WizardLM: Empowering large pre-trained language models to follow complex instructions — mentioned by Mathnerd314

Thu, 05 Dec 2024 18:11:13 GMT

Well, look at the process of training a chatbot: - first you make a "raw" corpus, with all the information needed to produce an answer - then you generate sample question-answer pairs - then you use AI to make better questions and better answers (look at e.g. WizardLM https://arxiv.org/pdf/2304.12244) - can also finetune with RLHF or modify the Q-A pairs directly - then you have a final model finetune once the Q-A pairs look good - then you use RAG over the corpus and the Q-A pairs because the model doesn't remember all the facts - then you have a bullshit detector to avoid hallucinations So…

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

WizardLM: Empowering large pre-trained language models to follow complex instructions — HN submission

Wed, 03 May 2023 15:51:52 GMT

WizardLM: Empowering Large Language Models to Follow Complex Instructions

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

WizardLM: Empowering large pre-trained language models to follow complex instructions · HackerPapers discussions

WizardLM: Empowering large pre-trained language models to follow complex instructions — mentioned by Mathnerd314

WizardLM: Empowering large pre-trained language models to follow complex instructions — HN submission