What Is Temperature in NLP?

Re:What Is Temperature in NLP? by taylorius on Monday March 13, 2023 @04:04AM (#35132539)

Roughly analogous process to the temperature parameter in simulated annealing, I think. Low temperature equates to a greedy algorithm (i.e. always take the most likely next word fragment) - higher temps. increase the probability of taking a lower probability fragment.

[ Parent | on HN ]

Re:What Is Temperature in NLP? by denysvitali on Monday March 13, 2023 @07:24AM (#35134164)

Basically exploration vs exploitation

[ Parent | on HN ]

Re:What Is Temperature in NLP? by albystein on Monday March 13, 2023 @12:24PM (#35137952)

I’m not sure if comparing it to the greedy algorithm is the correct way to think about it. Even after applying the temperature, if you use greedy decoding, you’ll still pick the output that has the highest probability. Where the concept of temperature is effective though is when you use a sampling method like sampling from a multinomial distribution, nucleus sampling, etc.

[ Parent | on HN ]

Re:What Is Temperature in NLP? by windsignaling on Monday March 13, 2023 @03:39PM (#35141289)

The analogy is apt. In SA, the temperature is used to make the distribution sharper or fatter. In this article, the temperature is used to make the distribution sharper or fatter.

[ Parent | on HN ]