提出可操作的消去性伤害定义，帮助识别NLP系统对群体的隐性抹除
On Defining Erasure Harms for NLP
- 构建结构化定义，明确判断消去性伤害所需的必要成分
- 强调实践者需明确定义并可操作化这些成分以测量伤害
- 适用于多场景，为伦理评估提供统一框架，适合研究者与工程师
NLP系统的部署引发了对其可能造成伤害的担忧，尤其是表征性伤害。近期研究开始概念化并度量一种特定伤害——消去性伤害。然而，该领域仍缺乏清晰且连贯的概念基础来识别和衡量此类伤害。现有对消去性的概念化往往过于宽泛，难以界定建立和测量消去性伤害所需条件；或仅针对特定场景，虽利于该场景下的测量，但难以推广至其他情境。为填补这一空白，本文提出一套结构化的消去性伤害定义，明确界定判断其是否发生的必要组成部分。从业者必须显式阐明并可操作化这些成分，才能有效测量消去性伤害。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。