple technique that concatenates document indices with referrals, i.e. text from other documents that cite or link to the given document, to provide significant performance gains for zero-shot information retrieval. The key insight behind our method is that referrals provide a more complete, multi-view representation of a document, much like incoming page links in algorithms like PageRank provide a comprehensive idea of a webpage's importance. RAR works with both sparse and dense retrievers, and outperforms generative text expansion techniques such as DocT5Query and Query2Doc a 37% and 21% absolute improvement on ACL paper retrieval Recall@10 -- while also eliminating expensive model training and inference. We also analyze different methods for multi-referral aggregation and show that RAR enables up-to-date information retrieval without re-training.