# On Defining Erasure Harms for NLP

arXiv: https://arxiv.org/abs/2606.15815 · HTML: https://mlsanity.com/paper/2606.15815/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 49 references that are in the map.
- First posted on arXiv 14 Jun 2026.

## Builds on (most cited first, 23 of 23)

- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization](https://mlsanity.com/paper/1808.08745/) (2018)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [Teaching Machines to Read and Comprehend](https://mlsanity.com/paper/1506.03340/) (2015)
- [StereoSet: Measuring stereotypical bias in pretrained language models](https://mlsanity.com/paper/2004.09456/) (2020)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [Text Summarization with Pretrained Encoders](https://mlsanity.com/paper/1908.08345/) (2019)
- [Measurement and Fairness](https://mlsanity.com/paper/1912.05511/) (2019)
- [Mitigating Gender Bias in Natural Language Processing: Literature Review](https://mlsanity.com/paper/1906.08976/) (2019)
- [HateCheck: Functional Tests for Hate Speech Detection Models](https://mlsanity.com/paper/2012.15606/) (2020)
- [Harms of Gender Exclusivity and Challenges in Non-Binary Representation in Language Technologies](https://mlsanity.com/paper/2108.12084/) (2021)
- [On Measures of Biases and Harms in NLP](https://mlsanity.com/paper/2108.03362/) (2021)
- [Position: Evaluating Generative AI Systems Is a Social Science Measurement Challenge](https://mlsanity.com/paper/2502.00561/) (2025)
- ["I'm fully who I am": Towards Centering Transgender and Non-Binary Voices to Measure Biases in Open Language Generation](https://mlsanity.com/paper/2305.09941/) (2023)
- [MISGENDERED: Limits of Large Language Models in Understanding Pronouns](https://mlsanity.com/paper/2306.03950/) (2023)
- [Theory-Grounded Measurement of U.S. Social Stereotypes in English Language Models](https://mlsanity.com/paper/2206.11684/) (2022)
- [Taxonomizing and Measuring Representational Harms: A Look at Image Tagging](https://mlsanity.com/paper/2305.01776/) (2023)
- [Geographical Erasure in Language Generation](https://mlsanity.com/paper/2310.14777/) (2023)
- ["One-Size-Fits-All"? Examining Expectations around What Constitute "Fair" or "Good" NLG System Behaviors](https://mlsanity.com/paper/2310.15398/) (2023)
- [Missing the Margins: A Systematic Literature Review on the Demographic Representativeness of LLMs](https://mlsanity.com/paper/2511.01864/) (2025)
- [A Tale of Two Identities: An Ethical Audit of Human and AI-Crafted Personas](https://mlsanity.com/paper/2505.07850/) (2025)
- [Taxonomizing Representational Harms using Speech Act Theory](https://mlsanity.com/paper/2504.00928/) (2025)

## Abstract (arXiv)

The deployment of NLP systems has raised concerns about harms they might produce, including representational harms. Recent literature has begun to conceptualize and measure one such harm, the harm of erasure. Nevertheless, the field lacks a clear and cohesive conceptual foundation for identifying and measuring erasure. Existing conceptualizations of erasure are often broad -- making it difficult to identify what is needed to establish and measure erasure -- or else specific to particular settings -- facilitating measurement for those settings but potentially challenging to adapt to other settings. To address this gap, we develop and propose a structured definition of erasure that clarifies what components are necessary for establishing whether erasure has occurred, which practitioners need to explicitly articulate and operationalize in order to measure erasure.