# Preprint reports search gains from combining model-generated query expansions

_Published Thursday, October 1, 2026 at 2:06 AM EDT · AI, Science · Latest · Tier 2 — Notable_

Researchers report that MERGE, a framework that combines query expansions from multiple language models, improved search ranking scores by +2.1 to +14.9 points over original queries on five BEIR benchmarks. The preprint tests a way to bridge vocabulary differences between search queries and documents.

Three open-source models independently expand each query, and a larger model synthesizes their outputs. An automatic prompt optimization loop selects prompts using downstream retrieval performance. The resulting query requires a single pass through BM25, a conventional document retriever, without re-indexing or combining separate rankings. The results remain benchmark findings rather than evidence of deployment performance.

## Sources

- [cs.CL updates on arXiv.org](https://arxiv.org/abs/2609.37574)

---
Canonical: https://techandbusiness.org/newswire/1rRKYgLjdLJeWaUeYSVSYz
Published: 2026-10-01T06:06:36.109Z
Story chronology: 2026-10-01T04:00:00.000Z
Retrieved: 2026-10-01T08:28:56.373Z
Publisher: Tech & Business (techandbusiness.org)