# Using LLMs to Model the Beliefs and Preferences of Targeted Populations

arXiv: https://arxiv.org/abs/2403.20252 · HTML: https://mlsanity.com/paper/2403.20252/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 18 references that are in the map.
- First posted on arXiv 29 Mar 2024.

## Builds on (most cited first, 13 of 13)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [Large Language Models](https://mlsanity.com/paper/2307.05782/) (2023)
- [AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback](https://mlsanity.com/paper/2305.14387/) (2023)
- [Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies](https://mlsanity.com/paper/2208.10264/) (2022)
- [Role-Play with Large Language Models](https://mlsanity.com/paper/2305.16367/) (2023)
- [Challenges and Applications of Large Language Models](https://mlsanity.com/paper/2307.10169/) (2023)
- [On Decoding Strategies for Neural Text Generators](https://mlsanity.com/paper/2203.15721/) (2022)
- [The Challenge of Using LLMs to Simulate Human Behavior: A Causal Inference Perspective](https://mlsanity.com/paper/2312.15524/) (2023)
- [Understanding and Shifting Preferences for Battery Electric Vehicles](https://mlsanity.com/paper/2202.08963/) (2022)

## Built on by (most cited first, 7 of 7)

- [Benchmarking Distributional Alignment of Large Language Models](https://mlsanity.com/paper/2411.05403/) (2024)
- [TeachTune: Reviewing Pedagogical Agents Against Diverse Student Profiles with Simulated Students](https://mlsanity.com/paper/2410.04078/) (2024)
- [Perceptions of Linguistic Uncertainty by Language Models and Humans](https://mlsanity.com/paper/2407.15814/) (2024)
- [Belief-Sim: Towards Belief-Driven Simulation of Demographic Misinformation Susceptibility](https://mlsanity.com/paper/2603.03585/) (2026)
- [Leveraging LLMs for Predictive Insights in Food Policy and Behavioral Interventions](https://mlsanity.com/paper/2411.08563/) (2024)
- [Whose Story Gets Told? Positionality and Bias in LLM Summaries of Life Narratives](https://mlsanity.com/paper/2604.20131/) (2026)
- [HouseholdBench: Evaluating Large Language Models as Predictors of Household Economic Behavior](https://mlsanity.com/paper/2610.07563/) (2026)

## Abstract (arXiv)

We consider the problem of aligning a large language model (LLM) to model the preferences of a human population. Modeling the beliefs, preferences, and behaviors of a specific population can be useful for a variety of different applications, such as conducting simulated focus groups for new products, conducting virtual surveys, and testing behavioral interventions, especially for interventions that are expensive, impractical, or unethical. Existing work has had mixed success using LLMs to accurately model human behavior in different contexts. We benchmark and evaluate two well-known fine-tuning approaches and evaluate the resulting populations on their ability to match the preferences of real human respondents on a survey of preferences for battery electric vehicles (BEVs). We evaluate our models against their ability to match population-wide statistics as well as their ability to match individual responses, and we investigate the role of temperature in controlling the trade-offs between these two. Additionally, we propose and evaluate a novel loss term to improve model performance on responses that require a numeric response.