A confidence-weighted ensemble of three LLMs improves Top-1 fault-classification accuracy to 0.917 in automotive HiL validation, exceeding the best single LLM.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
LLM Ensemble Fault Classification for Automotive HiL Validation
A confidence-weighted ensemble of three LLMs improves Top-1 fault-classification accuracy to 0.917 in automotive HiL validation, exceeding the best single LLM.