document-structure-extraction

Tag

Cards List
#document-structure-extraction

TETHER: Training-Free, Elastic, ToC-Anchored Hierarchy Extraction and Recovery in Design-Driven Long Documents

arXiv cs.CL ↗ · 10h ago Cached

The paper introduces TETHER, a training-free, two-stage neuro-symbolic framework that uses the Table of Contents as a structural prior with a Large Multimodal Model to extract and recover document hierarchies in long design-driven documents, achieving SOTA zero-shot results with 90% token reduction over end-to-end baselines.

0 favorites 0 likes
← Back to home

Submit Feedback