Multilingual Brain Surgeon: Large Language Models Can be Compressed Leaving No Language Behind
- URL: http://arxiv.org/abs/2404.04748v1
- Date: Sat, 6 Apr 2024 22:16:32 GMT
- Title: Multilingual Brain Surgeon: Large Language Models Can be Compressed Leaving No Language Behind
- Authors: Hongchuan Zeng, Hongshen Xu, Lu Chen, Kai Yu,
- Abstract summary: Large Language Models (LLMs) have ushered in a new era in Natural Language Processing, but their massive size demands effective compression techniques for practicality.
This paper introduces Multilingual Brain Surgeon (MBS), a novel calibration data sampling method for multilingual LLMs compression.
MBS overcomes the English-centric limitations of existing methods by sampling calibration data from various languages proportionally to the language distribution of the model training datasets.
- Score: 14.433894552549337
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Large Language Models (LLMs) have ushered in a new era in Natural Language Processing, but their massive size demands effective compression techniques for practicality. Although numerous model compression techniques have been investigated, they typically rely on a calibration set that overlooks the multilingual context and results in significant accuracy degradation for low-resource languages. This paper introduces Multilingual Brain Surgeon (MBS), a novel calibration data sampling method for multilingual LLMs compression. MBS overcomes the English-centric limitations of existing methods by sampling calibration data from various languages proportionally to the language distribution of the model training datasets. Our experiments, conducted on the BLOOM multilingual LLM, demonstrate that MBS improves the performance of existing English-centric compression methods, especially for low-resource languages. We also uncover the dynamics of language interaction during compression, revealing that the larger the proportion of a language in the training set and the more similar the language is to the calibration language, the better performance the language retains after compression. In conclusion, MBS presents an innovative approach to compressing multilingual LLMs, addressing the performance disparities and improving the language inclusivity of existing compression techniques.
Related papers
- Investigating Language-Specific Calibration For Pruning Multilingual Large Language Models [11.421452042888523]
We compare different calibration languages for pruning multilingual models across diverse languages, tasks, models, and SotA pruning techniques.
Our results offer practical suggestions, for example, calibrating in the target language can efficiently retain the language modeling capability but does not necessarily benefit downstream tasks.
arXiv Detail & Related papers (2024-08-26T16:29:13Z) - On the Calibration of Multilingual Question Answering LLMs [57.296161186129545]
We benchmark the calibration of several multilingual Large Language Models (MLLMs) on a variety of Question Answering tasks.
We study different dimensions of calibration in in-distribution, out-of-distribution, and cross-lingual transfer settings.
For decoder-only LLMs such as LlaMa2, we additionally find that in-context learning improves confidence calibration on multilingual data.
arXiv Detail & Related papers (2023-11-15T03:29:02Z) - Soft Language Clustering for Multilingual Model Pre-training [57.18058739931463]
We propose XLM-P, which contextually retrieves prompts as flexible guidance for encoding instances conditionally.
Our XLM-P enables (1) lightweight modeling of language-invariant and language-specific knowledge across languages, and (2) easy integration with other multilingual pre-training methods.
arXiv Detail & Related papers (2023-06-13T08:08:08Z) - Intriguing Properties of Compression on Multilingual Models [17.06142742945346]
We propose a framework to characterize the impact of sparsifying multilingual pre-trained language models during fine-tuning.
Applying this framework to mBERT named entity recognition models across 40 languages, we find that compression confers several intriguing and previously unknown generalization properties.
arXiv Detail & Related papers (2022-11-04T20:28:01Z) - A Simple and Effective Method to Improve Zero-Shot Cross-Lingual
Transfer Learning [6.329304732560936]
Existing zero-shot cross-lingual transfer methods rely on parallel corpora or bilingual dictionaries.
We propose Embedding-Push, Attention-Pull, and Robust targets to transfer English embeddings to virtual multilingual embeddings without semantic loss.
arXiv Detail & Related papers (2022-10-18T15:36:53Z) - High-resource Language-specific Training for Multilingual Neural Machine
Translation [109.31892935605192]
We propose the multilingual translation model with the high-resource language-specific training (HLT-MT) to alleviate the negative interference.
Specifically, we first train the multilingual model only with the high-resource pairs and select the language-specific modules at the top of the decoder.
HLT-MT is further trained on all available corpora to transfer knowledge from high-resource languages to low-resource languages.
arXiv Detail & Related papers (2022-07-11T14:33:13Z) - What Do Compressed Multilingual Machine Translation Models Forget? [102.50127671423752]
We show that the performance of under-represented languages drops significantly, while the average BLEU metric only slightly decreases.
We demonstrate that compression amplifies intrinsic gender and semantic biases, even in high-resource languages.
arXiv Detail & Related papers (2022-05-22T13:54:44Z) - UNKs Everywhere: Adapting Multilingual Language Models to New Scripts [103.79021395138423]
Massively multilingual language models such as multilingual BERT (mBERT) and XLM-R offer state-of-the-art cross-lingual transfer performance on a range of NLP tasks.
Due to their limited capacity and large differences in pretraining data, there is a profound performance gap between resource-rich and resource-poor target languages.
We propose novel data-efficient methods that enable quick and effective adaptation of pretrained multilingual models to such low-resource languages and unseen scripts.
arXiv Detail & Related papers (2020-12-31T11:37:28Z) - Cross-lingual Machine Reading Comprehension with Language Branch
Knowledge Distillation [105.41167108465085]
Cross-lingual Machine Reading (CLMRC) remains a challenging problem due to the lack of large-scale datasets in low-source languages.
We propose a novel augmentation approach named Language Branch Machine Reading (LBMRC)
LBMRC trains multiple machine reading comprehension (MRC) models proficient in individual language.
We devise a multilingual distillation approach to amalgamate knowledge from multiple language branch models to a single model for all target languages.
arXiv Detail & Related papers (2020-10-27T13:12:17Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.