Extract references from PDF

or drop PDF here

Status

Processing updates will appear here after upload.

Waiting for PDF Large PDFs may take 1-3 minutes. 0:00
Waiting for PDF
Workflow
01

Find the reference list

Locates bibliography headings, numbered lists, and reference blocks in the PDF.

02

Separate references

Turns individual citations into reviewable rows and separates unrelated text.

03

Extract citation fields

Finds titles, authors, years, journals, volumes, issues, pages, and identifiers.

04

Compare metadata with the PDF

Opens each record beside its highlighted citation text on the source PDF page.

05

Prepare review

Shows missing fields, conflicts, possible duplicates, and checks against scholarly sources.

06

Export reviewed references

Downloads selected records for reference managers, writing tools, spreadsheets, and audit workflows.

Features
Extract

Extract references from PDFs without copying bibliography entries by hand.

Check

Check records against scholarly sources and PDF text.

Complete

Automatically complete missing fields such as titles, authors, and journals.

Export

Export citations to any reference managers or text editors.

FAQ
PDFs and processing
What kind of PDFs work best?

Text-based research PDFs with selectable text and a clear References or Bibliography section work best.

Can it handle scanned or old PDFs?

Image-only scans usually need OCR first. After the PDF has a usable text layer, LumaCite can extract and review the references.

How long does PDF extraction take?

Most ordinary papers finish quickly. Large PDFs, long bibliographies, or difficult layouts can take one to three minutes.

What is the maximum PDF size?

The hosted upload path accepts PDFs up to about 45 MB. Smaller text-based PDFs process faster and are easier to verify.

Review and accuracy
What happens after I upload a PDF?

LumaCite opens a three-pane workspace with the source PDF, extracted reference rows, and editable citation fields.

Can I review citations before export?

Yes. Check extracted rows, fix fields, and select only the records you want to copy or download.

Does LumaCite verify every citation automatically?

No. It labels uncertain rows for review instead of pretending every extracted reference is fully verified.

Can it find DOI, PMID, arXiv, ISBN, or URLs?

Yes. LumaCite looks for common scholarly identifiers and uses them to improve matching and review signals.

Can I fix missing or incorrect fields?

Yes. Edit titles, authors, years, journals, identifiers, and other fields before export.

Export and next steps
Which export formats are supported?

Exports include formatted text, Markdown, Word bibliography text, BibTeX, RIS, EndNote XML, CSL-JSON, CSV, and an audit report.

Can I import the results into Zotero, Mendeley, or EndNote?

Yes. RIS and BibTeX work with many reference managers, and EndNote XML is available for EndNote workflows.

Does LumaCite replace my reference manager?

No. It prepares reviewed records from a PDF so you can move them into your citation manager, writing tool, spreadsheet, or research workflow.

Guides