Continually Updating Generative Retrieval on Dynamic Corpora

The majority of prior work on information retrieval (IR) assumes that the corpus is static, whereas in the real world, the documents are continually updated. In this paper, we incorporate often overlooked dynamic nature of knowledge into the retrieval systems. Our work treats retrieval not as static archives but as dynamic knowledge bases better aligned with real-world environments. We conduct a comprehensive evaluation of dual encoders and generative retrieval, utilizing the StreamingQA benchmark designed for the temporal knowledge updates. Our initial results show that while generative retrieval outperforms dual encoders in static settings, the opposite is true in dynamic settings. Surprisingly, however, when we utilize a parameter-efficient pre-training method to enhance adaptability of generative retrieval to new corpora, our resulting model, Dynamic Generative Retrieval (DynamicGR), exhibits unexpected findings. It (1) efficiently compresses new knowledge in their internal index, attaining a remarkable storage capacity due to its fully parametric architecture and (2) outperforms dual encoders not only in static settings but in dynamic scenarios with a 5% margin in hit@5, requiring 4 times less training time.