CLAPNQ: Cohesive Long-form Answers from Passages in Natural Questions for RAG systems
This work addresses the need for standardized benchmarking in RAG systems for researchers and developers, though it is incremental as it builds upon existing datasets and methods.
The authors introduced ClapNQ, a benchmark dataset for evaluating Retrieval Augmented Generation (RAG) systems in long-form question answering, featuring concise and cohesive answers grounded in passages from Natural Questions, with baseline experiments showing significant room for improvement in grounded RAG performance.
Retrieval Augmented Generation (RAG) has become a popular application for large language models. It is preferable that successful RAG systems provide accurate answers that are supported by being grounded in a passage without any hallucinations. While considerable work is required for building a full RAG pipeline, being able to benchmark performance is also necessary. We present ClapNQ, a benchmark Long-form Question Answering dataset for the full RAG pipeline. ClapNQ includes long answers with grounded gold passages from Natural Questions (NQ) and a corpus to perform either retrieval, generation, or the full RAG pipeline. The ClapNQ answers are concise, 3x smaller than the full passage, and cohesive, meaning that the answer is composed fluently, often by integrating multiple pieces of the passage that are not contiguous. RAG models must adapt to these properties to be successful at ClapNQ. We present baseline experiments and analysis for ClapNQ that highlight areas where there is still significant room for improvement in grounded RAG. CLAPNQ is publicly available at https://github.com/primeqa/clapnq