# LeMat-Synth: a multi-modal toolbox to curate broad synthesis procedure databases from scientific literature

arXiv: https://arxiv.org/abs/2510.26824 · HTML: https://mlsanity.com/paper/2510.26824/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 64 references that are in the map.
- First posted on arXiv 28 Oct 2025.

## Builds on (most cited first, 9 of 9)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP](https://mlsanity.com/paper/2212.14024/) (2022)
- [Reconstructing Materials Tetrahedron: Challenges in Materials Information Extraction](https://mlsanity.com/paper/2310.08383/) (2023)
- [Automated, LLM enabled extraction of synthesis details for reticular materials from scientific literature](https://mlsanity.com/paper/2411.03484/) (2024)
- [Leveraging Vision Capabilities of Multimodal LLMs for Automated Data Extraction from Plots](https://mlsanity.com/paper/2503.12326/) (2025)
- [Language Models Enable Data-Augmented Synthesis Planning for Inorganic Materials](https://mlsanity.com/paper/2506.12557/) (2025)
- [Text-to-Battery Recipe: A language modeling-based protocol for automatic battery recipe extraction and retrieval](https://mlsanity.com/paper/2407.15459/) (2024)
- [Towards Fully-Automated Materials Discovery via Large-Scale Synthesis Dataset and Expert-Level LLM-as-a-Judge](https://mlsanity.com/paper/2502.16457/) (2025)

## Built on by (most cited first, 2 of 2)

- [Beyond Manual Curation: Augmenting Targeted Protein Degradation Databases via Agentic Literature Extraction Workflows](https://mlsanity.com/paper/2605.11221/) (2026)
- [Generative and multimodal AI for materials prediction and design: Progress, challenges, and perspectives](https://mlsanity.com/paper/2607.21660/) (2026)

## Abstract (arXiv)

Wide access to advanced experimental methods in materials science has given rise to an abundance of procedural knowledge, which is scattered across decades of scientific literature and recorded in unstructured formats that are challenging to analyze systematically. In this work, we present LeMat-Synth Parser, a modular, open-source, and multi-modal extraction toolbox that utilizes large language models (LLMs) and vision language models (VLMs) to automatically structure synthesis protocols and performance metrics extracted from both text and figures of publications. Applying LeMat-Synth Parser to 81K open-access publications, we curate LeMat-Synth, an extensive dataset of 58K synthesis procedures and to our knowledge the largest and most diverse structured inorganic materials synthesis dataset to date, covering 35 synthesis methods and 16 material classes based on a domain-specific ontology. We validate extraction quality against annotations by domain experts and a scalable LLM-as-a-judge framework, and benchmark a suite of models to identify optimal configurations and characterize cross-model biases. To demonstrate the extensibility of LeMat-Synth Parser, we apply it to two distinct domains. First, we link synthesis protocols and catalyst identity to thermocatalytic performance across a corpus of ammonia-decomposition publications. Second, we cross-validate text- and figure-reported critical transition temperatures across 1,384 superconductivity papers, then use the validated pipeline to recover the critical transition temperature for every composition in a sample series. We release LeMat-Synth Parser and the LeMat-Synth dataset openly on GitHub and Hugging Face