Conveying Imagistic Thinking in Traditional Chinese Medicine Translation: A Prompt Engineering and LLM-Based Evaluation Framework
It provides an incremental methodological pathway for translating concept-dense ancient texts like TCM, improving accessibility for target-language readers in clinical practice.
This study tackled the problem of translating Traditional Chinese Medicine texts by addressing the loss of imagistic thinking in literal translations, using a human-in-the-loop framework with prompt engineering to guide LLMs in identifying and conveying metaphors and metonymies. The results showed that prompt-adjusted LLM translations outperformed human and baseline translations across five cognitive dimensions, with high consistency across models and simulated reader roles.
Traditional Chinese Medicine theory is built on imagistic thinking, in which medical principles and diagnostic and therapeutic logic are structured through metaphor and metonymy. However, existing English translations largely rely on literal rendering, making it difficult for target-language readers to reconstruct the underlying conceptual networks and apply them in clinical practice. This study adopted a human-in-the-loop framework and selected four passages from the medical canon Huangdi Neijing that are fundamental in theory. Through prompt-based cognitive scaffolding, DeepSeek V3.1 was guided to identify metaphor and metonymy in the source text and convey the theory in translation. In the evaluation stage, ChatGPT 5 Pro and Gemini 2.5 Pro were instructed by prompts to simulate three types of real-world readers. Human translations, baseline model translations, and prompt-adjusted translations were scored by the simulated readers across five cognitive dimensions, followed by structured interviews and Interpretative Phenomenological Analysis. Results show that the prompt-adjusted LLM translations perform best across all five dimensions, with high cross-model and cross-role consistency. The interview themes reveal differences between human and machine translation, effective strategies for metaphor and metonymy transfer, and readers' cognitive preferences. This study provides a cognitive, efficient and replicable HITL methodological pathway for translation of ancient, concept-dense texts like TCM.