Jiajun Ruan — accepted AI-conference papers

2026

Leak@$k$: Unlearning Does Not Make LLMs Forget Under Probabilistic Decoding

Hadi Reisizadeh, Jiajun Ruan, Yiwei Chen, Soumyadeep Pal, Sijia Liu, Mingyi Hong

ICML 2026poster

Unlearning in large language models (LLMs) is critical for regulatory compliance and for building ethical generative AI systems that avoid producing private, toxic, illegal, or copyrighted content. Despite rapid progress, in this work we show that \textit{almost all} existing unlearning methods fail…

Cited by 0 Source ↗Scholar ↗

2026

NetArena: Dynamically Generated LLM Benchmarks for Network Applications

Yajie Zhou, Jiajun Ruan, Eric S. Wang, Sadjad Fouladi, Francis Y. Yan, Kevin Hsieh +1

ICLR 2026poster

As large language models (LLMs) expand into high-stakes domains like network system operations, evaluating their real-world reliability becomes increasingly critical. However, existing benchmarks risk contamination due to static design, show high statistical variance from limited dataset size, and f…

Cited by 0 Source ↗code ↗Scholar ↗