Kuiz berkaitan panduan · Sederhana Tahap
Kuiz RAG Pembetulan (CRAG).
Menguji RAG Pembetulan: penilai perolehan, tindakan Betul, Salah dan Samar-samar, penghalusan pengetahuan dan pertukaran sandaran carian web.
soalan 1 daripada 8
Apakah kelemahan teras RAG standard yang ditangani oleh CRAG?
Pratonton setiap soalan8 soalan
Jawapan dan penjelasan muncul semasa anda mengambil kuiz.
- Apakah kelemahan teras RAG standard yang ditangani oleh CRAG?
- The generator trusts whatever the retriever returns
- Embeddings are too small
- Models cannot read long documents
- Vector databases are too slow
- Dalam kertas CRAG asal, apakah jenis model yang digunakan sebagai penilai perolehan semula?
- A large GPT-style generator
- A fine-tuned T5-large model
- A BM25 index
- A human reviewer
- Apakah yang CRAG lakukan apabila semua dokumen yang diambil mendapat markah rendah?
- Answers from the documents anyway
- Returns an error to the user
- Discards them, rewrites the query and uses web search
- Doubles the number of retrieved documents from the same index
- Apakah tujuan langkah mengurai kemudian gubah semula?
- To translate documents into another language
- To compress embeddings
- To rank web pages by popularity
- To split documents into strips and keep only relevant pieces
- Apabila penilai tidak pasti tentang perkaitan, tindakan manakah yang CRAG ambil?
- Ambiguous: combine refined internal knowledge with web results
- Correct: use internal documents only
- Incorrect: use web results only
- Stop and ask the user to rephrase
- Which statement about CRAG is a misconception according to the guide?
- It adds cost and latency
- It can wrap other RAG methods
- CRAG verifies that the final answer is correct
- It can use web search as a fallback
- What is the trade-off of setting a very strict relevance threshold?
- Weak documents slip through more often
- Fallback triggers often, adding web calls and latency
- The system stops using an evaluator
- Answers become shorter
- Why log which path (Correct, Ambiguous, Incorrect) each query took?
- It is required by the CRAG license
- It trains the embedding model automatically
- It removes the need for thresholds
- It reveals coverage gaps in the knowledge base worth fixing