Preprint
Sep 2026
Can Generative Retrievers Learn Semantic IDs Without Forgetting How to Speak?
Generative retrieval (GR) enables end-to-end retrieval by generating document semantic identifiers (SIDs). However, retrieval-only fine-tuning can over-specialize pretrained language models to SID prediction, substantially distorting their natural-language distribution and limiting their suitability for interactive sys...
Junchen Fu, Kleomenis Katevas, Vandana Rajan et al.
· 0 citations