# MolE-RAG: Molecular Structure-Enhanced Retrieval-Augmented Generation for Chemistry

arXiv: https://arxiv.org/abs/2606.05693 · HTML: https://mlsanity.com/paper/2606.05693/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical and biomedical RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 10 of its 37 references that are in the map.
- First posted on arXiv 4 Jun 2026.

## Placed in

- Retrieval-augmented generation / [Medical and biomedical RAG](https://mlsanity.com/rag/medical-and-biomedical-rag/)

## Builds on (most cited first, 10 of 10)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [MoleculeNet: A Benchmark for Molecular Machine Learning](https://mlsanity.com/paper/1703.00564/) (2017)
- [SchNet: A continuous-filter convolutional neural network for modeling quantum interactions](https://mlsanity.com/paper/1706.08566/) (2017)
- [SPECTER: Document-level Representation Learning using Citation-informed Transformers](https://mlsanity.com/paper/2004.07180/) (2020)
- [What can Large Language Models do in chemistry? A comprehensive benchmark on eight tasks](https://mlsanity.com/paper/2305.18365/) (2023)
- [A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discovery](https://mlsanity.com/paper/2406.10833/) (2024)
- [Molecular Property Prediction: A Multilevel Quantum Interactions Modeling Perspective](https://mlsanity.com/paper/1906.11081/) (2019)
- [Benchmarking Retrieval-Augmented Generation for Chemistry](https://mlsanity.com/paper/2505.07671/) (2025)
- [Bi-level Contrastive Learning for Knowledge-Enhanced Molecule Representations](https://mlsanity.com/paper/2306.01631/) (2023)

## Abstract (arXiv)

Large language models (LLMs) have shown promise for molecular property prediction, but their ability to reason over chemical structures remains limited, as molecular representations such as SMILES differ substantially from the natural language on which LLMs are primarily trained. To bridge this semantic and chemical knowledge gap, we propose MolE-RAG, a training-free, molecule-centric retrieval-augmented generation framework for LLM-based molecular property prediction. MolE-RAG augments each prediction with three complementary sources of inference-time context: retrieved chemistry literature, molecule-specific information including compound synonyms, identifiers, functional group annotations, and physicochemical descriptors, and structurally similar molecules retrieved from the training set. We evaluate MolE-RAG across nine molecular property prediction tasks using proprietary, chemistry-specialized, and open-source LLMs. Across general-purpose LLMs, MolE-RAG improves ROC-AUC by up to 28 percentage points on classification tasks and reduces regression RMSE by up to 67% relative to a SMILES-only baseline. We further find that the utility of each context source varies across models and tasks, with different models benefiting most from textual retrieval, molecular context, or structural retrieval. These results suggest that molecule-centric retrieval can improve LLM-based molecular property prediction without model fine-tuning while providing a flexible framework for integrating heterogeneous chemical knowledge at inference time.