T2MM: An LLM Supported Architecture For Inquiry-Based Modeling
Quick Answer
The T2MM architecture enhances inquiry-based modeling in education by integrating LLMs with interactive capabilities, outperforming traditional models in the VERA system.
Quick Take
The T2MM architecture enhances inquiry-based modeling in education by integrating LLMs with interactive capabilities, outperforming traditional models in the VERA system. It allows for dynamic model construction that adapts to learner inputs, demonstrating superior performance across all success metrics evaluated against baseline models.
Key Points
- T2MM integrates LLMs into the Virtual Experimental Research Assistant (VERA) for enhanced model construction.
- It creates interactive models that adapt to user adjustments, unlike static images.
- T2MM was evaluated using a custom dataset of natural language modeling requests.
- It outperformed baseline LLM-supported model generation across all measured success metrics.
- The architecture suggests pathways for developing more interactive multimodal LLM tools.
Paper Resources
Article Content
From source RSS / original summaryarXiv:2606. 11210v1 Announce Type: new Abstract: Model Construction is a foundational practice in science learning that relies on visualization and interactivity. Large Language Models, increasingly augmented with multimodal capabilities, have been integrated in education contexts to support learning. However, these tools lack visual interactivity that is required by some learning contexts.
We introduce Text to (T2MM), a robust, dynamic LLM supported architecture that assists in model construction within the open inquiry ecology-based modeling software Virtual Experimental Research Assistant (VERA). T2MM accounts for the current context of the learner's model and creates interactive models, rather than static images, enabling the model to remain responsive to manual adjustment.
To measure technical feasibility, we evaluate T2MM through a custom procedurally generated dataset of natural language learner modeling requests and target models within the VERA system. T2MM outperforms a baseline model generation architecture implemented through LLM-supported full code generation, common in the literature, across all measured success metrics.
Our contribution not only outlines LLM integration into a inquiry-based learning modeling tool, but also describes a possible architecture through which more interactive multimodal LLM tools can be created.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CL
See more →Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents?
The REFLECT benchmark reveals that current LLM judges are unreliable, achieving below 55% accuracy in evaluating reasoning and evidence use, highlighting the need for improved evaluation methods for deep research agents.