My understanding is that the extra token vectors generated as reasoning are still useful, but that their surface form (tokens themselves) do not necessarily reflect the underlying reasoning. i.e. reading the reasoning…
There's been quite a bit of research into this over the past 3-4 years under the name "generative retrieval." The general approach is to use a transformer and treat the weights as the index. You input the query, and…
My understanding is that the extra token vectors generated as reasoning are still useful, but that their surface form (tokens themselves) do not necessarily reflect the underlying reasoning. i.e. reading the reasoning…
There's been quite a bit of research into this over the past 3-4 years under the name "generative retrieval." The general approach is to use a transformer and treat the weights as the index. You input the query, and…