There are some algorithms, like local sensitivity hashes, that use probabilistic or other means to compute field values. In addition, there are some non-LLM models and algorithms for categorization (although these tend to be less useful except for categorizing to very common values like common news topics).
Chimera includes a local sensitivity hash probabilistic algorithm (and index) to find near text duplicates. We have also evaluated a variety of other algorithms and models that have not proven effective enough to include in the product.