# Facet-Level Persona Control by Trait-Activated Routing with Contrastive SAE for Role-Playing LLMs

arXiv: https://arxiv.org/abs/2602.19157 · HTML: https://mlsanity.com/paper/2602.19157/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Activation steering methods, one of 13 directions in Mechanistic interpretability.
- Builds on 18 of its 31 references that are in the map.
- First posted on arXiv 22 Feb 2026.

## Placed in

- Mechanistic interpretability / [Activation steering methods](https://mlsanity.com/mechinterp/activation-steering-methods/)

## Builds on (most cited first, 18 of 18)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [CTRL: A Conditional Transformer Language Model for Controllable Generation](https://mlsanity.com/paper/1909.05858/) (2019)
- [Persona Vectors: Monitoring and Controlling Character Traits in Language Models](https://mlsanity.com/paper/2507.21509/) (2025)
- [From Persona to Personalization: A Survey on Role-Playing Language Agents](https://mlsanity.com/paper/2404.18231/) (2024)
- [Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization](https://mlsanity.com/paper/2406.01171/) (2024)
- [InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews](https://mlsanity.com/paper/2310.17976/) (2023)
- [A Plug-and-Play Method for Controlled Text Generation](https://mlsanity.com/paper/2109.09707/) (2021)
- [Style Vectors for Steering Generative Large Language Model](https://mlsanity.com/paper/2402.01618/) (2024)
- [Steering off Course: Reliability Challenges in Steering Language Models](https://mlsanity.com/paper/2504.04635/) (2025)
- [SAE-SSV: Supervised Steering in Sparse Representation Spaces for Reliable Control of Language Models](https://mlsanity.com/paper/2505.16188/) (2025)
- [Identifying and Manipulating Personality Traits in LLMs Through Activation Engineering](https://mlsanity.com/paper/2412.10427/) (2024)
- [Improving LLM Reasoning through Interpretable Role-Playing Steering](https://mlsanity.com/paper/2506.07335/) (2025)
- [Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering](https://mlsanity.com/paper/2505.15038/) (2025)

## Abstract (arXiv)

Personality control in Role-Playing Agents (RPAs) is commonly achieved via training-free methods that inject persona descriptions and memory through prompts or retrieval-augmented generation, or via supervised fine-tuning (SFT) on persona-specific corpora. While SFT can be effective, it requires persona-labeled data and retraining for new roles, limiting flexibility. In contrast, prompt- and RAG-based signals are easy to apply but can be diluted in long dialogues, leading to drifting and sometimes inconsistent persona behavior. To address this, we propose a contrastive Sparse AutoEncoder (SAE) framework that learns facet-level personality control vectors aligned with the Big Five 30-facet model. A new 15,000-sample leakage-controlled corpus is constructed to provide balanced supervision for each facet. The learned vectors are integrated into the model's residual space and dynamically selected by a trait-activated routing module, enabling precise and interpretable personality steering. Experiments on Large Language Models (LLMs) show that the proposed method maintains stable character fidelity and output quality across contextualized settings, outperforming Contrastive Activation Addition (CAA) and prompt-only baselines. The combined SAE+Prompt configuration achieves the best overall performance, confirming that contrastively trained latent vectors can enhance persona control while preserving dialogue coherence. Dataset is available at: https://github.com/lunat5078/BigFive-Personality-Facets-Dataset