# Improving Language Model Personas via Rationalization with Psychological Scaffolds

arXiv: https://arxiv.org/abs/2504.17993 · HTML: https://mlsanity.com/paper/2504.17993/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 75 references that are in the map.
- First posted on arXiv 25 Apr 2025.

## Builds on (most cited first, 30 of 36)

- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [Out of One, Many: Using Language Models to Simulate Human Samples](https://mlsanity.com/paper/2209.06899/) (2022)
- [Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies](https://mlsanity.com/paper/2208.10264/) (2022)
- [Towards Measuring the Representation of Subjective Global Opinions in Language Models](https://mlsanity.com/paper/2306.16388/) (2023)
- [Scaling Synthetic Data Creation with 1,000,000,000 Personas](https://mlsanity.com/paper/2406.20094/) (2024)
- [Using cognitive psychology to understand GPT-3](https://mlsanity.com/paper/2206.14576/) (2022)
- [SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents](https://mlsanity.com/paper/2310.11667/) (2023)
- [Social Simulacra: Creating Populated Prototypes for Social Computing Systems](https://mlsanity.com/paper/2208.04024/) (2022)
- [How is ChatGPT's behavior changing over time?](https://mlsanity.com/paper/2307.09009/) (2023)
- [LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individuals](https://mlsanity.com/paper/2411.10109/) (2024)
- [Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Models](https://mlsanity.com/paper/2305.18189/) (2023)
- [Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs](https://mlsanity.com/paper/2311.04892/) (2023)
- [Do LLMs exhibit human-like response biases? A case study in survey design](https://mlsanity.com/paper/2311.04076/) (2023)
- [Quantifying the Persona Effect in LLM Simulations](https://mlsanity.com/paper/2402.10811/) (2024)
- [Measuring Association Between Labels and Free-Text Rationales](https://mlsanity.com/paper/2010.12762/) (2020)
- [Simulating Opinion Dynamics with Networks of LLM-based Agents](https://mlsanity.com/paper/2311.09618/) (2023)
- [Training Millions of Personalized Dialogue Agents](https://mlsanity.com/paper/1809.01984/) (2018)
- [Aligning Language Models to User Opinions](https://mlsanity.com/paper/2305.14929/) (2023)
- [CoMPosT: Characterizing and Evaluating Caricature in LLM Simulations](https://mlsanity.com/paper/2310.11501/) (2023)
- [Personalizing Dialogue Agents via Meta-Learning](https://mlsanity.com/paper/1905.10033/) (2019)
- [Evaluating Large Language Model Biases in Persona-Steered Generation](https://mlsanity.com/paper/2405.20253/) (2024)
- [Moral Mimicry: Large Language Models Produce Moral Rationalizations Tailored to Political Identity](https://mlsanity.com/paper/2209.12106/) (2022)
- [Are Large Language Models Consistent over Value-laden Questions?](https://mlsanity.com/paper/2407.02996/) (2024)
- [On the steerability of large language models toward data-driven personas](https://mlsanity.com/paper/2311.04978/) (2023)
- [Large Language Models Help Humans Verify Truthfulness -- Except When They Are Convincingly Wrong](https://mlsanity.com/paper/2310.12558/) (2023)
- [Virtual Personas for Language Models via an Anthology of Backstories](https://mlsanity.com/paper/2407.06576/) (2024)
- [Standardizing the Measurement of Text Diversity: A Tool and a Comparative Analysis of Scores](https://mlsanity.com/paper/2403.00553/) (2024)
- [Persona-DB: Efficient Large Language Model Personalization for Response Prediction with Collaborative Data Refinement](https://mlsanity.com/paper/2402.11060/) (2024)
- [Estimating the Personality of White-Box Language Models](https://mlsanity.com/paper/2204.12000/) (2022)

## Built on by (most cited first, 9 of 9)

- [A Survey on LLM-based Conversational User Simulation](https://mlsanity.com/paper/2604.24977/) (2026)
- [The Need for a Socially-Grounded Persona Framework for User Simulation](https://mlsanity.com/paper/2601.07110/) (2026)
- [Persona Prompting as a Lens on LLM Social Reasoning](https://mlsanity.com/paper/2601.20757/) (2026)
- [How Well Can LLM Agents Simulate End-User Security and Privacy Attitudes and Behaviors?](https://mlsanity.com/paper/2602.18464/) (2026)
- [PrimeX: A Dataset of Worldview, Opinion, and Explanation](https://mlsanity.com/paper/2510.00174/) (2025)
- [From Fallback to Frontline: When Can LLMs be Superior Annotators of Human Perspectives?](https://mlsanity.com/paper/2604.17968/) (2026)
- [Democratic ICAI: Debating Our Way to Steering Principles from Preferences](https://mlsanity.com/paper/2606.28294/) (2026)
- [PrivacySIM: Evaluating LLM Simulation of User Privacy Behavior](https://mlsanity.com/paper/2605.12147/) (2026)
- [PALMs: Using Multi Construct-Grounded Rationales for Modeling Population Preferences in LLMs](https://mlsanity.com/paper/2608.01458/) (2026)

## Abstract (arXiv)

Language models prompted with a user description or persona are being used to predict the user's preferences and opinions. However, existing approaches to building personas mostly rely on a user's demographic attributes and/or prior judgments, but not on any underlying reasoning behind a user's judgments. We introduce PB&J (Psychology of Behavior and Judgments), a framework that improves LM personas by incorporating potential rationales for why the user could have made a certain judgment. Our rationales are generated by a language model to explicitly reason about a user's behavior on the basis of their experiences, personality traits, or beliefs. Our method employs psychological scaffolds: structured frameworks such as the Big 5 Personality Traits or Primal World Beliefs to help ground the generated rationales in existing theories. Experiments on public opinion and movie preference prediction tasks demonstrate that language model personas augmented with PB&J rationales consistently outperform personas conditioned only on user demographics and / or judgments, including those that use a model's default chain-of-thought, which is not grounded in psychological theories. Additionally, our PB&J personas perform competitively with those using human-written rationales, suggesting the potential of synthetic rationales guided by existing theories.