Personalizing Student-Agent Interactions Using Log-Contextualized Retrieval Augmented Generation (RAG)
This work addresses the challenge of weak semantic links in student dialogue for personalizing STEM+C education, representing an incremental improvement over existing RAG methods.
The paper tackled the problem of hallucinations in large language models for personalized pedagogical agent interactions by proposing log-contextualized RAG (LC-RAG), which improved retrieval over a baseline and enabled the agent to deliver relevant, personalized guidance in a collaborative computational modeling environment.
Collaborative dialogue offers rich insights into students' learning and critical thinking, which is essential for personalizing pedagogical agent interactions in STEM+C settings. While large language models (LLMs) facilitate dynamic pedagogical interactions, hallucinations undermine confidence, trust, and instructional value. Retrieval-augmented generation (RAG) grounds LLM outputs in curated knowledge but requires a clear semantic link between user input and a knowledge base, which is often weak in student dialogue. We propose log-contextualized RAG (LC-RAG), which enhances RAG retrieval by using environment logs to contextualize collaborative discourse. Our findings show that LC-RAG improves retrieval over a discourse-only baseline and allows our collaborative peer agent, Copa, to deliver relevant, personalized guidance that supports students' critical thinking and epistemic decision-making in a collaborative computational modeling environment, C2STEM.