An end-to-end research project on correcting the systematic over-formatting habit of RLHF-trained language models.
Krishna Dahale
krishy-d
AI & ML interests
None yet
Recent Activity
published a Space about 1 month ago
krishy-d/prosify-demo updated a dataset about 1 month ago
krishy-d/formatbench updated a collection about 1 month ago
Prosify: Correcting Formatting Bias in LLMsOrganizations
None yet