# When Does Language Transfer Help? Sequential Fine-Tuning for Cross-Lingual Euphemism Detection

arXiv: https://arxiv.org/abs/2508.11831 · HTML: https://mlsanity.com/paper/2508.11831/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 22 references that are in the map.
- First posted on arXiv 15 Aug 2025.

## Builds on (most cited first, 13 of 13)

- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Don't Stop Pretraining: Adapt Language Models to Domains and Tasks](https://mlsanity.com/paper/2004.10964/) (2020)
- [How multilingual is Multilingual BERT?](https://mlsanity.com/paper/1906.01502/) (2019)
- [Self-Supervised Euphemism Detection and Identification for Content Moderation](https://mlsanity.com/paper/2103.16808/) (2021)
- [Fine-tuning Large Language Models with Sequential Instructions](https://mlsanity.com/paper/2403.07794/) (2024)
- [CATs are Fuzzy PETs: A Corpus and Analysis of Potentially Euphemistic Terms](https://mlsanity.com/paper/2205.02728/) (2022)
- [Searching for PETs: Using Distributional and Sentiment-Based Methods to Find Potentially Euphemistic Terms](https://mlsanity.com/paper/2205.10451/) (2022)
- [A Report on the Euphemisms Detection Shared Task](https://mlsanity.com/paper/2211.13327/) (2022)
- [EUREKA: EUphemism Recognition Enhanced through Knn-based methods and Augmentation](https://mlsanity.com/paper/2210.12846/) (2022)
- [Exploring Euphemism Detection in Few-Shot and Zero-Shot Settings](https://mlsanity.com/paper/2210.12926/) (2022)
- [FEED PETs: Further Experimentation and Expansion on the Disambiguation of Potentially Euphemistic Terms](https://mlsanity.com/paper/2306.00217/) (2023)
- [MEDs for PETs: Multilingual Euphemism Disambiguation for Potentially Euphemistic Terms](https://mlsanity.com/paper/2401.14526/) (2024)
- [Turkish Delights: a Dataset on Turkish Euphemisms](https://mlsanity.com/paper/2407.13040/) (2024)

## Built on by (most cited first, 1 of 1)

- [When Semantic Overlap Is Not Enough: Cross-Lingual Euphemism Transfer Between Turkish and English](https://mlsanity.com/paper/2602.16957/) (2026)

## Abstract (arXiv)

Euphemisms are culturally variable and often ambiguous, posing challenges for language models, especially in low-resource settings. This paper investigates how cross-lingual transfer via sequential fine-tuning affects euphemism detection across five languages: English, Spanish, Chinese, Turkish, and Yoruba. We compare sequential fine-tuning with monolingual and simultaneous fine-tuning using XLM-R and mBERT, analyzing how performance is shaped by language pairings, typological features, and pretraining coverage. Results show that sequential fine-tuning with a high-resource L1 improves L2 performance, especially for low-resource languages like Yoruba and Turkish. XLM-R achieves larger gains but is more sensitive to pretraining gaps and catastrophic forgetting, while mBERT yields more stable, though lower, results. These findings highlight sequential fine-tuning as a simple yet effective strategy for improving euphemism detection in multilingual models, particularly when low-resource languages are involved.