# XITE: Cross-lingual Interpolation for Transfer using Embeddings

arXiv: https://arxiv.org/abs/2604.23589 · HTML: https://mlsanity.com/paper/2604.23589/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 16 references that are in the map.
- First posted on arXiv 26 Apr 2026.

## Builds on (most cited first, 10 of 10)

- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Multilingual E5 Text Embeddings: A Technical Report](https://mlsanity.com/paper/2402.05672/) (2024)
- [MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classification](https://mlsanity.com/paper/2004.12239/) (2020)
- [Augmenting Data with Mixup for Sentence Classification: An Empirical Study](https://mlsanity.com/paper/1905.08941/) (2019)
- [Multilingual Alignment of Contextual Word Representations](https://mlsanity.com/paper/2002.03518/) (2020)
- [SeqMix: Augmenting Active Sequence Labeling via Sequence Mixup](https://mlsanity.com/paper/2010.02322/) (2020)
- [Adversarial Deep Averaging Networks for Cross-Lingual Sentiment Classification](https://mlsanity.com/paper/1606.01614/) (2016)
- [Enhancing Cross-lingual Transfer by Manifold Mixup](https://mlsanity.com/paper/2205.04182/) (2022)
- [Robust Unsupervised Cross-Lingual Word Embedding using Domain Flow Interpolation](https://mlsanity.com/paper/2210.03319/) (2022)

## Abstract (arXiv)

Facilitating cross-lingual transfer in multilingual language models remains a critical challenge. Towards this goal, we propose an embedding-based data augmentation technique called XITE. We start with unlabeled text from a low-resource target language, identify an English counterpart in a task-specific training corpus using embedding-based similarities and adopt its label. Next, we perform a simple interpolation of the source and target embeddings to create synthetic data for task-specific fine-tuning. Projecting the target text into a language-rich subspace using linear discriminant analysis (LDA), prior to interpolation, further boosts performance. Our cross-lingual embedding-based augmentation technique XITE yields significant improvements of up to 35.91% for sentiment analysis and up to 81.16% for natural language inference, using XLM-R, for a diverse set of target languages including Korean, Arabic, Urdu and Hindi. Apart from boosting cross-lingual transfer, adaptation using XITE also safeguards against forgetting and maintains task performance on the high-resource language.