After being asked to summarize a 50 page paper. A colleague took a stab at the summary by running it through ChatGPT. What Gerben found was interesting:
ChatGPT doesn’t summarise. When you ask ChatGPT to summarise this text, it instead shortens the text. And there is a fundamental difference between the two. To summarise, you need to understand what the paper is saying. To shorten text, not so much. To truly summarise, you need to be able to detect that from 40 sentences, 35 are leading up to the 36th, 4 follow it with some additional remarks, but it is that 36th that is essential for the summary and that without that 36th, the content is lost.
He concludes that LLM’s are influenced by how it was trained (it’s parameters) and the context you’ve given the LLM via the chat interface.
If the subject is well-represented by the parameters (there has been lots of it in the training material), the parameters dominate the summary more and the actual text you want to summarise influences the summary less. Hence: LLM Chatbots are pretty bad in making specific summaries of a subject that is widespread;… If the context is relatively small, it has little influence and the result is dominated by the parameters, so not by the text you are trying to summarise; If the context is large enough and the subject is not well-represented by the parameters (there hasn’t been much about it in the training material), the text you want to summarise dominates the result. But the mechanism you will see is ‘text shortening‘, not true summarising.