LANDeRMT: Detecting and Routing Language-Aware Neurons for Selectively Finetuning LLMs to Machine Translation

• URL: http://arxiv.org/abs/2409.19523v1
• Date: Sun, 29 Sep 2024 02:39:42 GMT
• Title: LANDeRMT: Detecting and Routing Language-Aware Neurons for Selectively Finetuning LLMs to Machine Translation
• Authors: Shaolin Zhu, Leiyu Pan, Bo Li, Deyi Xiong,
• Abstract summary: Large language models (LLMs) have shown promising results in multilingual translation even with limited bilingual supervision. Recent advancements in large language models (LLMs) have shown promising results in multilingual translation even with limited bilingual supervision. LandeRMT is a framework that selectively finetunes LLMs to textbfMachine textbfTranslation with diverse translation training data.
• Score: 43.26446958873554
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advancements in large language models (LLMs) have shown promising results in multilingual translation even with limited bilingual supervision. The major challenges are catastrophic forgetting and parameter interference for finetuning LLMs when provided parallel training data. To address these challenges, we propose LANDeRMT, a \textbf{L}anguage-\textbf{A}ware \textbf{N}euron \textbf{De}tecting and \textbf{R}outing framework that selectively finetunes LLMs to \textbf{M}achine \textbf{T}ranslation with diverse translation training data. In LANDeRMT, we evaluate the awareness of neurons to MT tasks and categorize them into language-general and language-specific neurons. This categorization enables selective parameter updates during finetuning, mitigating parameter interference and catastrophic forgetting issues. For the detected neurons, we further propose a conditional awareness-based routing mechanism to dynamically adjust language-general and language-specific capacity within LLMs, guided by translation signals. Experimental results demonstrate that the proposed LANDeRMT is very effective in learning translation knowledge, significantly improving translation quality over various strong baselines for multiple language pairs.

Related papers

• Beyond MLE: Investigating SEARNN for Low-Resourced Neural Machine Translation [0.09459165957946088]
  This project explored the potential of SEARNN to improve machine translation for low-resourced African languages. Experiments conducted on translation for English to Igbo, French to ewe, and French to ghomala directions. We proved that SEARNN is indeed a viable algorithm to effectively train RNNs on machine translation for low-resourced languages.
  arXiv  Detail & Related papers  (2024-05-20T06:28:43Z)
• TEaR: Improving LLM-based Machine Translation with Systematic Self-Refinement [26.26493253161022]
  Large Language Models (LLMs) have achieved impressive results in Machine Translation (MT) We introduce a systematic LLM-based self-refinement translation framework, named textbfTEaR.
  arXiv  Detail & Related papers  (2024-02-26T07:58:12Z)
• Salute the Classic: Revisiting Challenges of Machine Translation in the Age of Large Language Models [91.6543868677356]
  The evolution of Neural Machine Translation has been influenced by six core challenges. These challenges include domain mismatch, amount of parallel data, rare word prediction, translation of long sentences, attention model as word alignment, and sub-optimal beam search. This study revisits these challenges, offering insights into their ongoing relevance in the context of advanced Large Language Models.
  arXiv  Detail & Related papers  (2024-01-16T13:30:09Z)
• Only Send What You Need: Learning to Communicate Efficiently in Federated Multilingual Machine Translation [19.28500206536013]
  Federated learning (FL) is a promising approach for solving multilingual tasks. We propose a meta-learning-based adaptive parameter selection methodology, MetaSend, that improves the communication efficiency of model transmissions. We demonstrate that MetaSend obtains substantial improvements over baselines in translation quality in the presence of a limited communication budget.
  arXiv  Detail & Related papers  (2024-01-15T04:04:26Z)
• POMP: Probability-driven Meta-graph Prompter for LLMs in Low-resource Unsupervised Neural Machine Translation [32.76853731410492]
  Low-resource languages (LRLs) face challenges in supervised neural machine translation due to limited parallel data. We propose Probability-driven Meta-graph Prompter (POMP) to enhance Large Language Models' translation capabilities for LRLs. Our experiments show significant improvements in the translation quality of three LRLs.
  arXiv  Detail & Related papers  (2024-01-11T00:03:36Z)
• Towards Effective Disambiguation for Machine Translation with Large Language Models [65.80775710657672]
  We study the capabilities of large language models to translate "ambiguous sentences" Experiments show that our methods can match or outperform state-of-the-art systems such as DeepL and NLLB in four out of five language directions.
  arXiv  Detail & Related papers  (2023-09-20T22:22:52Z)
• Simultaneous Machine Translation with Large Language Models [51.470478122113356]
  We investigate the possibility of applying Large Language Models to SimulMT tasks. We conducted experiments using the textttLlama2-7b-chat model on nine different languages from the MUST-C dataset. The results show that LLM outperforms dedicated MT models in terms of BLEU and LAAL metrics.
  arXiv  Detail & Related papers  (2023-09-13T04:06:47Z)
• 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)
• Parameter-Efficient Neural Reranking for Cross-Lingual and Multilingual Retrieval [66.69799641522133]
  State-of-the-art neural (re)rankers are notoriously data hungry. Current approaches typically transfer rankers trained on English data to other languages and cross-lingual setups by means of multilingual encoders. We show that two parameter-efficient approaches to cross-lingual transfer, namely Sparse Fine-Tuning Masks (SFTMs) and Adapters, allow for a more lightweight and more effective zero-shot transfer.
  arXiv  Detail & Related papers  (2022-04-05T15:44:27Z)
• Sentence Boundary Augmentation For Neural Machine Translation Robustness [11.290581889247983]
  We show that sentence boundary segmentation has the largest impact on quality, and we develop a simple data augmentation strategy to improve segmentation robustness. We show that sentence boundary segmentation has the largest impact on quality, and we develop a simple data augmentation strategy to improve segmentation robustness.
  arXiv  Detail & Related papers  (2020-10-21T16:44:48Z)

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.