# Probing Persona-Dependent Preferences in Language Models

arXiv: https://arxiv.org/abs/2605.13339 · HTML: https://mlsanity.com/paper/2605.13339/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 48 references that are in the map.
- First posted on arXiv 13 May 2026.

## Builds on (most cited first, 30 of 33)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [Refusal in Language Models Is Mediated by a Single Direction](https://mlsanity.com/paper/2406.11717/) (2024)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets](https://mlsanity.com/paper/2310.06824/) (2023)
- [WildChat: 1M ChatGPT Interaction Logs in the Wild](https://mlsanity.com/paper/2405.01470/) (2024)
- [Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection](https://mlsanity.com/paper/2004.07667/) (2020)
- [Persona Vectors: Monitoring and Controlling Character Traits in Language Models](https://mlsanity.com/paper/2507.21509/) (2025)
- [Role-Play with Large Language Models](https://mlsanity.com/paper/2305.16367/) (2023)
- [Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs](https://mlsanity.com/paper/2502.17424/) (2025)
- [Language Models as Agent Models](https://mlsanity.com/paper/2212.01681/) (2022)
- [The Assistant Axis: Situating and Stabilizing the Default Persona of Language Models](https://mlsanity.com/paper/2601.10387/) (2026)
- [CREAK: A Dataset for Commonsense Reasoning over Entity Knowledge](https://mlsanity.com/paper/2109.01653/) (2021)
- [LLMs Encode Harmfulness and Refusal Separately](https://mlsanity.com/paper/2507.11878/) (2025)
- [Detecting Strategic Deception Using Linear Probes](https://mlsanity.com/paper/2502.03407/) (2025)
- [Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs](https://mlsanity.com/paper/2502.08640/) (2025)
- [Emotion Concepts and their Function in a Large Language Model](https://mlsanity.com/paper/2604.07729/) (2026)
- [Randomness, Not Representation: The Unreliability of Evaluating Cultural Alignment in LLMs](https://mlsanity.com/paper/2503.08688/) (2025)
- [Values in the Wild: Discovering and Analyzing Values in Real-World Language Model Interactions](https://mlsanity.com/paper/2504.15236/) (2025)
- [Taking AI Welfare Seriously](https://mlsanity.com/paper/2411.00986/) (2024)
- [Steering MoE LLMs via Expert (De)Activation](https://mlsanity.com/paper/2509.09660/) (2025)
- [Open Character Training: Shaping the Persona of AI Assistants through Constitutional AI](https://mlsanity.com/paper/2511.01689/) (2025)
- [Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas](https://mlsanity.com/paper/2505.14633/) (2025)
- [Can LLMs make trade-offs involving stipulated pain and pleasure states?](https://mlsanity.com/paper/2411.02432/) (2024)
- [Stress-Testing Model Specs Reveals Character Differences among Language Models](https://mlsanity.com/paper/2510.07686/) (2025)
- [Alignment Revisited: Are Large Language Models Consistent in Stated and Revealed Preferences?](https://mlsanity.com/paper/2506.00751/) (2025)
- [Linear representations in language models can change dramatically over a conversation](https://mlsanity.com/paper/2601.20834/) (2026)
- [Where is the Mind? Persona Vectors and LLM Individuation](https://mlsanity.com/paper/2604.17031/) (2026)

## Built on by (most cited first, 3 of 3)

- [AI Revealed Preferences](https://mlsanity.com/paper/2608.26178/) (2026)
- [Readable, Faithful, Used: Three Dissociable Properties of Demographic Identity in a Language Model](https://mlsanity.com/paper/2608.18768/) (2026)
- [Language Models Act on Hidden Valence](https://mlsanity.com/paper/2609.35591/) (2026)

## Abstract (arXiv)

Large language models (LLMs) can be said to have preferences: they reliably pick certain tasks and outputs over others, and preferences shaped by post-training and prompting appear to influence much of their behaviour. But models can also adopt different personas which have radically different preferences. How is this implemented internally? Does each persona use its own preference representations, or are some representations shared? We train linear probes on residual-stream activations of Gemma-3-27B and Qwen-3.5-122B to predict revealed pairwise task choices, and identify a genuine preference vector: it tracks the model's preferences as they shift across a range of prompts and situations, and on Gemma-3-27B steering along it causally controls pairwise choice. Some preference information transfers across the prompted personas we test: a probe trained on the helpful assistant predicts and steers the choices of qualitatively different personas, including an evil persona whose preferences anti-correlate with the Assistant's.