# CULL-MT: Compression Using Language and Layer pruning for Machine Translation

arXiv: https://arxiv.org/abs/2411.06506 · HTML: https://mlsanity.com/paper/2411.06506/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 38 references that are in the map.
- First posted on arXiv 10 Nov 2024.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [Training Deep Nets with Sublinear Memory Cost](https://mlsanity.com/paper/1604.06174/) (2016)
- [Sequence-Level Knowledge Distillation](https://mlsanity.com/paper/1606.07947/) (2016)
- [ZeRO-Offload: Democratizing Billion-Scale Model Training](https://mlsanity.com/paper/2101.06840/) (2021)
- [Massively Multilingual Neural Machine Translation](https://mlsanity.com/paper/1903.00089/) (2019)
- [When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method](https://mlsanity.com/paper/2402.17193/) (2024)
- [MADLAD-400: A Multilingual And Document-Level Large Audited Dataset](https://mlsanity.com/paper/2309.04662/) (2023)
- [Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning](https://mlsanity.com/paper/2303.15647/) (2023)
- [The Bottom-up Evolution of Representations in the Transformer: A Study with Machine Translation and Language Modeling Objectives](https://mlsanity.com/paper/1909.01380/) (2019)
- [On the Effect of Dropping Layers of Pre-trained Transformer Models](https://mlsanity.com/paper/2004.03844/) (2020)
- [Multi-Way, Multilingual Neural Machine Translation with a Shared Attention Mechanism](https://mlsanity.com/paper/1601.01073/) (2016)

## Built on by (most cited first, 3 of 3)

- [Efficient Speech Translation through Model Compression and Knowledge Distillation](https://mlsanity.com/paper/2505.20237/) (2025)
- [Iterative Layer Pruning for Efficient Translation Inference](https://mlsanity.com/paper/2510.22763/) (2025)
- [AfriNLLB: Efficient Translation Models for African Languages](https://mlsanity.com/paper/2602.09373/) (2026)

## Abstract (arXiv)

Multilingual machine translation models often outperform traditional bilingual models by leveraging translation knowledge transfer. Recent advancements have led to these models supporting hundreds of languages and achieving state-of-the-art results across various translation directions. However, as these models grow larger, their inference operations become increasingly costly. In many use cases, there is no need to support such a wide range of language pairs, as translation is typically needed in only a few selected directions. In this paper, we present CULL-MT, a compression method for machine translation models based on structural layer pruning and selected language directions. Our approach identifies and prunes unimportant layers using a greedy strategy, then mitigates the impact by applying knowledge distillation from the original model along with parameter-efficient fine-tuning. We apply CULL-MT to the NLLB-3.3B and LLaMA3.1-8B-Instruct models. In a multi-way translation scenario (Persian, French, and German to English), we find the NLLB-3.3B model to be robust, allowing 25% of layers to be pruned with only a 0.9 spBLEU drop. However, LLaMA3.1-8B-Instruct is more sensitive, with a 2.0 spBLEU drop after pruning 5 layers.