# On the Effectiveness and Generalization of Race Representations for Debiasing High-Stakes Decisions

arXiv: https://arxiv.org/abs/2504.06303 · HTML: https://mlsanity.com/paper/2504.06303/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 42 references that are in the map.
- First posted on arXiv 7 Apr 2025.

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

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small](https://mlsanity.com/paper/2211.00593/) (2022)
- [Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity](https://mlsanity.com/paper/2104.08786/) (2021)
- [BERT Rediscovers the Classical NLP Pipeline](https://mlsanity.com/paper/1905.05950/) (2019)
- [Refusal in Language Models Is Mediated by a Single Direction](https://mlsanity.com/paper/2406.11717/) (2024)
- [Probing Classifiers: Promises, Shortcomings, and Advances](https://mlsanity.com/paper/2102.12452/) (2021)
- [The Linear Representation Hypothesis and the Geometry of Large Language Models](https://mlsanity.com/paper/2311.03658/) (2023)
- [Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods](https://mlsanity.com/paper/1804.06876/) (2018)
- [Bias and Fairness in Large Language Models: A Survey](https://mlsanity.com/paper/2309.00770/) (2023)
- [The Woman Worked as a Babysitter: On Biases in Language Generation](https://mlsanity.com/paper/1909.01326/) (2019)
- [Gender Bias in Coreference Resolution](https://mlsanity.com/paper/1804.09301/) (2018)
- [Measuring Bias in Contextualized Word Representations](https://mlsanity.com/paper/1906.07337/) (2019)
- [AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders](https://mlsanity.com/paper/2501.17148/) (2025)
- [Probing Neural Network Comprehension of Natural Language Arguments](https://mlsanity.com/paper/1907.07355/) (2019)
- [Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations](https://mlsanity.com/paper/2303.02536/) (2023)
- [Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization](https://mlsanity.com/paper/2406.01171/) (2024)
- [On Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning](https://mlsanity.com/paper/2212.08061/) (2022)
- [Probing the Probing Paradigm: Does Probing Accuracy Entail Task Relevance?](https://mlsanity.com/paper/2005.00719/) (2020)
- [Evaluating and Mitigating Discrimination in Language Model Decisions](https://mlsanity.com/paper/2312.03689/) (2023)
- [Interpretability at Scale: Identifying Causal Mechanisms in Alpaca](https://mlsanity.com/paper/2305.08809/) (2023)
- [pyvene: A Library for Understanding and Improving PyTorch Models via Interventions](https://mlsanity.com/paper/2403.07809/) (2024)
- [Do Large Language Models Discriminate in Hiring Decisions on the Basis of Race, Ethnicity, and Gender?](https://mlsanity.com/paper/2406.10486/) (2024)
- [Stop! In the Name of Flaws: Disentangling Personal Names and Sociodemographic Attributes in NLP](https://mlsanity.com/paper/2405.17159/) (2024)
- [Does Editing Provide Evidence for Localization?](https://mlsanity.com/paper/2502.11447/) (2025)

## Built on by (most cited first, 5 of 5)

- [Robustly Improving LLM Fairness in Realistic Settings via Interpretability](https://mlsanity.com/paper/2506.10922/) (2025)
- [Ads in AI Chatbots? An Analysis of How Large Language Models Navigate Conflicts of Interest](https://mlsanity.com/paper/2604.08525/) (2026)
- [Can SAEs reveal and mitigate racial biases of LLMs in healthcare?](https://mlsanity.com/paper/2511.00177/) (2025)
- [White-Box Sensitivity Auditing with Steering Vectors](https://mlsanity.com/paper/2601.16398/) (2026)
- [Proxy reliance in large language model decisions is uncalibrated to predictive evidence](https://mlsanity.com/paper/2608.22887/) (2026)

## Abstract (arXiv)

Understanding and mitigating biases is critical for the adoption of large language models (LLMs) in high-stakes decision-making. We introduce Admissions and Hiring, decision tasks with hypothetical applicant profiles where a person's race can be inferred from their name, as simplified test beds for racial bias. We show that Gemma 2B Instruct and LLaMA 3.2 3B Instruct exhibit strong biases. Gemma grants admission to 26% more White than Black applicants, and LLaMA hires 60% more Asian than White applicants. We demonstrate that these biases are resistant to prompt engineering: multiple prompting strategies all fail to promote fairness. In contrast, using distributed alignment search, we can identify "race subspaces" within model activations and intervene on them to debias model decisions. Averaging the representation across all races within the subspaces reduces Gemma's bias by 37-57%. Finally, we examine the generalizability of Gemma's race subspaces, and find limited evidence for generalization, where changing the prompt format can affect the race representation. Our work suggests mechanistic approaches may provide a promising venue for improving the fairness of LLMs, but a universal race representation remains elusive.