Learn Before
Inference with Fine-Tuned Tool-Using LLMs
Once an LLM has been fine-tuned for tool use, its inference process is augmented. When the model generates a command for an external tool, that command is executed, and the tool's output is used to inform the subsequent steps of the generation process.
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
Data Annotation for LLM Tool Use Fine-Tuning
Inference with Fine-Tuned Tool-Using LLMs
Evaluating an LLM Implementation for a Flight Booking Chatbot
A development team has a powerful, general-purpose language model that they want to connect to a live weather API. When asked 'What's the weather in Paris?', the model currently generates a plausible but fictional weather report. What is the most critical reason for fine-tuning the model on a specialized dataset for this task?
A development team needs to modify a general-purpose Large Language Model so it can use an external calendar API. Arrange the following core steps of the fine-tuning process into the correct logical sequence.
Learn After
A user asks a language model, which has access to an external financial data tool, the following question: 'What is the current price of gold and what was the price one year ago?' Arrange the following actions in the logical order they would occur for the model to generate a complete answer.
Synthesizing Tool Output into a Final Response
A language model, fine-tuned to use an external weather tool, is asked: "What's the weather like in Paris today and what should I wear?". The model first generates a command to call the weather tool, which returns the following data:
{'temperature': '15°C', 'condition': 'Cloudy'}. What is the most crucial next step in the model's process to generate a complete and helpful final answer?