Advancements in Large Language Models for Education and Human Interaction

The field of Large Language Models (LLMs) is moving towards more innovative and interactive applications, particularly in education and human interaction. Researchers are exploring the potential of LLMs to provide personalized feedback, characterize affective dynamics, and facilitate learning satisfaction. The use of LLMs in educational contexts is becoming increasingly prominent, with a focus on improving student outcomes and enhancing the learning experience. Noteworthy papers in this area include:

  • ROBOPSY PL[AI], which demonstrates a novel approach to investigating how LLMs present collective memory through role-playing.
  • Ensembling Large Language Models to Characterize Affective Dynamics in Student-AI Tutor Dialogues, which introduces an ensemble-LLM framework for large-scale affect sensing in tutoring dialogues.
  • Personalized and Constructive Feedback for Computer Science Students Using the Large Language Model, which investigates the performance of LLMs in generating personalized feedback for students.

Sources

ROBOPSY PL[AI]: Using Role-Play to Investigate how LLMs Present Collective Memory

Automatic Piecewise Linear Regression for Predicting Student Learning Satisfaction

Personalized and Constructive Feedback for Computer Science Students Using the Large Language Model (LLM)

Ensembling Large Language Models to Characterize Affective Dynamics in Student-AI Tutor Dialogues

Built with on top of