paper-with-me

홈 › Papers

On Defining Erasure Harms for NLP

2026-06-14 · Yu Lu Liu, Arnav Goel, Jackie Chi Kit Cheung, Alexandra Olteanu, Ziang Xiao, Su Lin Blodgett 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.

📄 PDF Abstract BibTeX arXiv:2606.15815

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Harms of Gender Exclusivity and Challenges in Non-Binary Representation in Language Technologies

2021-08-27 · EMNLP 2021 11 · Sunipa Dev, Masoud Monajatipoor, Anaelia Ovalle, Arjun Subramonian 외

Gender is widely discussed in the context of language tasks and when examining the stereotypes propagated by language models. However, current discussions primarily treat gender as binary, which can perpetuate harms such…

Taxonomizing Representational Harms using Speech Act Theory

2025-04-01 · Emily Corvi, Hannah Washington, Stefanie Reed, Chad Atalla 외

Representational harms are widely recognized among fairness-related harms caused by generative language systems. However, their definitions are commonly under-specified. We make a theoretical contribution to the specific…

Fairnessvalid

The Psychosocial Impacts of Generative AI Harms

2024-05-02 · Faye-Marie Vassel, Evan Shieh, Cassidy R. Sugimoto, Thema Monroe-White

The rapid emergence of generative Language Models (LMs) has led to growing concern about the impacts that their unexamined adoption may have on the social well-being of diverse user groups. Meanwhile, LMs are increasingl…

Gender Trouble in Language Models: An Empirical Audit Guided by Gender Performativity Theory

2025-05-20 · Franziska Sofia Hafner, Ana Valdivia, Luc Rocher

Language models encode and subsequently perpetuate harmful gendered stereotypes. Research has succeeded in mitigating some of these harms, e.g. by dissociating non-gendered terms such as occupations from gendered terms s…

Anatomy

Representational Harms in LLM-Generated Narratives Against Global Majority Nationalities

2026-04-24 · Ilana Nguyen, Harini Suresh, Thema Monroe-White, Evan Shieh arxiv

Large language models (LLMs) are increasingly used for text generation tasks from everyday use to high-stakes enterprise and government applications, including simulated interviews with asylum seekers. While many works h…

Text Generation