Nicy Scaria

Nicy Scaria

Researcher, Educator, Traveller

Research

✅ Assessment of Large Language Models’ Ability to Generate Relevant and High-Quality Questions at Different Bloom’s Skill Levels

We examined the ability of five state-of-the-art LLMs to generate relevant and high-quality questions of different cognitive levels, as defined by Bloom’s taxonomy. We prompted each model with the same instructions and different contexts to generate 510 questions. Two human experts used a ten-item rubric to assess the linguistic and pedagogical relevance and quality of the questions. Our findings suggest that LLMs can generate relevant and high-quality educational questions of different cognitive levels, making them useful for creating assessments.

Alt text

Performance of different large language models on different evaluation metrics

🚙 Lateral Control of an Autonomous Vehicle

The electric power steering of the Suzuki Ignis (Robo-Taxi) was automatically controlled with an adaptive PID controller designed in MATLAB/SIMULINK using MicroAutoBox II. An Adaptive Model Predictive Controller was used for motion planning.

A simulation of the vehicle exhibiting autonomous control in CARLA