MolReasoner: Toward Effective and Interpretable Reasoning for Molecular LLMs
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911460545789952 |
|---|---|
| author | Zhao, Guojiang Lu, Zixiang Ge, Yutang Li, Sihang Cheng, Zheng Lin, Haitao Wu, Lirong Xia, Hanchen Cai, Hengxing Guo, Wentao Wang, Hongshuai Xu, Mingjun Zhu, Siyu Ke, Guolin Zhang, Linfeng Gao, Zhifeng |
| author_facet | Zhao, Guojiang Lu, Zixiang Ge, Yutang Li, Sihang Cheng, Zheng Lin, Haitao Wu, Lirong Xia, Hanchen Cai, Hengxing Guo, Wentao Wang, Hongshuai Xu, Mingjun Zhu, Siyu Ke, Guolin Zhang, Linfeng Gao, Zhifeng |
| contents | Large Language Models (LLMs) have shown impressive performance across various domains, but their ability to perform molecular reasoning remains underexplored. Existing methods mostly rely on general-purpose prompting, which lacks domain-specific molecular semantics, or fine-tuning, which faces challenges in interpretability and reasoning depth, often leading to structural and textual hallucinations. To address these issues, we introduce MolReasoner, a two-stage framework that transitions LLMs from memorization to high-fidelity chemical reasoning. In the Mol-SFT stage, knowledge-enhanced Chain-of-Thought (CoT) data provides a strong foundation, while the Mol-RL stage refines reasoning using a novel, task-adaptive reward system to mitigate hallucinations. Extensive evaluations demonstrate that MolReasoner significantly outperforms a wide range of strong baselines in both molecule generation and captioning tasks. Further analyses highlight the framework's synergistic design and its ability to produce more interpretable outputs. Our work presents a principled and effective new approach for advancing high-fidelity molecular reasoning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_02066 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MolReasoner: Toward Effective and Interpretable Reasoning for Molecular LLMs Zhao, Guojiang Lu, Zixiang Ge, Yutang Li, Sihang Cheng, Zheng Lin, Haitao Wu, Lirong Xia, Hanchen Cai, Hengxing Guo, Wentao Wang, Hongshuai Xu, Mingjun Zhu, Siyu Ke, Guolin Zhang, Linfeng Gao, Zhifeng Machine Learning Artificial Intelligence Computation and Language Large Language Models (LLMs) have shown impressive performance across various domains, but their ability to perform molecular reasoning remains underexplored. Existing methods mostly rely on general-purpose prompting, which lacks domain-specific molecular semantics, or fine-tuning, which faces challenges in interpretability and reasoning depth, often leading to structural and textual hallucinations. To address these issues, we introduce MolReasoner, a two-stage framework that transitions LLMs from memorization to high-fidelity chemical reasoning. In the Mol-SFT stage, knowledge-enhanced Chain-of-Thought (CoT) data provides a strong foundation, while the Mol-RL stage refines reasoning using a novel, task-adaptive reward system to mitigate hallucinations. Extensive evaluations demonstrate that MolReasoner significantly outperforms a wide range of strong baselines in both molecule generation and captioning tasks. Further analyses highlight the framework's synergistic design and its ability to produce more interpretable outputs. Our work presents a principled and effective new approach for advancing high-fidelity molecular reasoning. |
| title | MolReasoner: Toward Effective and Interpretable Reasoning for Molecular LLMs |
| topic | Machine Learning Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2508.02066 |