You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
- content: "What is a key advantage of using multi-stage reasoning in Large Language Models (LLMs)?"
18
-
choices:
19
-
- content: "It reduces the overall computational cost."
20
-
isCorrect: false
21
-
explanation: "Incorrect. Multi-stage reasoning doesn't reduce the overall computational cost."
22
-
- content: "Dividing a complex problem into smaller and more manageable tasks."
23
-
isCorrect: true
24
-
explanation: "Correct. Multi-stage reasoning involves dividing a complex problem into smaller, more manageable tasks that the model can solve sequentially. This approach improves the model’s ability to handle intricate reasoning processes by addressing each subtask independently before combining the results to solve the overall problem."
25
-
- content: "It eliminates the need for external data sources."
26
-
isCorrect: false
27
-
explanation: "Incorrect. Multi-stage reasoning doesn't eliminate the need for external data sources."
28
-
- content: "Which framework is commonly used for managing multi-stage reasoning systems in LLMs?"
29
-
choices:
30
-
- content: "Tensorflow"
31
-
isCorrect: false
32
-
explanation: "Incorrect. TensorFlow is an open-source platform used for building and deploying deep learning models."
33
-
- content: "PyTorch"
34
-
isCorrect: false
35
-
explanation: "Incorrect. PyTorch is an open-source deep learning framework used for developing and training machine learning models, with a focus on flexibility and dynamic computation graphs."
36
-
- content: "LangChain"
37
-
isCorrect: true
38
-
explanation: "Correct. LangChain is a popular framework that helps build complex reasoning systems by linking different reasoning tasks together."
39
-
- content: "In the context of multi-stage reasoning with LLMs, what is the primary role of a 'retriever' in a retriever-based chain?"
40
-
choices:
41
-
- content: "To generate new data based on the initial input."
42
-
isCorrect: false
43
-
explanation: "Incorrect. The 'retriever' isn't used to generate new data."
44
-
- content: "To retrieve relevant information or documents that can be used in subsequent reasoning stages."
45
-
isCorrect: true
46
-
explanation: "Correct. In a retriever-based chain, the retriever is responsible for fetching relevant information or documents from a predefined dataset or knowledge base. This retrieved information is then passed on to subsequent stages in the reasoning process, where it can be used to generate a more informed and accurate response."
47
-
- content: "To execute logical operations like AND, OR, and NOT."
48
-
isCorrect: false
49
-
explanation: "Incorrect. The 'retriever' isn't used to execute logical operations like AND, OR and NOT."
- content: "What is a key advantage of using multi-stage reasoning in Large Language Models (LLMs)?"
18
+
choices:
19
+
- content: "It reduces the overall computational cost."
20
+
isCorrect: false
21
+
explanation: "Incorrect. Multi-stage reasoning doesn't reduce the overall computational cost."
22
+
- content: "Dividing a complex problem into smaller and more manageable tasks."
23
+
isCorrect: true
24
+
explanation: "Correct. Multi-stage reasoning involves dividing a complex problem into smaller, more manageable tasks that the model can solve sequentially. This approach improves the model’s ability to handle intricate reasoning processes by addressing each subtask independently before combining the results to solve the overall problem."
25
+
- content: "It eliminates the need for external data sources."
26
+
isCorrect: false
27
+
explanation: "Incorrect. Multi-stage reasoning doesn't eliminate the need for external data sources."
28
+
- content: "Which framework is commonly used for managing multi-stage reasoning systems in LLMs?"
29
+
choices:
30
+
- content: "Tensorflow"
31
+
isCorrect: false
32
+
explanation: "Incorrect. TensorFlow is an open-source platform used for building and deploying deep learning models."
33
+
- content: "PyTorch"
34
+
isCorrect: false
35
+
explanation: "Incorrect. PyTorch is an open-source deep learning framework used for developing and training machine learning models, with a focus on flexibility and dynamic computation graphs."
36
+
- content: "LangChain"
37
+
isCorrect: true
38
+
explanation: "Correct. LangChain is a popular framework that helps build complex reasoning systems by linking different reasoning tasks together."
39
+
- content: "In the context of multi-stage reasoning with LLMs, what is the primary role of a 'retriever' in a retriever-based chain?"
40
+
choices:
41
+
- content: "To generate new data based on the initial input."
42
+
isCorrect: false
43
+
explanation: "Incorrect. The 'retriever' isn't used to generate new data."
44
+
- content: "To retrieve relevant information or documents that can be used in subsequent reasoning stages."
45
+
isCorrect: true
46
+
explanation: "Correct. In a retriever-based chain, the retriever is responsible for fetching relevant information or documents from a predefined dataset or knowledge base. This retrieved information is then passed on to subsequent stages in the reasoning process, where it can be used to generate a more informed and accurate response."
47
+
- content: "To execute logical operations like AND, OR, and NOT."
48
+
isCorrect: false
49
+
explanation: "Incorrect. The 'retriever' isn't used to execute logical operations like AND, OR and NOT."
Copy file name to clipboardExpand all lines: learn-pr/wwl-data-ai/multistage-reasoning-azure-databricks/includes/01-introduction.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -6,4 +6,4 @@ To address these limitations, you can use **multi-stage reasoning systems**. The
6
6
7
7
:::image type="content" source="../media/model-system.png" alt-text="Diagram illustrating the difference between using one complex model or building a multi-stage reasoning system.":::
8
8
9
-
In Azure Databricks, you can create multi-stage reasoning systems using popular libraries. When you combine the computing power of Apache Spark, the reliable data storage of Delta Lake, and advanced machine learning libraries, Databricks makes it easy to efficiently process complex tasks.
9
+
In Azure Databricks, you can create multi-stage reasoning systems using popular libraries. When you combine the computing power of Apache Spark, the reliable data storage of Delta Lake, and advanced machine learning libraries, Databricks makes it easy to efficiently process complex tasks.
0 commit comments