# Unboxing Occupational Bias: Grounded Debiasing of LLMs with U.S. Labor Data

arXiv: https://arxiv.org/abs/2408.11247 · HTML: https://mlsanity.com/paper/2408.11247/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 15 references that are in the map.
- First posted on arXiv 20 Aug 2024.

## Builds on (most cited first, 9 of 9)

- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models](https://mlsanity.com/paper/2306.11698/) (2023)
- [Bias Out-of-the-Box: An Empirical Analysis of Intersectional Occupational Biases in Popular Generative Language Models](https://mlsanity.com/paper/2102.04130/) (2021)
- [Self-Debiasing Large Language Models: Zero-Shot Recognition and Reduction of Stereotypes](https://mlsanity.com/paper/2402.01981/) (2024)
- [Auditing the Use of Language Models to Guide Hiring Decisions](https://mlsanity.com/paper/2404.03086/) (2024)
- [Distilling Large Language Models using Skill-Occupation Graph Context for HR-Related Tasks](https://mlsanity.com/paper/2311.06383/) (2023)
- [COBIAS: Assessing the Contextual Reliability of Bias Benchmarks for Language Models](https://mlsanity.com/paper/2402.14889/) (2024)

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

- [Bias in Large Language Models: Origin, Evaluation, and Mitigation](https://mlsanity.com/paper/2411.10915/) (2024)
- [Revealing and Reducing Gender Biases in Vision and Language Assistants (VLAs)](https://mlsanity.com/paper/2410.19314/) (2024)
- [Moral Sensitivity in LLMs: A Tiered Evaluation of Contextual Bias via Behavioral Profiling and Mechanistic Interpretability](https://mlsanity.com/paper/2605.03217/) (2026)
- [Mitigation of Gender and Ethnicity Bias in AI-Generated Stories through Model Explanations](https://mlsanity.com/paper/2509.04515/) (2025)
- [The Fair Game: Auditing & Debiasing AI Algorithms Over Time](https://mlsanity.com/paper/2508.06443/) (2025)

## Abstract (arXiv)

Large Language Models (LLMs) are prone to inheriting and amplifying societal biases embedded within their training data, potentially reinforcing harmful stereotypes related to gender, occupation, and other sensitive categories. This issue becomes particularly problematic as biased LLMs can have far-reaching consequences, leading to unfair practices and exacerbating social inequalities across various domains, such as recruitment, online content moderation, or even the criminal justice system. Although prior research has focused on detecting bias in LLMs using specialized datasets designed to highlight intrinsic biases, there has been a notable lack of investigation into how these findings correlate with authoritative datasets, such as those from the U.S. National Bureau of Labor Statistics (NBLS). To address this gap, we conduct empirical research that evaluates LLMs in a ``bias-out-of-the-box" setting, analyzing how the generated outputs compare with the distributions found in NBLS data. Furthermore, we propose a straightforward yet effective debiasing mechanism that directly incorporates NBLS instances to mitigate bias within LLMs. Our study spans seven different LLMs, including instructable, base, and mixture-of-expert models, and reveals significant levels of bias that are often overlooked by existing bias detection techniques. Importantly, our debiasing method, which does not rely on external datasets, demonstrates a substantial reduction in bias scores, highlighting the efficacy of our approach in creating fairer and more reliable LLMs.