# Efficient Terminology Integration for LLM-based Translation in Specialized Domains

arXiv: https://arxiv.org/abs/2410.15690 · HTML: https://mlsanity.com/paper/2410.15690/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 9 references that are in the map.
- First posted on arXiv 21 Oct 2024.

## Builds on (most cited first, 5 of 5)

- [Dictionary-based Phrase-level Prompting of Large Language Models for Machine Translation](https://mlsanity.com/paper/2302.07856/) (2023)
- [Training Neural Machine Translation To Apply Terminology Constraints](https://mlsanity.com/paper/1906.01105/) (2019)
- [Domain Terminology Integration into Machine Translation: Leveraging Large Language Models](https://mlsanity.com/paper/2310.14451/) (2023)
- [Encouraging Neural Machine Translation to Satisfy Terminology Constraints](https://mlsanity.com/paper/2106.03730/) (2021)
- [Terminology-Aware Translation with Constrained Decoding and Large Language Model Prompting](https://mlsanity.com/paper/2310.05824/) (2023)

## Built on by (most cited first, 7 of 7)

- [Science Across Languages: Assessing LLM Multilingual Translation of Scientific Papers](https://mlsanity.com/paper/2502.17882/) (2025)
- [TAT-R1: Terminology-Aware Translation with Reinforcement Learning and Word Alignment](https://mlsanity.com/paper/2505.21172/) (2025)
- [TermGPT: Multi-Level Contrastive Fine-Tuning for Terminology Adaptation in Legal and Financial Domain](https://mlsanity.com/paper/2511.09854/) (2025)
- [MERIT: Multilingual Expert-Reward Informed Tuning for Chinese-Centric Low-Resource Machine Translation](https://mlsanity.com/paper/2604.04839/) (2026)
- [To Write or to Automate Linguistic Prompts, That Is the Question](https://mlsanity.com/paper/2603.25169/) (2026)
- [AI-assisted cultural heritage dissemination: Comparing NMT and glossary-augmented LLM translation in rock art documents](https://mlsanity.com/paper/2605.14679/) (2026)
- [ChemCLIR-Bench: Benchmarking Cross-Lingual Information Retrieval in Multilingual Chemical Patents](https://mlsanity.com/paper/2609.23231/) (2026)

## Abstract (arXiv)

Traditional machine translation methods typically involve training models directly on large parallel corpora, with limited emphasis on specialized terminology. However, In specialized fields such as patent, finance, or biomedical domains, terminology is crucial for translation, with many terms that needs to be translated following agreed-upon conventions. In this paper we introduce a methodology that efficiently trains models with a smaller amount of data while preserving the accuracy of terminology translation. We achieve this through a systematic process of term extraction and glossary creation using the Trie Tree algorithm, followed by data reconstruction to teach the LLM how to integrate these specialized terms. This methodology enhances the model's ability to handle specialized terminology and ensures high-quality translations, particularly in fields where term consistency is crucial. Our approach has demonstrated exceptional performance, achieving the highest translation score among participants in the WMT patent task to date, showcasing its effectiveness and broad applicability in specialized translation domains where general methods often fall short.