引導式測驗 · 中等 等級
情境檢索測驗
測試上下文檢索:將文件上下文新增至區塊、使用上下文 BM25 進行上下文嵌入、重新排名和提示快取成本。
問題 1 的 8
情境檢索解決了什麼問題?
預覽每個問題8 問題
當您參加測驗時,就會出現答案和解釋。
- 情境檢索解決了什麼問題?
- Chunks lose information like company or time period when split from their document
- Embeddings are too expensive to store
- Language models cannot read tables
- BM25 cannot handle long queries
- 每個片段的上下文是如何產生的?
- By copying the document title only
- A language model reads the whole document and the chunk and writes a short situating explanation
- By a human editor for every chunk
- By averaging neighboring embeddings
- 在 Anthropic 的方法中,哪兩個索引會接收情境化的片段文字?
- A graph database and a cache
- A SQL table and a spreadsheet
- An embedding index and a BM25 keyword index
- Two separate vector indexes with different models
- 根據 Anthropic 報告的實驗,情境嵌入加上情境 BM25 大約減少了多少 top-20 檢索失敗?
- About 5 percent
- About 20 percent
- About 90 percent
- About 49 percent
- 為什麼提示快取會使情境檢索成本降低?
- It caches the document once and reuses it for every chunk's context call
- It skips the embedding step
- It removes the need for BM25
- It shortens each chunk
- Why is keeping BM25 in the pipeline especially useful with added context?
- BM25 understands synonyms better than embeddings
- Contexts often add exact identifiers like names, dates or codes that keyword search matches precisely
- BM25 requires no index
- BM25 replaces reranking
- When might contextual retrieval be unnecessary?
- When the documents are in English
- When using a reranker
- When the knowledge base is small enough to fit in the model's context window
- When chunks are longer than 50 tokens
- Where does the main extra cost of contextual retrieval occur?
- At query time for every user question
- In the reranker only
- In the user's browser
- At indexing time, with one model call per chunk