Training-free Seek framework beats BM25 by 82% on BRIGHT via self-evaluative iteration

_reachsumit · x · 2026-09-25

Seek, a training-free retrieval framework accepted at CIKM 2026, addresses the single-pass limitation of LLM retrievers and rerankers, where missed documents are permanently lost.

Each round, an LLM generates pseudo-passages conditioned on accumulated relevance feedback, a retriever surfaces fresh candidates, and an assessor assigns graded relevance to guide subsequent rounds.

Original post →

More from Research

Research channel →