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

• URL: http://arxiv.org/abs/2412.14050v3
• Date: Fri, 14 Feb 2025 15:39:29 GMT
• Title: Cross-Lingual Transfer of Debiasing and Detoxification in Multilingual LLMs: An Extensive Investigation
• Authors: Vera Neplenbroek, Arianna Bisazza, Raquel Fernández,
• Abstract summary: Recent generative large language models (LLMs) show remarkable performance in non-English languages. When prompted in those languages they tend to express higher harmful social biases and toxicity levels. 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.
• Score: 6.781972039785424
• License:
• Abstract: 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.

Related papers

• From One to Many: Expanding the Scope of Toxicity Mitigation in Language Models [10.807067327137855]
  As language models embrace multilingual capabilities, it's crucial our safety measures keep pace. In the absence of sufficient annotated datasets across languages, we employ translated data to evaluate and enhance our mitigation techniques. This allows us to examine the effects of translation quality and the cross-lingual transfer on toxicity mitigation.
  arXiv  Detail & Related papers  (2024-03-06T17:51:43Z)
• Vicinal Risk Minimization for Few-Shot Cross-lingual Transfer in Abusive Language Detection [19.399281609371258]
  Cross-lingual transfer learning from high-resource to medium and low-resource languages has shown encouraging results. We resort to data augmentation and continual pre-training for domain adaptation to improve cross-lingual abusive language detection.
  arXiv  Detail & Related papers  (2023-11-03T16:51:07Z)
• Cross-Lingual Transfer Learning for Phrase Break Prediction with Multilingual Language Model [13.730152819942445]
  Cross-lingual transfer learning can be particularly effective for improving performance in low-resource languages. This suggests that cross-lingual transfer can be inexpensive and effective for developing TTS front-end in resource-poor languages.
  arXiv  Detail & Related papers  (2023-06-05T04:10:04Z)
• Exploring Cross-lingual Textual Style Transfer with Large Multilingual Language Models [78.12943085697283]
  Detoxification is a task of generating text in polite style while preserving meaning and fluency of the original toxic text. This work investigates multilingual and cross-lingual detoxification and the behavior of large multilingual models like in this setting.
  arXiv  Detail & Related papers  (2022-06-05T20:02:30Z)
• Language Contamination Explains the Cross-lingual Capabilities of English Pretrained Models [79.38278330678965]
  We find that common English pretraining corpora contain significant amounts of non-English text. This leads to hundreds of millions of foreign language tokens in large-scale datasets. We then demonstrate that even these small percentages of non-English data facilitate cross-lingual transfer for models trained on them.
  arXiv  Detail & Related papers  (2022-04-17T23:56:54Z)
• Reward Modeling for Mitigating Toxicity in Transformer-based Language Models [0.0]
  Transformer-based language models are able to generate fluent text and be efficiently adapted across various natural language generation tasks. Language models that are pretrained on large unlabeled web text corpora have been shown to suffer from degenerating toxic content and social bias behaviors. We propose Reinforce-Detoxify; A reinforcement learning-based method for mitigating toxicity in language models.
  arXiv  Detail & Related papers  (2022-02-19T19:26:22Z)
• Mitigating Biases in Toxic Language Detection through Invariant Rationalization [70.36701068616367]
  biases toward some attributes, including gender, race, and dialect, exist in most training datasets for toxicity detection. We propose to use invariant rationalization (InvRat), a game-theoretic framework consisting of a rationale generator and a predictor, to rule out the spurious correlation of certain syntactic patterns. Our method yields lower false positive rate in both lexical and dialectal attributes than previous debiasing methods.
  arXiv  Detail & Related papers  (2021-06-14T08:49:52Z)
• On the Language Coverage Bias for Neural Machine Translation [81.81456880770762]
  Language coverage bias is important for neural machine translation (NMT) because the target-original training data is not well exploited in current practice. By carefully designing experiments, we provide comprehensive analyses of the language coverage bias in the training data. We propose two simple and effective approaches to alleviate the language coverage bias problem.
  arXiv  Detail & Related papers  (2021-06-07T01:55:34Z)
• Challenges in Automated Debiasing for Toxic Language Detection [81.04406231100323]
  Biased associations have been a challenge in the development of classifiers for detecting toxic language. We investigate recently introduced debiasing methods for text classification datasets and models, as applied to toxic language detection. Our focus is on lexical (e.g., swear words, slurs, identity mentions) and dialectal markers (specifically African American English)
  arXiv  Detail & Related papers  (2021-01-29T22:03:17Z)
• On Negative Interference in Multilingual Models: Findings and A Meta-Learning Treatment [59.995385574274785]
  We show that, contrary to previous belief, negative interference also impacts low-resource languages. We present a meta-learning algorithm that obtains better cross-lingual transferability and alleviates negative interference.
  arXiv  Detail & Related papers  (2020-10-06T20:48:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.