T2-R2 in five minutes
The model assigns scores to possible next tokens.
A fluent continuation is not a retrieved fact.
Training predicts text. It does not by itself check your files.
GPT-3's paper describes few-shot prompting of a large language model.
Grounding is a separate step you add.
Ask a model a question about a note it was not given. If it answers smoothly, you still do not have evidence the note says that.
Sources and go deeper
- Brown and co-authors, Language Models are Few-Shot Learners, 2020 paper last checked 2026-10
- Vaswani and co-authors, Attention Is All You Need, 2017 paper last checked 2026-10
- Large language model — Wikipedia wikipedia last checked 2026-10
- Attention Is All You Need — Wikipedia wikipedia last checked 2026-10