STORM: Stepwise Token Optimization with Reward-Guided Beam Search
Researchers have developed STORM, a self-supervised framework for lexical query expansion that improves information retrieval. This method uses a reward-guided beam search to optimize token generation, making it more effective for retrieval tasks. STORM offers a competitive, infrastructure-light alternative to dense neural retrieval systems, achieving strong performance across various benchmarks and languages. AI
IMPACT Offers a more efficient and infrastructure-light alternative to dense neural retrieval, potentially improving search performance across many languages.