21 LLMs tuned for special domains

Large language models are shifting from general word-based capability toward deeper domain knowledge through specialization. Teams are building smaller, focused models for specific professions such as medicine, law, and finance rather than relying on one all-purpose model. Specialization improves efficiency because smaller models cost less to run, and some systems combine multiple small models using mixture-of-experts methods. Training can also be cheaper once reliable domain corpora exist, avoiding unnecessary training on irrelevant material. Building trustworthy training data is challenging, so teams hire experts to create ontologies and verify answers with human review and references. Users expect fewer hallucinations for high-stakes decisions in medical and legal contexts.

"Instead of developing a one-size-fits-all leviathan, the best teams are building specialized models for niches-one for the doctors, one for the lawyers, one for the bankers, and so on. The trend won't end. Soon, orthopedic surgeons who do shoulder replacements may have one model for right-handed patients and another model for the left-handed ones."

"The trend toward specialization is driven as much by efficiency as quality. Focused models are smaller, and smaller models cost less to run. Indeed, some of the most prominent large models are really collections of small models that are unified by "mixture of experts" algorithms."

"There's no reason to burn a supertanker filled with oil just to teach a legal LLM the details of 17th century French poetry or the mating habits of river otters. As the kids say, "Skip to the good parts.""

"Many of the teams are hiring their own experts to build out ontologies and double-check the answers. They're relying on humans to make sure the facts are solid and backed by trustworthy references. When LLMs were new, users would forgive a few hallucinations. That won't fly with users who have serious questions like legal or medical decisions."

Read at InfoWorld