# MixLoRA-DSI: Dynamically Expandable Mixture-of-LoRA Experts for Rehearsal-Free Generative Retrieval over Dynamic Corpora Source: [MixLoRA-DSI: Dynamically Expandable Mixture-of-LoRA Experts for Rehearsal-Free Generative Retrieval over Dynamic Corpora]() Collection index: [llms.txt]() Data updated: 2025-10-26T05:09:30.174Z Authors: Tuan-Luc Huynh, Thuy-Trang Vu, Weiqing Wang, Trung Le, Dragan Ga\\v{s}evi\\'c, Yuan-Fang Li, Thanh-Toan Do Published: 2025-07-14T05:04:32.000Z ## Abstract Continually updating model-based indexes in generative retrieval with new documents remains challenging, as full retraining is computationally expensive and impractical under resource constraints. We propose MixLoRA-DSI, a novel framework that combines an expandable mixture of Low-Rank Adaptation experts with a layer-wise out-of-distribution (OOD)-driven expansion strategy. Instead of allocating new experts for each new corpus, our proposed expansion strategy enables sublinear parameter growth by selectively introducing new experts only when significant number of OOD documents are detected. Experiments on NQ320k and MS MARCO Passage demonstrate that MixLoRA-DSI outperforms full-model update baselines, with minimal parameter overhead and substantially lower training costs. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Continual Generative Information Retrieval on Natural Questions](): Continual Generative Information Retrieval; Natural Questions; D0 Score: 77.89. - [Continual Generative Information Retrieval on MS MARCO](): Continual Generative Information Retrieval; MS Marco; Score D0: 65.27. ## Original sources and implementation [Original paper]() [PDF]()