# Language Models Enable Data-Augmented Synthesis Planning for Inorganic Materials

arXiv: https://arxiv.org/abs/2506.12557 · HTML: https://mlsanity.com/paper/2506.12557/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 62 references that are in the map.
- First posted on arXiv 14 Jun 2025.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Language Models are Few-shot Multilingual Learners](https://mlsanity.com/paper/2109.07684/) (2021)
- [Predicting materials properties without crystal structure: Deep representation learning from stoichiometry](https://mlsanity.com/paper/1910.00617/) (2019)
- [FlowLLM: Flow Matching for Material Generation with Large Language Models as Base Distributions](https://mlsanity.com/paper/2410.23405/) (2024)
- [Inorganic Materials Synthesis Planning with Literature-Trained Neural Networks](https://mlsanity.com/paper/1901.00032/) (2018)
- [Precursor recommendation for inorganic synthesis by machine learning materials similarity from scientific literature](https://mlsanity.com/paper/2302.02303/) (2023)
- [Retrieval-Retro: Retrieval-based Inorganic Retrosynthesis with Expert Knowledge](https://mlsanity.com/paper/2410.21341/) (2024)
- [Benchmarking large language models for materials synthesis: the case of atomic layer deposition](https://mlsanity.com/paper/2412.10477/) (2024)

## Built on by (most cited first, 7 of 7)

- [A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools](https://mlsanity.com/paper/2506.20743/) (2025)
- [DiffSyn: A Generative Diffusion Approach to Materials Synthesis Planning](https://mlsanity.com/paper/2509.17094/) (2025)
- [LeMat-Synth: a multi-modal toolbox to curate broad synthesis procedure databases from scientific literature](https://mlsanity.com/paper/2510.26824/) (2025)
- [MSP-LLM: A Unified Large Language Model Framework for Complete Material Synthesis Planning](https://mlsanity.com/paper/2602.07543/) (2026)
- [Hypothesis-Driven Autonomous Materials Synthesis with Multimodal LLM Agents](https://mlsanity.com/paper/2609.18598/) (2026)
- [Coupling Language Models with Physics-based Simulation for Synthesis of Inorganic Materials](https://mlsanity.com/paper/2606.00315/) (2026)
- [CondMSP: Condition-Informed and Resource-Aware Inorganic Materials Synthesis Planning](https://mlsanity.com/paper/2610.15603/) (2026)

## Abstract (arXiv)

Inorganic synthesis planning currently relies primarily on heuristic approaches or machine-learning models trained on limited datasets, which constrains its generality. We demonstrate that language models, without task-specific fine-tuning, can recall synthesis conditions. Off-the-shelf models, such as GPT-4.1, Gemini 2.0 Flash and Llama 4 Maverick, achieve a Top-1 precursor-prediction accuracy of up to 53.8 % and a Top-5 performance of 66.1 % on a held-out set of 1,000 reactions. They also predict calcination and sintering temperatures with mean absolute errors below 126 degC, matching specialized regression methods. Ensembling these language models further enhances predictive accuracy and reduces inference cost per prediction by up to 70 %. We subsequently employ language models to generate 28,548 synthetic reaction recipes, which we combine with literature-mined examples to pretrain a transformer-based model, SyntMTE. After fine-tuning on the combined dataset, SyntMTE reduces mean-absolute error in sintering temperature prediction to 73 degC and in calcination temperature to 98 degC. This strategy improves models by up to 8.7 % compared with baselines trained exclusively on experimental data. Finally, in a case study on Li7La3Zr2O12 solid-state electrolytes, we demonstrate that SyntMTE reproduces the experimentally observed dopant-dependent sintering trends. Our hybrid workflow enables scalable, data-efficient inorganic synthesis planning.