| title | DiagnosticIQ: A Benchmark for LLM-Based Industrial Maintenance Action Recommendation from Symbolic Rules |
|---|---|
| authors | Devin Yasith De Silva, Dhaval Patel, Christodoulos Constantinides, Shuxin Lin, Nianjun Zhou, Paul J Adams, Sal Rosato, Nicolas Constantinides, Deborah L. McGuinness, Jayant Kalagnanam |
| date | 2026-05-09 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2605.08614 |
| affiliation | IBM |
| upvotes | 6 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf |
| abstract | Monitoring complex industrial assets relies on engineer-authored symbolic rules that trigger based on sensor conditions and prompt technicians to perform corrective actions. The bottleneck is not detection but response: translating rules into maintenance steps requires asset-specific knowledge gained through years of practice. We investigate whether LLMs can serve as decision support for this rule-to-action step and introduce , a benchmark of 6{,}690 expert-validated multiple-choice questions from 118 rule-action pairs across 16 asset types. We contribute (i) a symbolic-to-MCQA pipeline normalizing rules to Disjunctive Normal Form with embedding-based distractor sampling, (ii) five variants probing distinct failure modes (Pro, Pert, Verbose, Aug, Rationale), and (iii) a benchmark of 29 LLMs and 4 embedding baselines. A human evaluation (9 practitioners, mean 45.0\%) confirms requires specialist knowledge beyond operational experience. Three findings stand out. The frontier has closed: the top three LLMs lie within one Macro point, with Bradley-Terry Elo placing claude-opus-4-6 30 points above the next model. Yet \,Pro exposes brittleness, with every model losing 13--60\% relative accuracy under distractor expansion. \,Aug exposes pattern-matching: under condition inversion, frontier models still select the original answer 49--63\% of the time. The deployment bottleneck is not capability but calibration: frontier models handle template-style fault detection but break under structural perturbation. |
cite
@misc{silva2026diagnosticiq,
title={DiagnosticIQ: A Benchmark for LLM-Based Industrial Maintenance Action Recommendation from Symbolic Rules},
author={Devin Yasith De Silva and Dhaval Patel and Christodoulos Constantinides and Shuxin Lin and Nianjun Zhou and Paul J Adams and Sal Rosato and Nicolas Constantinides and Deborah L. McGuinness and Jayant Kalagnanam},
year={2026},
eprint={2605.08614},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2605.08614}
}