# Self-hosted Lecture-to-Quiz: Local LLM MCQ Generation with Deterministic Quality Control

arXiv: https://arxiv.org/abs/2603.08729 · HTML: https://mlsanity.com/paper/2603.08729/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 19 references that are in the map.
- First posted on arXiv 20 Feb 2026.

## Builds on (most cited first, 8 of 8)

- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [RACE: Large-scale ReAding Comprehension Dataset From Examinations](https://mlsanity.com/paper/1704.04683/) (2017)
- [Learning to Ask: Neural Question Generation for Reading Comprehension](https://mlsanity.com/paper/1705.00106/) (2017)
- [Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translation](https://mlsanity.com/paper/1804.06609/) (2018)
- [A Novel Multi-Stage Prompting Approach for Language Agnostic MCQ Generation using GPT](https://mlsanity.com/paper/2401.07098/) (2024)
- [Multiple-Choice Question Generation Using Large Language Models: Methodology and Educator Insights](https://mlsanity.com/paper/2506.04851/) (2025)
- [Cognitively Diverse Multiple-Choice Question Generation: A Hybrid Multi-Agent Framework with Large Language Models](https://mlsanity.com/paper/2602.03704/) (2026)

## Built on by (most cited first, 2 of 2)

- [Arithmetic OOD Failure Unfolds in Stages in Minimal GPTs](https://mlsanity.com/paper/2603.26828/) (2026)
- [AI to Learn 2.0: A Deliverable-Oriented Governance Framework and Maturity Rubric for Opaque AI in Learning-Intensive Domains](https://mlsanity.com/paper/2604.19751/) (2026)

## Abstract (arXiv)

We present an end-to-end self-hosted (API-free) pipeline, where API-free means that lecture content is not sent to any external LLM service, that converts lecture PDFs into multiple-choice questions (MCQs) using a local LLM plus deterministic quality control (QC). The pipeline is designed for black-box minimization: LLMs may assist drafting, but the final released artifacts are plain-text question banks with an explicit QC trace and without any need to call an LLM at deployment time. We run a seed sweep on three short "dummy lectures" (information theory, thermodynamics, and statistical mechanics), collecting 15 runs x 8 questions = 120 accepted candidates (122 attempts total under bounded retries). All 120 accepted candidates satisfy hard QC checks (JSON schema conformance, a single marked correct option, and numeric/constant equivalence tests); however, the warning layer flags 8/120 items (spanning 8 runs) that expose residual quality risks such as duplicated distractors or missing rounding instructions. We report a warning taxonomy with concrete before->after fixes, and we release the final 24-question set (three lectures x 8 questions) as JSONL/CSV for Google Forms import (e.g., via Apps Script or API tooling) included as ancillary files under anc/. Finally, we position the work through the AI to Learn (AI2L) rubric lens and argue that self-hosted MCQ generation with explicit QC supports privacy, accountability, and Green AI in educational workflows.