Abstract
The current neural machine translation (NMT) models face several challenges including the high cost of parallel sentence pairs and difficulties in learning from limited error examples. To address these issues, we propose a novel framework, Large Language Models as Environments (LLMaE), which leverages interactions with large language models (LLMs) to enhance NMT performance. The LLMaE framework comprises three logically sequential steps: behavior imitation, reward feedback, and introspection. The behavior imitation step facilitates the NMT model to mimic the behavioral patterns of the LLMs. The reward feedback step leverages the quality assessments provided by the LLMs to optimize the NMT model and encourage it to produce more accurate translations. Finally, the introspection step enables the NMT model to learn from limited error examples by generating introspective examples. Each stage builds on the previous one, creating a cycle of continuous improvement. Extensive experimental results demonstrate that our proposed method significantly improves the performance of NMT in various scenarios and with different LLMs.
Funding Information
  • National Natural Science Foundation of China (62476271)
  • Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS2024316)

This publication has 31 references indexed in Scilit: