Bohdan Turbal

Max Springer, Chung Peng Lee, Blossom Metevier et al.

Fine-tuning aligned language models on benign tasks unpredictably degrades safety guardrails, even when training data contains no harmful content and developers have no adversarial intent. We show that the prevailing explanation, that fine-tuning updates should be orthogonal to safety-critical directions in high-dimensional parameter space, offers false reassurance: we show this orthogonality is structurally unstable and collapses under the dynamics of gradient descent. We then resolve this through a novel geometric analysis, proving that alignment concentrates in low-dimensional subspaces with sharp curvature, creating a brittle structure that first-order methods cannot detect or defend. While initial fine-tuning updates may indeed avoid these subspaces, the curvature of the fine-tuning loss generates second-order acceleration that systematically steers trajectories into alignment-sensitive regions. We formalize this mechanism through the Alignment Instability Condition, three geometric properties that, when jointly satisfied, lead to safety degradation. Our main result establishes a quartic scaling law: alignment loss grows with the fourth power of training time, governed by the sharpness of alignment geometry and the strength of curvature coupling between the fine-tuning task and safety-critical parameters. These results expose a structural blind spot in the current safety paradigm. The dominant approaches to safe fine-tuning address only the initial snapshot of a fundamentally dynamic problem. Alignment fragility is not a bug to be patched; it is an intrinsic geometric property of gradient descent on curved manifolds. Our results motivate the development of curvature-aware methods, and we hope will further enable a shift in alignment safety analysis from reactive red-teaming to predictive diagnostics for open-weight model deployment.

Bohdan Turbal, Blossom Metevier, Max Springer et al.

Fine-tuning aligned language models on benign tasks (e.g. math tutoring) systematically breaks safety guardrails, even when training data contains no harmful content. While mechanistic approaches have shed light on where alignment resides in model weights, they do not by provide a general formal framework for deriving guarantees about when fine-tuning degrades it -- leaving the field without principled tools for predicting or preventing alignment collapse. We develop a local geometric framework through geometric analysis of parameter-space trajectories and apply it to understand the fragility of alignment in fine-tuning. While first-order analysis suggests orthogonal updates are safe, we prove this is illusory: the curvature of the fine-tuning loss induces second-order acceleration that can induce second-order drift into alignment-sensitive regions. We formalize a construct of our framework as the Alignment Instability Condition (AIC), three geometric properties that, when present, are sufficient to guarantee degradation. Our main result proves quartic onset of alignment degradation along gradient-flow trajectories, determined by how sharply alignment depends on specific parameters and how strongly tasks couple to these parameters. These findings yield formal sufficient conditions under which static first-order protection can fail under gradient descent. We further empirically validate the framework's foundations, showing that the Fisher Information Matrix provides a proxy for the degree of safety degradation across diverse fine-tuning.

Bohdan Turbal, Anastasiia Mazur, Jiaxu Zhao et al.

We investigate the adversarial robustness of LLMs in transfer learning scenarios. Through comprehensive experiments on multiple datasets (MBIB Hate Speech, MBIB Political Bias, MBIB Gender Bias) and various model architectures (BERT, RoBERTa, GPT-2, Gemma, Phi), we reveal that transfer learning, while improving standard performance metrics, often leads to increased vulnerability to adversarial attacks. Our findings demonstrate that larger models exhibit greater resilience to this phenomenon, suggesting a complex interplay between model size, architecture, and adaptation methods. Our work highlights the crucial need for considering adversarial robustness in transfer learning scenarios and provides insights into maintaining model security without compromising performance. These findings have significant implications for the development and deployment of LLMs in real-world applications where both performance and robustness are paramount.