Personality Latents: Conditioning Frozen Language Models on Individuals from Their Own Writing

A new arXiv paper (2610.36805v1) introduces Personality Latents (PL), a method that learns a latent representation for each person from their own writing — with no personality labels and no authored profile — and injects it into a frozen language model as a soft prefix. On the MBTI axes, PL reaches an AUC ahead of persona embedding and prompt-based baselines under identical settings, and the ranking holds when answers are scored in three different embedding spaces. A latent learned with Qwen2.5-3B-Instruct also transfers personality to Llama-3.1-8B-Instruct through a new adapter alone.

arXiv:2610.36805v1 Announce Type: new Abstract: Controlling the personality of a language model usually relies on written profiles or named trait categories, so it can only express what an author writes down or what a taxonomy names. We instead propose Personality Latents PL , which learn a latent for each person from their own writing, with no personality labels and no authored profile, and inject it into a frozen language model as a soft prefix. Following generative latent optimization, each training person receives a free latent that is optimized through the frozen model itself, while an encoder learns to predict these latents so that a new person needs only one forward pass, with optional refinement at test time. We evaluate on held-out people by having the conditioned model answer neutral and interview questions and reading personality from its answers with scorers trained on real human writing. On the MBTI axes PL reaches an AUC of , ahead of persona embedding and prompt-based baselines under identical settings, and the ranking holds when the answers are scored in three different embedding spaces. A latent learned with Qwen2.5-3B-Instruct also transfers personality to Llama-3.1-8B-Instruct through a new adapter alone.