Introducing ORKG ASK: an AI-driven Scholarly Literature Search and Exploration System Taking a Neuro-Symbolic Approach

2025-12-18

AI Summary

To address the growing challenge of information overload in academic literature retrieval, this paper introduces ASK—a natural language–driven academic search framework designed specifically for researchers. ASK pioneers a neuro-symbolic architecture that synergistically integrates vector-based retrieval (for efficient candidate recall), domain-specific knowledge graphs (to enable interpretable, structured reasoning), and large language models (for deep semantic understanding); it further employs retrieval-augmented generation (RAG) to decompose research queries, extract salient information, and generate traceable, citation-grounded answers. Experimental results demonstrate that ASK significantly outperforms existing baselines on complex, multi-faceted research questions, achieving superior answer accuracy, interpretability, and user satisfaction. By unifying efficiency, transparency, and reliability, ASK establishes a novel paradigm for scholarly search systems.

Technology Category

• Search and Optimization: Learning to Search
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Natural Language Processing: Question Answering

Application Category

• Search and Retrieval-Augmented AI: Large language models for search
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

As the volume of published scholarly literature continues to grow, finding relevant literature becomes increasingly difficult. With the rise of generative Artificial Intelligence (AI), and particularly Large Language Models (LLMs), new possibilities emerge to find and explore literature. We introduce ASK (Assistant for Scientific Knowledge), an AI-driven scholarly literature search and exploration system that follows a neuro-symbolic approach. ASK aims to provide active support to researchers in finding relevant scholarly literature by leveraging vector search, LLMs, and knowledge graphs. The system allows users to input research questions in natural language and retrieve relevant articles. ASK automatically extracts key information and generates answers to research questions using a Retrieval-Augmented Generation (RAG) approach. We present an evaluation of ASK, assessing the system's usability and usefulness. Findings indicate that the system is user-friendly and users are generally satisfied while using the system.

Problem

• Develops AI-driven system for scholarly literature search
• Uses neuro-symbolic approach to find relevant research articles
• Extracts key information and answers research questions automatically

Innovation

• Neuro-symbolic AI approach for literature search
• Uses vector search, LLMs, and knowledge graphs
• Implements Retrieval-Augmented Generation for answers