# Many-Shot In-Context Learning for Molecular Inverse Design

arXiv: https://arxiv.org/abs/2407.19089 · HTML: https://mlsanity.com/paper/2407.19089/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 22 references that are in the map.
- First posted on arXiv 26 Jul 2024.

## Builds on (most cited first, 8 of 8)

- [Large Language Models](https://mlsanity.com/paper/2307.05782/) (2023)
- [ChemCrow: Augmenting large-language models with chemistry tools](https://mlsanity.com/paper/2304.05376/) (2023)
- [Large-Scale Chemical Language Representations Capture Molecular Structure and Properties](https://mlsanity.com/paper/2106.09553/) (2021)
- [Many-Shot In-Context Learning](https://mlsanity.com/paper/2404.11018/) (2024)
- [In-Context Learning with Long-Context Models: An In-Depth Exploration](https://mlsanity.com/paper/2405.00200/) (2024)
- [Can Large Language Models Empower Molecular Property Prediction?](https://mlsanity.com/paper/2307.07443/) (2023)
- [Scaffold-constrained molecular generation](https://mlsanity.com/paper/2009.07778/) (2020)
- [DrugLLM: Open Large Language Model for Few-shot Molecule Generation](https://mlsanity.com/paper/2405.06690/) (2024)

## Built on by (most cited first, 6 of 6)

- [A Survey of Scaling in Large Language Model Reasoning](https://mlsanity.com/paper/2504.02181/) (2025)
- [ExLLM: Experience-Enhanced LLM Optimization for Molecular Design and Beyond](https://mlsanity.com/paper/2502.12845/) (2025)
- [Auto-Demo Prompting: Leveraging Generated Outputs as Demonstrations for Enhanced Batch Prompting](https://mlsanity.com/paper/2410.01724/) (2024)
- [Towards Compute-Optimal Many-Shot In-Context Learning](https://mlsanity.com/paper/2507.16217/) (2025)
- [AdapShot: Adaptive Many-Shot In-Context Learning with Semantic-Aware KV Cache Reuse](https://mlsanity.com/paper/2605.03644/) (2026)
- [Assay2Mol: large language model-based drug design using BioAssay context](https://mlsanity.com/paper/2507.12574/) (2025)

## Abstract (arXiv)

Large Language Models (LLMs) have demonstrated great performance in few-shot In-Context Learning (ICL) for a variety of generative and discriminative chemical design tasks. The newly expanded context windows of LLMs can further improve ICL capabilities for molecular inverse design and lead optimization. To take full advantage of these capabilities we developed a new semi-supervised learning method that overcomes the lack of experimental data available for many-shot ICL. Our approach involves iterative inclusion of LLM generated molecules with high predicted performance, along with experimental data. We further integrated our method in a multi-modal LLM which allows for the interactive modification of generated molecular structures using text instructions. As we show, the new method greatly improves upon existing ICL methods for molecular design while being accessible and easy to use for scientists.