Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.16034 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911398832898048 |
|---|---|
| author | Cristofano, Tony |
| author_facet | Cristofano, Tony |
| contents | Refusal behavior in aligned LLMs is often viewed as model-specific, yet we hypothesize it stems from a universal, low-dimensional semantic circuit shared across models. To test this, we introduce Trajectory Replay via Concept-Basis Reconstruction, a framework that transfers refusal interventions from donor to target models, spanning diverse architectures (e.g., Dense to MoE) and training regimes, without using target-side refusal supervision. By aligning layers via concept fingerprints and reconstructing refusal directions using a shared ``recipe'' of concept atoms, we map the donor's ablation trajectory into the target's semantic space. To preserve capabilities, we introduce a weight-SVD stability guard that projects interventions away from high-variance weight subspaces to prevent collateral damage. Our evaluation across 8 model pairs confirms that these transferred recipes consistently attenuate refusal while maintaining performance, providing strong evidence for the semantic universality of safety alignment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_16034 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Universal Refusal Circuits Across LLMs: Cross-Model Transfer via Trajectory Replay and Concept-Basis Reconstruction Cristofano, Tony Computation and Language Refusal behavior in aligned LLMs is often viewed as model-specific, yet we hypothesize it stems from a universal, low-dimensional semantic circuit shared across models. To test this, we introduce Trajectory Replay via Concept-Basis Reconstruction, a framework that transfers refusal interventions from donor to target models, spanning diverse architectures (e.g., Dense to MoE) and training regimes, without using target-side refusal supervision. By aligning layers via concept fingerprints and reconstructing refusal directions using a shared ``recipe'' of concept atoms, we map the donor's ablation trajectory into the target's semantic space. To preserve capabilities, we introduce a weight-SVD stability guard that projects interventions away from high-variance weight subspaces to prevent collateral damage. Our evaluation across 8 model pairs confirms that these transferred recipes consistently attenuate refusal while maintaining performance, providing strong evidence for the semantic universality of safety alignment. |
| title | Universal Refusal Circuits Across LLMs: Cross-Model Transfer via Trajectory Replay and Concept-Basis Reconstruction |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2601.16034 |