# ARID: A Deployable Edge AI System for Structured Information Extraction from Industrial Maintenance Work Orders

arXiv: https://arxiv.org/abs/2609.23582 · HTML: https://mlsanity.com/paper/2609.23582/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 20 references that are in the map.
- First posted on arXiv 20 Sep 2026.

## Builds on (most cited first, 14 of 14)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Efficient Guided Generation for Large Language Models](https://mlsanity.com/paper/2307.09702/) (2023)
- [Mixture of LoRA Experts](https://mlsanity.com/paper/2404.13628/) (2024)
- [EdgeMoE: Empowering Sparse Large Language Models on Mobile Devices](https://mlsanity.com/paper/2308.14352/) (2023)
- [NAT: Noise-Aware Training for Robust Neural Sequence Labeling](https://mlsanity.com/paper/2005.07162/) (2020)
- [CLONE: Customizing LLMs for Efficient Latency-Aware Inference at the Edge](https://mlsanity.com/paper/2506.02847/) (2025)
- [LD-MoLE: Learnable Dynamic Routing for Mixture of LoRA Experts](https://mlsanity.com/paper/2509.25684/) (2025)
- [EdgeLoRA: An Efficient Multi-Tenant LLM Serving System on Edge Devices](https://mlsanity.com/paper/2507.01438/) (2025)
- [MaintNet: A Collaborative Open-Source Library for Predictive Maintenance Language Resources](https://mlsanity.com/paper/2005.12443/) (2020)
- [Which Quantization Should I Use? A Unified Evaluation of llama.cpp Quantization on Llama-3.1-8B-Instruct](https://mlsanity.com/paper/2601.14277/) (2026)
- [Understanding the Performance and Power of LLM Inferencing on Edge Accelerators](https://mlsanity.com/paper/2506.09554/) (2025)
- [MoLoRA: Composable Specialization via Per-Token Adapter Routing](https://mlsanity.com/paper/2603.15965/) (2026)
- [Trusted Knowledge Extraction for Operations and Maintenance Intelligence](https://mlsanity.com/paper/2507.22935/) (2025)
- [KEO: Knowledge Extraction on OMIn via Knowledge Graphs and RAG for Safety-Critical Aviation Maintenance](https://mlsanity.com/paper/2510.05524/) (2025)

## Abstract (arXiv)

Maintenance work orders must often be processed offline on embedded hardware, yet downstream software requires predictable structured output. We present ARID (Aviation-inspired Routing for Industrial Deployment), which extracts component, failure mode, symptom, and maintenance action into fixed-schema JSON on an 8 GB NVIDIA Jetson Orin NX. ARID combines conservative dual-teacher filtering, targeted noise-aware synthesis, one routing decision per work order, 4-bit inference, and grammar-constrained decoding. From 2,326 unlabeled OMIn records, it retains 716 training pairs and adds 99 topology-constrained records targeting action extraction. On 300 human-labeled records, ARID reaches 84.8% token-F1 on the reference stack and 82.9% on the deployed Jetson. Resident serving achieves 5,310/5,656 ms P50/P99 at 12.5 W. On zero-shot MaintNet transfer, semantic F1 falls to 46.4% while parser success remains at least 99.8%, showing that output validity transfers but field semantics do not.