2 papers
cs.CL2026
Function Induction and Task Generalization: An Interpretability Study with Off-by-One Addition
Qinyuan Ye, Robin Jia, Xiang Ren
Large language models demonstrate the intriguing ability to perform unseen tasks via in-context learning. However, it remains unclear what mechanisms inside the model drive such ta…
cs.CL2025
Rethinking Backdoor Detection Evaluation for Language Models
Jun Yan, Wenjie Jacky Mo, Xiang Ren +1
Backdoor attacks, in which a model behaves maliciously when given an attacker-specified trigger, pose a major security risk for practitioners who depend on publicly released langua…