Distractor document chunk size #272
Unanswered
cemremengu
asked this question in
Q&A
Replies: 1 comment
-
This part looks like the example datapoint has been compressed for ease of presentation. They should be
However,I do not tend to discredit this paper, I'm puzzled by this paper because many details were missed, such as how to difference the oracle documents If this is just something I missed when I read the paper, I hope I can be told where the answers to these questions are ;( |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
I am currently checking out RAFT. In this part we need to append
4 randomly selected chunks as distractor documents
for each QA pair according to algorithm. However, the appended chunks in the example datapoint are shorter than 512 tokens.Are they just truncated or I am missing something else?
Beta Was this translation helpful? Give feedback.
All reactions