RAMP: Retrieval and Attribute-Marking Enhanced Prompting for Attribute-Controlled Translation
This work addresses a domain-specific problem in machine translation for applications requiring stylistic control, but it is incremental as it builds on existing prompting techniques.
The paper tackles the problem of attribute-controlled translation (ACT) by proposing RAMP, a method that uses retrieval and attribute-marking with large language models to improve accuracy in few-shot and zero-shot settings, achieving better performance than standard prompting.
Attribute-controlled translation (ACT) is a subtask of machine translation that involves controlling stylistic or linguistic attributes (like formality and gender) of translation outputs. While ACT has garnered attention in recent years due to its usefulness in real-world applications, progress in the task is currently limited by dataset availability, since most prior approaches rely on supervised methods. To address this limitation, we propose Retrieval and Attribute-Marking enhanced Prompting (RAMP), which leverages large multilingual language models to perform ACT in few-shot and zero-shot settings. RAMP improves generation accuracy over the standard prompting approach by (1) incorporating a semantic similarity retrieval component for selecting similar in-context examples, and (2) marking in-context examples with attribute annotations. Our comprehensive experiments show that RAMP is a viable approach in both zero-shot and few-shot settings.