datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
narrativeqa-rag
NarrativeQA RAG
Dataset for Retrieval-Augmented Generation (RAG) based on NarrativeQA.
Structure
Subset
Splits
Description
corpus
train (default)
Wikipedia plot summaries shared across all query splits
queries
train, dev, test
Reading comprehension questions
qrels
train, dev, test
Relevance judgments (query ↔ document)
answers
train, dev, test
Reference answers (longest annotated answer)
Dataset statistics
Split
Queries… See the full description on the dataset page: https://huggingface.co/datasets/DinoStackAI/narrativeqa-rag.narrative-bench
Narrative Identity Effect on LLM Reasoning
Description
{'model': Value('string'), 'biography_level': Value('int64'), 'persona_type': Value('string'), 'task_type': Value('string'), 'accuracy': Value('bool'), 'prompt': Value('string'), 'completion': Value('string'), 'completion_len': Value('int64'), 'lexical_diversity': Value('float64'), 'mattr': Value('float64'), 'sentiment_valence': Value('float64'), 'sentiment_arousal': Value('float64'), 'self_reference_rate':… See the full description on the dataset page: https://huggingface.co/datasets/OusiaResearch/narrative-bench.