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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Tykhonov, Vyacheslav, Yang, Han, Mayr, Philipp, Touber, Jetze, Scharnhorst, Andrea
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909651260407808
author Tykhonov, Vyacheslav
Yang, Han
Mayr, Philipp
Touber, Jetze
Scharnhorst, Andrea
author_facet Tykhonov, Vyacheslav
Yang, Han
Mayr, Philipp
Touber, Jetze
Scharnhorst, Andrea
contents This demo paper reports on a new workflow \textit{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 \textit{EverythingData} at the backend, \textit{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 \textit{method data analysis} journal published by GESIS -- Leibniz-Institute for the Social Sciences. We also point to further application areas.
format Preprint
id arxiv_https___arxiv_org_abs_2505_11633
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Chatting with Papers: A Hybrid Approach Using LLMs and Knowledge Graphs
Tykhonov, Vyacheslav
Yang, Han
Mayr, Philipp
Touber, Jetze
Scharnhorst, Andrea
Digital Libraries
Artificial Intelligence
This demo paper reports on a new workflow \textit{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 \textit{EverythingData} at the backend, \textit{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 \textit{method data analysis} journal published by GESIS -- Leibniz-Institute for the Social Sciences. We also point to further application areas.
title Chatting with Papers: A Hybrid Approach Using LLMs and Knowledge Graphs
topic Digital Libraries
Artificial Intelligence
url https://arxiv.org/abs/2505.11633