A large language model-based chatbot system framework for urban planners
Bibliographic record
Abstract
Currently, urban planners, private developers, and related stakeholders face significant challenges due to the complexity and dispersion of municipal bylaws and zoning regulations across jurisdictions. This study proposes a novel Large Language Model (LLM)-based chatbot framework 1 1 GitHub: https://github.com/zhoux121/School_of_cities_AI designed to streamline access to and interpretation of these regulations. The framework integrates a hybrid database system, combining pre-collected static data from official sources with dynamically scraped real-time content, ensuring comprehensive and up-to-date information retrieval. Leveraging GPT-3.5-turbo for hierarchical text preprocessing and a dual retrieval mechanism (BM25 and cosine similarity with Reciprocal Rank Fusion), the framework achieves strong accuracy in answering regulatory queries. Evaluated across six Canadian cities, the model demonstrated 72–92% accuracy on binary questions and 40–70% on continuous questions, outperforming baseline models such as GPT-4o and LLaMA 3.2. This approach not only reduces administrative burdens but also enhances accessibility for stakeholders, offering a scalable solution for navigating fragmented urban policy landscapes.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.003 | 0.003 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.011 | 0.005 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".