Nirmalendu Prakash
5 papers · 2023–2026 · 4 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
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(11)
🐣
Hot Topic Early Bird
🏆
Keyword Champion
(2)
Top co-authors
Research topics
Keywords
large language model
(2)
refusal behavior
(2)
sparse autoencoder
(2)
debiasing method
(1)
mechanistic interpretability
(1)
jailbreak attack
(1)
steering vector
(1)
social bia
(1)
hate speech detection
(1)
bias evaluation
(1)
causal mediation
(1)
fine-tuned model
(1)
feature intervention
(1)
activation space
(1)
transformer layer
(1)
logit len
(1)
functional testing
(1)
singapore language
(1)
feature ablation
(1)
backdoor removal
(1)
Papers
Beyond I’m Sorry, I Can’t: Dissecting Large-Language-Model Refusal
AAAI 2026
Activation Space Interventions Can Be Transferred Between Large Language Models
ICML 2025
Understanding Refusal in Language Models with Sparse Autoencoders
EMNLP 2025
SGHateCheck: Functional Tests for Detecting Hate Speech in Low-Resource Languages of Singapore
NAACL 2024
Layered Bias: Interpreting Bias in Pretrained Large Language Models
EMNLP 2023