Text Classification via Large Language Models — HN submission

Mon, 16 Oct 2023 19:43:34 GMT

Text Classification via Large Language Models

1 point; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.

Text Classification via Large Language Models — mentioned by PaulHoule

Thu, 12 Oct 2023 20:41:37 GMT

Depends how you define quality. This paper reflects my own experience https://arxiv.org/abs/2305.08377 and shows how LLM technology has a lot more to offer than "ChatGPT". The real takeaway is that by training LLMs with real training data (even with a "less powerful" model) you can get an error rate more than 10x less than you get with the "zero shot" model of asking ChatGPT to answer a question for you the same way that Mickey Mouse asked the broom to clean up for him in Fantasia. The "few-shot" approach of supplying a few examples in the attention window was a little better but not much.…

Paper and discussion history. A mention is not an endorsement.

Text Classification via Large Language Models · HackerPapers discussions

Text Classification via Large Language Models — HN submission

Text Classification via Large Language Models — mentioned by PaulHoule