paper-with-me

Papers

Tower: An Open Multilingual Large Language Model for Translation-Related Tasks

2024-02-27 · Duarte M. Alves, José Pombal, Nuno M. Guerreiro, Pedro H. Martins, João Alves, Amin Farajian, Ben Peters, Ricardo Rei, Patrick Fernandes, Sweta Agrawal, Pierre Colombo, José G. C. de Souza, André F. T. Martins

While general-purpose large language models (LLMs) demonstrate proficiency on multiple tasks within the domain of translation, approaches based on open LLMs are competitive only when specializing on a single task. In this paper, we propose a recipe for tailoring LLMs to multiple tasks present in translation workflows. We perform continued pretraining on a multilingual mixture of monolingual and parallel data, creating TowerBase, followed by finetuning on instructions relevant for translation processes, creating TowerInstruct. Our final model surpasses open alternatives on several tasks relevant to translation workflows and is competitive with general-purpose closed LLMs. To facilitate future research, we release the Tower models, our specialization dataset, an evaluation framework for LLMs focusing on the translation ecosystem, and a collection of model generations, including ours, on our benchmark.

📄 PDF Abstract BibTeX arXiv:2402.17733

Code (4)

deep-spin/tower-eval 공식 구현
epfllm/megatron-llm 공식 구현 pytorch
coldmist-lu/mqm_ape
dayeonki/rewrite_mt pytorch

Tasks

Language ModelingLanguage ModellingLarge Language ModelTranslation

Similar Papers 제목 키워드 기반

xTower: A Multilingual LLM for Explaining and Correcting Translation Errors

2024-06-27 · Marcos Treviso, Nuno M. Guerreiro, Sweta Agrawal, Ricardo Rei 외

While machine translation (MT) systems are achieving increasingly strong performance on benchmarks, they often produce translations with errors and anomalies. Understanding these errors can potentially help improve the t…

Error UnderstandingLanguage ModelingLanguage ModellingLarge Language Model+2

Multilingual Machine Translation with Open Large Language Models at Practical Scale: An Empirical Study

2025-02-04 · Menglong Cui, Pengzhi Gao, Wei Liu, Jian Luan 외

Large language models (LLMs) have shown continuously improving multilingual capabilities, and even small-scale open-source models have demonstrated rapid performance enhancement. In this paper, we systematically explore …

Continual PretrainingMachine TranslationTranslation

TowerVision: Understanding and Improving Multilinguality in Vision-Language Models

2025-10-22 · André G. Viveiros, Patrick Fernandes, Saul Santos, Sonal Sannigrahi 외 arxiv

Despite significant advances in vision-language models (VLMs), most existing work follows an English-centric design process, limiting their effectiveness in multilingual settings. In this work, we provide a comprehensive…

From TOWER to SPIRE: Adding the Speech Modality to a Text-Only LLM

2025-03-13 · Kshitij Ambilduke, Ben Peters, Sonal Sannigrahi, Anil Keshwani 외

Large language models (LLMs) have shown remarkable performance and generalization capabilities across multiple languages and tasks, making them very attractive targets for multi-modality integration (e.g., images or spee…

Translation

MultiSynt/MT: Trillion-Token Multi-Parallel Pre-Training Data Translated Across 36 Languages

2026-07-01 · Maximilian Idahl, Jörg Tiedemann, Sampo Pyysalo, David Salinas 외 arxiv

Open web-scale pre-training corpora remain concentrated in English, limiting multilingual LLM development. We introduce MultiSynt/MT, an open synthetic parallel corpus with approximately 4.8 trillion target-language toke…