Short answer. Partly, and not in the way most teams assume. A born-digital PDF is readable because it carries a text layer; a scanned one is a picture of a document and yields nothing without OCR. Images are mostly understood through the text around them — filename, alt text, caption, nearby copy. Video is read almost entirely through its transcript, title and description, which is why transcripts have emerged as one of the strongest correlates of AI visibility. Every format earns citations through text.
Teams routinely assume that a vision-capable model reads a chart the way a person does, and that a video with a million views carries weight because it is a video. Neither is how a citation gets made. This piece sets out what each format actually contributes, why PDFs get read but rarely cited well, how images and video are really understood, and the order to fix things in.
What can each format actually contribute?
All three can contribute, but only through text. Every format that gets cited does so because something in it was readable as text.
That single principle explains most of the confusion here. Answer engines synthesise text answers, so a format earns a citation when it yields extractable, attributable text. The differences between formats are really differences in how much text they expose, and how reliably.
There is a commercial reason to care. Analysis of AI Overview inclusion has found that multimodal content — text combined with images, video and structured data — shows the strongest correlation with inclusion of any factor studied, reported at r=0.92 in 2026 research. Multiformat pages perform well. Formats that hide their content do not.
Why do PDFs get read but rarely cited well?
Because a PDF is a print format pretending to be a web page. The text is often there; the structure an engine needs to quote it accurately frequently is not.
Start with the split that decides everything. A born-digital PDF, exported from a word processor or design tool, contains an embedded text layer and can be parsed directly. A scanned PDF is a sequence of images and, without OCR, contains no machine-readable text at all. Every whitepaper, report and datasheet on your site falls into one of those two categories, and many organisations do not know which.
Even when the text is present, three structural problems reduce citability.
| Problem | What breaks |
|---|---|
| Reading order | Multi-column layouts, sidebars and pull quotes parse in the wrong sequence, so extracted passages come out scrambled and unquotable |
| Tables | A visual grid flattens into a run of numbers with no relationships preserved — a particular loss, because tabular data is otherwise highly quotable |
| Missing context | No reliable heading hierarchy, no schema markup, no publish date in a machine-readable field, no internal links. The page hosting the file may have all of that; the file does not |
Practitioners building retrieval pipelines report exactly this: poor reading order and broken tables damage chunking and answer quality even when the raw text extracts fine.
The practical conclusion is not to abandon PDFs. It is to stop treating them as the primary version of anything you want cited. Publish an HTML page carrying the same content, properly structured, and offer the PDF as the download. The HTML earns the citation; the PDF serves the reader who wants to print it.
How do engines actually understand images and video?
Through the text attached to them. Vision capability exists, but the reliable path to citation runs through captions, alt text, transcripts and descriptions.
Images. Modern models can describe an image, but an answer engine deciding whether to cite a page is working mostly from the text around it: filename, alt attribute, caption, nearby paragraph, structured data. This is why charts perform better when their key finding also appears in the caption or body copy. An image carrying a statistic that no sentence on the page repeats is a statistic the engine cannot quote. Google has also indicated that where images appear in responses they are linked back to their sources, so descriptive attribution matters.
Video. The evidence here is the strongest in this whole area. YouTube consistently ranks among the most-cited domains across answer engines, and research across 75,000 brands found that brand mentions in YouTube video titles and transcripts were the single strongest correlating factor with AI Overview visibility among all signals studied. Practitioner analysis points the same way: transcript density, chapter markers and structured descriptions all lift extractability.
Read that carefully, because it is easy to misread. It is not that video content is favoured. It is that a video with a rich transcript is a text document with a video attached, and the transcript is what gets read. A video with an auto-generated, uncorrected or absent transcript contributes very little.
The multilingual dimension is where this gets commercially interesting. A transcript exists in one language unless someone produces the others, and automatic captioning degrades sharply in lower-resource languages and regional accents. A company with excellent English transcripts and nothing else is invisible the moment a customer asks in Bahasa Indonesia or Arabic. Producing accurate transcripts and captions across languages is work Lifewood does through native speakers in its delivery network — in this context a visibility investment rather than an accessibility afterthought.
What should you fix first?
In this order, because the effort-to-effect ratio differs sharply.
- Audit which PDFs are scanned. Open each one and try to select text. If you cannot, no engine can read it either. Run OCR — or better, republish as HTML.
- Give every important PDF an HTML equivalent. Same content, question-shaped headings, an answer near the top of each section, real HTML tables rather than images of tables.
- Write alt text that states the finding, not the file. "Bar chart showing rural internet use at 58% against 85% urban" is useful. "chart1.png" is not.
- Repeat the key number in prose. A statistic that exists only inside an image effectively does not exist for citation purposes.
- Publish corrected transcripts, not auto-captions. Add chapter markers and a structured description. Treat the transcript as a page in its own right.
- Do the same in every language you sell in. Transcripts, captions and alt text are language-specific assets; coverage in one language buys nothing in another.
- Check crawler access to your media directories. A
robots.txtrule blocking/assets/or/downloads/quietly excludes everything above, and nothing in your analytics will report it.
See AEO services for how this fits a wider visibility programme, and What gets you cited by AI answer engines for the passage-level rubric.
Sources and further reading
- Leapd, on Ahrefs research across 75,000 brands and YouTube transcripts as a visibility factor.
- AIDev, "The 2026 GEO Playbook" — multimodal correlation with AI Overview inclusion.
- Everything-PR, "AI Platform Citation Source Index 2026" — most-cited domains and transcript extractability.
- LlamaIndex, "Best AI PDF Parsers" — born-digital versus scanned PDFs, reading order and table structure.
- Triaza, "AI Search in 2026: How to Get Cited by Answer Engines" — source and image linking behaviour.