Boosting LLM's Molecular Structure Elucidation with Knowledge Enhanced Tree Search Reasoning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918074935934976 |
|---|---|
| author | Zhuang, Xiang Wu, Bin Cui, Jiyu Feng, Kehua Li, Xiaotong Xing, Huabin Ding, Keyan Zhang, Qiang Chen, Huajun |
| author_facet | Zhuang, Xiang Wu, Bin Cui, Jiyu Feng, Kehua Li, Xiaotong Xing, Huabin Ding, Keyan Zhang, Qiang Chen, Huajun |
| contents | Molecular structure elucidation involves deducing a molecule's structure from various types of spectral data, which is crucial in chemical experimental analysis. While large language models (LLMs) have shown remarkable proficiency in analyzing and reasoning through complex tasks, they still encounter substantial challenges in molecular structure elucidation. We identify that these challenges largely stem from LLMs' limited grasp of specialized chemical knowledge. In this work, we introduce a Knowledge-enhanced reasoning framework for Molecular Structure Elucidation (K-MSE), leveraging Monte Carlo Tree Search for test-time scaling as a plugin. Specifically, we construct an external molecular substructure knowledge base to extend the LLMs' coverage of the chemical structure space. Furthermore, we design a specialized molecule-spectrum scorer to act as a reward model for the reasoning process, addressing the issue of inaccurate solution evaluation in LLMs. Experimental results show that our approach significantly boosts performance, particularly gaining more than 20% improvement on both GPT-4o-mini and GPT-4o. Our code is available at https://github.com/HICAI-ZJU/K-MSE. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_23056 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Boosting LLM's Molecular Structure Elucidation with Knowledge Enhanced Tree Search Reasoning Zhuang, Xiang Wu, Bin Cui, Jiyu Feng, Kehua Li, Xiaotong Xing, Huabin Ding, Keyan Zhang, Qiang Chen, Huajun Computation and Language Molecular structure elucidation involves deducing a molecule's structure from various types of spectral data, which is crucial in chemical experimental analysis. While large language models (LLMs) have shown remarkable proficiency in analyzing and reasoning through complex tasks, they still encounter substantial challenges in molecular structure elucidation. We identify that these challenges largely stem from LLMs' limited grasp of specialized chemical knowledge. In this work, we introduce a Knowledge-enhanced reasoning framework for Molecular Structure Elucidation (K-MSE), leveraging Monte Carlo Tree Search for test-time scaling as a plugin. Specifically, we construct an external molecular substructure knowledge base to extend the LLMs' coverage of the chemical structure space. Furthermore, we design a specialized molecule-spectrum scorer to act as a reward model for the reasoning process, addressing the issue of inaccurate solution evaluation in LLMs. Experimental results show that our approach significantly boosts performance, particularly gaining more than 20% improvement on both GPT-4o-mini and GPT-4o. Our code is available at https://github.com/HICAI-ZJU/K-MSE. |
| title | Boosting LLM's Molecular Structure Elucidation with Knowledge Enhanced Tree Search Reasoning |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2506.23056 |