Prosify: Correcting Formatting Bias in LLMs An end-to-end research project on correcting the systematic over-formatting habit of RLHF-trained language models. krishy-d/formatbench Viewer • Updated Jun 7 • 591 • 39 krishy-d/prosify_qwen_1.5b_lora Text Generation • Updated Jun 7 • 3
Prosify: Correcting Formatting Bias in LLMs An end-to-end research project on correcting the systematic over-formatting habit of RLHF-trained language models. krishy-d/formatbench Viewer • Updated Jun 7 • 591 • 39 krishy-d/prosify_qwen_1.5b_lora Text Generation • Updated Jun 7 • 3
