Zenodo_Repository for "A Variety-Aware Retrieval-Augmented Generation Framework for Terminology Support in Chinese Medical Interpreting"
Abstract
VACMI-LLM A Variety-Aware, Retrieval-Augmented Framework for Terminology Support in Chinese Medical Interpreting VACMI-LLM is a research framework for terminology support across Mainland China, Hong Kong, and Taiwan. It combines semantic extraction, variety-aware glossary retrieval, and constrained generation to present region-specific medical terms while keeping glossary-supported results distinct from provisional model-generated suggestions. How it works 1. Semantic extraction identifies and normalizes medical expressions.2. Variety-aware retrieval searches VACMI-KB for region-labelled terminology.3. Constrained generation presents supported terms and clearly labelled provisional suggestions. Repository layout - src contains the pipeline implementation and command-line interface. - data contains the frozen knowledge base and searchable index terms. - reproducibility contains the released study inputs, retained outputs, record-level scoring and adjudication tables, results, environment information, and offline verifier. - Questionnaire.md contains the original professional-evaluation instrument; private response exports and personally identifying information are not released. Run VACMI-LLM Python 3.13 is recommended. Install the required packages from the repository root: python -m pip install -r requirements.txt Set `DEEPSEEK_API_KEY` and `SILICONFLOW_API_KEY` in your local environment, then run: python src/00_run_vacmi_cli.py The runtime writes generated indexes and…
Read the paper
Related studies
- Knowledge Management Perspective of Generative Artificial Intelligence
- Navigating Generative Artificial Intelligence Promises and Perils for Knowledge and Creative Work
- Characterizing the evolving research on enterprise content management
- Large language models and multimodal foundation models for precision oncology
- From Generative AI to Extended Reality: Multidisciplinary Perspectives on the Challenges, Opportunities, and Future of Educational Computing
- Generative Artificial Intelligence: A New Engine for Advancing Environmental Science and Engineering
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.