PromptDSI: Prompt-based Rehearsal-free Instance-wise Incremental Learning for Document Retrieval

Differentiable Search Index (DSI) utilizes Pre-trained Language Models (PLMs) for efficient document retrieval without relying on external indexes. However, DSI needs full re-training to handle updates in dynamic corpora, causing significant computational inefficiencies. We introduce PromptDSI, a prompt-based rehearsal-free approach for instance-wise incremental learning document retrieval. PromptDSI attaches prompts to the frozen PLM's encoder of DSI, leveraging its powerful representation to efficiently index new corpora while maintaining a balance between stability and plasticity. We eliminate the initial forward pass of prompt-based continual learning methods that doubles training and inference time. Moreover, we propose a topic-aware prompt pool that employs neural topic embeddings as fixed keys. This strategy ensures diverse and effective prompt usage, addressing the challenge of parameter underutilization caused by the collapse of the query-key matching mechanism. Our empirical evaluations demonstrate that BERT-based PromptDSI matches IncDSI in managing forgetting while improving new corpora performance by more than 4% Hits@10 on NQ320k and upto 3% MRR@10 on MS MARCO 300k.

@article{huynh2025_2406.12593,
  title={ PromptDSI: Prompt-based Rehearsal-free Instance-wise Incremental Learning for Document Retrieval },
  author={ Tuan-Luc Huynh and Thuy-Trang Vu and Weiqing Wang and Yinwei Wei and Trung Le and Dragan Gasevic and Yuan-Fang Li and Thanh-Toan Do },
  journal={arXiv preprint arXiv:2406.12593},
  year={ 2025 }
}