Generalization as an Outcome of SFT
A key result of Supervised Fine-Tuning (SFT) is that the model gains the ability to generalize its task execution capabilities. For instance, after being fine-tuned on a set of question-answer pairs, an LLM can correctly respond to new questions that were not included in the specialized SFT dataset.
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
Instruction Fine-Tuning
Potential for Undesirable Content Generation After SFT
Example of SFT: Question-Answering Task
Applicability of Supervised Fine-Tuning
Practical Implementation Challenges of SFT
Maximum Likelihood Estimation (MLE) as the Objective for Supervised Fine-Tuning
Instruction Fine-Tuning as a Technique of SFT
Size and Specialization of SFT Datasets
Generalization as an Outcome of SFT
Characteristics of SFT Datasets
Generalization from Supervised Fine-Tuning
Definition of SFT Datasets
A development team starts with a base language model that has been pre-trained on a massive, general-purpose dataset from the web. To make the model a specialized customer service chatbot, the team initiates a second phase of training. How would the dataset used in this second phase most likely differ from the original pre-training dataset?
Comparison of SFT and Pre-training Datasets
SFT as a Post-Training Phase
Adapting a Model for a New Task
A law firm wants to develop a language model that can take a lengthy legal contract as input and produce a concise, one-paragraph summary highlighting key clauses like the term, liability limits, and governing law. They have a team of paralegals available to create a high-quality dataset of several thousand contract-summary pairs. Which of the following approaches is the most effective and direct way to train the model for this specific task?
Learn After
A development team adapts a pre-trained language model using a dataset of 5,000 customer support questions and their ideal answers. After this adaptation process is complete, they evaluate the model's performance. Which of the following outcomes provides the strongest evidence that the model has successfully generalized its ability to answer customer questions?
Evaluating Fine-Tuning Outcomes
Evaluating the Success of Model Adaptation