# IDEA2: Expert-in-the-loop competency question elicitation for collaborative ontology engineering

arXiv: https://arxiv.org/abs/2604.01344 · HTML: https://mlsanity.com/paper/2604.01344/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 51 references that are in the map.
- First posted on arXiv 1 Apr 2026.

## Builds on (most cited first, 13 of 13)

- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [A Survey of Human-in-the-loop for Machine Learning](https://mlsanity.com/paper/2108.00941/) (2021)
- [Croissant: A Metadata Format for ML-Ready Datasets](https://mlsanity.com/paper/2403.19546/) (2024)
- [LLMs4OL: Large Language Models for Ontology Learning](https://mlsanity.com/paper/2307.16648/) (2023)
- [CrowdTruth 2.0: Quality Metrics for Crowdsourcing with Disagreement](https://mlsanity.com/paper/1808.06080/) (2018)
- [ArCo: the Italian Cultural Heritage Knowledge Graph](https://mlsanity.com/paper/1905.02840/) (2019)
- [OntoChat: a Framework for Conversational Ontology Engineering using Language Models](https://mlsanity.com/paper/2403.05921/) (2024)
- [An Experiment in Retrofitting Competency Questions for Existing Ontologies](https://mlsanity.com/paper/2311.05662/) (2023)
- [Large Language Models (LLMs) for Requirements Engineering (RE): A Systematic Literature Review](https://mlsanity.com/paper/2509.11446/) (2025)
- [A RAG Approach for Generating Competency Questions in Ontology Engineering](https://mlsanity.com/paper/2409.08820/) (2024)
- [Using Large Language Models for Knowledge Engineering (LLMKE): A Case Study on Wikidata](https://mlsanity.com/paper/2309.08491/) (2023)
- [Bench4KE: Benchmarking Automated Competency Question Generation](https://mlsanity.com/paper/2505.24554/) (2025)
- [A Comparative Study of Competency Question Elicitation Methods from Ontology Requirements](https://mlsanity.com/paper/2507.02989/) (2025)

## Abstract (arXiv)

Competency question (CQ) elicitation represents a critical but resource-intensive bottleneck in ontology engineering. This foundational phase is often hampered by the communication gap between domain experts, who possess the necessary knowledge, and ontology engineers, who formalise it. This paper introduces IDEA2, a novel, semi-automated workflow that integrates Large Language Models (LLMs) within a collaborative, expert-in-the-loop process to address this challenge. The methodology is characterised by a core iterative loop: an initial LLM-based extraction of CQs from requirement documents, a co-creational review and feedback phase by domain experts on an accessible collaborative platform, and an iterative, feedback-driven reformulation of rejected CQs by an LLM until consensus is achieved. To ensure transparency and reproducibility, the entire lifecycle of each CQ is tracked using a provenance model that captures the full lineage of edits, anonymised feedback, and generation parameters. The workflow was validated in 2 real-world scenarios (scientific data, cultural heritage), demonstrating that IDEA2 can accelerate the requirements engineering process, improve the acceptance and relevance of the resulting CQs, and exhibit high usability and effectiveness among domain experts. We release all code and experiments at https://github.com/KE-UniLiv/IDEA2