LacMaterial: Large Language Models as Analogical Chemists for Materials Discovery
This work addresses the challenge of limited human insight in materials discovery by leveraging LLMs for cross-domain analogies, offering an incremental improvement in generating novel hypotheses.
The paper tackled the problem of discovering novel battery materials by using large language models (LLMs) for analogical reasoning, resulting in the generation of candidates outside established compositional spaces that outperformed standard prompting baselines.
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.