Unified Model
Anthropic_HH_Golden
Dataset Card for Anthropic_HH_Golden
This dataset is constructed to test the ULMA technique as mentioned in the paper Unified Language Model Alignment with Demonstration and Point-wise Human Preference (under review, and an arxiv link will be provided soon). They show that replacing the positive samples in a preference dataset by high-quality demonstration data (golden data) greatly improves the performance of various alignment methods (RLHF, DPO, ULMA). In particular, the ULMA… See the full description on the dataset page: https://huggingface.co/datasets/Unified-Language-Model-Alignment/Anthropic_HH_Golden.new-bridge-model-12-layer-unified-train-v2-60000unified_model_datanew-bridge-model-12-layer-unified-train-v1new-bridge-model-12-layer-unified-train-v1-gigaspeechunified-model