AttributionBench's four source datasets

Emerging

1papers using it

2026first seen

AttributionBench's four source datasets contain human-labeled data used to evaluate the effectiveness of automatic metrics for attributing generated answers in retrieval-augmented generation tasks.

🔎 Find this dataset

Papers using AttributionBench's four source datasets (1)

Do LLM Attribution Metrics Transfer? Auditing Retrieval-Augmented Generation Evaluation Across Datasets and Constructs2026