The paper delivers a taxonomy of seven LLM study types in software engineering along with eight guidelines that separate mandatory requirements from recommended practices to address reproducibility challenges.
Safety and Performance, Why not Both? Bi-Objective Optimized Model Compression toward AI Software Deployment
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 1representative citing papers
A ReLU-catalyzed abstraction method yields tighter bounds for transformer verification by converting dot-product constraints into ReLU forms that leverage standard convex relaxations.
An industrial experience report applying simulation-driven FMEA to an e-bike CPS, where expert validation confirmed model accuracy and revealed unexpected fault effects in 5 of 13 cases.
citing papers explorer
-
Guidelines for Empirical Studies in Software Engineering involving Large Language Models
The paper delivers a taxonomy of seven LLM study types in software engineering along with eight guidelines that separate mandatory requirements from recommended practices to address reproducibility challenges.
-
Precise Verification of Transformers through ReLU-Catalyzed Abstraction Refinement
A ReLU-catalyzed abstraction method yields tighter bounds for transformer verification by converting dot-product constraints into ReLU forms that leverage standard convex relaxations.
-
Failure Modes and Effects Analysis: An Experience from the E-Bike Domain
An industrial experience report applying simulation-driven FMEA to an e-bike CPS, where expert validation confirmed model accuracy and revealed unexpected fault effects in 5 of 13 cases.