SciDoc2Diagrammer-MAF: Towards Generation of Scientific Diagrams from Documents guided by Multi-Aspect Feedback Refinement

TL;DR

This paper introduces SciDoc2Diagram, a system for generating scientific diagrams from papers, utilizing multi-aspect feedback refinement to improve accuracy and visual quality, supported by a new benchmark dataset.

Contribution

It presents a novel multi-step pipeline with feedback refinement for diagram generation from scientific texts, outperforming existing models in accuracy and visual appeal.

Findings

Refinement strategy improves factual correctness and visual quality.

System outperforms existing models on automatic and human evaluations.

Introduces SciDoc2DiagramBench dataset for benchmarking.

Abstract

Automating the creation of scientific diagrams from academic papers can significantly streamline the development of tutorials, presentations, and posters, thereby saving time and accelerating the process. Current text-to-image models struggle with generating accurate and visually appealing diagrams from long-context inputs. We propose SciDoc2Diagram, a task that extracts relevant information from scientific papers and generates diagrams, along with a benchmarking dataset, SciDoc2DiagramBench. We develop a multi-step pipeline SciDoc2Diagrammer that generates diagrams based on user intentions using intermediate code generation. We observed that initial diagram drafts were often incomplete or unfaithful to the source, leading us to develop SciDoc2Diagrammer-Multi-Aspect-Feedback (MAF), a refinement strategy that significantly enhances factual correctness and visual appeal and outperforms existing models on both automatic and human judgement.