“仇恨在翻译中丢失了吗？”：多语言LGBTQIA+仇恨言论检测的评估
"Is Hate Lost in Translation?": Evaluation of Multilingual LGBTQIA+ Hate Speech Detection
AI总结：
本文评估了大型语言模型在英语、意大利语、中文和英语-泰米尔语中检测LGBTQIA+仇恨言论的能力，发现微调能持续提升性能，而机器翻译效果不一，且自动翻译难以捕捉语言的社会文化细微差别。
摘要：
本文探讨了大型语言模型在多种语言（包括英语、意大利语、中文和（语码转换）英语-泰米尔语）中检测LGBTQIA+仇恨言论的挑战，研究了机器翻译的影响以及仇恨言论的细微差别是否在翻译中得以保留。我们检验了零样本和微调GPT的仇恨言论检测能力。研究结果表明：（1）英语的性能最高，而英语-泰米尔语的语码转换场景性能最低；（2）微调在所有语言中均能持续提升性能，而翻译的效果则好坏参半。通过对原文和机器翻译文本进行仇恨言论检测的简单实验以及定性错误分析，本文揭示了语言的社会文化细微差别和复杂性，这些可能是自动翻译无法捕捉的。
英文摘要：
This paper explores the challenges of detecting LGBTQIA+ hate speech of large language models across multiple languages, including English, Italian, Chinese and (code-switched) English-Tamil, examining the impact of machine translation and whether the nuances of hate speech are preserved across translation. We examine the hate speech detection ability of zero-shot and fine-tuned GPT. Our findings indicate that: (1) English has the highest performance and the code-switching scenario of English-Tamil being the lowest, (2) fine-tuning improves performance consistently across languages whilst translation yields mixed results. Through simple experimentation with original text and machine-translated text for hate speech detection along with a qualitative error analysis, this paper sheds light on the socio-cultural nuances and complexities of languages that may not be captured by automatic translation.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
