Intrinsic Guardrails: How Semantic Geometry of Personality Interacts with Emergent Misalignment in LLMs
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914554141736960 |
|---|---|
| author | Aneja, Krishak Mittal, Manas Goel, Anmol Kumaraguru, Ponnurangam Bonagiri, Vamshi Krishna |
| author_facet | Aneja, Krishak Mittal, Manas Goel, Anmol Kumaraguru, Ponnurangam Bonagiri, Vamshi Krishna |
| contents | Fine-tuning Large Language Models (LLMs) on benign narrow data can sometimes induce broad harmful behaviors, a vulnerability termed emergent misalignment (EM). While prior work links these failures to specific directions in the activation space, their relationship to the model's broader persona remains unexplored. We map the latent personality space of LLMs through established psychometric profiles like the Big Five, Dark Triad, and LLM-specific behaviors (e.g. evil, sycophancy), and show that the semantic geometry is highly stable across aligned models and their corrupted fine-tunes. Through causal interventions, we find that directions isolating social valence, such as the 'Evil' persona vector, and a Semantic Valence Vector (SVV) that we introduce, function as intrinsic guardrails: ablating them drives the misalignment rates above $40$%, while amplifying them suppresses the failure mode to less than $3$%. Leveraging the structural stability of the personality space, we show that vectors extracted $\textit{a priori}$ from an instruct-tuned model transfer zero-shot to successfully regulate EM in corrupted fine-tunes. Overall, our findings suggest that harmful fine-tuning does not overwrite a model's internal representation of personality, allowing conserved representations to serve as robust, cross-distribution guardrails. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_10633 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Intrinsic Guardrails: How Semantic Geometry of Personality Interacts with Emergent Misalignment in LLMs Aneja, Krishak Mittal, Manas Goel, Anmol Kumaraguru, Ponnurangam Bonagiri, Vamshi Krishna Computation and Language Artificial Intelligence Fine-tuning Large Language Models (LLMs) on benign narrow data can sometimes induce broad harmful behaviors, a vulnerability termed emergent misalignment (EM). While prior work links these failures to specific directions in the activation space, their relationship to the model's broader persona remains unexplored. We map the latent personality space of LLMs through established psychometric profiles like the Big Five, Dark Triad, and LLM-specific behaviors (e.g. evil, sycophancy), and show that the semantic geometry is highly stable across aligned models and their corrupted fine-tunes. Through causal interventions, we find that directions isolating social valence, such as the 'Evil' persona vector, and a Semantic Valence Vector (SVV) that we introduce, function as intrinsic guardrails: ablating them drives the misalignment rates above $40$%, while amplifying them suppresses the failure mode to less than $3$%. Leveraging the structural stability of the personality space, we show that vectors extracted $\textit{a priori}$ from an instruct-tuned model transfer zero-shot to successfully regulate EM in corrupted fine-tunes. Overall, our findings suggest that harmful fine-tuning does not overwrite a model's internal representation of personality, allowing conserved representations to serve as robust, cross-distribution guardrails. |
| title | Intrinsic Guardrails: How Semantic Geometry of Personality Interacts with Emergent Misalignment in LLMs |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2605.10633 |