# Rigorous Evaluation of Large Language Models for Malaria Drug Discovery: Trade-offs in Performance, Scale, and Resource Utility

arXiv: https://arxiv.org/abs/2608.20418 · HTML: https://mlsanity.com/paper/2608.20418/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 28 references that are in the map.
- First posted on arXiv 18 Aug 2026.

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

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [ChemBERTa: Large-Scale Self-Supervised Pretraining for Molecular Property Prediction](https://mlsanity.com/paper/2010.09885/) (2020)
- [Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development](https://mlsanity.com/paper/2102.09548/) (2021)
- [What can Large Language Models do in chemistry? A comprehensive benchmark on eight tasks](https://mlsanity.com/paper/2305.18365/) (2023)
- [Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Models](https://mlsanity.com/paper/2306.08018/) (2023)
- [LlaSMol: Advancing Large Language Models for Chemistry with a Large-Scale, Comprehensive, High-Quality Instruction Tuning Dataset](https://mlsanity.com/paper/2402.09391/) (2024)
- [Molecular representation learning with language models and domain-relevant auxiliary tasks](https://mlsanity.com/paper/2011.13230/) (2020)
- [InstructMol: Multi-Modal Integration for Building a Versatile and Reliable Molecular Assistant in Drug Discovery](https://mlsanity.com/paper/2311.16208/) (2023)
- [Tx-LLM: A Large Language Model for Therapeutics](https://mlsanity.com/paper/2406.06316/) (2024)
- [Benchmarking Pretrained Molecular Embedding Models For Molecular Representation Learning](https://mlsanity.com/paper/2508.06199/) (2025)
- [Lo-Hi: Practical ML Drug Discovery Benchmark](https://mlsanity.com/paper/2310.06399/) (2023)

## Abstract (arXiv)

We introduce Malaria-Instruct, a curated instruction-following dataset derived from the ChEMBL Legacy Malaria corpus for Malaria virtual screening, and conduct a systematic evaluation of five open-source LLMs; Gemma-2 2B/9B, TxGemma-2B/9B, and LlaSMol-Mistral-7B, on a rigorous out-of-distribution data split. Performance was benchmarked against classical ML models (Random Forest, XGBoost) and frontier proprietary models (Gemini 2.5, OpenAI o3) under few-shot conditions. Fine-tuned LLMs substantially outperformed all baselines: TxGemma-9B achieved the highest ROC-AUC (0.731 ± 0.005) and LlaSMol-Mistral-7B the best enrichment factor (EF@1% ≈ 4.99). Domain-specific fine-tuning proved categorically indispensable with TxGemma-9B collapsing from ROC-AUC 0.731 to 0.499, under its best few-shot condition, and neither Gemini 2.5 (ROC-AUC ≈ 0.53) nor o3 (ROC-AUC ≈ 0.59) achieved reliable discrimination without fine-tuning. Biomedical pretraining conferred a measurable advantage at equivalent scale, while chemistry-aware pretraining yielded superior prospective enrichment. Fine-tuned open-source LLMs represent a compelling, resource-efficient paradigm for antimalarial VS, outperforming both classical pipelines and proprietary reasoning models under structurally challenging conditions.