4 papers · 1 filter
How Language Models Process Negation
Zhejian Zhou, Tianyi Zhou, Robin Jia +1
We study how Large Language Models (LLMs) process negation mechanistically. First, we establish that even though open-weight models often provide wrong answers to questions involvi…
Sampling More, Getting Less: Calibration is the Diversity Bottleneck in LLMs
Amin Banayeeanzade, Qingchuan Yang, Dhruv Tarsadiya +6
Diversity is essential for language-model applications ranging from creative generation to scientific discovery, yet modern LLMs often collapse into a narrow subset of plausible ou…
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…
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…