activity
20182026
most citedVerification for Machine Learning, Autonomy, and Neural Networks Survey

91 citations · 98 across the 7 of their papers we have counts for

collaborators
Showing 2026Show all

1 paper · 1 filter

cs.SE2026

Efficiency Hallucination: Formalizing and Measuring Behavioral Calibration in LLM-Based Code Optimization

Sarah Wilson, Gail Kaiser, Patrick Musau

The integration of Large Language Models (LLMs) into automated code optimization introduces a critical reliability risk we term the Efficiency Hallucination: an LLM's tendency to i…