SOURCE-LINKED INTELLIGENCE

Retrieval-Guided Fine-Tuning as Noisy Estimation: Risk bounds and Architectural Analysis

arXiv · AI, language, vision and robotics · article · Sep 13, 2026 · UTC

Retrieval-Guided Fine-Tuning (RAG-FT) incorporates retrieved data directly into the training objective, but the statistical consequences of noisy retrieval during training remain theoretically undercharacterized. We study this question by modeling RAG-FT as an estimation problem in a multi-task linear regression framework, using an OLS proxy for single-layer linear self-attention to obtain finite-sample risk bounds. Under homoscedastic retrieval noise, we show that retrieval failure decays exponentially with task separation relative to noise, and derive explicit finite-sample conditions under

Read original source ↗ Open in workspace

recordType

paper

region

Global