Metraipolis › archive › dc_87c2fa0e288b

$μ^2$-Bench: A Multilingual Machine Unlearning Benchmark — arXiv:2609.20945

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.20945
License (as archived)
CC0-1.0
Archived
2026-10-10T01:27:09.827Z
SHA-256 of the archived text
075b9e07acbe2795570881b6cdc9e001fbab0f1051ba298ba82cbfbc1ae8c6c4
Stable URL of this page
https://metraipolis.com/documento/dc_87c2fa0e288b

How to cite

$μ^2$-Bench: A Multilingual Machine Unlearning Benchmark — arXiv:2609.20945 — arXiv (en), https://arxiv.org/abs/2609.20945 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_87c2fa0e288b (Metraipolis archive dc_87c2fa0e288b, sha256 075b9e07acbe2795570881b6cdc9e001fbab0f1051ba298ba82cbfbc1ae8c6c4)
BibTeX
@misc{dc87c2fa0e288b,
  title = {$μ^2$-Bench: A Multilingual Machine Unlearning Benchmark — arXiv:2609.20945},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.20945},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_87c2fa0e288b; sha256 075b9e07acbe2795570881b6cdc9e001fbab0f1051ba298ba82cbfbc1ae8c6c4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.20945. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Undesired information such as harmful content and private data propagates through Multilingual Large Language Models (LLMs) via direct training and indirect cross-linguistic spread. Multilingual Machine Unlearning (MMU) aims to remove such information, yet its evaluation remains underexplored, leaving unclear whether unlearning truly eliminates target knowledge across all languages. To bridge this gap, we introduce $\mu^2$-Bench, an MMU benchmark that simulates the full pipeline of memorization, unlearning, and evaluation across diverse languages. It 1) spans a broad set of languages, 2) evaluates on both training and hold-out languages, and 3) assesses knowledge as dispersed across multiple languages. We show that successful MMU requires methods that reflect multilingual characteristics, and conduct analysis to provide deeper insights into MMU.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-21 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.20945 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-10T01:00:30.264Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).