Sanjeevan Selvaganapathy
Publication record assembled from the DBLP archive of ranked conferences.
Papers indexed
2
Venues
2
Active years
2026–2026
Best venue rank
A*
Where they publish
Papers
2 indexed papers, newest first.
| Year | Venue | Title | Authors |
|---|---|---|---|
| 2026 | ACL | Confident, Calibrated, or Complicit: Safety Alignment and Ideological Bias in LLM Hate Speech Detection. | Sanjeevan Selvaganapathy, Mehwish Nasim |
| 2026 | EACL | Activation-Space Personality Steering: Hybrid Layer Selection for Stable Trait Control in LLMs. | Pranav Bhandari, Nicolas Fay, Sanjeevan Selvaganapathy, Amitava Datta, Usman Naseem, Mehwish Nasim |