No Train but Gain: Language Arithmetic for training-free Language Adapters enhancement

TL;DR

This paper introduces a training-free language arithmetic method to enhance multilingual language adapters, significantly improving cross-lingual performance, especially in zero-shot scenarios, by applying post-processing techniques.

Contribution

It presents a novel language arithmetic approach that extends task arithmetic to multilingual models, enabling training-free post-processing to boost cross-lingual transfer.

Findings

Consistent performance improvements across three downstream tasks.

Significant gains in zero-shot cross-lingual applications.

Effective enhancement without additional training or fine-tuning.

Abstract

Modular deep learning is the state-of-the-art solution for lifting the curse of multilinguality, preventing the impact of negative interference and enabling cross-lingual performance in Multilingual Pre-trained Language Models. However, a trade-off of this approach is the reduction in positive transfer learning from closely related languages. In response, we introduce a novel method called language arithmetic, which enables training-free post-processing to address this limitation. Extending the task arithmetic framework, we apply learning via addition to the language adapters, transitioning the framework from a multi-task to a multilingual setup. The effectiveness of the proposed solution is demonstrated on three downstream tasks in a MAD-X-based set of cross-lingual schemes, acting as a post-processing procedure. Language arithmetic consistently improves the baselines with significant gains, especially in the most challenging case of zero-shot application. Our code and models are available at https://github.com/mklimasz/language-arithmetic .