大模型生成的酷儿叙事受限且刻板，缺乏多样性与深度。
Unequal Voices: How LLMs Construct Constrained Queer Narratives
- 分析大模型对酷儿群体的三类有害表述：刻板印象、内容狭窄、话语排斥。
- 实验证明大模型在描绘酷儿人物时显著缺乏多样性与复杂性。
- 适合关注AI伦理、社会偏见与包容性生成的研究者阅读。
社会群体在话语中被边缘化的一种方式是，关于他们的叙述往往默认局限于狭隘、刻板的主题范围。相比之下，主流群体则被允许展现人类存在的全部复杂性。本文从有害表征、内容狭窄和话语他者化三个维度，描述大模型生成中的酷儿形象受限现象，并提出可检验的假设。实验结果表明，大模型在刻画酷儿人物时存在显著局限性，其叙事远未达到应有的丰富性和真实性。
原文摘要 · Abstract (English)
One way social groups are marginalized in discourse is that the narratives told about them often default to a narrow, stereotyped range of topics. In contrast, default groups are allowed the full complexity of human existence. We describe the constrained representations of queer people in LLM generations in terms of harmful representations, narrow representations, and discursive othering and formulate hypotheses to test for these phenomena. Our results show that LLMs are significantly limited in their portrayals of queer personas.
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。