aitutor-assessmentkit 0.1.7

AITutor-AssessmentKit is the first open-source toolkit designed to evaluate the pedagogical performance of AI tutors in student mistake remediation tasks. With the growing capabilities of large language models (LLMs), this library provides a systematic approach to assess their teaching potential across multiple dimensions in educational dialogues.

AITutor-AssessmentKit: An Open-Source Library to Measure Pedagogical Ability of AI Tutors in Educational Dialogues

---

The AITutor-AssessmentKit is the first open-source library to enable the pedagogical abilities assessment of large language model (LLM)-powered AI tutors in educational dialogues. This unified framework:

• Evaluates AI tutor responses across eight comprehensive dimensions in the context of student error remediation tasks in mathematics.
• Offers a pluggable and customizable interface for integrating models and LLM releases from the community.

By providing an efficient, scalable alternative to costly and subjective human evaluations, AITutor-AssessmentKit facilitates on-the-fly assessment of AI tutors.

---

📥 Installation

To install AITutor-AssessmentKit with pip, type:

pip install aitutor-assessmentkit

---

📚 Overview of the AITutor-AssessmentKit

The library comprises three modular components:

1. autoeval: For automated evaluation.
2. llmeval: For LLM-based evaluation.
3. visualizer: For visualization and interpretation of evaluation scores.

---

📖 Tutorials

We provide several resources to help you get started:

1. Tutorial Notebook-I: Automated Evaluation with AITutor-AssessmentKit
2. Tutorial Notebook-II: LLM-Based Evaluation with AITutor-AssessmentKit
3. Tutorial Notebook-III: Visualizing AI Tutor Performance with AITutor-AssessmentKit

For a quick overview, check out our Demo Notebook.

---

🚀 Next Steps

Here are the upcoming milestones for the project:

1. Create and release detailed documentation.
2. Publish a longer tutorial video.
3. Develop a GUI-friendly interaction mode.

---

📜 Citation

If you use AITutor-AssessmentKit in your research, please cite us:

@inproceedings{maurya2024aitutorassessmentkit,
  title={AITutor-AssessmentKit: An Open-Source Library to Measure Pedagogical Ability of AI Tutors in Educational Dialogues},
  author={Kaushal Kumar Maurya and Ekaterina Kochmar},
  year={2024}
}

---

📧 Contact

For any questions or support, feel free to reach out:

📧 Kaushal Kumar Maurya: [e-mail]

---