# DiFair: A Benchmark for Disentangled Assessment of Gender Knowledge and Bias

arXiv: https://arxiv.org/abs/2310.14329 · HTML: https://mlsanity.com/paper/2310.14329/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 29 references that are in the map.
- First posted on arXiv 22 Oct 2023.

## Builds on (most cited first, 4 of 4)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [Measuring and Reducing Gendered Correlations in Pre-trained Models](https://mlsanity.com/paper/2010.06032/) (2020)

## Built on by (most cited first, 9 of 9)

- [Gender Bias in Decision-Making with Large Language Models: A Study of Relationship Conflicts](https://mlsanity.com/paper/2410.11084/) (2024)
- [FLEX: A Benchmark for Evaluating Robustness of Fairness in Large Language Models](https://mlsanity.com/paper/2503.19540/) (2025)
- [GECOBench: A Gender-Controlled Text Dataset and Benchmark for Quantifying Biases in Explanations](https://mlsanity.com/paper/2406.11547/) (2024)
- [Blind Men and the Elephant: Diverse Perspectives on Gender Stereotypes in Benchmark Datasets](https://mlsanity.com/paper/2501.01168/) (2025)
- [Detecting Linguistic Bias in Government Documents Using Large language Models](https://mlsanity.com/paper/2502.13548/) (2025)
- [Gender Encoding Patterns in Pretrained Language Model Representations](https://mlsanity.com/paper/2503.06734/) (2025)
- [Breaking the Benchmark: Revealing LLM Bias via Minimal Contextual Augmentation](https://mlsanity.com/paper/2510.23921/) (2025)
- [ArgBench: Benchmarking LLMs on Computational Argumentation Tasks](https://mlsanity.com/paper/2604.17366/) (2026)
- [GKnow: Measuring the Entanglement of Gender Bias and Factual Gender](https://mlsanity.com/paper/2605.12299/) (2026)

## Abstract (arXiv)

Numerous debiasing techniques have been proposed to mitigate the gender bias that is prevalent in pretrained language models. These are often evaluated on datasets that check the extent to which the model is gender-neutral in its predictions. Importantly, this evaluation protocol overlooks the possible adverse impact of bias mitigation on useful gender knowledge. To fill this gap, we propose DiFair, a manually curated dataset based on masked language modeling objectives. DiFair allows us to introduce a unified metric, gender invariance score, that not only quantifies a model's biased behavior, but also checks if useful gender knowledge is preserved. We use DiFair as a benchmark for a number of widely-used pretained language models and debiasing techniques. Experimental results corroborate previous findings on the existing gender biases, while also demonstrating that although debiasing techniques ameliorate the issue of gender bias, this improvement usually comes at the price of lowering useful gender knowledge of the model.