2 papers
cs.LG2026
Measuring, Localizing, and Ablating Alignment Signatures in LLMs
Aniket Anand, Janvijay Singh, Zhewei Sun +2
Aligned language models often exhibit a recognizable AI-like style, yet its connection to post-training and internal representations remains poorly understood. In this work, we stu…
cs.CL2025
How do Language Models Generate Slang: A Systematic Comparison between Human and Machine-Generated Slang Usages
Siyang Wu, Zhewei Sun
Slang is a commonly used type of informal language that poses a daunting challenge to NLP systems. Recent advances in large language models (LLMs), however, have made the problem m…