# On the Independence of Association Bias and Empirical Fairness in Language Models

arXiv: https://arxiv.org/abs/2304.10153 · HTML: https://mlsanity.com/paper/2304.10153/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 67 references that are in the map.
- First posted on arXiv 20 Apr 2023.

## Builds on (most cited first, 30 of 39)

- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Language (Technology) is Power: A Critical Survey of "Bias" in NLP](https://mlsanity.com/paper/2005.14050/) (2020)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [Inherent Trade-Offs in the Fair Determination of Risk Scores](https://mlsanity.com/paper/1609.05807/) (2016)
- [On Measuring Social Biases in Sentence Encoders](https://mlsanity.com/paper/1903.10561/) (2019)
- [Fairness Without Demographics in Repeated Loss Minimization](https://mlsanity.com/paper/1806.08010/) (2018)
- [Mitigating Gender Bias in Natural Language Processing: Literature Review](https://mlsanity.com/paper/1906.08976/) (2019)
- [Measuring Bias in Contextualized Word Representations](https://mlsanity.com/paper/1906.07337/) (2019)
- [Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them](https://mlsanity.com/paper/1903.03862/) (2019)
- [Social Biases in NLP Models as Barriers for Persons with Disabilities](https://mlsanity.com/paper/2005.00813/) (2020)
- [Learning Gender-Neutral Word Embeddings](https://mlsanity.com/paper/1809.01496/) (2018)
- [Intrinsic Bias Metrics Do Not Correlate with Application Bias](https://mlsanity.com/paper/2012.15859/) (2020)
- [Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overview](https://mlsanity.com/paper/1912.11078/) (2019)
- [Assessing Social and Intersectional Biases in Contextualized Word Representations](https://mlsanity.com/paper/1911.01485/) (2019)
- [Sustainable Modular Debiasing of Language Models](https://mlsanity.com/paper/2109.03646/) (2021)
- [XAI for Transformers: Better Explanations through Conservative Propagation](https://mlsanity.com/paper/2202.07304/) (2022)
- [A Clarification of the Nuances in the Fairness Metrics Landscape](https://mlsanity.com/paper/2106.00467/) (2021)
- [Understanding the Origins of Bias in Word Embeddings](https://mlsanity.com/paper/1810.03611/) (2018)
- [Does Gender Matter? Towards Fairness in Dialogue Systems](https://mlsanity.com/paper/1910.10486/) (2019)
- [A Survey on Gender Bias in Natural Language Processing](https://mlsanity.com/paper/2112.14168/) (2021)
- [Fairness risk measures](https://mlsanity.com/paper/1901.08665/) (2019)
- [Quantifying Social Biases in NLP: A Generalization and Empirical Comparison of Extrinsic Fairness Metrics](https://mlsanity.com/paper/2106.14574/) (2021)
- [Unmasking Contextual Stereotypes: Measuring and Mitigating BERT's Gender Bias](https://mlsanity.com/paper/2010.14534/) (2020)
- [On the Intrinsic and Extrinsic Fairness Evaluation Metrics for Contextualized Language Representations](https://mlsanity.com/paper/2203.13928/) (2022)
- [Measuring Social Biases in Grounded Vision and Language Embeddings](https://mlsanity.com/paper/2002.08911/) (2020)
- [Perturbation Augmentation for Fairer NLP](https://mlsanity.com/paper/2205.12586/) (2022)
- [What's in a Name? Reducing Bias in Bios without Access to Protected Attributes](https://mlsanity.com/paper/1904.05233/) (2019)
- [FairLex: A Multilingual Benchmark for Evaluating Fairness in Legal Text Processing](https://mlsanity.com/paper/2203.07228/) (2022)
- [Debiasing isn't enough! -- On the Effectiveness of Debiasing MLMs and their Social Biases in Downstream Tasks](https://mlsanity.com/paper/2210.02938/) (2022)

