From text to insight: large language models for materials science data extraction
The vast majority of materials science knowledge exists in unstructured natural language,
yet structured data is crucial for innovative and systematic materials design. Traditionally, the …
yet structured data is crucial for innovative and systematic materials design. Traditionally, the …
Integrating machine learning and large language models to advance exploration of electrochemical reactions
Electrochemical C‐H oxidation reactions offer a sustainable route to functionalize
hydrocarbons, yet identifying suitable substrates and optimizing synthesis remain …
hydrocarbons, yet identifying suitable substrates and optimizing synthesis remain …
Large property models: a new generative machine-learning formulation for molecules
Generative models for the inverse design of molecules with particular properties have been
heavily hyped, but have yet to demonstrate significant gains over machine-learning …
heavily hyped, but have yet to demonstrate significant gains over machine-learning …
Suitability of large language models for extraction of high-quality chemical reaction dataset from patent literature
With the advent of artificial intelligence (AI), it is now possible to design diverse and novel
molecules from previously unexplored chemical space. However, a challenge for chemists is …
molecules from previously unexplored chemical space. However, a challenge for chemists is …
What I Learned from Analyzing Accurate Mass Data of 3000 Supporting Information Files
M Christmann - Organic Letters, 2024 - ACS Publications
A Python script for the systematic, high-throughput analysis of accurate mass data was
developed and tested on more than 3000 Supporting Information (SI) PDFs from Organic …
developed and tested on more than 3000 Supporting Information (SI) PDFs from Organic …
LLMatDesign: Autonomous Materials Discovery with Large Language Models
Discovering new materials can have significant scientific and technological implications but
remains a challenging problem today due to the enormity of the chemical space. Recent …
remains a challenging problem today due to the enormity of the chemical space. Recent …
Augmented and Programmatically Optimized LLM Prompts Reduce Chemical Hallucinations
S Reed - 2025 - chemrxiv.org
Utilizing Large Language Models (LLMs) for handling scientific information comes with risk
of the outputs not matching expectations, commonly called hallucinations. To fully utilize …
of the outputs not matching expectations, commonly called hallucinations. To fully utilize …
What I Learned from Analyzing Accurate Mass Data of 3000 SI Files
M Christmann - 2024 - chemrxiv.org
A Python script for the systematic, high-throughput analysis of accurate mass data was
developed and tested on over 3,000 Supporting Information (SI) PDFs from Organic Letters …
developed and tested on over 3,000 Supporting Information (SI) PDFs from Organic Letters …