activity
20222026
most citedA Multi-task Model for Sentiment Aided Stance Detection of Climate Change Tweets

3 citations · 3 across the 2 of their papers we have counts for

collaborators
Showing 2026Show all

1 paper · 1 filter

cs.CL2026

When Safety Speaks a Language: A Mechanistic Analysis of Safety-Language Identity Entanglement in LLMs

Apoorva Upadhyaya, Sandipan Sikdar

Safety alignment of large language models (LLMs) degrades across languages, yet the internal mechanism driving this asymmetry remains poorly understood. Our work, therefore, presen…