# "Is Hate Lost in Translation?": Evaluation of Multilingual LGBTQIA+ Hate Speech Detection

arXiv: https://arxiv.org/abs/2410.11230 · HTML: https://mlsanity.com/paper/2410.11230/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 23 references that are in the map.
- First posted on arXiv 15 Oct 2024.

## Builds on (most cited first, 8 of 8)

- [A Survey of Code-switching: Linguistic and Social Perspectives for Language Technologies](https://mlsanity.com/paper/2301.01967/) (2023)
- [Facilitating Fine-grained Detection of Chinese Toxic Language: Hierarchical Taxonomy, Resources, and Benchmarks](https://mlsanity.com/paper/2305.04446/) (2023)
- ["HOT" ChatGPT: The promise of ChatGPT in detecting and discriminating hateful, offensive, and toxic comments on social media](https://mlsanity.com/paper/2304.10619/) (2023)
- [Revisiting Machine Translation for Cross-lingual Classification](https://mlsanity.com/paper/2305.14240/) (2023)
- [Dataset for Identification of Homophobia and Transophobia in Multilingual YouTube Comments](https://mlsanity.com/paper/2109.00227/) (2021)
- [T3L: Translate-and-Test Transfer Learning for Cross-Lingual Text Classification](https://mlsanity.com/paper/2306.04996/) (2023)
- [QueerBench: Quantifying Discrimination in Language Models Toward Queer Identities](https://mlsanity.com/paper/2406.12399/) (2024)
- [Bridging the gap in online hate speech detection: a comparative analysis of BERT and traditional models for homophobic content identification on X/Twitter](https://mlsanity.com/paper/2405.09221/) (2024)

## Abstract (arXiv)

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.