## Built on by (most cited first, 29 of 29)

- [Bias and Fairness in Large Language Models: A Survey](https://mlsanity.com/paper/2309.00770/) (2023)
- [Fairness in Large Language Models: A Taxonomic Survey](https://mlsanity.com/paper/2404.01349/) (2024)
- [FairMT-Bench: Benchmarking Fairness for Multi-turn Dialogue in Conversational LLMs](https://mlsanity.com/paper/2410.19317/) (2024)
- [Content Moderation by LLM: From Accuracy to Legitimacy](https://mlsanity.com/paper/2409.03219/) (2024)
- [Investigating Implicit Bias in Large Language Models: A Large-Scale Study of Over 50 LLMs](https://mlsanity.com/paper/2410.12864/) (2024)
- [BiasAlert: A Plug-and-play Tool for Social Bias Detection in LLMs](https://mlsanity.com/paper/2407.10241/) (2024)
- [Bias and Volatility: A Statistical Framework for Evaluating Large Language Model's Stereotypes and the Associated Generation Inconsistency](https://mlsanity.com/paper/2402.15481/) (2024)
- [Evaluating Fairness in Large Vision-Language Models Across Diverse Demographic Attributes and Prompts](https://mlsanity.com/paper/2406.17974/) (2024)
- [Tackling Bias in Pre-trained Language Models: Current Trends and Under-represented Societies](https://mlsanity.com/paper/2312.01509/) (2023)
- [On the Interplay between Fairness and Explainability](https://mlsanity.com/paper/2310.16607/) (2023)
- [Evaluating Bias and Fairness in Gender-Neutral Pretrained Vision-and-Language Models](https://mlsanity.com/paper/2310.17530/) (2023)
- [How far can bias go? Tracing bias from pretraining data to alignment](https://mlsanity.com/paper/2411.19240/) (2024)
- [Factual and Personalized Recommendations using Language Models and Reinforcement Learning](https://mlsanity.com/paper/2310.06176/) (2023)
- [Fair Text Classification with Wasserstein Independence](https://mlsanity.com/paper/2311.12689/) (2023)
- [A Group Fairness Lens for Large Language Models](https://mlsanity.com/paper/2312.15478/) (2023)
- [Addressing Both Statistical and Causal Gender Fairness in NLP Models](https://mlsanity.com/paper/2404.00463/) (2024)
- [Why Don't Prompt-Based Fairness Metrics Correlate?](https://mlsanity.com/paper/2406.05918/) (2024)
- [Blind Men and the Elephant: Diverse Perspectives on Gender Stereotypes in Benchmark Datasets](https://mlsanity.com/paper/2501.01168/) (2025)
- [Fair Text Classification via Transferable Representations](https://mlsanity.com/paper/2503.07691/) (2025)
- [Exploring Gender Bias in Large Language Models: An In-depth Dive into the German Language](https://mlsanity.com/paper/2507.16557/) (2025)
- [Detecting Bias in Large Language Models: Fine-tuned KcBERT](https://mlsanity.com/paper/2403.10774/) (2024)
- [Social Bias in Multilingual Language Models: A Survey](https://mlsanity.com/paper/2508.20201/) (2025)
- [When LLMs Imagine People: A Human-Centered Persona Brainstorm Audit for Bias and Fairness in Creative Applications](https://mlsanity.com/paper/2602.00044/) (2026)
- [Fairness Certification for Natural Language Processing and Large Language Models](https://mlsanity.com/paper/2401.01262/) (2024)
- [Ethics Whitepaper: Whitepaper on Ethical Research into Large Language Models](https://mlsanity.com/paper/2410.19812/) (2024)
- [A Critical Review of Predominant Bias in Neural Networks](https://mlsanity.com/paper/2502.11031/) (2025)
- [How do datasets, developers, and models affect biases in a low-resourced language?: The Case of the Bengali Language](https://mlsanity.com/paper/2506.06816/) (2025)
- [Calibrating WEAT Against Anisotropy: ZCA Whitening as a Geometric Pre-Processing Step for Embedding Association Tests](https://mlsanity.com/paper/2608.06908/) (2026)
- [Mitigating Bias in Large Vision-Language Models via Counterfactual Ensemble Decoding](https://mlsanity.com/paper/2608.21415/) (2026)

## Abstract (arXiv)

The societal impact of pre-trained language models has prompted researchers to probe them for strong associations between protected attributes and value-loaded terms, from slur to prestigious job titles. Such work is said to probe models for bias or fairness-or such probes 'into representational biases' are said to be 'motivated by fairness'-suggesting an intimate connection between bias and fairness. We provide conceptual clarity by distinguishing between association biases (Caliskan et al., 2022) and empirical fairness (Shen et al., 2022) and show the two can be independent. Our main contribution, however, is showing why this should not come as a surprise. To this end, we first provide a thought experiment, showing how association bias and empirical fairness can be completely orthogonal. Next, we provide empirical evidence that there is no correlation between bias metrics and fairness metrics across the most widely used language models. Finally, we survey the sociological and psychological literature and show how this literature provides ample support for expecting these metrics to be uncorrelated.