Appendices for Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks A Implementation Details For Open-domain QA we report test numbers using 15 retrieved documents for RAG-Token models

For Open-domain QA we report test numbers using 15 retrieved documents for RAG-Token models. Thorough Decoding approach since answers are generally short. Decoding approach for RAG-Sequence models, as Thorough Decoding did not improve performance. Figure 4 shows the user interface for human evaluation. Annotators were encouraged to research the topic using the internet, and were given detailed instructions and worked examples in a full instructions tab.