# Improving Ontology Requirements Engineering with OntoChat and Participatory Prompting

arXiv: https://arxiv.org/abs/2408.15256 · HTML: https://mlsanity.com/paper/2408.15256/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 12 references that are in the map.
- First posted on arXiv 9 Aug 2024.

## Builds on (most cited first, 5 of 5)

- [LLM-assisted Knowledge Graph Engineering: Experiments with ChatGPT](https://mlsanity.com/paper/2307.06917/) (2023)
- [Exploring Large Language Models for Ontology Alignment](https://mlsanity.com/paper/2309.07172/) (2023)
- [Towards Ontology Construction with Language Models](https://mlsanity.com/paper/2309.09898/) (2023)
- [Using Large Language Models for OntoClean-based Ontology Refinement](https://mlsanity.com/paper/2403.15864/) (2024)
- [Participatory prompting: a user-centric research method for eliciting AI assistance opportunities in knowledge workflows](https://mlsanity.com/paper/2312.16633/) (2023)

## Built on by (most cited first, 3 of 3)

- [Bench4KE: Benchmarking Automated Competency Question Generation](https://mlsanity.com/paper/2505.24554/) (2025)
- [Investigating Language Model Capabilities to Represent and Process Formal Knowledge: A Preliminary Study to Assist Ontology Engineering](https://mlsanity.com/paper/2509.10249/) (2025)
- [Elenchus: Generating Knowledge Bases from Prover-Skeptic Dialogues](https://mlsanity.com/paper/2603.06974/) (2026)

## Abstract (arXiv)

Past ontology requirements engineering (ORE) has primarily relied on manual methods, such as interviews and collaborative forums, to gather user requirements from domain experts, especially in large projects. Current OntoChat offers a framework for ORE that utilises large language models (LLMs) to streamline the process through four key functions: user story creation, competency question (CQ) extraction, CQ filtration and analysis, and ontology testing support. In OntoChat, users are expected to prompt the chatbot to generate user stories. However, preliminary evaluations revealed that they struggle to do this effectively. To address this issue, we experimented with a research method called participatory prompting, which involves researcher-mediated interactions to help users without deep knowledge of LLMs use the chatbot more effectively. This participatory prompting user study produces pre-defined prompt templates based on user queries, focusing on creating and refining personas, goals, scenarios, sample data, and data resources for user stories. These refined user stories will subsequently be converted into CQs.