Conveying Imagistic Thinking in TCM Translation: A Prompt Engineering and LLM-Based Evaluation Framework

• URL: http://arxiv.org/abs/2511.23059v1
• Date: Fri, 28 Nov 2025 10:35:10 GMT
• Title: Conveying Imagistic Thinking in TCM Translation: A Prompt Engineering and LLM-Based Evaluation Framework
• Authors: Jiatong Han,
• Abstract summary: Traditional Chinese Medicine theory is built on imagistic thinking, in which medical principles and diagnostic and therapeutic logic are structured through metaphor and metonymy.<n>This study adopted a human-in-the-loop framework and selected four passages from the medical canon Huangdi Neijing that are fundamental in theory.<n>DeepSeek V3.1 was guided to identify metaphor and metonymy in the source text and convey the theory in translation.
• Score: 2.4294291235324867
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• When Meanings Meet: Investigating the Emergence and Quality of Shared Concept Spaces during Multilingual Language Model Training [57.230355403478995]
  We investigate the development of language-agnostic concept spaces during pretraining of EuroLLM.<n>We find that shared concept spaces emerge early and continue to refine, but that alignment with them is language-dependent.<n>In contrast to prior work, our fine-grained manual analysis reveals that some apparent gains in translation quality reflect shifts in behavior.
  arXiv  Detail & Related papers  (2026-01-30T11:23:01Z)
• Conveying Imagistic Thinking in Traditional Chinese Medicine Translation: A Prompt Engineering and LLM-Based Evaluation Framework [2.4294291235324867]
  Existing English translations largely rely on literal rendering.<n>This study adopted a human-in-the-loop framework and selected four passages from the medical canon Huangdi Neijing that are fundamental in theory.
  arXiv  Detail & Related papers  (2025-12-01T02:27:44Z)
• Liaozhai through the Looking-Glass: On Paratextual Explicitation of Culture-Bound Terms in Machine Translation [70.43884512651668]
  We formalize Genette's (1987) theory of paratexts from literary and translation studies to introduce the task of paratextual explicitation for machine translation.<n>We construct a dataset of 560 expert-aligned paratexts from four English translations of the classical Chinese short story collection Liaozhai.<n>Our findings demonstrate the potential of paratextual explicitation in advancing machine translation beyond linguistic equivalence.
  arXiv  Detail & Related papers  (2025-09-27T16:27:36Z)
• Pun Intended: Multi-Agent Translation of Wordplay with Contrastive Learning and Phonetic-Semantic Embeddings [0.0]
  This research proposes a novel approach for translating puns from English to French by combining state-of-the-art large language models with specialized techniques for wordplay generation.<n>Our methodology's primary objective is to capture the linguistic creativity and humor of the source text wordplay, rather than simply duplicating its vocabulary.
  arXiv  Detail & Related papers  (2025-07-09T03:09:14Z)
• The Paradox of Poetic Intent in Back-Translation: Evaluating the Quality of Large Language Models in Chinese Translation [2.685668802278156]
  This study constructs a diverse corpus encompassing Chinese scientific terminology, historical translation paradoxes, and literary metaphors.<n>We evaluate BLEU, CHRF, TER, and semantic similarity metrics across six major large language models (LLMs) and three traditional translation tools.
  arXiv  Detail & Related papers  (2025-04-22T21:48:05Z)
• From Metaphor to Mechanism: How LLMs Decode Traditional Chinese Medicine Symbolic Language for Modern Clinical Relevance [3.3692821811360743]
  We propose a novel multi-agent and chain-of-thought (CoT) framework designed to interpret Traditional Chinese Medicine (TCM) metaphors accurately and map them to Western medical concepts.<n>We detail a methodology for building a metaphor-rich TCM dataset, discuss strategies for effectively integrating multi-agent collaboration and CoT reasoning, and articulate the theoretical underpinnings that guide metaphor interpretation.<n>Our work aims to support clinical decision-making, cross-system educational initiatives, and integrated healthcare research, ultimately offering a robust scaffold for reconciling TCM's symbolic language with the mechanistic focus of Western medicine.
  arXiv  Detail & Related papers  (2025-03-04T16:22:49Z)
• DRT: Deep Reasoning Translation via Long Chain-of-Thought [73.21414200780171]
  We introduce DRT, an attempt to bring the success of long chain-of-thought to neural machine translation (MT)<n>We first mine sentences containing similes or metaphors from existing literature books, and then develop a multi-agent framework to translate these sentences via long thought.<n>Using Qwen2.5 and LLama-3.1 as the backbones, DRT models can learn the thought process during machine translation.
  arXiv  Detail & Related papers  (2024-12-23T11:55:33Z)
• Large Language Models as Neurolinguistic Subjects: Discrepancy between Performance and Competence [49.60849499134362]
  This study investigates the linguistic understanding of Large Language Models (LLMs) regarding signifier (form) and signified (meaning)<n>We introduce a neurolinguistic approach, utilizing a novel method that combines minimal pair and diagnostic probing to analyze activation patterns across model layers.<n>We found: (1) Psycholinguistic and neurolinguistic methods reveal that language performance and competence are distinct; (2) Direct probability measurement may not accurately assess linguistic competence; and (3) Instruction tuning won't change much competence but improve performance.
  arXiv  Detail & Related papers  (2024-11-12T04:16:44Z)
• (Perhaps) Beyond Human Translation: Harnessing Multi-Agent Collaboration for Translating Ultra-Long Literary Texts [56.7988577327046]
  We introduce TransAgents, a novel multi-agent framework that simulates the roles and collaborative practices of a human translation company.<n>Our findings highlight the potential of multi-agent collaboration in enhancing translation quality, particularly for longer texts.
  arXiv  Detail & Related papers  (2024-05-20T05:55:08Z)
• Temporal Dynamics of Emotion and Cognition in Human Translation: Integrating the Task Segment Framework and the HOF Taxonomy [0.0]
  The article develops a generative model of the human translating mind, grounded in empirical translation process data.<n>The article relates this embedded generative model to various theoretical frameworks, dual-process theories and Robinson's (2023) ideosomatic theory of translation.
  arXiv  Detail & Related papers  (2024-05-06T02:07:13Z)
• Translation Artifacts in Cross-lingual Transfer Learning [51.66536640084888]
  We show that machine translation can introduce subtle artifacts that have a notable impact in existing cross-lingual models. In natural language inference, translating the premise and the hypothesis independently can reduce the lexical overlap between them. We also improve the state-of-the-art in XNLI for the translate-test and zero-shot approaches by 4.3 and 2.8 points, respectively.
  arXiv  Detail & Related papers  (2020-04-09T17:54:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.