Pre-training BART on OCR text and augmenting input with LLM-generated question-answer pairs yields small metric gains on administrative document summarization, measured against LLM-written references.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2024 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
DocSum: Domain-Adaptive Pre-training for Document Abstractive Summarization
Pre-training BART on OCR text and augmenting input with LLM-generated question-answer pairs yields small metric gains on administrative document summarization, measured against LLM-written references.