Artificial Intelligence Stack Exchange is a question and answer site for people interested in conceptual questions about life and challenges in a world where "cognitive" functions can be mimicked in purely digital environment. It only takes a minute to sign up.
Sign up to join this community
One of the innovations with OpenAI's ChatGPT is how natural it is for users to interact with it.
What is the technical enabler for ChatGPT to maintain the context of previous questions in its answers? For example, ChatGPT understands a prompt of "tell me more" and expands on it's previous answer.
Does it use activations from previous questions? Is there a separate input for the context? How does it work?
Based on an answer by OpenAI, it appears that the illusion of understanding context is created by the model's capacity to accept very long input sequences. The OpenAI FAQ states that approximately 3000 words can be given as input. This together with the fact that GPT-3 was trained to produce text that continues a given prompt could explain the context feature.
In practice, each prompt is probably extended with the previous outputs and prompt, as much as the input sequence length allows. So, all of the context is actually in the prompt.
Edit 18.2.2023
After spending some time with large language models and reading up the theory, I think my old answer is an understatement of ChatGPT's capabilities.
It is likely that there are several engineering approaches to improve the context after the maximum content length is exceeded. These include (but are probably not limited to)
Based on nothing but my own experience trying to build a similar chatbot using text-davinci-003, I think they are using the model itself to summarize the conversation, then feeding that summary back into the prompt. I get good results when doing this - though obviously the team behind ChatGPT does a better job.
Here is an example using the discussion under the question above:
You are a user named "AI" in an online forum. Below is a conversation about a question. Please add your contribution to the conversation.
Question: """
One of the innovations with OpenAI's ChatGPT is how natural it is for users to interact with it.
What is the technical enabler for ChatGPT to maintain the context of previous questions in its answers? For example, ChatGPT understands a prompt of "tell me more" and expands on it's previous answer.
Does it use activations from previous questions? Is there a separate input for the context? How does it work? """
Rainb: """
ChatGPT says: "ChatGPT uses a type of natural language processing called "transformer" architecture, which is a type of neural network that is designed to process and generate language. One of the key features of transformer architecture is that it allows the model to maintain a "context" of previous inputs. This is achieved through the use of self-attention mechanisms, which allow the model to weight different parts of the input differently based on how relevant they are to the current context. This allows the model to generate more nuanced and context-aware responses." """
milez: """
It does, indeed, but the transformer architecture alone does not explain this capability. Maintaining context requires something else. In fact, I think being a transformer is irrelevant for this purpose. """
Rexcirus: """
My best guess is that the whole conversation is fed as input for the next reply. But looking into openai labelling guidance, it looks that the data collection is single Q&A only. """
Rexcirus: """
If my guess is correct, when the conversation is very long ChatGPT should start forgetting previous bits, due to the maximum sequence size. """
yters: """
The ability to maintain context is very mysterious. What is most mysterious to me is that if I continuously converse with ChatGPT it has no problem maintaining context. On the other hand, if I break in the middle of a conversation, and then come back to it some time later, it's as if ChatGPT has had a memory wipe and has a lot of trouble regaining the thread of the conversation. Since ChatGPT is a neural network where the output is generated based on the previous 2048 input tokens, the amount of time between responses should have no bearing on the output generated. """
milez: """
Great observation @yters. Could it be a bug: the interface correctly shows the previous conversation, but the service fails to send this to the OpenAI APIs after some time. """
AI: """
It is possible that the OpenAI API may be designed to automatically discard the context after some time to avoid the system being overburdened with large conversations. Another possibility is that the system may be storing the context, but using a different mechanism than the transformer architecture to access it.
"""
Now, I'll ask it to summarize the conversation so far:
You are a user named "AI" in an online forum. Below is a conversation about a question. Please summarize the interaction so far.
[I then pasted in everything from the Question down in the previous prompt/response]
The conversation so far has focused on understanding the technical enablers that allow ChatGPT to maintain context in its answers. Rainb has suggested that this is done through transformer architecture and self-attention mechanisms. Rexcirus has suggested that the whole conversation may be fed as input for the next reply. Yters has then posed the interesting question of why, when the conversation is broken off and then resumed, ChatGPT has difficulty regaining the thread. Milez has suggested that this could be a bug in the interface.
Finally, I delete most of the conversation except for the summary and last few responses and alter the prompt a little to alert it to the presence of the summary:
You are a user named "AI" in an online forum. Below is a summary of the conversation so far about a question, and the last few responses to that question. Please add your contribution to the conversation.
Summary: The conversation so far has focused on understanding the technical enablers that allow ChatGPT to maintain context in its answers. Rainb has suggested that this is done through transformer architecture and self-attention mechanisms. Rexcirus has suggested that the whole conversation may be fed as input for the next reply. Yters has then posed the interesting question of why, when the conversation is broken off and then resumed, ChatGPT has difficulty regaining the thread. Milez has suggested that this could be a bug in the interface.
yters: """
The ability to maintain context is very mysterious. What is most mysterious to me is that if I continuously converse with ChatGPT it has no problem maintaining context. On the other hand, if I break in the middle of a conversation, and then come back to it some time later, it's as if ChatGPT has had a memory wipe and has a lot of trouble regaining the thread of the conversation. Since ChatGPT is a neural network where the output is generated based on the previous 2048 input tokens, the amount of time between responses should have no bearing on the output generated. """
milez: """
Great observation @yters. Could it be a bug: the interface correctly shows the previous conversation, but the service fails to send this to the OpenAI APIs after some time. """AI: That is an interesting point, @Milez. It could be that the interface does not accurately display the previous conversation to the API, or that there is a bug in the API that causes it to not be able to accurately generate a response with the 2048 input tokens when the conversation is broken off and then resumed. It would be interesting to investigate further.
I've had some success with this method, though it does still lose detail. Improving the prompt to create a more detailed summary helps. It's amazing how much of a conversation is full of repetitive filler, and how concisely it can be summarized. Maybe this is some kind of lingual compression? :)
