Scholar
Utsav Maskey
Google Scholar ID: NeR5aJUAAAAJ
Macquarie University
Natural Language Processing
AI Alignment
Low Resource NLP
LLM Safety
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
18
H-index
2
i10-index
1
Publications
7
Co-authors
0
Publications
6 items
Over-Refusal and Representation Subspaces: A Mechanistic Analysis of Task-Conditioned Refusal in Aligned LLMs
2026
Cited
0
Steering Over-refusals Towards Safety in Retrieval Augmented Generation
2025
Cited
0
Can maiBERT Speak for Maithili?
2025
Cited
0
SafeConstellations: Steering LLM Safety to Reduce Over-Refusals Through Task-Specific Trajectory
2025
Cited
0
Should LLM Safety Be More Than Refusing Harmful Instructions?
2025
Cited
0
Benchmarking Large Language Models for Cryptanalysis and Mismatched-Generalization
2025
Cited
0
