# TIDE: Textual Identity Detection for Evaluating and Augmenting Classification and Language Models

arXiv: https://arxiv.org/abs/2309.04027 · HTML: https://mlsanity.com/paper/2309.04027/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 56 references that are in the map.
- First posted on arXiv 7 Sep 2023.

## Builds on (most cited first, 22 of 22)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Language (Technology) is Power: A Critical Survey of "Bias" in NLP](https://mlsanity.com/paper/2005.14050/) (2020)
- [Recipes for building an open-domain chatbot](https://mlsanity.com/paper/2004.13637/) (2020)
- [Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification](https://mlsanity.com/paper/1903.04561/) (2019)
- [Persistent Anti-Muslim Bias in Large Language Models](https://mlsanity.com/paper/2101.05783/) (2021)
- [AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias](https://mlsanity.com/paper/1810.01943/) (2018)
- [Fairness without Demographics through Adversarially Reweighted Learning](https://mlsanity.com/paper/2006.13114/) (2020)
- [Ex Machina: Personal Attacks Seen at Scale](https://mlsanity.com/paper/1610.08914/) (2016)
- ["I'm sorry to hear that": Finding New Biases in Language Models with a Holistic Descriptor Dataset](https://mlsanity.com/paper/2205.09209/) (2022)
- [Counterfactual Fairness in Text Classification through Robustness](https://mlsanity.com/paper/1809.10610/) (2018)
- [Intrinsic Bias Metrics Do Not Correlate with Application Bias](https://mlsanity.com/paper/2012.15859/) (2020)
- [Aequitas: A Bias and Fairness Audit Toolkit](https://mlsanity.com/paper/1811.05577/) (2018)
- [Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overview](https://mlsanity.com/paper/1912.11078/) (2019)
- [Measuring the Reliability of Hate Speech Annotations: The Case of the European Refugee Crisis](https://mlsanity.com/paper/1701.08118/) (2017)
- [Discrimination in Online Ad Delivery](https://mlsanity.com/paper/1301.6822/) (2013)
- ["What We Can't Measure, We Can't Understand": Challenges to Demographic Data Procurement in the Pursuit of Fairness](https://mlsanity.com/paper/2011.02282/) (2020)
- [Learning Fair Classifiers with Partially Annotated Group Labels](https://mlsanity.com/paper/2111.14581/) (2021)
- [Proxy Fairness](https://mlsanity.com/paper/1806.11212/) (2018)
- [Demographic-Reliant Algorithmic Fairness: Characterizing the Risks of Demographic Data Collection in the Pursuit of Fairness](https://mlsanity.com/paper/2205.01038/) (2022)
- [Are "Undocumented Workers" the Same as "Illegal Aliens"? Disentangling Denotation and Connotation in Vector Spaces](https://mlsanity.com/paper/2010.02976/) (2020)
- [A Unified Feature Representation for Lexical Connotations](https://mlsanity.com/paper/2006.00635/) (2020)
- [Fairness for Text Classification Tasks with Identity Information Data Augmentation Methods](https://mlsanity.com/paper/2203.03541/) (2022)

## Abstract (arXiv)

Machine learning models can perpetuate unintended biases from unfair and imbalanced datasets. Evaluating and debiasing these datasets and models is especially hard in text datasets where sensitive attributes such as race, gender, and sexual orientation may not be available. When these models are deployed into society, they can lead to unfair outcomes for historically underrepresented groups. In this paper, we present a dataset coupled with an approach to improve text fairness in classifiers and language models. We create a new, more comprehensive identity lexicon, TIDAL, which includes 15,123 identity terms and associated sense context across three demographic categories. We leverage TIDAL to develop an identity annotation and augmentation tool that can be used to improve the availability of identity context and the effectiveness of ML fairness techniques. We evaluate our approaches using human contributors, and additionally run experiments focused on dataset and model debiasing. Results show our assistive annotation technique improves the reliability and velocity of human-in-the-loop processes. Our dataset and methods uncover more disparities during evaluation, and also produce more fair models during remediation. These approaches provide a practical path forward for scaling classifier and generative model fairness in real-world settings.