STORM: New Framework Improves Lexical Search by Optimizing Query Expansion with Retrieval Rewards
Researchers have introduced STORM, a self-supervised framework that improves BM25-based lexical retrieval by training language models to expand queries using token-level retrieval reward signals from beam search. The system addresses a longstanding limitation of lexical retrievers—vocabulary mismatch—without requiring the expensive corpus re-indexing that dense neural retrieval models demand. STORM's ability to match or outperform much larger proprietary rewriters while preserving BM25's speed and infrastructure simplicity could reduce the cost and complexity of deploying high-quality search systems.
STORM (Stepwise Token Optimization with Reward-guided beaM search) is a newly proposed framework for lexical query expansion that trains language model rewriters using retrieval metrics as a token-level training signal rather than relying on delayed, sequence-level supervision. At each generation step, candidate query expansions are scored against a BM25 index and low-reward continuations are pruned, allowing the model to concentrate on retrieval-effective vocabulary. Evaluated on TREC DL and BEIR benchmarks, models ranging from 0.6B to 8B parameters trained with STORM match or surpass competitive LLM-based rewriters while retaining BM25's retrieval speed. The 8B-parameter variant rivals far larger proprietary rewriting systems. Notably, STORM also transfers zero-shot to 18 languages on the MIRACL benchmark, outperforming dedicated multilingual dense retrievers on average—a result achieved without any multilingual fine-tuning. The framework requires no changes to the underlying inverted index when models are updated, making it a lightweight alternative to dense or learned-sparse neural retrieval systems that require full corpus re-encoding.
What different sources said
- arXiv cs.AICenter
STORM: Stepwise Token Optimization with Reward-Guided Beam Search
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.