arXiv：cs.AI· Atreya Ghosal, Ashim Gupta, Vivek Srikumar·· 16 小时前
LLM 如何构建受限的酷儿叙事：一项关于不平等声音的研究
Unequal Voices: How LLMs Construct Constrained Queer Narratives
AI 导读
研究发现 LLM 在刻画酷儿人物时存在显著局限，其生成叙事往往默认落入狭隘、刻板的主题范围。论文将这种受限表征归纳为有害表征、狭隘表征和话语他者化三类，并据此提出假设进行检验。
正文
Abstract: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.
| Subjects: | Computers and Society (cs.CY); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2507.15585 [cs.CY] |
| (or arXiv:2507.15585v2 [cs.CY] for this version) | |
| https://doi.org/10.48550/arXiv.2507.15585 arXiv-issued DOI via DataCite |
Submission history
From: Atreya Ghosal [view email]
[v1]
Mon, 21 Jul 2025 13:03:38 UTC (9,780 KB)
[v2]
Mon, 12 Oct 2026 18:16:58 UTC (1,042 KB)
来源：arXiv：cs.AI · arxiv.org