[Submitted on 8 Mar 2026 (v1), last revised 16 Oct 2026 (this version, v4)]
Abstract:Many RAG pipelines pay one LLM call per chunk at indexing time to add titles, summaries, keywords and questions (enrichment) or document context (contextual retrieval, CR). We ask what that call buys over free structure and a better retriever. Our advice: upgrade the retriever first, chunk at headers, and enrich mainly for lexical retrieval. Under a plan made public before any index was built, 7B enrichment beats a free section-path prefix under a hybrid retriever by +5.5 recall points on Qasper; on FreshStack its gain (+2.7) does not survive Holm adjustment. It is equivalent to CR, which sends 5.8-8.7 times the input tokens, and Qasper answer F1 (7B reader) is equivalent for both contrasts. Header-led chunks beat 512-character windows; on FreshStack they lose to overlapping 256-token windows. Under qwen3-embedding and a reranker, the two strongest of eight retrievers (named as secondary before any outcome was computed), the CIs of 7B enrichment against the free prefix fall within the equivalence margins; under BM25 it gains +8.7. Exploratory analyses attribute the hybrid gain to document expansion and to repairing an untuned rank fusion; the free prefix under either strong retriever beats hybrid enrichment by +3.4 to +6.3 points, though the best 120B-indexed configuration leads the best free one by +2.5 on Qasper. Add-ons built on the call do no better than LLM-free controls, and late chunking lowers Qasper recall. We release the plan, harness and per-question results.
Submission history
From: Bhavik Mangla [view email]
[v1] Sun, 8 Mar 2026 07:28:53 UTC (83 KB)
[v2] Fri, 27 Mar 2026 05:05:15 UTC (82 KB)
[v3] Fri, 2 Oct 2026 18:11:56 UTC (39 KB)
[v4] Fri, 16 Oct 2026 22:49:03 UTC (100 KB)
