Comparison of LLMs in extracting synthesis conditions and generating Q&A datasets for metal–organic frameworks

2025/01/01 by Yuang Shi, Nakul Rampal, Chengbin Zhao +4 · 2 voices · 1 citation
Chemistry · Materials Science · #Metal-Organic Frameworks: Synthesis and Applications #Machine Learning in Materials Science #Zeolite Catalysis and Synthesis

paper · pdf · doi:10.1039/d5dd00081e

openalex publication_date 2025/01/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/05/21

Abstract

Spoiler alert: Claude and Gemini did better than GPT-4 in extracting information from chemistry literature.

Citations

• Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
• LLM-based MOFs Synthesis Condition Extraction using Few-Shot Demonstrations

Cited by

• OPENXRD: a comprehensive benchmark framework for LLM/MLLM XRD question answering

Discussions

• Today's featured article from Yaghi et al. assesses popular LLMs as tools for extracting information from the literature on reticular chemistry, in particular generating Q&A datasets and extracting s [bsky, 2 points, 0 comments]
• In my work the GPT model is fine-tuned which makes a big difference. Will the race have a different outcome if fine-tuning is added? #chemsky DOI doi.org/10.1039/D5DD... [bsky, 2 points, 0 comments]

Related

• Mining Insights on Metal-Organic Framework Synthesis from Scientific Literature Texts
• 34 Examples of LLM Applications in Materials Science and Chemistry: Towards Automation, Assistants, Agents, and Accelerated Scientific Discovery
• MSQA: Benchmarking LLMs on Graduate-Level Materials Science Reasoning and Knowledge
• LLM-based MOFs Synthesis Condition Extraction using Few-Shot Demonstrations
• Do humans and large language models agree on the quality of synthesis plans?