LitLinker: Supporting the Ideation of Interdisciplinary Contexts with Large Language Models for Teaching Literature in Elementary Schools

TL;DR

This work introduces LitLinker, an LLM-powered tool that aids elementary-school teachers in ideating interdisciplinary contexts for literature instruction. Using an iterative, teacher-centered design with 13 participating educators, the authors implement a four-role, multi-agent framework that grounds AI outputs in a curated context pool and generates detailed lesson-planning outputs. In a within-subject study (N=16) LitLinker improves integration depth and reduces workload compared with a baseline LLM, while expert interviews (N=9) validate its usefulness and highlight considerations for curriculum alignment and UI refinements. The paper also articulates design implications for AI–teacher collaboration, emphasizing reflective practice, diverse context resources, and user-specific customization. Overall, LitLinker demonstrates the potential and limitations of embedding AI agents in teacher workflows to support interdisciplinary education, with open-source prospects and directions for future multimodal and standards-aligned extensions.

Abstract

Teaching literature under interdisciplinary contexts (e.g., science, art) that connect reading materials has become popular in elementary schools. However, constructing such contexts is challenging as it requires teachers to explore substantial amounts of interdisciplinary content and link it to the reading materials. In this paper, we develop LitLinker via an iterative design process involving 13 teachers to facilitate the ideation of interdisciplinary contexts for teaching literature. Powered by a large language model (LLM), LitLinker can recommend interdisciplinary topics and contextualize them with the literary elements (e.g., paragraphs, viewpoints) in the reading materials. A within-subjects study (N=16) shows that compared to an LLM chatbot, LitLinker can improve the integration depth of different subjects and reduce workload in this ideation task. Expert interviews (N=9) also demonstrate LitLinker's usefulness for supporting the ideation of interdisciplinary contexts for teaching literature. We conclude with concerns and design considerations for supporting interdisciplinary teaching with LLMs.

Figures (6)

• Figure 1: The user interface of LitLinker, translated from Chinese either by Google Translator or manually.
• Figure 2: The user interface of LitLinker's Outcome Generation Panel, translated from Chinese either by Google Translator or manually. The content in this figure serves as an example of outcomes.
• Figure 3: The architecture of LitLinker. The illustration of the main workflow of LitLinker. The responses to user's queries with gray background are not shown in this figure.
• Figure 4: RQ1 results regarding the outcomes evaluated by E1 in seven different aspects. ***: p<0.001, **: p<0.01, *: p<0.05, +: p<0.1
• Figure 5: RQ2 results regarding evaluating how LitLinker affects the workload during the task. For each metric, a higher NASA-TLX score suggests a higher perceived workload. ***: p<0.001, **: p<0.01, *: p<0.05, +: p<0.1