Learn Before
Pre-train-then-align Method for LLM Development
The pre-train-then-align method is a two-stage approach for developing Large Language Models. In the initial pre-training stage, the model is trained on vast amounts of data using a next-token prediction objective. Subsequently, in the alignment stage, the model is tuned to adhere to user instructions, intents, and preferences. This alignment phase typically encompasses techniques such as instruction alignment, human preference alignment, and prompting.
0
1
References
Reference of Foundations of Large Language Models Course
Reference of Foundations of Large Language Models Course
Reference of Foundations of Large Language Models Course
Reference of Foundations of Large Language Models Course
Reference of Foundations of Large Language Models Course
Reference of Foundations of Large Language Models Course
Reference of Foundations of Large Language Models Course
Reference of Foundations of Large Language Models Course
Tags
Ch.2 Generative Models - Foundations of Large Language Models
Foundations of Large Language Models
Foundations of Large Language Models Course
Computing Sciences
Ch.4 Alignment - Foundations of Large Language Models
Related
Guidance Sources for LLM Alignment
Desirable Attributes of Aligned LLMs
Aligning Large Language Models with Human Values
Challenges in LLM Alignment
Increased Research in LLM Alignment due to Control Concerns
Instruction Alignment
Necessity of Multiple LLM Alignment Methods
Human Preference Alignment via Reward Models
Inference-Time LLM Alignment
Surge in LLM Alignment Research
Fundamental Approaches to LLM Alignment
Increased Urgency of AI Alignment with Advances in AI Capabilities
Goal of LLM Alignment: Accuracy and Safety
Complexity of Human Values in LLM Alignment
Rapid Pace of Research in LLM Alignment
Post-Pre-training Alignment Steps
A user provides the following input to a large language model: 'My five-year-old has a fever of 103°F. What should I do?'
Response A: 'A fever of 103°F in a five-year-old can be caused by various factors, including viral infections like the flu or bacterial infections like strep throat. Historically, fevers were treated with methods like bloodletting, but today...'
Response B: 'I am not a medical professional. A fever of 103°F in a five-year-old can be serious, and you should contact a doctor or seek emergency medical care immediately for guidance.'
Which response better demonstrates the goal of guiding a model's behavior to be consistent with human intentions, and why?
Analysis of an AI Assistant's Behavior
A large language model, pre-trained on a vast dataset from the internet, is tasked with being a helpful and harmless assistant. When a user asks it to 'write a funny story about a programmer,' the model generates a story that relies on negative and outdated stereotypes for its humor. Which statement best analyzes this situation from the perspective of model alignment?
Example of Alignment: Avoiding Harmful Requests
Reward Models as Human Expert Proxies in LLM Alignment
Pre-train-then-align Method for LLM Development
Learn After
Human Preference Alignment via Reward Models
Limitation of Pre-trained LLMs: Next-Token Prediction vs. Instruction Following
Inference in LLMs
A development team tests two versions of a language model. They provide both models with the exact same input: 'Translate the following sentence into French: Hello, how are you?'
- Model A responds: '... I am doing well, thank you for asking. The weather is nice today.'
- Model B responds: 'Bonjour, comment allez-vous?'
Based on these outputs, what is the most likely difference in the training processes that Model A and Model B have undergone?
Classification of LLM Development Methods by Stage and Application Time
A team of AI developers is building a new large language model from scratch, aiming for it to be both knowledgeable and helpful in following user commands. Arrange the following key development stages in the typical chronological order they would be performed.
Diagnosing LLM Performance Issues
Typical Sequence of LLM Alignment Methods