SOURCE-LINKED INTELLIGENCE

Stick to What You Know: A Study of Knowledge-Aligned Supervised Fine-Tuning

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Supervised fine-tuning (SFT) trains a base language model to imitate target responses, and these targets may require knowledge the base model has not robustly internalized. We study this as a source of hallucinations and frame a group of mitigation methods as \emph{knowledge-aligned SFT}: constraining SFT training targets to the base model's parametric knowledge. Under a unified setup, we compare existing generation-based and estimation-based knowledge-alignment methods and introduce two new variants: Evidence Rewrite, which verifies base-model generations using external evidence, and Recall R

Read original source ↗ Open in workspace

recordType

paper

region

Global