Database Paper Browser

Back to papers

Doctopus: Budget-aware Structural Table Extraction from Unstructured Documents

Summary: Doctopus: a budget-aware system that mixes LLMs and cheaper non-LLM strategies for structural attribute extraction, using index-based chunk retrieval to minimize token costs. Per-attribute quality estimation and cost-constrained optimization select strategies; +11% quality at equal cost on a 4-dataset benchmark. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID
13993
Venue
VLDB
Year
2025
Pagerank
4.3849295e-05
Overall Rank
9,152 | 36.34%
DOI
10.14778/3749646.3749647

Incoming Non-self Citations Over Time

Authors

Incoming Citations (Sorted by Pagerank)

Showing 1 of 1 citing papers.

Rank Citing Paper Year Venue Pagerank
10,144 Beyond Relational: Semantic-Aware Multi-Modal Analytics with LLM-Native Query Optimization 2026 SIGMOD 4.1945683e-05
Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 5 of 5 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Previous Page 1 / 1 Next

Semantically Similar Papers