Fine-tuning with negative samples, possible?

shure.alpha · August 22, 2024, 1:52pm

What do you think? @realreasonwang

shure.alpha · September 11, 2024, 9:53am

Topic		Replies	Views
Fine-Tuning to Avoid Scary Responses (Negative Reward) API api	9	1999	August 25, 2023
Fine tuning using negative examples? API fine-tuning	5	4736	December 24, 2023
RLHF after Fine-Tuning Davinci? API	7	2149	February 21, 2024
Building chatbot that needs to respond to user messages that are censored API	8	347	December 28, 2025
Prompt Assistance , Potentially Fine Tuning oddity Prompting	6	1294	February 7, 2023