Shaona Ghosh
8 papers · 2015–2025 · 5 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 ↓+4 more ↓ Show less ↑
π£ Hot Topic Early Bird π Academic Marathon Β· Half π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (28) π Conference Polyglot Β· Silver
π§
Keyword Pioneer
ποΈ
Keyword Collector
(52)
β‘
Prolific Year Β· Productive
π
Renaissance Researcher
(6)
Top co-authors
Research topics
Artificial Intelligence
(7)
Core AI
(6)
Machine Learning
(4)
Natural Language Processing
(4)
Deep Learning
(3)
Application Areas
(3)
Resources & Methods
(3)
Learning Types Β· Deep Learning
(2)
Learning Types Β· Machine Learning
(2)
Models
(2)
Computer Science
(1)
Interdisciplinary
(1)
Mathematics & Optimization
(1)
Security & Privacy
(1)
Applications
(1)
Keywords
large language model
(4)
ai safety
(3)
dialogue system
(2)
graph classification
(1)
content moderation
(1)
multilingual processing
(1)
multimodal learning
(1)
neural network interpretability
(1)
mistake bound
(1)
ising model
(1)
synthetic data generation
(1)
instruction tuning
(1)
safety alignment
(1)
online prediction
(1)
marginal probability
(1)
topic coherence
(1)
adversarial attack
(1)
markov random field
(1)
responsible ai
(1)
cross-lingual transfer
(1)
Papers
AEGIS2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM Guardrails
NAACL 2025
A Simple Yet Effective Method for Non-Refusing Context Relevant Fine-grained Safety Steering in LLMs
EMNLP 2025
CultureGuard: Towards Culturally-Aware Dataset and Guard Model for Multilingual Safety Applications
IJCNLP 2025
GeoSAFE - A Novel Geospatial Artificial Intelligence Safety Assurance Framework and Evaluation for LLM Moderation
IJCNLP 2025
Guardrails and Security for LLMs: Safe, Secure and Controllable Steering of LLM Applications
ACL 2025
CantTalkAboutThis: Aligning Language Models to Stay on Topic in Dialogues
EMNLP 2024
Neuramanteau: A Neural Network Ensemble Model for Lexical Blends
IJCNLP 2017
Online Prediction at the Limit of Zero Temperature
NeurIPS 2015