# Extroversion or Introversion? Controlling The Personality of Your Large Language Models

arXiv: https://arxiv.org/abs/2406.04583 · HTML: https://mlsanity.com/paper/2406.04583/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Human values and AI feedback alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 22 of its 47 references that are in the map.
- First posted on arXiv 7 Jun 2024.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Human values and AI feedback alignment](https://mlsanity.com/alignment/human-values-and-ai-feedback-alignment/)

## Builds on (most cited first, 22 of 22)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [LIMA: Less Is More for Alignment](https://mlsanity.com/paper/2305.11206/) (2023)
- [GLM: General Language Model Pretraining with Autoregressive Blank Infilling](https://mlsanity.com/paper/2103.10360/) (2021)
- [The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only](https://mlsanity.com/paper/2306.01116/) (2023)
- [A Survey on In-context Learning](https://mlsanity.com/paper/2301.00234/) (2022)
- [Toxicity in ChatGPT: Analyzing Persona-assigned Language Models](https://mlsanity.com/paper/2304.05335/) (2023)
- [Pre-Trained Models: Past, Present and Future](https://mlsanity.com/paper/2106.07139/) (2021)
- [Predictability and Surprise in Large Generative Models](https://mlsanity.com/paper/2202.07785/) (2022)
- [Who is GPT-3? An Exploration of Personality, Values and Demographics](https://mlsanity.com/paper/2209.14338/) (2022)
- [DeepSpeed-Chat: Easy, Fast and Affordable RLHF Training of ChatGPT-like Models at All Scales](https://mlsanity.com/paper/2308.01320/) (2023)
- [Estimating the Personality of White-Box Language Models](https://mlsanity.com/paper/2204.12000/) (2022)
- [Systematic Evaluation of GPT-3 for Zero-Shot Personality Estimation](https://mlsanity.com/paper/2306.01183/) (2023)
- [Investigating Audio, Visual, and Text Fusion Methods for End-to-End Automatic Personality Prediction](https://mlsanity.com/paper/1805.00705/) (2018)
- [A Language-independent and Compositional Model for Personality Trait Recognition from Short Texts](https://mlsanity.com/paper/1610.04345/) (2016)
- [Lexical-semantic resources: yet powerful resources for automatic personality classification](https://mlsanity.com/paper/1711.09824/) (2017)

## Built on by (most cited first, 2 of 2)

- [Structured Personality Control and Adaptation for LLM Agents](https://mlsanity.com/paper/2601.10025/) (2026)
- [SteerDuplex: Steerable Duplex Speech Dialogue Models](https://mlsanity.com/paper/2609.12623/) (2026)

## Abstract (arXiv)

Large language models (LLMs) exhibit robust capabilities in text generation and comprehension, mimicking human behavior and exhibiting synthetic personalities. However, some LLMs have displayed offensive personality, propagating toxic discourse. Existing literature neglects the origin and evolution of LLM personalities, as well as the effective personality control. To fill these gaps, our study embarked on a comprehensive investigation into LLM personality control. We investigated several typical methods to influence LLMs, including three training methods: Continual Pre-training, Supervised Fine-Tuning (SFT), and Reinforcement Learning from Human Feedback (RLHF), along with inference phase considerations (prompts). Our investigation revealed a hierarchy of effectiveness in control: Prompt > SFT > RLHF > Continual Pre-train. Notably, SFT exhibits a higher control success rate compared to prompt induction. While prompts prove highly effective, we found that prompt-induced personalities are less robust than those trained, making them more prone to showing conflicting personalities under reverse personality prompt induction. Besides, harnessing the strengths of both SFT and prompt, we proposed underlinePrompt underlineInduction post underlineSupervised underlineFine-tuning (PISF), which emerges as the most effective and robust strategy for controlling LLMs' personality, displaying high efficacy, high success rates, and high robustness. Even under reverse personality prompt induction, LLMs controlled by PISF still exhibit stable and robust personalities.