LacMaterial: Large Language Models as Analogical Chemists for Materials Discovery

TL;DR

This paper demonstrates that large language models can serve as analogical chemists, generating novel materials by leveraging cross-domain and in-domain analogies, thus advancing materials discovery beyond traditional methods.

Contribution

The study introduces novel methods for using LLMs to perform analogy-driven reasoning in materials science, enabling the generation of innovative battery materials beyond conventional approaches.

Findings

LLMs can retrieve cross-domain analogs to guide materials exploration.

LLMs outperform standard prompting in generating novel candidate materials.

Analogical reasoning with LLMs leads to candidates outside traditional compositional spaces.

Abstract

Analogical reasoning, the transfer of relational structures across contexts (e.g., planet is to sun as electron is to nucleus), is fundamental to scientific discovery. Yet human insight is often constrained by domain expertise and surface-level biases, limiting access to deeper, structure-driven analogies both within and across disciplines. Large language models (LLMs), trained on vast cross-domain data, present a promising yet underexplored tool for analogical reasoning in science. Here, we demonstrate that LLMs can generate novel battery materials by (1) retrieving cross-domain analogs and analogy-guided exemplars to steer exploration beyond conventional dopant substitutions, and (2) constructing in-domain analogical templates from few labeled examples to guide targeted exploitation. These explicit analogical reasoning strategies yield candidates outside established compositional spaces and outperform standard prompting baselines. Our findings position LLMs as interpretable, expert-like hypothesis generators that leverage analogy-driven generalization for scientific innovation.