-
Anthropic Helpfulness Base eval
The dataset used in the paper is the Anthropic Helpfulness Base eval dataset. -
Anthropic Helpfulness Base
The dataset used in the paper is the Anthropic Helpfulness Base train dataset and the Anthropic Helpfulness eval dataset. -
SHP dataset
The SHP dataset is used to evaluate the performance of the proposed Compositional Preference Models (CPMs). -
HH-RLHF dataset
The HH-RLHF dataset is used to evaluate the performance of the proposed Compositional Preference Models (CPMs).
