Book
Open access
Jul 2026
The Poisoned Chalice of LLM Evaluation Report
The first Poisoned Chalice of LLM Evaluation Competition is organized, which frames contamination detection as a white-box membership inference task on source code and provides participants with curated datasets, target models, baseline attacks, and a final evaluation on a held-out model and dataset.
J. Katzy, Ali Al-Kaswan, R. Popescu et al.
· SIGSOFT FSE Companion · 1 citation
· ⚡1