# Integrating Chemistry Knowledge in Large Language Models via Prompt Engineering

arXiv: https://arxiv.org/abs/2404.14467 · HTML: https://mlsanity.com/paper/2404.14467/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 67 references that are in the map.
- First posted on arXiv 22 Apr 2024.

## Builds on (most cited first, 15 of 15)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT](https://mlsanity.com/paper/2302.11382/) (2023)
- [MathPrompter: Mathematical Reasoning using Large Language Models](https://mlsanity.com/paper/2303.05398/) (2023)
- [Large-Scale Chemical Language Representations Capture Molecular Structure and Properties](https://mlsanity.com/paper/2106.09553/) (2021)
- [Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future](https://mlsanity.com/paper/2309.15402/) (2023)
- [Few-shot training LLMs for project-specific code-summarization](https://mlsanity.com/paper/2207.04237/) (2022)
- [Inverse design of 3d molecular structures with conditional generative neural networks](https://mlsanity.com/paper/2109.04824/) (2021)
- [Unifying machine learning and quantum chemistry -- a deep neural network for molecular wavefunctions](https://mlsanity.com/paper/1906.10033/) (2019)
- [MathChat: Converse to Tackle Challenging Math Problems with LLM Agents](https://mlsanity.com/paper/2306.01337/) (2023)
- [Large Language Models as Master Key: Unlocking the Secrets of Materials Science with GPT](https://mlsanity.com/paper/2304.02213/) (2023)
- [Exploring the MIT Mathematics and EECS Curriculum Using Large Language Models](https://mlsanity.com/paper/2306.08997/) (2023)

## Built on by (most cited first, 10 of 10)

- [Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning](https://mlsanity.com/paper/2502.02871/) (2025)
- [Large Language-Geometry Model: When LLM meets Equivariance](https://mlsanity.com/paper/2502.11149/) (2025)
- [Training-Free Active Learning Framework in Materials Science with Large Language Models](https://mlsanity.com/paper/2511.19730/) (2025)
- [Reshaping MOFs text mining with a dynamic multi-agents framework of large language model](https://mlsanity.com/paper/2504.18880/) (2025)
- [A Survey of Large Language Models in Discipline-specific Research: Challenges, Methods and Opportunities](https://mlsanity.com/paper/2507.08425/) (2025)
- [Large Language Models Are Self-Taught Reasoners: Enhancing LLM Applications via Tailored Problem-Solving Demonstrations](https://mlsanity.com/paper/2408.12315/) (2024)
- [CIEGAD: Cluster-Conditioned Interpolative and Extrapolative Framework for Geometry-Aware and Domain-Aligned Data Augmentation](https://mlsanity.com/paper/2512.10178/) (2025)
- [Fine-tuning DeepSeek-OCR-2 for Molecular Structure Recognition](https://mlsanity.com/paper/2604.03476/) (2026)
- [Extending the Hegselmann-Krause Model of Opinion Dynamics to include AI Oracles](https://mlsanity.com/paper/2502.19701/) (2025)
- [Can AI Master Econometrics? Evidence from Econometrics AI Agent on Expert-Level Tasks](https://mlsanity.com/paper/2506.00856/) (2025)

## Abstract (arXiv)

This paper presents a study on the integration of domain-specific knowledge in prompt engineering to enhance the performance of large language models (LLMs) in scientific domains. A benchmark dataset is curated to encapsulate the intricate physical-chemical properties of small molecules, their drugability for pharmacology, alongside the functional attributes of enzymes and crystal materials, underscoring the relevance and applicability across biological and chemical domains.The proposed domain-knowledge embedded prompt engineering method outperforms traditional prompt engineering strategies on various metrics, including capability, accuracy, F1 score, and hallucination drop. The effectiveness of the method is demonstrated through case studies on complex materials including the MacMillan catalyst, paclitaxel, and lithium cobalt oxide. The results suggest that domain-knowledge prompts can guide LLMs to generate more accurate and relevant responses, highlighting the potential of LLMs as powerful tools for scientific discovery and innovation when equipped with domain-specific prompts. The study also discusses limitations and future directions for domain-specific prompt engineering development.