Get started
Author

Sanjeevan Selvaganapathy

Observed name: Selvaganapathy, Sanjeevan
OpenAlex ID: A5120303690
Confident, Calibrated, or Complicit: Safety Alignment and Ideological Bias in LLM Hate Speech Detection
2026 · Sanjeevan Selvaganapathy, Mehwish Nasim · Proceedings of the conference - Association for Computational Linguistics. Meeting · 1
PDF
Confident, Calibrated, or Complicit: Safety Alignment and Ideological Bias in LLM Hate Speech Detection
2026 · Association for Computational Linguistics 2026, Nasim, Mehwish, et al. · Underline Science Inc.
Activation-Space Personality Steering: Hybrid Layer Selection for Stable Trait Control in LLMs
2026 · Association for Computational Linguistics 2026, Bhandari, Pranav, et al. · Underline Science Inc.
Activation-Space Personality Steering: Hybrid Layer Selection for Stable Trait Control in LLMs
2026 · Pranav Bhandari, Nicolas Fay, et al. · Conference of the European Chapter of the Association for Computational Linguistics
Do LLMs Use Cultural Knowledge Without Being Told? A Multilingual Evaluation of Implicit Pragmatic Adaptation
2026 · Mehwish Nasim, Sanjeevan Selvaganapathy, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)
PDF
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
2026 · Neel Sabhahit, Sanjeevan Selvaganapathy, et al. · International Workshop on Semantic Evaluation (SemEval)
PDF
Activation-Space Personality Steering: Hybrid Layer Selection for Stable Trait Control in LLMs
2025 · Bhandari, Pranav, Fay, Nicolas, et al. · arXiv (Cornell University)
PDF
Works count: 7
Citation count: 1
H-index: 1
I10-index:
Year
Topic
Type