Extending CREAMT: Leveraging Large Language Models for Literary Translation Post-Editing
This addresses efficiency and creativity challenges for literary translators working with high-resource languages, though it appears incremental as it builds on existing post-editing methods with LLMs.
The study tackled the problem of post-editing machine translation for creative literary texts by evaluating large language models (LLMs), finding that post-editing LLM-generated translations significantly reduces editing time while maintaining similar creativity levels compared to human translation.
Post-editing machine translation (MT) for creative texts, such as literature, requires balancing efficiency with the preservation of creativity and style. While neural MT systems struggle with these challenges, large language models (LLMs) offer improved capabilities for context-aware and creative translation. This study evaluates the feasibility of post-editing literary translations generated by LLMs. Using a custom research tool, we collaborated with professional literary translators to analyze editing time, quality, and creativity. Our results indicate that post-editing LLM-generated translations significantly reduces editing time compared to human translation while maintaining a similar level of creativity. The minimal difference in creativity between PE and MT, combined with substantial productivity gains, suggests that LLMs may effectively support literary translators working with high-resource languages.