Multi-Task Capability through Diverse Fine-Tuning Datasets
A Large Language Model can be fine-tuned to handle multiple Natural Language Processing (NLP) tasks simultaneously by training it on a dataset that includes instructions and corresponding outputs from a variety of different problems.
0
1
Tags
Ch.4 Alignment - Foundations of Large Language Models
Foundations of Large Language Models
Foundations of Large Language Models Course
Computing Sciences
Related
Multi-Task Capability through Diverse Fine-Tuning Datasets
Modern Focus of Instruction Fine-Tuning Datasets
Using Diverse Data to Steer LLM Specialization
Examples of Instruction-Following Tasks in SFT Datasets
A development team has fine-tuned a large language model to be a helpful assistant. They observe that the model excels at summarizing technical documents and answering direct factual questions, which were the primary tasks in its fine-tuning dataset. However, when users ask it to perform more creative tasks like writing a short poem or brainstorming marketing slogans, the model's performance is poor and generic. Which of the following strategies would be the most effective next step to improve t
Using Varied Instructions for a Single Task to Enhance Data Diversity
Improving a Customer Service Chatbot's Robustness
Characteristics and Limitations of Early Instruction Fine-Tuning Datasets
Evaluating a Fine-Tuning Strategy for LLMs
Example of a Recipe Generation Task for LLMs
Example of a Creative Writing Task for LLMs
Example of a Math Word Problem Task for LLMs
Learn After
Evaluating Multi-Task Fine-Tuning Strategies for AI Assistants
Developing a Multi-Function Customer Service AI
A development team is building a single language model intended to serve as a versatile corporate assistant. The model must be able to summarize internal reports, answer questions based on a company knowledge base, and draft professional emails. After an initial training phase, the team observes that the model is excellent at drafting emails but performs poorly on summarization and question-answering. Which of the following adjustments to their training process is most likely to create a single