QUESTER: Query Specification for Generative Retrieval
By: Arthur Satouf , Yuxuan Zong , Habiboulaye Amadou-Boubacar and more
Potential Business Impact:
Finds information faster using smart AI.
Generative Retrieval (GR) differs from the traditional index-then-retrieve pipeline by storing relevance in model parameters and directly generating document identifiers. However, GR often struggles to generalize and is costly to scale. We introduce QUESTER (QUEry SpecificaTion gEnerative Retrieval), which reframes GR as query specification generation - in this work, a simple keyword query handled by BM25 - using a (small) LLM. The policy is trained using reinforcement learning techniques (GRPO). Across in- and out-of-domain evaluations, we show that our model is more effective than BM25, and competitive with neural IR models, while maintaining a good efficiency
Similar Papers
Does Generative Retrieval Overcome the Limitations of Dense Retrieval?
Information Retrieval
Finds information by creating answers, not just searching.
DualGR: Generative Retrieval with Long and Short-Term Interests Modeling
Information Retrieval
Recommends videos users will watch longer.
ZeroGR: A Generalizable and Scalable Framework for Zero-Shot Generative Retrieval
Information Retrieval
Helps computers find information without prior training.