MERGE: Multi-LLM Ensemble for Retrieval via Generative Enrichment
Merges query expansions from three small open-source LLMs into a single query for BM25, with every prompt tuned automatically against retrieval quality rather than hand-tuned per LLM.
📝 arxiv.org/abs/2609.37574
arxiv.org
MERGE: Multi-LLM Ensemble for Retrieval via Generative Enrichment
Large Language Models (LLMs) are increasingly used to enrich user queries in information retrieval (IR) so that a standard retriever such as BM25 can bridge vocabulary gaps with the target corpus. Any...