# Transforming Expert Knowledge into Scalable Ontology via Large Language Models

arXiv: https://arxiv.org/abs/2506.08422 · HTML: https://mlsanity.com/paper/2506.08422/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 39 references that are in the map.
- First posted on arXiv 10 Jun 2025.

## Builds on (most cited first, 20 of 20)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them](https://mlsanity.com/paper/2210.09261/) (2022)
- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [Large Language Models as Optimizers](https://mlsanity.com/paper/2309.03409/) (2023)
- [Explain Yourself! Leveraging Language Models for Commonsense Reasoning](https://mlsanity.com/paper/1906.02361/) (2019)
- [Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning](https://mlsanity.com/paper/2205.09712/) (2022)
- [Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programs](https://mlsanity.com/paper/2406.11695/) (2024)
- [Token-Budget-Aware LLM Reasoning](https://mlsanity.com/paper/2412.18547/) (2024)
- [Language Models of Code are Few-Shot Commonsense Learners](https://mlsanity.com/paper/2210.07128/) (2022)
- [Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond](https://mlsanity.com/paper/2103.10689/) (2021)
- [In-Context Learning Unlocked for Diffusion Models](https://mlsanity.com/paper/2305.01115/) (2023)
- [How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach](https://mlsanity.com/paper/2503.01141/) (2025)
- [Improving Consistency in Large Language Models through Chain of Guidance](https://mlsanity.com/paper/2502.15924/) (2025)
- [Potential and Perils of Large Language Models as Judges of Unstructured Textual Data](https://mlsanity.com/paper/2501.08167/) (2025)
- [Reconciling Methodological Paradigms: Employing Large Language Models as Novice Qualitative Research Assistants in Talent Management Research](https://mlsanity.com/paper/2408.11043/) (2024)
- [Healthcare Knowledge Graph Construction: State-of-the-art, open issues, and opportunities](https://mlsanity.com/paper/2207.03771/) (2022)

## Built on by (most cited first, 1 of 1)

- [Reasoning-Native Agentic Communication for 6G](https://mlsanity.com/paper/2602.17738/) (2026)

## Abstract (arXiv)

Having a unified, coherent taxonomy is essential for effective knowledge representation in domain-specific applications as diverse terminologies need to be mapped to underlying concepts. Traditional manual approaches to taxonomy alignment rely on expert review of concept pairs, but this becomes prohibitively expensive and time-consuming at scale, while subjective interpretations often lead to expert disagreements. Existing automated methods for taxonomy alignment have shown promise but face limitations in handling nuanced semantic relationships and maintaining consistency across different domains. These approaches often struggle with context-dependent concept mappings and lack transparent reasoning processes. We propose a novel framework that combines large language models (LLMs) with expert calibration and iterative prompt optimization to automate taxonomy alignment. Our method integrates expert-labeled examples, multi-stage prompt engineering, and human validation to guide LLMs in generating both taxonomy linkages and supporting rationales. In evaluating our framework on a domain-specific mapping task of concept essentiality, we achieved an F1-score of 0.97, substantially exceeding the human benchmark of 0.68. These results demonstrate the effectiveness of our approach in scaling taxonomy alignment while maintaining high-quality mappings and preserving expert oversight for ambiguous cases.