paper-with-me

홈 › Papers

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

2024-09-28 · Ishani Mondal, Zongxia Li, Yufang Hou, Anandhavelu Natarajan, Aparna Garimella, Jordan Boyd-Graber

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.

📄 PDF Abstract BibTeX arXiv:2409.19242

Code (0)

등록된 구현이 없습니다.

Tasks

BenchmarkingCode Generation

Similar Papers 제목 키워드 기반

DiagrammerGPT: Generating Open-Domain, Open-Platform Diagrams via LLM Planning

2023-10-18 · Abhay Zala, Han Lin, Jaemin Cho, Mohit Bansal

Text-to-image (T2I) generation has seen significant growth over the past few years. Despite this, there has been little work on generating diagrams with T2I models. A diagram is a symbolic/schematic representation that e…

SciDocBench: A Workflow-Centered Benchmark and Data Pipeline for Scientific Document Understanding

2026-09-04 · Shenxi Wu, Yuhong Liu, Haosong Zhang, Tongjin Zou 외 arxiv

Scientific papers require models to reason jointly over text, equations, figures, tables, code, and datasets while preserving the provenance of supporting evidence. Existing benchmarks typically evaluate these capabiliti…

Overview of SCIDOCA 2025 Shared Task on Citation Prediction, Discovery, and Placement

2025-09-29 · An Dao, Vu Tran, Le-Minh Nguyen, Yuji Matsumoto arxiv

We present an overview of the SCIDOCA 2025 Shared Task, which focuses on citation discovery and prediction in scientific documents. The task is divided into three subtasks: (1) Citation Discovery, where systems must iden…

Encoding Multi-Domain Scientific Papers by Ensembling Multiple CLS Tokens

2023-09-08 · Ronald Seoh, Haw-Shiuan Chang, Andrew McCallum

Many useful tasks on scientific documents, such as topic classification and citation prediction, involve corpora that span multiple scientific domains. Typically, such tasks are accomplished by representing the text with…

Citation PredictionTopic Classification

SPECTER: Document-level Representation Learning using Citation-informed Transformers

2020-04-15 · ACL 2020 6 · Arman Cohan, Sergey Feldman, Iz Beltagy, Doug Downey 외

Representation learning is a critical ingredient for natural language processing systems. Recent Transformer language models like BERT learn powerful textual representations, but these models are targeted towards token- …

Citation PredictionDocument ClassificationGeneral ClassificationLanguage Modeling+3