Signals 4 · free daily AI digest

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

Paper recorded by Signals 4 on 2026-08-31 in cs.AI. Abstract reproduced from arXiv; link to the original below.

Published 2026-08-31 on arXiv · recorded by Signals 4 on 2026-09-01

Category: cs.AI · 人工智能 · first seen 2026-09-01

Abstract

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

Read on arXiv →

#258 most recent of 300 cs.AI papers we have recorded · ↑ newer: LLM Judges Verify Presence, Not Absence: Omission Blindness in AI Clin · ↓ older: Evaluating and Improving LLM Self-Modeling
Cite this page: Stick to What You Know: A Study of Knowledge-Aligned Supervised Fine-Tuning: the #258 most recent of 300 cs.AI papers we have recorded (as of 2026-08-31). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/stick-to-what-you-know-a-study-of-knowledge-aligned-supervised-fine-tuning.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.AI papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions