# Bolek: A Multimodal Language Model for Molecular Reasoning

arXiv: https://arxiv.org/abs/2605.02745 · HTML: https://mlsanity.com/paper/2605.02745/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 22 of its 72 references that are in the map.
- First posted on arXiv 4 May 2026.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)

## Builds on (most cited first, 22 of 22)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Galactica: A Large Language Model for Science](https://mlsanity.com/paper/2211.09085/) (2022)
- [A Molecular Multimodal Foundation Model Associating Molecule Graphs with Natural Language](https://mlsanity.com/paper/2209.05481/) (2022)
- [LlaSMol: Advancing Large Language Models for Chemistry with a Large-Scale, Comprehensive, High-Quality Instruction Tuning Dataset](https://mlsanity.com/paper/2402.09391/) (2024)
- [ChemBERTa-2: Towards Chemical Foundation Models](https://mlsanity.com/paper/2209.01712/) (2022)
- [ChemLLM: A Chemical Large Language Model](https://mlsanity.com/paper/2402.06852/) (2024)
- [BioMedGPT: Open Multimodal Generative Pre-trained Transformer for BioMedicine](https://mlsanity.com/paper/2308.09442/) (2023)
- [InstructMol: Multi-Modal Integration for Building a Versatile and Reliable Molecular Assistant in Drug Discovery](https://mlsanity.com/paper/2311.16208/) (2023)
- [Developing ChemDFM as a large language foundation model for chemistry](https://mlsanity.com/paper/2401.14818/) (2024)
- [Beyond Chemical QA: Evaluating LLM's Chemical Reasoning with Modular Chemical Operations](https://mlsanity.com/paper/2505.21318/) (2025)
- [TxGemma: Efficient and Agentic LLMs for Therapeutics](https://mlsanity.com/paper/2504.06196/) (2025)
- [Tx-LLM: A Large Language Model for Therapeutics](https://mlsanity.com/paper/2406.06316/) (2024)
- [LLaMo: Large Language Model-based Molecular Graph Assistant](https://mlsanity.com/paper/2411.00871/) (2024)
- [A quantitative analysis of knowledge-learning preferences in large language models in molecular science](https://mlsanity.com/paper/2402.04119/) (2024)
- [ChemToolAgent: The Impact of Tools on Language Agents for Chemistry Problem Solving](https://mlsanity.com/paper/2411.07228/) (2024)
- [Advancing Molecular Graph-Text Pre-training via Fine-grained Alignment](https://mlsanity.com/paper/2409.14106/) (2024)
- [KnowMol: Advancing Molecular Large Language Models with Multi-Level Chemical Knowledge](https://mlsanity.com/paper/2510.19484/) (2025)
- [MolX: Enhancing Large Language Models for Molecular Understanding With A Multi-Modal Extension](https://mlsanity.com/paper/2406.06777/) (2024)
- [MolPILE -- large-scale, diverse dataset for molecular representation learning](https://mlsanity.com/paper/2509.18353/) (2025)

## Abstract (arXiv)

Molecular property models increasingly support high-stakes drug-discovery decisions, but their outputs are often difficult to audit: classical predictors return scores without rationale, while language models can produce fluent explanations weakly grounded in the input molecule. We introduce Bolek, a compact multimodal language model that grounds natural-language reasoning in molecular structure by injecting a Morgan fingerprint embedding into an instruction-tuned text decoder. Bolek is fine-tuned on molecular alignment tasks, including molecule description, RDKit descriptor prediction, and substructure detection, and on downstream reasoning over 15 TDC binary classification tasks using synthetic chains-of-thought anchored in concrete molecular features. Across these tasks, Bolek outperforms its Qwen3-4B-Instruct base on all endpoints in yes/no mode and on 13 of 15 in chain-of-thought mode, raising mean ROC/PR AUC from 0.55 to 0.76. It also outperforms TxGemma-9B-Chat on 13 of 15 binary classification tasks despite being less than half its size. Bolek's explanations are more grounded than those of the baseline LLMs: it cites numerical descriptors 10-100x more often per chain-of-thought, and the cited values agree strongly with RDKit for key descriptors such as TPSA, MolLogP, and MolWt (Spearman rho = 0.87-0.91). Generalisation extends beyond the training panel: on 15 unseen TDC classification endpoints, Bolek matches TxGemma on five, and it produces non-trivial rank correlations on three held-out regression endpoints despite never seeing downstream regression during training. These results suggest that targeted modality injection and reasoning supervision tied to verifiable molecular features can yield compact, auditable molecular reasoning models.