# 'Rich Dad, Poor Lad': How do Large Language Models Contextualize Socioeconomic Factors in College Admission ?

arXiv: https://arxiv.org/abs/2509.16400 · HTML: https://mlsanity.com/paper/2509.16400/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 82 references that are in the map.
- First posted on arXiv 19 Sep 2025.

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

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [Counterfactual Fairness](https://mlsanity.com/paper/1703.06856/) (2017)
- [Certifying and removing disparate impact](https://mlsanity.com/paper/1412.3756/) (2014)
- [Safe RLHF: Safe Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2310.12773/) (2023)
- [On Fairness and Calibration](https://mlsanity.com/paper/1709.02012/) (2017)
- [Cognitive Bias in Decision-Making with LLMs](https://mlsanity.com/paper/2403.00811/) (2024)
- [Fast Model Debias with Machine Unlearning](https://mlsanity.com/paper/2310.12560/) (2023)
- [(A)I Am Not a Lawyer, But...: Engaging Legal Experts towards Responsible LLM Policies for Legal Advice](https://mlsanity.com/paper/2402.01864/) (2024)
- [Post-processing for Individual Fairness](https://mlsanity.com/paper/2110.13796/) (2021)
- [Thinking Fair and Slow: On the Efficacy of Structured Prompts for Debiasing Language Models](https://mlsanity.com/paper/2405.10431/) (2024)
- [Bias patterns in the application of LLMs for clinical decision support: A comprehensive study](https://mlsanity.com/paper/2404.15149/) (2024)
- [A Comprehensive Survey of Bias in LLMs: Current Landscape and Future Directions](https://mlsanity.com/paper/2409.16430/) (2024)
- [Prompting Fairness: Integrating Causality to Debias Large Language Models](https://mlsanity.com/paper/2403.08743/) (2024)
- [Fairness through Difference Awareness: Measuring Desired Group Discrimination in LLMs](https://mlsanity.com/paper/2502.01926/) (2025)
- [Guiding LLM Decision-Making with Fairness Reward Models](https://mlsanity.com/paper/2507.11344/) (2025)
- [Language Models Predict Empathy Gaps Between Social In-groups and Out-groups](https://mlsanity.com/paper/2503.01030/) (2025)
- [Poor Alignment and Steerability of Large Language Models: Evidence from College Admission Essays](https://mlsanity.com/paper/2503.20062/) (2025)
- [On the Mutual Influence of Gender and Occupation in LLM Representations](https://mlsanity.com/paper/2503.06792/) (2025)

## Built on by (most cited first, 1 of 1)

- [ABLEIST: Intersectional Disability Bias in LLM-Generated Hiring Scenarios](https://mlsanity.com/paper/2510.10998/) (2025)

## Abstract (arXiv)

Large Language Models (LLMs) are increasingly involved in high-stakes domains, yet how they reason about socially sensitive decisions remains underexplored. We present a large-scale audit of LLMs' treatment of socioeconomic status (SES) in college admissions decisions using a novel dual-process framework inspired by cognitive science. Leveraging a synthetic dataset of 30,000 applicant profiles grounded in real-world correlations, we prompt 4 open-source LLMs (Qwen 2, Mistral v0.3, Gemma 2, Llama 3.1) under 2 modes: a fast, decision-only setup (System 1) and a slower, explanation-based setup (System 2). Results from 5 million prompts reveal that LLMs consistently favor low-SES applicants -- even when controlling for academic performance -- and that System 2 amplifies this tendency by explicitly invoking SES as compensatory justification, highlighting both their potential and volatility as decision-makers. We then propose DPAF, a dual-process audit framework to probe LLMs' reasoning behaviors in sensitive applications.