Skip to main content

Questions tagged [chatgpt]

ChatGPT is a Large Language Model (LLM). Don't use this tag to ask for clarification of "advice" given by ChatGPT, but only for questions about its statistical underpinnings. Note that "advice" given by ChatGPT is frequently wrong and misleading!

Filter by
Sorted by
Tagged with
0 votes
0 answers
72 views

Are LLMs stateful or stateless during the generation process?

Are LLMs like OpenAI's gpt-* stateful or stateless during the generation of the response? I've read a couple of articles like this but am still not quite sure about that. I understand they are ...
Dr. Hans-Peter Störr's user avatar
2 votes
0 answers
83 views

What are the pros and cons of leveraging OpenAI's ChatGPT for data analysis? [closed]

I have been using OpenAI's ChatGPT 4 for some time now, for a variety of medical, educational, scholarly, and statistical tasks. I find it very informative, detailed, and flexible, and it can provide ...
0 votes
0 answers
42 views

How is OpenAI embedding obtained

There is OpenAI embedding API https://platform.openai.com/docs/guides/embeddings. How is this embedding related to the GPT3.5 transformer model architecture? Is it the vectors learned from the input ...
Salty Gold Fish's user avatar
7 votes
3 answers
2k views

How do you add knowledge to LLMs?

I recently heard an interesting comment from a gentleman on YouTube and it made sense instantly. To paraphrase he explained that "fine-tuning" an LM is not necessarily adding knowledge to a ...
Edv Beq's user avatar
  • 738
11 votes
1 answer
1k views

Source of randomness in ChatGPT

I've read that ChatGPT will sometimes give different answers to the same prompt. In other words, there is an element of randomness. Where does this randomness come from? Is there some sort of ...
Ryan Zotti's user avatar
  • 6,717
2 votes
1 answer
92 views

Question about retraining a regression model

Exercise. Suppose you train a Ridge model to a regression problem that has a normalized perfomance measure (say K) that attains a value in the interval [0,1], where 0 means that the model is terrible ...
xyz's user avatar
  • 185
1 vote
1 answer
523 views

Regarding the objective of PPO training in instructGPT

The following objective is taken from the paper 'Training language models to follow instructions with human feedback':which is used to fine-tune the pre-trained language model using Proximal Policy ...
Sam's user avatar
  • 403
14 votes
4 answers
1k views

Why do language models like InstructGPT and LLM utilize reinforcement learning instead of supervised learning to learn based on user-ranked examples?

Why do language models like InstructGPT and LLM utilize reinforcement learning instead of supervised learning to learn based on user-ranked examples? Language models like InstructGPT and ChatGPT are ...
resnet's user avatar
  • 1,270