Shared Purpose of Tool Use and RAG in Context Generation
Despite differences in execution timing, both tool use and Retrieval-Augmented Generation (RAG) share the fundamental goal of enhancing language model predictions. From a modeling perspective, they both function by using external resources to supply sufficient and relevant context before the final output is generated.
0
1
Tags
Ch.3 Prompting - Foundations of Large Language Models
Foundations of Large Language Models
Foundations of Large Language Models Course
Computing Sciences
Related
Consider two systems that use a large language model to answer user queries by incorporating external information. Analyze the descriptions below and identify the primary difference in their operational flow.
System A: A customer support chatbot. When a user asks a question, the system first searches a knowledge base of product manuals for relevant articles. These articles are then combined with the user's question and passed to the language model to generate a final, comprehensive answer.
Analysis of Information Access Timing
You are analyzing two different systems that use a language model to answer questions with external information. One system gathers all necessary information before generating a response, while the other calls for information dynamically during the generation process. Match each operational characteristic to the correct system.
Learn After
Consider two language model systems. System A is provided with a set of relevant documents from a database at the same time it receives a user's query, before it begins generating a response. System B, in the middle of generating a response, pauses to execute a function that fetches real-time data, then uses that data to complete its answer. From a modeling perspective, what is the most accurate description of the fundamental goal shared by both systems?
Architectural Solutions for Context-Aware AI
The fact that Retrieval-Augmented Generation (RAG) gathers information before inference begins, while tool use accesses functions during inference, means that from a modeling perspective, they serve fundamentally different purposes in enhancing language model outputs.
The Agentic Perspective on Context Generation