Pruning Multilingual Large Language Models for Multilingual Inference
Multilingual large language models (MLLMs), trained on multilingual balanced data, demonstrate better zero-shot learning performance in non-English languages compared to large language models trained on English-dominant data. However, the disparity in performance between English and non-English languages remains a challenge yet to be fully addressed. A distinctive characteristic of MLLMs is their high-quality translation capabilities, indicating an acquired proficiency in aligning between languages. This study explores how to enhance the zero-shot performance of MLLMs in non-English languages by leveraging their alignment capability between English and non-English languages. To achieve this, we first analyze the behavior of MLLMs when performing translation and reveal that there are large magnitude features that play a critical role in the translation process. Inspired by these findings, we retain the weights associated with operations involving the large magnitude features and prune other weights to force MLLMs to rely on these features for tasks beyond translation. We empirically demonstrate that this pruning strategy can enhance the MLLMs' performance in non-English language.
Code (1)
Tasks
TranslationZero-Shot LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Probing Structured Pruning on Multilingual Pre-trained Models: Settings, Algorithms, and Efficiency
Structured pruning has been extensively studied on monolingual pre-trained language models and is yet to be fully evaluated on their multilingual counterparts. This work investigates three aspects of structured pruning o…
Memory-efficient NLLB-200: Language-specific Expert Pruning of a Massively Multilingual Machine Translation Model
The recently released NLLB-200 is a set of multilingual Neural Machine Translation models that cover 202 languages. The largest model is based on a Mixture of Experts architecture and achieves SoTA results across many la…
GPUMachine TranslationMixture-of-ExpertsTransfer Learning+1Investigating Language-Specific Calibration For Pruning Multilingual Large Language Models
Recent advances in large language model (LLM) pruning have shown state-of-the-art (SotA) compression results in post-training and retraining-free settings while maintaining high predictive performance. However, previous …
Language ModelingLanguage ModellingLarge Language ModelDynamic ASR Pathways: An Adaptive Masking Approach Towards Efficient Pruning of A Multilingual ASR Model
Neural network pruning offers an effective method for compressing a multilingual automatic speech recognition (ASR) model with minimal performance loss. However, it entails several rounds of pruning and re-training neede…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Network Pruningspeech-recognition+1On the Prunability of Attention Heads in Multilingual BERT
Large multilingual models, such as mBERT, have shown promise in crosslingual transfer. In this work, we employ pruning to quantify the robustness and interpret layer-wise importance of mBERT. On four GLUE tasks, the rela…