PAGED: A Benchmark for Procedural Graphs Extraction from Documents

TL;DR

This paper introduces PAGED, a comprehensive benchmark with a high-quality dataset for evaluating procedural graph extraction from documents, revealing current limitations and exploring the potential of large language models with a novel self-refine strategy.

Contribution

The paper presents PAGED, a new benchmark with a dataset and evaluation framework, and assesses both traditional methods and large language models for procedural graph extraction.

Findings

Existing methods rely heavily on hand-crafted rules and lack data.

Large language models show advantages in textual element identification.

LMMs have gaps in building logical procedural structures.

Abstract

Automatic extraction of procedural graphs from documents creates a low-cost way for users to easily understand a complex procedure by skimming visual graphs. Despite the progress in recent studies, it remains unanswered: whether the existing studies have well solved this task (Q1) and whether the emerging large language models (LLMs) can bring new opportunities to this task (Q2). To this end, we propose a new benchmark PAGED, equipped with a large high-quality dataset and standard evaluations. It investigates five state-of-the-art baselines, revealing that they fail to extract optimal procedural graphs well because of their heavy reliance on hand-written rules and limited available data. We further involve three advanced LLMs in PAGED and enhance them with a novel self-refine strategy. The results point out the advantages of LLMs in identifying textual elements and their gaps in building logical structures. We hope PAGED can serve as a major landmark for automatic procedural graph extraction and the investigations in PAGED can offer insights into the research on logic reasoning among non-sequential elements.