Latent Personality Alignment: Improving harmlessness without mentioning harms

Linh Le, David Williams-King, Mohamed Amine Merzouk, Aton Kamanda, Adam ObermanSubmission to ICLR 2026 · Withdrawn

Its authors withdrew this paper, so there is no full text to read or summarize.

Abstract

Current safety training methods for large language models rely on extensive datasets of harmful prompts paired with refusal responses, requiring many thousands of examples to achieve robustness against adversarial attacks. However, these approaches suffer from poor generalization to novel attack vectors and require substantial computational resources. We propose Latent Personality Alignment (LPA), a data-efficient alternative that trains models to embody beneficial personality traits rather than memorizing specific refusal patterns. Using fewer than 100 abstract personality statements, LPA guides models toward positive traits through latent adversarial training. Our approach achieves comparable safety performance to methods trained on hundreds of thousands of harmful examples while maintaining superior utility on benign tasks. These results suggest that personality-based alignment offers a more principled and scalable approach to harmlessness training than current methods.
BibTeX
@misc{le2026latent,
  author = {Linh Le and David Williams-King and Mohamed Amine Merzouk and Aton Kamanda and Adam Oberman},
  title = {{Latent Personality Alignment: Improving harmlessness without mentioning harms}},
  year = {2026},
  eprint = {2605.08496},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.08496},
}
Figure