Knowledge Synthesis Graph: An LLM-Based Approach for Modeling Student Collaborative Discourse

2026-02-05

AI Summary

This study addresses the challenge students face in asynchronous text-based discussions, where discerning the connections and evolution among ideas often hinders collaborative knowledge building. To overcome this limitation, the research introduces, for the first time, a large language model (LLM) to model collaborative discourse as a Knowledge Synthesis Graph (KSG). Through prompt engineering and iterative expert-informed coding, the approach automatically identifies distinct ideas and explicitly represents their cognitive relationships, thereby structuring and visualizing distributed, dynamic discourse. Experimental results demonstrate the feasibility of generating reliable KSGs across different LLMs, offering both a technical foundation and pedagogical insights for supporting complex knowledge work in collaborative learning environments.

Technology Category

• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Discourse, Pragmatics & Argument Mining

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
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work

Abstract

Asynchronous, text-based discourse-such as students'posts in discussion forums-is widely used to support collaborative learning. However, the distributed and evolving nature of such discourse often makes it difficult to see how ideas connect, develop, and build on one another over time. As a result, learners may struggle to recognize relationships among ideas-a process that is critical for idea advancement in productive collaborative discourse. To address this challenge, we explore how large language models (LLMs) can provide representational guidance by modeling student discourse as a Knowledge Synthesis Graph (KSG). The KSG identifies ideas from student discourse and visualizes their epistemic relationships, externalizing the current state of collaborative knowledge in a form that can support further inquiry and idea advancement. In this study, we present the design of the KSG and evaluate the LLM-based approach for constructing KSGs from authentic student discourse data. Through multi-round human-expert coding and prompt iteration, our results demonstrate the feasibility of using our approach to construct reliable KSGs across different models. This work provides a technical foundation for modeling collaborative discourse with LLMs and offers pedagogical implications for augmenting complex knowledge work in collaborative learning environments.

Problem

• collaborative discourse
• knowledge synthesis
• idea advancement
• asynchronous discussion
• epistemic relationships

Innovation

• Knowledge Synthesis Graph
• Large Language Models
• Collaborative Discourse
• Epistemic Relationships
• Prompt Engineering