Gabliteration: Adaptive Multi-Directional Neural Weight Modification for Selective Behavioral Alteration in Large Language Models

• URL: http://arxiv.org/abs/2512.18901v1
• Date: Sun, 21 Dec 2025 22:12:54 GMT
• Title: Gabliteration: Adaptive Multi-Directional Neural Weight Modification for Selective Behavioral Alteration in Large Language Models
• Authors: Gökdeniz Gülmez,
• Abstract summary: We present Gabliteration, a novel neural weight modification technique.<n>We implement adaptive multi-directional projections with regularized layer selection.<n>We validate our method through the gabliterated-v1 model series available on Hugging Face.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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.

Related papers

• Improving Multi-Class Calibration through Normalization-Aware Isotonic Techniques [3.2514496966247535]
  We propose novel isotonic normalization-aware techniques for multiclass calibration.<n>Unlike prior approaches, our methods inherently account for probability normalization.<n>Our approach consistently improves negative log-likelihood (NLL) and expected calibration error (ECE) metrics.
  arXiv  Detail & Related papers  (2025-12-09T19:15:19Z)
• Test-Time Model Adaptation for Quantized Neural Networks [37.84294929199108]
  Quantized models often suffer from severe performance degradation in dynamic environments with potential domain shifts.<n>Test-time adaptation (TTA) has emerged as an effective solution by enabling models to learn adaptively from test data.<n>We propose a continual zeroth-order adaptation (ZOA) framework that enables efficient model adaptation using only two forward passes.
  arXiv  Detail & Related papers  (2025-08-04T08:24:19Z)
• Model Hemorrhage and the Robustness Limits of Large Language Models [119.46442117681147]
  Large language models (LLMs) demonstrate strong performance across natural language processing tasks, yet undergo significant performance degradation when modified for deployment.<n>We define this phenomenon as model hemorrhage - performance decline caused by parameter alterations and architectural changes.
  arXiv  Detail & Related papers  (2025-03-31T10:16:03Z)
• Training Deep Learning Models with Norm-Constrained LMOs [56.00317694850397]
  We propose a new family of algorithms that uses the linear minimization oracle (LMO) to adapt to the geometry of the problem.<n>We demonstrate significant speedups on nanoGPT training using our algorithm, Scion, without any reliance on Adam.
  arXiv  Detail & Related papers  (2025-02-11T13:10:34Z)
• Large Language Models to Diffusion Finetuning [20.251827725749607]
  We show our finetuned models achieve monotonically increasing accuracy, directly translating to improved performance across downstream tasks.<n>Our method is universally applicable to any foundation model pre-trained with a cross-entropy loss.
  arXiv  Detail & Related papers  (2025-01-27T04:59:29Z)
• Merging Models on the Fly Without Retraining: A Sequential Approach to Scalable Continual Model Merging [75.93960998357812]
  Deep model merging represents an emerging research direction that combines multiple fine-tuned models to harness their capabilities across different tasks and domains.<n>Current model merging techniques focus on merging all available models simultaneously, with weight matrices-based methods being the predominant approaches.<n>We propose a training-free projection-based continual merging method that processes models sequentially.
  arXiv  Detail & Related papers  (2025-01-16T13:17:24Z)
• Continuous Language Model Interpolation for Dynamic and Controllable Text Generation [6.280884105594514]
  We focus on the challenging case where the model must dynamically adapt to diverse -- and often changing -- user preferences.<n>We leverage adaptation methods based on linear weight, casting them as continuous multi-domain interpolators.<n>We show that varying the weights yields predictable and consistent change in the model outputs.
  arXiv  Detail & Related papers  (2024-04-10T15:55:07Z)
• When to Update Your Model: Constrained Model-based Reinforcement Learning [50.74369835934703]
  We propose a novel and general theoretical scheme for a non-decreasing performance guarantee of model-based RL (MBRL) Our follow-up derived bounds reveal the relationship between model shifts and performance improvement. A further example demonstrates that learning models from a dynamically-varying number of explorations benefit the eventual returns.
  arXiv  Detail & Related papers  (2022-10-15T17:57:43Z)
• A Variational Inference Approach to Inverse Problems with Gamma Hyperpriors [60.489902135153415]
  This paper introduces a variational iterative alternating scheme for hierarchical inverse problems with gamma hyperpriors. The proposed variational inference approach yields accurate reconstruction, provides meaningful uncertainty quantification, and is easy to implement.
  arXiv  Detail & Related papers  (2021-11-26T06:33:29Z)
• Gone Fishing: Neural Active Learning with Fisher Embeddings [55.08537975896764]
  There is an increasing need for active learning algorithms that are compatible with deep neural networks. This article introduces BAIT, a practical representation of tractable, and high-performing active learning algorithm for neural networks.
  arXiv  Detail & Related papers  (2021-06-17T17:26:31Z)
• Uncertainty Modelling in Risk-averse Supply Chain Systems Using Multi-objective Pareto Optimization [0.0]
  One of the arduous tasks in supply chain modelling is to build robust models against irregular variations. We have introduced a novel methodology namely, Pareto Optimization to handle uncertainties and bound the entropy of such uncertainties by explicitly modelling them under some apriori assumptions.
  arXiv  Detail & Related papers  (2020-04-24T21:04:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.