Graphy'our Data: Towards End-to-End Modeling, Exploring and Generating Report from Raw Data

TL;DR

Graphy is an end-to-end platform that automates the transformation of raw documents into structured graphs, enabling efficient exploration and high-quality report generation for large, unstructured datasets like literature surveys.

Contribution

This work introduces Graphy, a novel system combining data scraping, graph modeling, and LLM-driven exploration for comprehensive document investigation.

Findings

Successfully processed over 50,000 papers with references

Enabled iterative exploration and report generation

Demonstrated application in literature survey scenarios

Abstract

Large Language Models (LLMs) have recently demonstrated remarkable performance in tasks such as Retrieval-Augmented Generation (RAG) and autonomous AI agent workflows. Yet, when faced with large sets of unstructured documents requiring progressive exploration, analysis, and synthesis, such as conducting literature survey, existing approaches often fall short. We address this challenge -- termed Progressive Document Investigation -- by introducing Graphy, an end-to-end platform that automates data modeling, exploration and high-quality report generation in a user-friendly manner. Graphy comprises an offline Scrapper that transforms raw documents into a structured graph of Fact and Dimension nodes, and an online Surveyor that enables iterative exploration and LLM-driven report generation. We showcase a pre-scrapped graph of over 50,000 papers -- complete with their references -- demonstrating how Graphy facilitates the literature-survey scenario. The demonstration video can be found at https://youtu.be/uM4nzkAdGlM.