Exploring Cross-lingual Latent Transplantation: Mutual Opportunities and Open Challenges

TL;DR

This paper introduces XTransplant, a framework for enhancing multilingual capabilities and cultural adaptability in LLMs by transplanting latent activations across languages, revealing underutilized potential.

Contribution

The paper proposes a novel probing framework, XTransplant, that exploits internal multilingual knowledge in LLMs to improve cross-lingual and cultural understanding.

Findings

XTransplant improves multilingual capabilities, especially for low-resource languages.

Attention modules are crucial for multilingual understanding.

Feed-forward modules better capture culture-specific knowledge.

Abstract

Current large language models (LLMs) often exhibit imbalances in multilingual capabilities and cultural adaptability, largely attributed to their English-centric pre-training data. In this paper, we introduce and investigate cross-lingual latent transplantation (XTransplant), a probing framework which aims to further exploit the model's internalized multilingual knowledge during inference and examine its effects on the multilingual capability and cultural adaptability of LLMs. XTransplant framework enables models to harness the complementary strengths of both English and non-English resources by transplanting latent activations across languages. Through extensive analysis, we empirically demonstrate that XTransplant, a form of cross-lingual interaction, has mutually beneficial effects on the multilingual capability and cultural adaptability of LLMs, particularly for low-resource languages and cultures. We further reveal that attention modules play a pivotal role in supporting multilingual understanding, while feed-forward modules are more adept at capturing culture-specific knowledge. In addition, we conduct in-depth analysis of XTransplant's stability, effectiveness, and generalizability. By probing the upper bound performance of XTransplant, we expose the considerable underutilization of current LLMs' multilingual potential-a challenge that remains open. We hope our analysis offers a new lens for advancing cross-lingual interactions and better leveraging models' internalized multilingual knowledge.