Graph of AI Ideas: Leveraging Knowledge Graphs and LLMs for AI Research Idea Generation

2025-03-11

AI Summary

To address the challenge of generating high-quality research ideas in AI, this paper proposes a large language model (LLM) enhancement method grounded in a citation-based semantic knowledge graph. First, it explicitly models scholarly citation relationships as semantically labeled edges in a knowledge graph—uniquely capturing structured representations of papers, authors, techniques, and their evolutionary dynamics. Second, it designs a graph-augmented prompting framework inspired by human cognitive mechanisms and fine-tunes the LLM to support trend-aware idea generation. Experimental results demonstrate statistically significant improvements over strong baselines across human-evaluated dimensions—including novelty, clarity, and feasibility—validating that semantic citation graphs effectively enhance LLMs’ scientific creativity. The approach yields an interpretable, traceable AI-assisted paradigm for scientific discovery, wherein generated ideas are grounded in and auditable against the underlying scholarly knowledge structure.

Technology Category

• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

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

Abstract

Reading relevant scientific papers and analyzing research development trends is a critical step in generating new scientific ideas. However, the rapid increase in the volume of research literature and the complex citation relationships make it difficult for researchers to quickly analyze and derive meaningful research trends. The development of large language models (LLMs) has provided a novel approach for automatically summarizing papers and generating innovative research ideas. However, existing paper-based idea generation methods either simply input papers into LLMs via prompts or form logical chains of creative development based on citation relationships, without fully exploiting the semantic information embedded in these citations. Inspired by knowledge graphs and human cognitive processes, we propose a framework called the Graph of AI Ideas (GoAI) for the AI research field, which is dominated by open-access papers. This framework organizes relevant literature into entities within a knowledge graph and summarizes the semantic information contained in citations into relations within the graph. This organization effectively reflects the relationships between two academic papers and the advancement of the AI research field. Such organization aids LLMs in capturing the current progress of research, thereby enhancing their creativity. Experimental results demonstrate the effectiveness of our approach in generating novel, clear, and effective research ideas.

Problem

• Analyzing large volumes of research literature efficiently
• Exploiting semantic information in citation relationships
• Enhancing AI research idea generation using knowledge graphs

Innovation

• Utilizes knowledge graphs for organizing AI literature
• Integrates LLMs with semantic citation analysis
• Enhances AI research idea generation through structured data