.png){kind=icon}
.png){kind=icon}
Return
CLAPnq: Cohesive Long-form Answers from Passages in Natural Questions for RAG systems
.png){kind=icon}
OA
AI
S
A
S
DOI：10.1162/tacl_a_00729.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Retrieval Augmented Generation (RAG) hasbecome a popular application for large lan-guage models. It is preferable that successfulRAG systems provide accurate answers thatare supported by being grounded in a passagewithout any hallucinations. While consider-able work is required for building a full RAGpipeline, being able to benchmark performanceis also necessary. We present CLAPNQ,abenchmark Long-form Question Answeringdataset for the full RAG pipeline. CLAPNQincludes long answers with grounded goldpassages from Natural Questions (NQ) and acorpus to perform either retrieval, generation,or the full RAG pipeline. The CLAPNQanswersareconcise, 3x smaller than the full passage,andcohesive, meaning that the answer is com-posed fluently, often by integrating multiplepieces of the passage that are not contiguous.RAG models must adapt to these properties tobe successful at CLAPNQ. We present base-line experiments and analysis for CLAPNQthat highlight areas where there is still signifi-cant room for improvement in grounded RAG.CLAPNQis publicly available athttps://github.com/primeqa/clapnq.
Journal
T
IF:
6.9
Papers:
486
Citations:
5.7K
Organization
No organization information available
Cited Papers