Interdisciplinary Colloquium on Digitalisation of Research: "AI-Supported Scholarly Research with ORKG Ask and TIB AIssistant" 02.10.2025 with Allard Oelen
Abstract
The presentation of the Interdisciplinary Colloquium on Digitalisation of Research "AI-Supported Scholarly Research with ORKG Ask and TIB AIssistant" 02.10.2025 by Allard Oelen. Artificial intelligence, and specifically LLMs, have the capability to organize scholarly knowledge and support researchers throughout the research life cycle. In this presentation, we will discuss two AI services developed by TIB, that provide researchers with tools to leverage AI in their work. Firstly, we will present ORKG Ask, a scholarly search and exploration platform. ORKG Ask allows users to ask research questions and find literature related to these questions among it more than 75 million indexed scholarly artifacts. Information is automatically extracted to answer the research question and is presented alongside additional key insights from the articles. A summary of the most relevant literature is generated as well. Finally, filtering tools allow users to narrow down the search to find specific articles they are interested in. Secondly, we discuss the TIB AIssistant, a novel service that provides researchers AI support throughout the research life cycle. The AIssistant is a domain agnostic platform where different assistants can be used in sequence to perform specific research tasks. In addition to the specialized prompts, it integrates external scholarly services that are organized in the tool library. Examples of assistants include research idea generation, research question formulation, literature discovery, and article drafting. Ultimately, the AIssistant provides researchers with a flexible AI-supported platform for accessing tools and approaches to support their research.
Full text
AI-Supported Scholarly Research with ORKG Ask and TIB AIssistant Allard Oelen1 Session moderator: Anna Jacyszyn2 Interdisciplinary Colloquium on Digitalisation of Research, FIZ Karlsruhe, 2 October 2025 (1) TIB - Leibniz Information Centre for Science and Technology and University Library, Leibniz University Hannover (2) FIZ Karlsruhe - Leibniz Institute for Information Infrastructure
Photos and recording Pixabay, ste_phania 2 Interdisciplinary Colloquium on Digitalisation of Research, Allard Oelen, 2 October 2025 www.youtube.com/@DiTraRe
3 Interdisciplinary Colloquium on Digitalisation of Research, Allard Oelen, 2 October 2025
AI-Supported Scholarly Research with ORKG Ask and TIB AIssistant DiTraRe Interdisciplinary Colloquium - October 2nd 2025 Allard Oelen TIB Leibniz Information Centre for Science and Technology, Hannover, Germany
●Introduction to scholarly communication ●ORKG Ask ●TIB AIssistant ●Q&A Today’s outline 30 mins
●Introduction to scholarly communication ●ORKG Ask ●TIB AIssistant ●Q&A Today’s outline 30 mins
Traditional scholarly search systems ●Keyword-based search standard to find scholarly articles Research question: How does climate change influence biodiversity in polar and alpine ecosystems? Search query
Traditional scholarly search systems ●Keyword-based search standard to find scholarly articles Research question: How does climate change influence biodiversity in polar and alpine ecosystems? climate change AND biodiversity AND ecosystems AND … Search query
Traditional scholarly search systems ●Keyword-based search standard to find scholarly articles Research question: How does climate change influence biodiversity in polar and alpine ecosystems? climate change AND biodiversity AND ecosystems AND … Search query Problem: Nuances of the original information need are lost… Problem: Takes a lot of time to see whether the listed articles are indeed relevant… Problem: … and at the end the original research question is still not answered
●Objective: provide a scholarly search system that finds related literature for a specific research question → Open source, reproducible and transparent ●High level system architecture: Approach: ORKG Ask (Assistant for Scientific Knowledge)
●Objective: provide a scholarly search system that finds related literature for a specific research question → Open source, reproducible and transparent ●High level system architecture: Approach: ORKG Ask (Assistant for Scientific Knowledge) ORKG Ask user interface Semantic search system (Vector stores) Large language models (LLMs) Knowledge Graphs (KGs) Paper Corpus (77M scholarly artifacts)
Question answering Reference manager Filtering Saved searches Export Custom extraction Latest technologies Responsive Dark mode Reproducibility Top authors / Datasets & Software
Question answering Reference manager Filtering Saved searches Export Custom extraction Latest technologies Responsive Dark mode Reproducibility Top authors / Datasets & Software
Question answering Reference manager Filtering BibTeX powered Saved searches Export Custom extraction Latest technologies Responsive Dark mode Paper details Question answering Paper-based answer Synthesized answer
Question answering Reference manager Filtering Saved searches Export Custom extraction Latest technologies Responsive Dark mode Reproducibility Top authors / Datasets & Software
Question answering Reference manager Filtering BibTeX powered Saved searches Export Custom extraction Latest technologies Responsive Dark mode Paper details Add additional entries, or upload your entire bibliography Reference manager Add papers to My library
