Academic papers (two-column format) not parsed correctly. #472

Open
opened 2026-02-16 00:17:57 -05:00 by yindo · 0 comments
Owner

Originally created by @timezyme on GitHub (May 13, 2025).

Describe the bug
Cannot maintain reading order of parsed text from two-column formatted academic PDF papers.

See job id. Notice the flow of text from page 1 to page 2. Most text from Column 1 on page 2 is missing.

Files

xiong20b.pdf

Job ID
986f35d0-83f0-4d96-b092-315cc7f3cbee

Additional context
See job id

Originally created by @timezyme on GitHub (May 13, 2025). **Describe the bug** Cannot maintain reading order of parsed text from two-column formatted academic PDF papers. See job id. Notice the flow of text from page 1 to page 2. Most text from Column 1 on page 2 is missing. **Files** [xiong20b.pdf](https://github.com/user-attachments/files/20190772/xiong20b.pdf) **Job ID** 986f35d0-83f0-4d96-b092-315cc7f3cbee **Additional context** See job id
yindo added the bug label 2026-02-16 00:17:57 -05:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: run-llama/llama_cloud_services#472