News for hackers. Stuff that matters.
Re:Training and Aligning LLMs with RLHF and RLHF Alternatives by scoresmoke on Sunday September 10, 2023 @05:55PM (#37460490)
Discussions about LLM alignment often miss topics of data quality and quantity. It turns out that current models like Llama 2 use 10K+ prompts and responses for supervised fine-tuning (SFT) and 100K+ human preference pairs. While the preferences are pretty easy to annotate, producing a good SFT dataset is uneasy.

https://evalovernite.substack.com/p/rlhf-math-aint-enough

https://doi.org/10.5281/zenodo.8186168

There are no comments on this comment yet.