Question answering Reference manager Filtering BibTeX powered Saved searches Export Custom extraction Latest technologies Responsive Dark mode Paper details Reference manager Import existing bibliographies Reference manager
Question answering Reference manager Filtering BibTeX powered Saved searches Export Custom extraction Latest technologies Responsive Dark mode Paper details Reference manager Extraction information from your own bibliography Reference manager
Question answering Reference manager Filtering Saved searches Export Custom extraction Latest technologies Responsive Dark mode Reproducibility Top authors / Datasets & Software
Question answering Reference manager Filtering BibTeX powered Saved searches Export Custom extraction Latest technologies Responsive Dark mode Paper details Custom extraction Extract additional knowledge by changing the columns of the results table
Question answering Reference manager Filtering Saved searches Export Custom extraction Latest technologies Responsive Dark mode Reproducibility Top authors / Datasets & Software
Question answering Reference manager Filtering BibTeX powered Saved searches Export Custom extraction Latest technologies Responsive Dark mode Paper details Retrieve previously saved searches Saved searches Save searches and make them part of your research workflow
Question answering Reference manager Filtering Saved searches Export Custom extraction Latest technologies Responsive Dark mode Reproducibility Top authors / Datasets & Software
Question answering Reference manager Filtering BibTeX powered Saved searches Export Custom extraction Latest technologies Responsive Dark mode Paper details Export results to CSV Export Export results to ORKG and use it for creating a new comparison Export papers
Question answering Reference manager Filtering Saved searches Export Custom extraction Latest technologies Responsive Dark mode Reproducibility Top authors / Datasets & Software
Question answering Reference manager Filtering BibTeX powered Saved searches Export Custom extraction Latest technologies Responsive Dark mode Paper details Responsive & Dark mode Fully responsive Dark mode
Question answering Reference manager Filtering Saved searches Export Custom extraction Latest technologies Responsive Dark mode Reproducibility Top authors / Datasets & Software
Question answering Reference manager Filtering BibTeX powered Saved searches Export Custom extraction Latest technologies Responsive Dark mode Paper details Reproducibility Reproducibility dropdown
TIB AIssistant
●General user interaction by task: a. Assistants b. Default set of tools c. Assets ■Input ■Output ●Each phase can be used in isolation or in sequence TIB AIssistant
●General user interaction by task: a. Assistants b. Default set of tools c. Assets ■Input ■Output ●Each phase can be used in isolation or in sequence Input: Results from previous step Input: User provided TIB AIssistant
Assistant Tools Assets, input/output
Assistant Tools Assets, input/output
grobit Tools
TIB AIssistant as platform ●Initial implementation shows how the platform can be used ●Everyone is encouraged to contribute → Create assistants, add tools, etc. ●Ensures you do not have to start from scratch when implementing research focused LLMs
Configurability
Configurability
Configurability Assistants Tools Assets
Future directions ●The AIssistant is mostly a frontend application as LLMs do the heavy lifting ●Simplifying the platform to encourage contributions
Future directions ●The AIssistant is mostly a frontend application as LLMs do the heavy lifting ●Simplifying the platform to encourage contributions Assistants: Collection of prompts Tools: Collection of REST endpoints Assets: Data storage
Future directions ●The AIssistant is mostly a frontend application as LLMs do the heavy lifting ●Simplifying the platform to encourage contributions Assistants: Collection of prompts Tools: Collection of REST endpoints Assets: Data storage Feature: Dynamic library of (scholarly) prompts
Future directions ●The AIssistant is mostly a frontend application as LLMs do the heavy lifting ●Simplifying the platform to encourage contributions Assistants: Collection of prompts Tools: Collection of REST endpoints Assets: Data storage Feature: Dynamic library of (scholarly) prompts Feature: MCP (Model-Context Protocol) server with GUI
Future directions ●The AIssistant is mostly a frontend application as LLMs do the heavy lifting ●Simplifying the platform to encourage contributions Assistants: Collection of prompts Tools: Collection of REST endpoints Assets: Data storage Feature: Dynamic library of (scholarly) prompts Feature: MCP (Model-Context Protocol) server with GUI Feature: dynamic data generation, LLM determines schema
More information soon! Stay tuned!
Licenses ●Icons by: Font Awesome Free 7.1.0 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free Copyright 2025 Fonticons, Inc.
Discussion Session 5 Interdisciplinary Colloquium on Digitalisation of Research, Allard Oelen, 2 October 2025
6 Interdisciplinary Colloquium on Digitalisation of Research, Allard Oelen, 2 October 2025
DiTraRe Symposium ■2-3 December 2025 ■ZKM Karlsruhe ■Sessions on: ○Knowledge Representation and AI ○Law and Ethics in Digitalisation of Research ○Research Infrastructures ○Impact on Science and Society ■Call for posters: deadline 17.10! https://www.ditrare.de/en/symposium-2025 7 Interdisciplinary Colloquium on Digitalisation of Research, Allard Oelen, 2 October 2025