Importance-Aligned Normalization: Controlling Per-Fact Recall Strength in Supervised Fine-Tuning

Supervised fine-tuning (SFT) is the standard means of injecting new facts into a language model, but it does not control how strongly, or from which direction, each injected fact will be recalled. We propose Importance-Aligned Normalization (IAN), an objective that injects a per-instance importance scalar w in [0, 1] into the training signal to modulate per-fact recall strength. IAN normalizes each per-sequence gradient to unit norm, multiplies it by w, and adds a bidirectional auxiliary objective that re-reads the same sequence under a bidirectional mask and predicts the subject tokens, with a coefficient proportional to w^2. The data are left unchanged; only the gradient combination rule changes. Injecting 300 facts into Gemma 3 4B, 12B, and 27B and measuring at the fact level, we find that importance modulates reverse recall at all three sizes (Spearman 0.21-0.23 averaged over three importance assignments; uniform SFT is near 0), and that both reverse recall and preservation of pre-existing known facts exceed those of uniform SFT at equal compute. Same-data, equal-compute ablations show that interference suppression comes from per-sequence gradient normalization, the slope comes from w, and the reverse direction requires a fact-level signal rather than KL distillation. The same framework also applies to self-distillation teacher rows.

Authors

Institutions

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-16
DOI
https://doi.org/10.5281/zenodo.24270228
Primary Topic
Topic Modeling
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Importance-Aligned Normalization: Controlling Per-Fact Recall Strength in Supervised Fine-Tuning

Kwangsu Kim
2 links
Zenodo (CERN European Organization for Nuclear Research)
Topic Modeling
preprint

Importance-Aligned Normalization: Controlling Per-Fact Recall Strength in Supervised Fine-Tuning

Kwangsu Kim
preprint en

Abstract

Supervised fine-tuning (SFT) is the standard means of injecting new facts into a language model, but it does not control how strongly, or from which direction, each injected fact will be recalled. We propose Importance-Aligned Normalization (IAN), an objective that injects a per-instance importance scalar w in [0, 1] into the training signal to modulate per-fact recall strength. IAN normalizes each per-sequence gradient to unit norm, multiplies it by w, and adds a bidirectional auxiliary objective that re-reads the same sequence under a bidirectional mask and predicts the subject tokens, with a coefficient proportional to w^2. The data are left unchanged; only the gradient combination rule changes. Injecting 300 facts into Gemma 3 4B, 12B, and 27B and measuring at the fact level, we find that importance modulates reverse recall at all three sizes (Spearman 0.21-0.23 averaged over three importance assignments; uniform SFT is near 0), and that both reverse recall and preservation of pre-existing known facts exceed those of uniform SFT at equal compute. Same-data, equal-compute ablations show that interference suppression comes from per-sequence gradient normalization, the slope comes from w, and the reverse direction requires a fact-level signal rather than KL distillation. The same framework also applies to self-distillation teacher rows.

Zenodo (CERN European Organization for Nuclear Research)
Kookmin University (KR)
Topic Modeling
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon