# Disentangling Dialect from Social Bias via Multitask Learning to Improve Fairness

arXiv: https://arxiv.org/abs/2406.09977 · HTML: https://mlsanity.com/paper/2406.09977/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 62 references that are in the map.
- First posted on arXiv 14 Jun 2024.

## Builds on (most cited first, 30 of 33)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [Language (Technology) is Power: A Critical Survey of "Bias" in NLP](https://mlsanity.com/paper/2005.14050/) (2020)
- [AdapterFusion: Non-Destructive Task Composition for Transfer Learning](https://mlsanity.com/paper/2005.00247/) (2020)
- [Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints](https://mlsanity.com/paper/1707.09457/) (2017)
- [Social Bias Frames: Reasoning about Social and Power Implications of Language](https://mlsanity.com/paper/1911.03891/) (2019)
- [BERTweet: A pre-trained language model for English Tweets](https://mlsanity.com/paper/2005.10200/) (2020)
- [Synthetic and Natural Noise Both Break Neural Machine Translation](https://mlsanity.com/paper/1711.02173/) (2017)
- [Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detection](https://mlsanity.com/paper/2111.07997/) (2021)
- [Sentence Encoders on STILTs: Supplementary Training on Intermediate Labeled-data Tasks](https://mlsanity.com/paper/1811.01088/) (2018)
- [Racial Bias in Hate Speech and Abusive Language Detection Datasets](https://mlsanity.com/paper/1905.12516/) (2019)
- [Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology](https://mlsanity.com/paper/1906.04571/) (2019)
- [Demographic Dialectal Variation in Social Media: A Case Study of African-American English](https://mlsanity.com/paper/1608.08868/) (2016)
- [Fine-tuned Language Models are Continual Learners](https://mlsanity.com/paper/2205.12393/) (2022)
- [Hate Speech Detection and Racial Bias Mitigation in Social Media based on BERT model](https://mlsanity.com/paper/2008.06460/) (2020)
- [LLMaAA: Making Large Language Models as Active Annotators](https://mlsanity.com/paper/2310.19596/) (2023)
- [Racial Disparity in Natural Language Processing: A Case Study of Social Media African-American English](https://mlsanity.com/paper/1707.00061/) (2017)
- [Demoting Racial Bias in Hate Speech Detection](https://mlsanity.com/paper/2005.12246/) (2020)
- [Investigating African-American Vernacular English in Transformer-Based Text Generation](https://mlsanity.com/paper/2010.02510/) (2020)
- [VALUE: Understanding Dialect Disparity in NLU](https://mlsanity.com/paper/2204.03031/) (2022)
- [Fairness Metrics: A Comparative Analysis](https://mlsanity.com/paper/2001.07864/) (2020)
- [Stereotypical Bias Removal for Hate Speech Detection Task using Knowledge-based Generalizations](https://mlsanity.com/paper/2001.05495/) (2020)
- [Quantifying the Dialect Gap and its Correlates Across Languages](https://mlsanity.com/paper/2310.15135/) (2023)
- [Few-shot Instruction Prompts for Pretrained Language Models to Detect Social Biases](https://mlsanity.com/paper/2112.07868/) (2021)
- [Mitigating Racial Biases in Toxic Language Detection with an Equity-Based Ensemble Framework](https://mlsanity.com/paper/2109.13137/) (2021)
- [On the Difference of BERT-style and CLIP-style Text Encoders](https://mlsanity.com/paper/2306.03678/) (2023)
- [Argument from Old Man's View: Assessing Social Bias in Argumentation](https://mlsanity.com/paper/2011.12014/) (2020)
- [Fair and Unbiased Algorithmic Decision Making: Current State and Future Challenges](https://mlsanity.com/paper/1901.04730/) (2019)

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

- [Say It Another Way: Auditing LLMs with a User-Grounded Automated Paraphrasing Framework](https://mlsanity.com/paper/2505.03563/) (2025)

## Abstract (arXiv)

Dialects introduce syntactic and lexical variations in language that occur in regional or social groups. Most NLP methods are not sensitive to such variations. This may lead to unfair behavior of the methods, conveying negative bias towards dialect speakers. While previous work has studied dialect-related fairness for aspects like hate speech, other aspects of biased language, such as lewdness, remain fully unexplored. To fill this gap, we investigate performance disparities between dialects in the detection of five aspects of biased language and how to mitigate them. To alleviate bias, we present a multitask learning approach that models dialect language as an auxiliary task to incorporate syntactic and lexical variations. In our experiments with African-American English dialect, we provide empirical evidence that complementing common learning approaches with dialect modeling improves their fairness. Furthermore, the results suggest that multitask learning achieves state-of-the-art performance and helps to detect properties of biased language more reliably.