BridG MT: Enhancing LLMs’ Machine Translation Capabilities with Sentence Bridging and Gradual MT
Year: 2025
Type: conference-paper
Abstract: Recent Large Language Models (LLMs) have demonstrated impressive translation performance without requiring fine-tuning on additional parallel corpora.However, they still face significant challenges in certain scenarios, particularly when translating low-resource languages.A common approach to address this issue is to provide external knowledge, such as few-shot examples, to assist LLMs in translating specific source sentences.However, this method is fundamentally limited by the quality or quantity of relevant sources, which cannot always be guaranteed.To reduce LLMs' reliance on external sources, we propose BridG MT, a method that combines Sentence Bridging, which generates a sequence of sentences as a bridge that gradually transition from easyto-translate to more difficult, and Gradual MT, which sequentially translates these sentences using earlier translations as few-shot examples for subsequent ones.Experiments conducted on four LLMs across seven languages demonstrate that our method effectively enhances translation performance, even outperforming translation methods that rely on a large number of few-shot examples.
Authors: Seungwoo Choi, Gahyun Yoo, Jay-Yoon Lee
Institution: Seoul National University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Funders: Korea Medical Device Development Fund, National Research Foundation, Seoul National University, Ministry of Trade, Industry and Energy, Ministry of Food and Drug Safety, Korea Institute of Science and Technology, Korea Institute of Science and Technology Information, National Research Foundation of Korea, Ministry of Science and ICT, South Korea, Institute for Information and Communications Technology Promotion
Award: G2045000886
OpenAlex ID: W4412944499