Papers
arxiv:2505.11633

Chatting with Papers: A Hybrid Approach Using LLMs and Knowledge Graphs

Published on Jun 17, 2025
Authors:
,
,
,
,

Abstract

A workflow called GhostWriter combines large language models and knowledge graphs within retrieval-augmented generation to enable controlled, iterative querying and chatting with document collections for research support.

This demo paper reports on a new workflow GhostWriter that combines the use of Large Language Models and Knowledge Graphs (semantic artifacts) to support navigation through collections. Situated in the research area of Retrieval Augmented Generation, this specific workflow represents the creation of local and adaptable chatbots. Based on the tool-suite EverythingData at the backend, GhostWriter provides an interface that enables querying and ``chatting'' with a collection. Applied iteratively, the workflow supports the information needs of researchers when interacting with a collection of papers, whether it be to gain an overview, to learn more about a specific concept and its context, and helps the researcher ultimately to refine their research question in a controlled way. We demonstrate the workflow for a collection of articles from the method data analysis journal published by GESIS -- Leibniz-Institute for the Social Sciences. We also point to further application areas.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2505.11633
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2505.11633 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2505.11633 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2505.11633 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.