Gabliteration: Adaptive Multi-Directional Neural Weight Modification for Selective Behavioral Alteration in Large Language Models
Fuente:
arXiv
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908793845055488 |
|---|---|
| author | Gülmez, Gökdeniz |
| author_facet | Gülmez, Gökdeniz |
| contents | We present Gabliteration, a novel neural weight modification technique that advances beyond traditional abliteration methods by implementing adaptive multi-directional projections with regularized layer selection. Our approach addresses the fundamental limitation of existing methods that compromise model quality while attempting to modify specific behavioral patterns. Through dynamic layer optimization, regularized projection matrices, and adaptive scaling mechanisms, we achieve theoretically superior weight modification while minimizing quality degradation in unrelated domains. We validate our method through the gabliterated-v1 model series (0.6B to 4B parameters) available on Hugging Face, demonstrating practical applicability across multiple model scales. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_18901 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Gabliteration: Adaptive Multi-Directional Neural Weight Modification for Selective Behavioral Alteration in Large Language Models Gülmez, Gökdeniz Artificial Intelligence Machine Learning We present Gabliteration, a novel neural weight modification technique that advances beyond traditional abliteration methods by implementing adaptive multi-directional projections with regularized layer selection. Our approach addresses the fundamental limitation of existing methods that compromise model quality while attempting to modify specific behavioral patterns. Through dynamic layer optimization, regularized projection matrices, and adaptive scaling mechanisms, we achieve theoretically superior weight modification while minimizing quality degradation in unrelated domains. We validate our method through the gabliterated-v1 model series (0.6B to 4B parameters) available on Hugging Face, demonstrating practical applicability across multiple model scales. |
| title | Gabliteration: Adaptive Multi-Directional Neural Weight Modification for Selective Behavioral Alteration in Large Language Models |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2512.18901 |