Question about Algorithm 1 table in self rag paper download from ariv about self-rag

[fate-ubw]

I figured out the fifth line in algorithm self_rag inference.the meaning of "M predicts ISREL given x, d and yt given x, d, y<t for each d ∈ D". In my opinion, given x, d and yt is no need. "given x, d, y<t " is right." is very easy if you read the code in eval demos.
here is the explaination:

• input of the slef_rag model(real data)

evidence_augmented_inputs = "### Instruction:\nWhat is Henry Feilden's occupation?\n\n### Response:\n[Retrieval]<paragraph>Henry Feilden (Conservative politician)\n Henry Master Feilden (21 February 1818 – 5 September 1875) was an English Conservative Party politician.</paragraph>"

preds = model.generate(evidence_augmented_inputs, sampling_params)

(Pdb) pred_token_ids
[32004, 24030, 719, 5169, 789, 264, 338, 263, 14099, 29889, 32012, 32011, 2]
(Pdb) pred_text
'Henry Feilden is a politician.'
(Pdb) tokenizer.convert_ids_to_tokens(pred_token_ids)
['[Relevant]', 'Hen', 'ry', '▁Fe', 'ild', 'en', '▁is', '▁a', '▁politician', '.', '[Fully supported]', '[Utility:5]', '</s>'] 

As you can see the value above. '[Fully supported]' and '[Utility:5]' will be output after model output yt.

• In paper
  d = [Retrieval]Henry Feilden (Conservative politician)\n Henry Master Feilden (21 February 1818 – 5 September 1875) was an English Conservative Party politician.
  yt = 'Henry Feilden is a politician.'
  y<t = ### Instruction:\nWhat is Henry Feilden's occupation?\n\n### Response:\n (there is no preceeding sentence, because the number of retrieval is one, )

I will close this comment, bucause I have aleardy understand this algorithm. fell free to reopen and comment~