[mobeets]

I was surprised to see the author claim that citations in the Introduction are a bad thing. I do think ML papers are generally pretty bad at acknowledging other relevant literature, but this makes me think it’s an active decision somehow

[Majromax]

Looking at the differences between the rejected and accepted papers, I don't think it's quite a matter of 'avoiding citations'. The changes seem to break along two lines.

1. Avoid overly general citations. The rejected paper leads with references to image captioning tasks in general and visual question-answering, neither of which is directly advanced by the described study. The accepted paper avoids these general citations in favour of more specific literature that works directly on the image-comparison task.

2. Don't lead with citations. The accepted paper has its citations at the end of the introduction, on page 2.

I think that each change is reasonably justified.

In avoiding overly-general citations, the common practice in machine learning literature is to publish short papers (10 pages or fewer for the main body), and column inches spent in an exhaustive literature review are inches not spent clearly describing the new study.

Placing citations towards the end of the introduction is consistent with the "inverted pyramid" school of writing, most commonly seen in journalism. Leaving the review process out of it for the moment, an ordinary researcher reading the article probably would rather know what the paper is claiming more than what the paper is citing. A page-one that can tell a reader whether they'll be interested in the rest of the article does readers a service.

[dagw]

You should definitely cite, but move the citations to where they are the most relevant and make them specific. The abstract and introduction should be more focused on what you've achieved, and overview of how you've achieved it, and why it is interesting. There generally shouldn't be too much to cite here. The exact details of methods used and everything you've built on comes later in the paper and that is where citations become important and relevant.

My least favourite type of citations in introductions, that I often see from more junior researches are ones that look like:

"In this paper we use a Machine Learning [1][2][3] technique known as Convolutional [4] Neural Networks [5][6][7][8] to..."