Integrating Chemistry Knowledge in Large Language Models via Prompt Engineering
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..
| Medienart: |
|
|---|
Preprint| Erscheinungsjahr: |
2024 |
|---|---|
| Erschienen: |
2024 |
| Enthalten in: |
arXiv.org - (2024) vom: 22. Apr. Zur Gesamtaufnahme - year:2024 |
|---|
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Liu, Hongxuan [VerfasserIn] |
|---|
| Links: |
Volltext [kostenfrei] |
|---|
| Themen: |
000 |
|---|
| Förderinstitution / Projekttitel: |
|
|---|
| PPN (Katalog-ID): |
XAR04336814X |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | XAR04336814X | ||
| 003 | DE-627 | ||
| 005 | 20240424080411.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 240424s2024 xx |||||o 00| ||eng c | ||
| 035 | |a (DE-627)XAR04336814X | ||
| 035 | |a (arXiv)2404.14467 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Liu, Hongxuan |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Integrating Chemistry Knowledge in Large Language Models via Prompt Engineering |
| 264 | 1 | |c 2024 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 520 | |a 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. | ||
| 650 | 4 | |a Computer Science - Computation and Language |7 (dpeaa)DE-84 | |
| 650 | 4 | |a Computer Science - Artificial Intelligence |7 (dpeaa)DE-84 | |
| 650 | 4 | |a 000 |7 (dpeaa)DE-84 | |
| 700 | 1 | |a Yin, Haoyu |e verfasserin |4 aut | |
| 700 | 1 | |a Luo, Zhiyao |e verfasserin |4 aut | |
| 700 | 1 | |a Wang, Xiaonan |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t arXiv.org |g (2024) vom: 22. Apr. |
| 773 | 1 | 8 | |g year:2024 |g day:22 |g month:04 |
| 856 | 4 | 0 | |u https://arxiv.org/abs/2404.14467 |x 0 |z kostenfrei |3 Volltext |
| 912 | |a GBV_XAR | ||
| 951 | |a AR | ||
| 952 | |j 2024 |b 22 |c 04 | ||