# Which LoRA? An Empirical Study on the Effectiveness of LoRA Techniques During Multilingual Instruction Tuning

arXiv: https://arxiv.org/abs/2606.10428 · HTML: https://mlsanity.com/paper/2606.10428/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 20 references that are in the map.
- First posted on arXiv 9 Jun 2026.

## Builds on (most cited first, 11 of 11)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [XNLI: Evaluating Cross-lingual Sentence Representations](https://mlsanity.com/paper/1809.05053/) (2018)
- [VeRA: Vector-based Random Matrix Adaptation](https://mlsanity.com/paper/2310.11454/) (2023)
- [Do Llamas Work in English? On the Latent Language of Multilingual Transformers](https://mlsanity.com/paper/2402.10588/) (2024)
- [Multilingual Instruction Tuning With Just a Pinch of Multilinguality](https://mlsanity.com/paper/2401.01854/) (2024)
- [Language Arithmetics: Towards Systematic Language Neuron Identification and Manipulation](https://mlsanity.com/paper/2507.22608/) (2025)
- [Challenges in Adapting Multilingual LLMs to Low-Resource Languages using LoRA PEFT Tuning](https://mlsanity.com/paper/2411.18571/) (2024)
- [Low-Rank Adaptation for Multilingual Summarization: An Empirical Study](https://mlsanity.com/paper/2311.08572/) (2023)
- [Continually Adding New Languages to Multilingual Language Models](https://mlsanity.com/paper/2509.11414/) (2025)
- [LinguaMap: Which Layers of LLMs Speak Your Language and How to Tune Them?](https://mlsanity.com/paper/2601.20009/) (2026)
- [What Causes Knowledge Loss in Multilingual Language Models?](https://mlsanity.com/paper/2504.20356/) (2025)

## Abstract (arXiv)

We investigate whether commonly available LoRA variants have an advantage over basic LoRA in multilingual instruction tuning. Experiments involving LoRA and four other variants on two datasets across diverse target languages show that there is no significant advantage in using more complex LoRA variants instead of basic LoRA, with respect to balancing cross-lingual transfer and knowledge retention. An analysis of hidden embeddings reveal that layer-wise language representation remains largely similar across LLMs fine-tuned with different LoRA techniques, suggesting that architectural novelty of LoRA techniques may not translate into better cross-lingual adaptation.