Vector embeddings derived from large language models (LLMs) show promise in capturing latent information from the literature. Interestingly, these can be integrated into material embeddings, potentially useful for data-driven predictions of materials properties. We investigate the extent to which LLM-derived vectors capture the desired information and their potential to provide insights into material properties without additional training. Our findings indicate that, although LLMs can be used to generate representations reflecting certain property information, extracting the embeddings requires identifying the optimal contextual clues and appropriate comparators. Despite this restriction, it appears that LLMs still have the potential to be useful in generating meaningful materials-science representations.

Users expect to see that friendly search box in their applications. They seem to really like it, because it's so simple to use. You don't need a user manual to figure out search. In fact, if your application doesn't have search, you'll be pelted with negative reviews. No wonder you see search in so many applications. It's very difficult to implement. We all know it's more than just simple text matching. Those of us with database backgrounds know that searching for "prefix*" is a lot easier than searching for "*suffix". And users want to do all sorts of weird searches like "*run*", which should match ran, or shrunken or brunt, or--you get the idea. Quick search results and performance are important, as is accuracy and ranking.