business enterprise
Document Ingestion Erased the Author's Emphasis
Mainstream converters dropped color and highlighting cues, turning singled-out policy requirements into confident misses.
Summary
Mainstream converters dropped color and highlighting cues, turning singled-out policy requirements into confident misses.
Using 76 real policy documents and deterministic labels from their OOXML properties, the study asks agents to recover requirements authors visually singled out. Formatting-blind ingestion fell from 0.690 micro-F1 to 0.150 with one converter and 0.075 as plain text. Highlight and color accounted for nearly all of the measured loss, and color was preserved by none of the mainstream converters tested. The pattern replicated in PDF and across six answering models. The result concerns visual emphasis in this corpus, not every document or requirement.
Why it matters
Mainstream converters dropped color and highlighting cues, turning singled-out policy requirements into confident misses.
Limits and context
- The result concerns visual emphasis in this corpus, not every document or requirement.
Key claims
Mainstream converters dropped color and highlighting cues, turning singled-out policy requirements into confident misses.
Qualification: The result concerns visual emphasis in this corpus, not every document or requirement.
Evidence: source-2026-10-22-013
Sources
- arXiv preprint 2610.30026, original v1arXiv · primary research
Corrections
No corrections have been recorded for this story.