IAR Framework: 3-Stage Post-Training for Retrieval-Free Knowledge Internalization

_reachsumit · x · 2026-08-21

The paper presents IAR (Inject, Align, Recover), a three-stage post-training framework designed to internalize document collections into parametric knowledge for retrieval-free QA. The method consists of:

Experiments on Llama, Phi, Qwen, and SmolLM show that IAR improves domain QA accuracy by an average of 3.6 percentage points and general performance (IFEval, MMLU, MSBench) by 12.1 percentage points, outperforming Vanilla SFT.

Related event: BAAI Unveils IAR Framework for Retrieval-Free Knowledge Injection(2 posts)→

Original post →

More from Research

Research channel →