Sanjeevan Selvaganapathy
3 papers · 2026–2026 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
Venues
Top co-authors
Research topics
Keywords
text classification
(1)
model calibration
(1)
safety alignment
(1)
low-resource language
(1)
low-rank subspace
(1)
polarization detection
(1)
hate speech detection
(1)
multilingual classification
(1)
small language model
(1)
ideological bia
(1)
activation space
(1)
large language model
(1)
big five personality trait
(1)
personality steering
(1)
hidden state activation
(1)
trait control
(1)
fairness disparity
(1)
Papers
Activation-Space Personality Steering: Hybrid Layer Selection for Stable Trait Control in LLMs
EACL 2026
Confident, Calibrated, or Complicit: Safety Alignment and Ideological Bias in LLM Hate Speech Detection
ACL 2026
NASIMLab at SemEval-2026 Task 9: A Comparative Analysis of Fine-Tuned Small Language Models vs. Generative Large Language Models for Multilingual Polarization Type Detection
SemEval 2026