Extending CREAMT: Leveraging Large Language Models for Literary Translation Post-Editing

2025-04-03

AI Summary

This study investigates the feasibility of post-editing literary translations generated by large language models (LLMs), aiming to balance translator efficiency with stylistic fidelity and creative expression. A controlled experiment was conducted with professional literary translators, employing customized editing tools and a multidimensional evaluation framework assessing time efficiency, creativity, and faithfulness, complemented by expert human quality ratings. Results systematically validate the LLM-assisted post-editing paradigm for literary translation: post-editing reduced translation time significantly—by approximately 40% on average—relative to full human translation, without statistically significant degradation in creativity or stylistic consistency. The primary contribution is the empirical establishment of a robust, practice-oriented workflow wherein LLMs serve as reliable first-draft sources for high-resource language pairs. This work provides foundational evidence and methodological guidance for human–AI collaboration in literary translation.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Cognitive Modeling & Cognitive Systems: Computational Creativity

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

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.

Problem

• Balancing efficiency and creativity in literary translation post-editing
• Evaluating LLMs for context-aware creative translation post-editing
• Assessing productivity gains and creativity in LLM-assisted literary translation

Innovation

• Leveraging LLMs for literary translation post-editing
• Custom tool for editing time and quality analysis
• LLMs reduce editing time while preserving creativity