IBM's STAIR uses tables of contents for generative retrieval, hitting 82.6% Recall@1

omarsar0 · x · 2026-09-07

IBM's STAIR paper tackles a familiar RAG pain point: retrievers chunk long documents by length, discarding the hierarchy the document already has.

Key ideas:

Results on the new SearchTome benchmark:

Original post →

More from Research

Research channel →