LLMs fine-tuned for malaria drug discovery outperform proprietary models

A new study introduces Malaria-Instruct, a dataset designed for malaria drug discovery using large language models (LLMs). The research evaluated several open-source LLMs, finding that fine-tuned models significantly outperformed classical machine learning methods and even proprietary models like Gemini 2.5 and OpenAI o3 when not fine-tuned. Domain-specific fine-tuning was crucial for performance, with models like TxGemma-9B and LlaSMol-Mistral-7B showing the best results in virtual screening for antimalarial compounds. AI

IMPACT Fine-tuned open-source LLMs offer a resource-efficient alternative for specialized scientific discovery tasks, potentially accelerating drug development.

RANK_REASON The cluster contains an academic paper detailing a new dataset and rigorous evaluation of LLMs for a specific scientific task. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• ChEMBL Legacy Malaria corpus
• Gemini 2 5
• Gemma-2 2B
• LlaSMol-Mistral-7B
• Malaria-Instruct
• OpenAI o3
• random forest
• TxGemma-2B
• TxGemma-9B
• XGBoost

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →