News for hackers. Stuff that matters.

A comment on /story/40725329. Parent comment

Re: by hobofan on Thursday June 20, 2024 @04:29AM (#40736323)
It sounds like a real use case, but possibly quite overkill to use an LLM.

Unless you need to have some "reasoning" to classify the documents correctly, a much more lightweight BERT-like model (RoBERTa or DistilBERT) will perform on par in accuracy while being a lot faster.

[ Parent | on HN ]
Re: by t-writescode on Thursday June 20, 2024 @04:48AM (#40736439)
"while being a lot faster", yes; but something that LLMs do that those other tools don't is being hilariously approachable.

LLMs can operate as a very, very *very* approachable natural language processing model without needing to know all the gritty details of NLP.

[ Parent | on HN ]