# Stable and Explainable Personality Trait Evaluation in Large Language Models with Internal Activations

arXiv: https://arxiv.org/abs/2601.09833 · HTML: https://mlsanity.com/paper/2601.09833/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 43 references that are in the map.
- First posted on arXiv 14 Jan 2026.

## Builds on (most cited first, 20 of 20)

- [Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning](https://mlsanity.com/paper/2205.05638/) (2022)
- [PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traits](https://mlsanity.com/paper/2305.02547/) (2023)
- [Personality Traits in Large Language Models](https://mlsanity.com/paper/2307.00184/) (2023)
- [Which of These Best Describes Multiple Choice Evaluation with LLMs? A) Forced B) Flawed C) Fixable D) All of the Above](https://mlsanity.com/paper/2502.14127/) (2025)
- [BIG5-CHAT: Shaping LLM Personalities Through Training on Human-Grounded Data](https://mlsanity.com/paper/2410.16491/) (2024)
- [You don't need a personality test to know these models are unreliable: Assessing the Reliability of Large Language Models on Psychometric Instruments](https://mlsanity.com/paper/2311.09718/) (2023)
- [Deep learning is adaptive to intrinsic dimensionality of model smoothness in anisotropic Besov space](https://mlsanity.com/paper/1910.12799/) (2019)
- [Self-Assessment Tests are Unreliable Measures of LLM Personality](https://mlsanity.com/paper/2309.08163/) (2023)
- [When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers](https://mlsanity.com/paper/2504.10957/) (2025)
- [The Personality Illusion: Revealing Dissociation Between Self-Reports & Behavior in LLMs](https://mlsanity.com/paper/2509.03730/) (2025)
- [Evaluating Personality Traits in Large Language Models: Insights from Psychological Questionnaires](https://mlsanity.com/paper/2502.05248/) (2025)
- [An Evaluation on Large Language Model Outputs: Discourse and Memorization](https://mlsanity.com/paper/2304.08637/) (2023)
- [Personality Vector: Modulating Personality of Large Language Models by Model Merging](https://mlsanity.com/paper/2509.19727/) (2025)
- [LMLPA: Language Model Linguistic Personality Assessment](https://mlsanity.com/paper/2410.17632/) (2024)
- [BILLY: Steering Large Language Models via Merging Persona Vectors for Creative Generation](https://mlsanity.com/paper/2510.10157/) (2025)
- [PersonaFuse: A Personality Activation-Driven Framework for Enhancing Human-LLM Interactions](https://mlsanity.com/paper/2509.07370/) (2025)
- [From Five Dimensions to Many: Large Language Models as Precise and Interpretable Psychological Profilers](https://mlsanity.com/paper/2511.03235/) (2025)
- [CAPE: Context-Aware Personality Evaluation Framework for Large Language Models](https://mlsanity.com/paper/2508.20385/) (2025)
- [Evaluating LLM Alignment on Personality Inference from Real-World Interview Data](https://mlsanity.com/paper/2509.13244/) (2025)
- [Mutual Learning for Hashing: Unlocking Strong Hash Functions from Weak Supervision](https://mlsanity.com/paper/2510.07703/) (2025)

## Built on by (most cited first, 8 of 8)

- [Air-Know: Arbiter-Calibrated Knowledge-Internalizing Robust Network for Composed Image Retrieval](https://mlsanity.com/paper/2604.19386/) (2026)
- [ConeSep: Cone-based Robust Noise-Unlearning Compositional Network for Composed Image Retrieval](https://mlsanity.com/paper/2604.20358/) (2026)
- [TEMA: Anchor the Image, Follow the Text for Multi-Modification Composed Image Retrieval](https://mlsanity.com/paper/2604.21806/) (2026)
- [ActorMind: Emulating Human Actor Reasoning for Speech Role-Playing](https://mlsanity.com/paper/2604.11103/) (2026)
- [Learning from Contrasts: Synthesizing Reasoning Paths from Diverse Search Trajectories](https://mlsanity.com/paper/2604.11365/) (2026)
- [Efficient Safety Alignment of Language Models via Latent Personality Traits](https://mlsanity.com/paper/2607.07918/) (2026)
- [SkillEval: Decomposing Agent Skill Quality into Interpretable Signals](https://mlsanity.com/paper/2608.06891/) (2026)
- [Causal Evidence Extraction and Triangulation in Crisis Reports using Large Language Models: A ReliefWeb-based Study](https://mlsanity.com/paper/2608.04576/) (2026)

## Abstract (arXiv)

Evaluating personality traits in Large Language Models (LLMs) is key to model interpretation, comparison, and responsible deployment. However, existing questionnaire-based evaluation methods exhibit limited stability and offer little explainability, as their results are highly sensitive to minor variations in prompt phrasing or role-play configurations. To address these limitations, we propose an internal-activation-based approach, termed Persona-Vector Neutrality Interpolation (PVNI), for stable and explainable personality trait evaluation in LLMs. PVNI extracts a persona vector associated with a target personality trait from the model's internal activations using contrastive prompts. It then estimates the corresponding neutral score by interpolating along the persona vector as an anchor axis, enabling an interpretable comparison between the neutral prompt representation and the persona direction. We provide a theoretical analysis of the effectiveness and generalization properties of PVNI. Extensive experiments across diverse LLMs demonstrate that PVNI yields substantially more stable personality trait evaluations than existing methods, even under questionnaire and role-play variants.