Learn Before
Maximum Likelihood Estimation (MLE) Objective in Supervised Language Model Training
In standard supervised training, the objective for a Large Language Model is to maximize the probability of generating a correct 'gold-standard' output sequence, , given an input, . This is achieved through Maximum Likelihood Estimation (MLE), where the model, which produces a series of token distributions, is trained to align these predictions with the one-hot distributions representing the target sequence. The formal objective is to maximize the conditional probability: .
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
Embedding Task Knowledge into LLM Parameters via Fine-Tuning
A software company wants to adapt a general-purpose language model to serve as a specialized customer service chatbot for their product. The model currently provides generic answers and lacks knowledge of the company's specific software features. Which of the following strategies represents the most direct and effective method for updating the model's parameters to produce accurate, product-specific responses?
Embedding Task Knowledge into LLM Parameters via Fine-Tuning
Impact of Dataset Quality on Fine-Tuning
Diagnosing a Flawed Fine-Tuning Process
Maximum Likelihood Estimation (MLE) Objective in Supervised Language Model Training
Learn After
A language model is being trained with a supervised objective to maximize the probability of the correct output. Given the input 'The largest city in the US is', the target output is the two-token sequence 'New York'. Two different models are evaluated on this single instance.
- Model A predicts the first token 'New' with a probability of 0.6, and then predicts the second token 'York' with a probability of 0.8.
- Model B predicts the first token 'New' with a probability of 0.9, and then predicts the second token 'York' with a probability of 0.4.
Based on the standard training objective for this task, which statement correctly analyzes the models' performance on this specific example?
Analyzing Model Training with Flawed Data
Limitations of Supervised Fine-Tuning for LLM Alignment
Parameter Updates in Supervised LLM Training