Paper Survey: From RLHF to DPO and GRPO: A Lineage Map of LLM Preference - #110

Paper Survey: From RLHF to DPO and GRPO: A Lineage Map of LLM Preference#110

bits-bytes-nn wants to merge 1 commit into

mainbits-bytes-nn/bits-bytes-nn.github.io:mainfrom

paper-reviews/survey-llm-rlhf-dpo-da36ac9abits-bytes-nn/bits-bytes-nn.github.io:paper-reviews/survey-llm-rlhf-dpo-da36ac9aCopy head branch name to clipboard