# Stan: An LLM-based thermodynamics course assistant

arXiv: https://arxiv.org/abs/2603.04657 · HTML: https://mlsanity.com/paper/2603.04657/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 27 references that are in the map.
- First posted on arXiv 4 Mar 2026.

## Builds on (most cited first, 12 of 12)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [Textbooks Are All You Need II: phi-1.5 technical report](https://mlsanity.com/paper/2309.05463/) (2023)
- [Large Language Models for Education: A Survey and Outlook](https://mlsanity.com/paper/2403.18105/) (2024)
- [Practical and Ethical Challenges of Large Language Models in Education: A Systematic Scoping Review](https://mlsanity.com/paper/2303.13379/) (2023)
- [Computing Education in the Era of Generative AI](https://mlsanity.com/paper/2306.02608/) (2023)
- [Assigning AI: Seven Approaches for Students, with Prompts](https://mlsanity.com/paper/2306.10052/) (2023)
- [Harnessing LLMs in Curricular Design: Using GPT-4 to Support Authoring of Learning Objectives](https://mlsanity.com/paper/2306.17459/) (2023)
- [Using Large Language Models for Solving Thermodynamic Problems](https://mlsanity.com/paper/2502.05195/) (2025)
- [How critically can an AI think? A framework for evaluating the quality of thinking of generative artificial intelligence](https://mlsanity.com/paper/2406.14769/) (2024)
- [Small Models, Big Support: A Local LLM Framework for Educator-Centric Content Creation and Assessment with RAG and CAG](https://mlsanity.com/paper/2506.05925/) (2025)
- [From Canonical to Complex: Benchmarking LLM Capabilities in Undergraduate Thermodynamics](https://mlsanity.com/paper/2508.21452/) (2025)

## Abstract (arXiv)

Discussions of AI in education focus predominantly on student-facing tools -- chatbots, tutors, and problem generators -- while the potential for the same infrastructure to support instructors remains largely unexplored. We describe Stan, a suite of tools for an undergraduate chemical engineering thermodynamics course built on a data pipeline that we develop and deploy in dual roles: serving students and supporting instructors from a shared foundation of lecture transcripts and a structured textbook index. On the student side, a retrieval-augmented generation (RAG) pipeline answers natural-language queries by extracting technical terms, matching them against the textbook index, and synthesizing grounded responses with specific chapter and page references. On the instructor side, the same transcript corpus is processed through structured analysis pipelines that produce per-lecture summaries, identify student questions and moments of confusion, and catalog the anecdotes and analogies used to motivate difficult material -- providing a searchable, semester-scale record of teaching that supports course reflection, reminders, and improvement. All components, including speech-to-text transcription, structured content extraction, and interactive query answering, run entirely on locally controlled hardware using open-weight models (Whisper large-v3, Llama~3.1 8B) with no dependence on cloud APIs, ensuring predictable costs, full data privacy, and reproducibility independent of third-party services. We describe the design, implementation, and practical failure modes encountered when deploying 7--8 billion parameter models for structured extraction over long lecture transcripts, including context truncation, bimodal output distributions, and schema drift, along with the mitigations that resolved them.