# Do "New Snow Tablets" Contain Snow? Large Language Models Over-Rely on Names to Identify Ingredients of Chinese Drugs

arXiv: https://arxiv.org/abs/2504.03786 · HTML: https://mlsanity.com/paper/2504.03786/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 12 references that are in the map.
- First posted on arXiv 3 Apr 2025.

## Builds on (most cited first, 9 of 9)

- [A Careful Examination of Large Language Model Performance on Grade School Arithmetic](https://mlsanity.com/paper/2405.00332/) (2024)
- [DoctorGLM: Fine-tuning your Chinese Doctor is not a Herculean Task](https://mlsanity.com/paper/2304.01097/) (2023)
- [CMB: A Comprehensive Medical Benchmark in Chinese](https://mlsanity.com/paper/2308.08833/) (2023)
- [ChiMed-GPT: A Chinese Medical Large Language Model with Full Training Regime and Better Alignment to Human Preferences](https://mlsanity.com/paper/2311.06025/) (2023)
- [Taiyi: A Bilingual Fine-Tuned Large Language Model for Diverse Biomedical Tasks](https://mlsanity.com/paper/2311.11608/) (2023)
- [MedFuzz: Exploring the Robustness of Large Language Models in Medical Question Answering](https://mlsanity.com/paper/2406.06573/) (2024)
- [Language Models are Surprisingly Fragile to Drug Names in Biomedical Benchmarks](https://mlsanity.com/paper/2406.12066/) (2024)
- [BianCang: A Traditional Chinese Medicine Large Language Model](https://mlsanity.com/paper/2411.11027/) (2024)
- [Difficult Task Yes but Simple Task No: Unveiling the Laziness in Multimodal LLMs](https://mlsanity.com/paper/2410.11437/) (2024)

## Built on by (most cited first, 1 of 1)

- [Gated Differentiable Working Memory for Long-Context Language Modeling](https://mlsanity.com/paper/2601.12906/) (2026)

## Abstract (arXiv)

Traditional Chinese Medicine (TCM) has seen increasing adoption in healthcare, with specialized Large Language Models (LLMs) emerging to support clinical applications. A fundamental requirement for these models is accurate identification of TCM drug ingredients. In this paper, we evaluate how general and TCM-specialized LLMs perform when identifying ingredients of Chinese drugs. Our systematic analysis reveals consistent failure patterns: models often interpret drug names literally, overuse common herbs regardless of relevance, and exhibit erratic behaviors when faced with unfamiliar formulations. LLMs also fail to understand the verification task. These findings demonstrate that current LLMs rely primarily on drug names rather than possessing systematic pharmacological knowledge. To address these limitations, we propose a Retrieval Augmented Generation (RAG) approach focused on ingredient names. Experiments across 220 TCM formulations show our method significantly improves accuracy from approximately 50% to 82% in ingredient verification tasks. Our work highlights critical weaknesses in current TCM-specific LLMs and offers a practical solution for enhancing their clinical reliability.