SOURCE-LINKED INTELLIGENCE

Per-Query Gating of LLM Rerankers for Multi-Hop Retrieval

arXiv · AI, language, vision and robotics · article · Sep 19, 2026 · UTC

LLM rerankers add of the order of \$0.2-0.3 per 1,000 queries and about a second of tail latency on top of a graph-augmented dense pipeline such as HippoRAG2, and on three multi-hop benchmarks they improve final-hop top-K coverage on seven of nine (dataset, K) cells, by up to +34.8 pp. We ask whether a learned per-query gate can skip the reranker where it will not help, using only features available before the LLM call (27 score and lexical statistics of the two retrieval lists plus a PCA of a small query embedding) with an executable fallback. Every choice, including the fallback and the thre

Read original source ↗ Open in workspace

recordType

paper

region

Global