# AI Text-to-Behavior: A Study In Steerability

arXiv: https://arxiv.org/abs/2308.07326 · HTML: https://mlsanity.com/paper/2308.07326/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 28 references that are in the map.
- First posted on arXiv 7 Aug 2023.

## Builds on (most cited first, 12 of 12)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [A Categorical Archive of ChatGPT Failures](https://mlsanity.com/paper/2302.03494/) (2023)
- [Prompt Compression and Contrastive Conditioning for Controllability and Toxicity Reduction in Language Models](https://mlsanity.com/paper/2210.03162/) (2022)
- [STEVE-1: A Generative Model for Text-to-Behavior in Minecraft](https://mlsanity.com/paper/2306.00937/) (2023)
- [Latent Dirichlet Allocation (LDA) and Topic modeling: models, applications, a survey](https://mlsanity.com/paper/1711.04305/) (2017)
- [Exploring the psychology of LLMs' Moral and Legal Reasoning](https://mlsanity.com/paper/2308.01264/) (2023)
- [Thought Cloning: Learning to Think while Acting by Imitating Human Thinking](https://mlsanity.com/paper/2306.00323/) (2023)
- [Creating a Large Language Model of a Philosopher](https://mlsanity.com/paper/2302.01339/) (2023)
- [A Mixture-of-Expert Approach to RL-based Dialogue Management](https://mlsanity.com/paper/2206.00059/) (2022)
- [Revisiting the Reliability of Psychological Scales on Large Language Models](https://mlsanity.com/paper/2305.19926/) (2023)
- [ArtWhisperer: A Dataset for Characterizing Human-AI Interactions in Artistic Creations](https://mlsanity.com/paper/2306.08141/) (2023)
- [Intent-Aware Contextual Recommendation System](https://mlsanity.com/paper/1711.10558/) (2017)

## Built on by (most cited first, 11 of 11)

- [Do LLMs Have Distinct and Consistent Personality? TRAIT: Personality Testset designed for LLMs with Psychometrics](https://mlsanity.com/paper/2406.14703/) (2024)
- [Self-Assessment Tests are Unreliable Measures of LLM Personality](https://mlsanity.com/paper/2309.08163/) (2023)
- [PERSONA: Dynamic and Compositional Inference-Time Personality Control via Activation Vector Algebra](https://mlsanity.com/paper/2602.15669/) (2026)
- [Self-assessment, Exhibition, and Recognition: a Review of Personality in Large Language Models](https://mlsanity.com/paper/2406.17624/) (2024)
- [Identifying Multiple Personalities in Large Language Models with External Evaluation](https://mlsanity.com/paper/2402.14805/) (2024)
- [Humanizing LLMs: A Survey of Psychological Measurements with Tools, Datasets, and Human-Agent Applications](https://mlsanity.com/paper/2505.00049/) (2025)
- [What's Producible May Not Be Reachable: Measuring the Steerability of Generative Models](https://mlsanity.com/paper/2503.17482/) (2025)
- [Intentional Biases in LLM Responses](https://mlsanity.com/paper/2311.07611/) (2023)
- [Integrating Personality into Digital Humans: A Review of LLM-Driven Approaches for Virtual Reality](https://mlsanity.com/paper/2503.16457/) (2025)
- [Psychologically Enhanced AI Agents](https://mlsanity.com/paper/2509.04343/) (2025)
- [PILOT: Steering Synthetic Data Generation with Psychological & Linguistic Output Targeting](https://mlsanity.com/paper/2509.15447/) (2025)

## Abstract (arXiv)

The research explores the steerability of Large Language Models (LLMs), particularly OpenAI's ChatGPT iterations. By employing a behavioral psychology framework called OCEAN (Openness, Conscientiousness, Extroversion, Agreeableness, Neuroticism), we quantitatively gauged the model's responsiveness to tailored prompts. When asked to generate text mimicking an extroverted personality, OCEAN scored the language alignment to that behavioral trait. In our analysis, while "openness" presented linguistic ambiguity, "conscientiousness" and "neuroticism" were distinctly evoked in the OCEAN framework, with "extroversion" and "agreeableness" showcasing a notable overlap yet distinct separation from other traits. Our findings underscore GPT's versatility and ability to discern and adapt to nuanced instructions. Furthermore, historical figure simulations highlighted the LLM's capacity to internalize and project instructible personas, precisely replicating their philosophies and dialogic styles. However, the rapid advancements in LLM capabilities and the opaque nature of some training techniques make metric proposals degrade rapidly. Our research emphasizes a quantitative role to describe steerability in LLMs, presenting both its promise and areas for further refinement in aligning its progress to human intentions.