Bibextract Survey Extractor

Example Use Cases

• 1

  Extract related work and survey sections from arXiv papers.

• 2

  Normalize and merge bibliographic citations from multiple papers.

• 3

  Build large corpora of background content by recursively extracting related work sections.

Description

Bibextract is a Python package with a Rust backend designed to extract survey, background, and related work sections directly from the LaTeX source of arXiv papers. It reconstructs and normalizes bibliography entries from BBL files, merging citations across multiple papers to create a unified output. This tool facilitates building large corpora of related work content for LLM agents by automating the extraction and citation process.