I've mentioned this sort of process in recent talks, though it is still technology in its very early stages. The idea is to tailor the input data for an AI to ensure it gets its facts right. Here we read about one such technique, "retrieval augmented language modeling (RALM), which tries to train language models to fetch information from external sources... A RALM model, on the other hand, adds a 'knowledge retriever' to find the document that is most likely to contain information relevant to the prompt. It will then use the content of that document as part of its prompt to generate more reliable output." Longer-term, I think, models will consult larger bodies of structured data to add to and inform output generation.
Today: 10 Total: 97 [Direct link] [Share]
