# Cross-Lingual Transfer of Debiasing and Detoxification in Multilingual LLMs: An Extensive Investigation

arXiv: https://arxiv.org/abs/2412.14050 · HTML: https://mlsanity.com/paper/2412.14050/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 53 of its 90 references that are in the map.
- First posted on arXiv 18 Dec 2024.

## Builds on (most cited first, 30 of 53)

- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [StereoSet: Measuring stereotypical bias in pretrained language models](https://mlsanity.com/paper/2004.09456/) (2020)
- [Bag of Tricks for Efficient Text Classification](https://mlsanity.com/paper/1607.01759/) (2016)
- [CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models](https://mlsanity.com/paper/2010.00133/) (2020)
- [BBQ: A Hand-Built Bias Benchmark for Question Answering](https://mlsanity.com/paper/2110.08193/) (2021)
- [How multilingual is Multilingual BERT?](https://mlsanity.com/paper/1906.01502/) (2019)
- [On the Cross-lingual Transferability of Monolingual Representations](https://mlsanity.com/paper/1910.11856/) (2019)
- [The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation](https://mlsanity.com/paper/2106.03193/) (2021)
- [LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset](https://mlsanity.com/paper/2309.11998/) (2023)
- [Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints](https://mlsanity.com/paper/1707.09457/) (2017)
- [Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model](https://mlsanity.com/paper/2402.07827/) (2024)
- [ToxicChat: Unveiling Hidden Challenges of Toxicity Detection in Real-World User-AI Conversation](https://mlsanity.com/paper/2310.17389/) (2023)
- [A New Generation of Perspective API: Efficient Multilingual Character-level Transformers](https://mlsanity.com/paper/2202.11176/) (2022)
- [A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity](https://mlsanity.com/paper/2401.01967/) (2024)
- [Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning](https://mlsanity.com/paper/2402.06619/) (2024)
- [Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints](https://mlsanity.com/paper/2309.16240/) (2023)
- [When Being Unseen from mBERT is just the Beginning: Handling New Languages With Multilingual Language Models](https://mlsanity.com/paper/2010.12858/) (2020)
- [Aya 23: Open Weight Releases to Further Multilingual Progress](https://mlsanity.com/paper/2405.15032/) (2024)
- [Cross-Lingual Consistency of Factual Knowledge in Multilingual Language Models](https://mlsanity.com/paper/2310.10378/) (2023)
- [UNKs Everywhere: Adapting Multilingual Language Models to New Scripts](https://mlsanity.com/paper/2012.15562/) (2020)
- [Detoxifying Language Models Risks Marginalizing Minority Voices](https://mlsanity.com/paper/2104.06390/) (2021)

## Built on by (most cited first, 5 of 5)

- [Breaking mBad! Supervised Fine-tuning for Cross-Lingual Detoxification](https://mlsanity.com/paper/2505.16722/) (2025)
- [Analyzing Bias in False Refusal Behavior of Large Language Models for Hate Speech Detoxification](https://mlsanity.com/paper/2601.08668/) (2026)
- [Taiwan Safety Benchmark and Breeze Guard: Toward Trustworthy AI for Taiwanese Mandarin](https://mlsanity.com/paper/2603.07286/) (2026)
- [Where Does Toxicity Live? Mechanistic Localization and Targeted Suppression in Language Models](https://mlsanity.com/paper/2605.27997/) (2026)
- [A Survey of Toxicity Detection and Mitigation Strategies for Multilingual Language Models](https://mlsanity.com/paper/2606.25380/) (2026)

## Abstract (arXiv)

Recent generative large language models (LLMs) show remarkable performance in non-English languages, but when prompted in those languages they tend to express higher harmful social biases and toxicity levels. Prior work has shown that finetuning on specialized datasets can mitigate this behavior, and doing so in English can transfer to other languages. In this work, we investigate the impact of different finetuning methods on the model's bias and toxicity, but also on its ability to produce fluent and diverse text. We reduce biases by finetuning on curated non-harmful text, but find only direct preference optimization to be effective for mitigating toxicity. The mitigation caused by applying these methods in English also transfers to non-English languages. We find evidence that the extent to which transfer takes place can be predicted by the amount of data in a given language present in the model's pretraining data. However, this transfer of bias and toxicity mitigation often comes at the expense of decreased language generation ability in non-English languages, highlighting the importance of developing language-specific bias and toxicity mitigation methods.