industrial-maintenance

Tag

Cards List
#industrial-maintenance

DiagFlowBench: Evaluating How Language Models Handle Off-Procedure Inputs in Grounded Diagnostic Dialogue

arXiv cs.AI · 2026-06-17 Cached

This paper introduces DiagFlowBench, a benchmark dataset of 1,676 multi-turn diagnostic conversations derived from industrial flowcharts, designed to evaluate how well language models handle off-procedure inputs and abstain from giving inappropriate advice.

0 favorites 0 likes
#industrial-maintenance

DiagnosticIQ: A Benchmark for LLM-Based Industrial Maintenance Action Recommendation from Symbolic Rules

arXiv cs.AI · 2026-05-12 Cached

This paper introduces DiagnosticIQ, a benchmark for evaluating LLMs in translating industrial symbolic maintenance rules into actionable steps. It highlights that while frontier models perform well on standard tasks, they exhibit brittleness and pattern-matching behaviors under structural perturbations.

0 favorites 0 likes
← Back to home

Submit Feedback