n_girard@alien.topBtoLocalLLaMA@poweruser.forum•Are there any data cleaning focused LLMs? [also, rant]English
1·
1 year agoWhat I wanted to experiment but haven’t yet, is to provide the models with markdown text whose both sections and paragraphs are numbered ; and instruct them to list the section numbers and/or paragraph numbers related to some topic.
The next step would be to extract the relevant passages using the list(s).
Has anyone ever tried this approach ? Any thoughts ?
Hopefully I’m not being offtopic here, but a recent paper suggested that repeating a requirement several times within the same instructions lead the model to be more compliant towards it.
Do you know whether it’s true or grounded ?
Thanks in advance.