Metraipolis › archive › dc_950c6ed457cf
Cross-lingual Representation Learning via Centroid Intervention Fusion — arXiv:2608.26357
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.26357
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T15:19:29.501Z
- SHA-256 of the archived text
856aadb5e23cdd2f7d8b67a1096c166c631c8c40b4993d5582627773634fc79b- Stable URL of this page
https://metraipolis.com/documento/dc_950c6ed457cf
How to cite
Cross-lingual Representation Learning via Centroid Intervention Fusion — arXiv:2608.26357 — arXiv (en), https://arxiv.org/abs/2608.26357 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_950c6ed457cf (Metraipolis archive dc_950c6ed457cf, sha256 856aadb5e23cdd2f7d8b67a1096c166c631c8c40b4993d5582627773634fc79b)
BibTeX
@misc{dc950c6ed457cf,
title = {Cross-lingual Representation Learning via Centroid Intervention Fusion — arXiv:2608.26357},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.26357},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_950c6ed457cf; sha256 856aadb5e23cdd2f7d8b67a1096c166c631c8c40b4993d5582627773634fc79b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.26357. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models (LLMs) exhibit uneven multilingual performance, especially when dealing with low-resource languages. Inference-time intervention offers a lightweight way to improve cross-lingual transfer by modifying the hidden states produced by the LLMs during the forward pass, without updating model parameters. However, existing cross-lingual intervention methods typically learn separate projections from source to target languages, which limits scalability and prevents knowledge sharing across languages. We propose Centroid Intervention Fusion (CIF), a projection fusion framework that consolidates multiple multilingual intervention projections into a single language-shared operator. Across multilingual commonsense reasoning, natural language inference, factual editing, and machine translation benchmarks, CIF outperforms the strongest prior pairwise intervention baseline by up to +3.378 pp on average across four model backbones, while supporting performance gains for low resource languages. The code is available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.CL). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2608.26357 — 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 2026-10-17T15:15:18.047Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).