# Trusted Knowledge Extraction for Operations and Maintenance Intelligence

arXiv: https://arxiv.org/abs/2507.22935 · HTML: https://mlsanity.com/paper/2507.22935/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 56 references that are in the map.
- First posted on arXiv 24 Jul 2025.

## Builds on (most cited first, 17 of 17)

- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [Autoregressive Entity Retrieval](https://mlsanity.com/paper/2010.00904/) (2020)
- [ReFinED: An Efficient Zero-shot-capable Approach to End-to-End Entity Linking](https://mlsanity.com/paper/2207.04108/) (2022)
- [Packed Levitated Marker for Entity and Relation Extraction](https://mlsanity.com/paper/2109.06067/) (2021)
- [Coreference Resolution without Span Representations](https://mlsanity.com/paper/2101.00434/) (2021)
- [DeepStruct: Pretraining of Language Models for Structure Prediction](https://mlsanity.com/paper/2205.10475/) (2022)
- [Autoregressive Structured Prediction with Language Models](https://mlsanity.com/paper/2210.14698/) (2022)
- [Coreference Resolution through a seq2seq Transition-Based System](https://mlsanity.com/paper/2211.12142/) (2022)
- [Anaphora and Coreference Resolution: A Review](https://mlsanity.com/paper/1805.11824/) (2018)
- [Entity Linking Meets Deep Learning: Techniques and Solutions](https://mlsanity.com/paper/2109.12520/) (2021)
- [SoK: The Privacy Paradox of Large Language Models: Advancements, Privacy Risks, and Mitigation](https://mlsanity.com/paper/2506.12699/) (2025)
- [Research Trends for the Interplay between Large Language Models and Knowledge Graphs](https://mlsanity.com/paper/2406.08223/) (2024)
- [UniRel: Unified Representation and Interaction for Joint Relational Triple Extraction](https://mlsanity.com/paper/2211.09039/) (2022)
- [MaintNet: A Collaborative Open-Source Library for Predictive Maintenance Language Resources](https://mlsanity.com/paper/2005.12443/) (2020)
- [Do "English" Named Entity Recognizers Work Well on Global Englishes?](https://mlsanity.com/paper/2404.13465/) (2024)
- [Learning to Adapt to Low-Resource Paraphrase Generation](https://mlsanity.com/paper/2412.17111/) (2024)
- [Extracting Semantics from Maintenance Records](https://mlsanity.com/paper/2108.05454/) (2021)

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

- [KEO: Knowledge Extraction on OMIn via Knowledge Graphs and RAG for Safety-Critical Aviation Maintenance](https://mlsanity.com/paper/2510.05524/) (2025)
- [ARID: A Deployable Edge AI System for Structured Information Extraction from Industrial Maintenance Work Orders](https://mlsanity.com/paper/2609.23582/) (2026)

## Abstract (arXiv)

Deriving operational intelligence from organizational data repositories is a key challenge due to the dichotomy of data confidentiality vs data integration objectives, as well as the limitations of Natural Language Processing (NLP) tools relative to the specific knowledge structure of domains such as operations and maintenance. In this work, we discuss Knowledge Graph construction and break down the Knowledge Extraction process into its Named Entity Recognition, Coreference Resolution, Named Entity Linking, and Relation Extraction functional components. We then evaluate sixteen NLP tools in concert with or in comparison to the rapidly advancing capabilities of Large Language Models (LLMs). We focus on the operational and maintenance intelligence use case for trusted applications in the aircraft industry. A baseline dataset is derived from a rich public domain US Federal Aviation Administration dataset focused on equipment failures or maintenance requirements. We assess the zero-shot performance of NLP and LLM tools that can be operated within a controlled, confidential environment (no data is sent to third parties). Based on our observation of significant performance limitations, we discuss the challenges related to trusted NLP and LLM tools as well as their Technical Readiness Level for wider use in mission-critical industries such as aviation. We conclude with recommendations to enhance trust and provide our open-source curated dataset to support further baseline testing and evaluation.