Multilingual Amnesia: On the Transferability of Unlearning in Multilingual LLMs

• URL: http://arxiv.org/abs/2601.05641v1
• Date: Fri, 09 Jan 2026 08:59:42 GMT
• Title: Multilingual Amnesia: On the Transferability of Unlearning in Multilingual LLMs
• Authors: Alireza Dehghanpour Farashah, Aditi Khandelwal, Marylou Fauchard, Zhuan Shi, Negar Rostamzadeh, Golnoosh Farnadi,
• Abstract summary: We study multilingual unlearning using the Aya-Expanse 8B model under two settings: data unlearning and concept unlearning.<n>We extend benchmarks for factual knowledge and stereotypes to ten languages through translation.<n>Our experiments show that unlearning in high-resource languages is generally more stable, with asymmetric transfer effects observed between typologically related languages.
• Score: 24.59074126514084
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As multilingual large language models become more widely used, ensuring their safety and fairness across diverse linguistic contexts presents unique challenges. While existing research on machine unlearning has primarily focused on monolingual settings, typically English, multilingual environments introduce additional complexities due to cross-lingual knowledge transfer and biases embedded in both pretraining and fine-tuning data. In this work, we study multilingual unlearning using the Aya-Expanse 8B model under two settings: (1) data unlearning and (2) concept unlearning. We extend benchmarks for factual knowledge and stereotypes to ten languages through translation: English, French, Arabic, Japanese, Russian, Farsi, Korean, Hindi, Hebrew, and Indonesian. These languages span five language families and a wide range of resource levels. Our experiments show that unlearning in high-resource languages is generally more stable, with asymmetric transfer effects observed between typologically related languages. Furthermore, our analysis of linguistic distances indicates that syntactic similarity is the strongest predictor of cross-lingual unlearning behavior.

Related papers

• When Meanings Meet: Investigating the Emergence and Quality of Shared Concept Spaces during Multilingual Language Model Training [57.230355403478995]
  We investigate the development of language-agnostic concept spaces during pretraining of EuroLLM.<n>We find that shared concept spaces emerge early and continue to refine, but that alignment with them is language-dependent.<n>In contrast to prior work, our fine-grained manual analysis reveals that some apparent gains in translation quality reflect shifts in behavior.
  arXiv  Detail & Related papers  (2026-01-30T11:23:01Z)
• Revisiting Multilingual Data Mixtures in Language Model Pretraining [20.282622416939997]
  We study the impact of different multilingual data mixtures in pretraining large language models.<n>We find that combining English and multilingual data does not necessarily degrade the in-language performance of either group.<n>We do not observe a significant "curse of multilinguality" as the number of training languages increases.
  arXiv  Detail & Related papers  (2025-10-29T20:46:03Z)
• How does a Multilingual LM Handle Multiple Languages? [0.0]
  This study critically examines capabilities in multilingual understanding, semantic representation, and cross-lingual knowledge transfer.<n>It assesses semantic similarity by analyzing multilingual word embeddings for consistency using cosine similarity.<n>It examines BLOOM-1.7B and Qwen2 through Named Entity Recognition and sentence similarity tasks to understand their linguistic structures.
  arXiv  Detail & Related papers  (2025-02-06T18:08:14Z)
• Large Language Models Share Representations of Latent Grammatical Concepts Across Typologically Diverse Languages [15.203789021094982]
  In large language models (LLMs), how are multiple languages learned and encoded?<n>We train sparse autoencoders on Llama-3-8B and Aya-23-8B, and demonstrate that abstract grammatical concepts are often encoded in feature directions shared across many languages.
  arXiv  Detail & Related papers  (2025-01-10T21:18:21Z)
• Thank You, Stingray: Multilingual Large Language Models Can Not (Yet) Disambiguate Cross-Lingual Word Sense [30.62699081329474]
  We introduce a novel benchmark for cross-lingual sense disambiguation, StingrayBench. We collect false friends in four language pairs, namely Indonesian-Malay, Indonesian-Tagalog, Chinese-Japanese, and English-German. In our analysis of various models, we observe they tend to be biased toward higher-resource languages.
  arXiv  Detail & Related papers  (2024-10-28T22:09:43Z)
• The Role of Language Imbalance in Cross-lingual Generalisation: Insights from Cloned Language Experiments [57.273662221547056]
  In this study, we investigate an unintuitive novel driver of cross-lingual generalisation: language imbalance. We observe that the existence of a predominant language during training boosts the performance of less frequent languages. As we extend our analysis to real languages, we find that infrequent languages still benefit from frequent ones, yet whether language imbalance causes cross-lingual generalisation there is not conclusive.
  arXiv  Detail & Related papers  (2024-04-11T17:58:05Z)
• Phylogeny-Inspired Adaptation of Multilingual Models to New Languages [43.62238334380897]
  We show how we can use language phylogenetic information to improve cross-lingual transfer leveraging closely related languages. We perform adapter-based training on languages from diverse language families (Germanic, Uralic, Tupian, Uto-Aztecan) and evaluate on both syntactic and semantic tasks.
  arXiv  Detail & Related papers  (2022-05-19T15:49:19Z)
• Discovering Representation Sprachbund For Multilingual Pre-Training [139.05668687865688]
  We generate language representation from multilingual pre-trained models and conduct linguistic analysis. We cluster all the target languages into multiple groups and name each group as a representation sprachbund. Experiments are conducted on cross-lingual benchmarks and significant improvements are achieved compared to strong baselines.
  arXiv  Detail & Related papers  (2021-09-01T09:32:06Z)
• AM2iCo: Evaluating Word Meaning in Context across Low-ResourceLanguages with Adversarial Examples [51.048234591165155]
  We present AM2iCo, Adversarial and Multilingual Meaning in Context. It aims to faithfully assess the ability of state-of-the-art (SotA) representation models to understand the identity of word meaning in cross-lingual contexts. Results reveal that current SotA pretrained encoders substantially lag behind human performance.
  arXiv  Detail & Related papers  (2021-04-17T20:23:45Z)
• Gender Bias in Multilingual Embeddings and Cross-Lingual Transfer [101.58431011820755]
  We study gender bias in multilingual embeddings and how it affects transfer learning for NLP applications. We create a multilingual dataset for bias analysis and propose several ways for quantifying bias in multilingual representations.
  arXiv  Detail & Related papers  (2020-05-02T04:34:37Z)
• Bridging Linguistic Typology and Multilingual Machine Translation with Multi-View Language Representations [83.27475281544868]
  We use singular vector canonical correlation analysis to study what kind of information is induced from each source. We observe that our representations embed typology and strengthen correlations with language relationships. We then take advantage of our multi-view language vector space for multilingual machine translation, where we achieve competitive overall translation accuracy.
  arXiv  Detail & Related papers  (2020-04-30T16:25:39Z)

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.