Token Sampling from a Conditional Probability Distribution

Temperature-Scaled Softmax for Renormalized Probability

A language model has calculated the following raw scores (logits) for the next potential token: {'mat': 3.0, 'rug': 2.5, 'chair': 2.0, 'moon': -1.0}. To control the randomness of the output, a temperature parameter is applied to these scores before they are converted into a final probability distribution for sampling. Which of the following probability distributions most likely resulted from applying a low temperature (e.g., a value less than 1.0)?

Troubleshooting a Factual Chatbot's Output

You are configuring a text generation model for different tasks. Match each task with the description of the temperature setting that would be most appropriate to achieve the desired output.

Temperature-Scaled Softmax for Token Probability

Token Sampling from a Conditional Probability Distribution

Calculating Next-Token Probability

An autoregressive model is generating a sequence and has computed the following unnormalized scores (logits) for three candidate next tokens: Token A (3.0), Token B (1.0), and Token C (0.0). If a constant value of 10.0 is added to each of these three logits before the final probability normalization step, how will the resulting conditional probabilities for the tokens be affected?

An autoregressive language model calculates unnormalized scores (logits) for a set of candidate next tokens. These scores are then transformed into a probability distribution. What is the primary reason for applying an exponential function to each logit before the final normalization step?

Temperature-Scaled Softmax for Token Probability

Temperature-Scaled Softmax for Renormalized Probability