Bridging the Plausibility-Validity Gap by Fine-Tuning a Reasoning-Enhanced LLM for Chemical Synthesis and Discovery
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915709303390208 |
|---|---|
| author | Malikussaid Nuha, Hilal Hudan Kurniawan, Isman |
| author_facet | Malikussaid Nuha, Hilal Hudan Kurniawan, Isman |
| contents | Large Language Models frequently generate outputs that appear scientifically reasonable yet violate fundamental principles--a phenomenon we characterize as the "plausibility-validity gap." This challenge proves especially acute in chemistry, where superficial correctness masks deeper errors in molecular structure, reaction mechanisms, and synthetic pathways. We present a systematic approach combining a reasoning-centric model architecture (Magistral Small) with Low-Rank Adaptation fine-tuning on a dual-domain dataset covering molecular properties and chemical transformations. Evaluation reveals substantial improvements: the fine-tuned system achieves 96.3% format adherence, 97.4% chemical validity, and 74.4% synthesis feasibility. Comparative analysis shows our approach outperforms specialized translation models like MolT5 (97.4% vs 77.2% validity) while achieving performance comparable to complex tool-augmented systems like ChemCrow (9.0/10 vs 9.24/10 expert rating) through a more transparent, efficient methodology. Results demonstrate a learning hierarchy where syntactic correctness develops before chemical understanding, which precedes synthetic planning capability. This work establishes a reproducible framework for transforming generalist language models into dependable scientific tools while identifying critical areas including stereochemical precision, knowledge currency, and computational accessibility as key challenges for future advancement. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_07328 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Bridging the Plausibility-Validity Gap by Fine-Tuning a Reasoning-Enhanced LLM for Chemical Synthesis and Discovery Malikussaid Nuha, Hilal Hudan Kurniawan, Isman Machine Learning Artificial Intelligence Computational Engineering, Finance, and Science Chemical Physics 68T07 (Primary) 92E10, 68T50, 68T30 (Secondary) I.2.7; J.2; I.2.6; I.2.1 Large Language Models frequently generate outputs that appear scientifically reasonable yet violate fundamental principles--a phenomenon we characterize as the "plausibility-validity gap." This challenge proves especially acute in chemistry, where superficial correctness masks deeper errors in molecular structure, reaction mechanisms, and synthetic pathways. We present a systematic approach combining a reasoning-centric model architecture (Magistral Small) with Low-Rank Adaptation fine-tuning on a dual-domain dataset covering molecular properties and chemical transformations. Evaluation reveals substantial improvements: the fine-tuned system achieves 96.3% format adherence, 97.4% chemical validity, and 74.4% synthesis feasibility. Comparative analysis shows our approach outperforms specialized translation models like MolT5 (97.4% vs 77.2% validity) while achieving performance comparable to complex tool-augmented systems like ChemCrow (9.0/10 vs 9.24/10 expert rating) through a more transparent, efficient methodology. Results demonstrate a learning hierarchy where syntactic correctness develops before chemical understanding, which precedes synthetic planning capability. This work establishes a reproducible framework for transforming generalist language models into dependable scientific tools while identifying critical areas including stereochemical precision, knowledge currency, and computational accessibility as key challenges for future advancement. |
| title | Bridging the Plausibility-Validity Gap by Fine-Tuning a Reasoning-Enhanced LLM for Chemical Synthesis and Discovery |
| topic | Machine Learning Artificial Intelligence Computational Engineering, Finance, and Science Chemical Physics 68T07 (Primary) 92E10, 68T50, 68T30 (Secondary) I.2.7; J.2; I.2.6; I.2.1 |
| url | https://arxiv.org/abs/2507.07328 |