Parag Agrawal
8 papers · 2019–2025 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
🌍 Conference Polyglot (7) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🗺️ Taxonomy Completionist (12) 🏃 Academic Marathon (6)
🐝
Cross-Pollinator
(11)
⚡
Prolific Year
(7)
Conferences
NAACL (2)
ACL (1)
COLING (1)
EMNLP (1)
ICML (1)
IJCAI (1)
SEMEVAL (1)
Top co-authors
Keywords
large language model
(5)
safety evaluation
(2)
conversational ai
(1)
sentiment classification
(1)
toxicity detection
(1)
responsible ai
(1)
deep learning
(1)
tree structure
(1)
adversarial perturbation
(1)
bias mitigation
(1)
uncertainty estimation
(1)
prompt optimization
(1)
cultural sensitivity
(1)
dataset curation
(1)
adversarial testing
(1)
harmful content filtering
(1)
model debiasing
(1)
ai safety evaluation
(1)
harm detection
(1)
lexical feature
(1)
Papers
SCULPT: Systematic Tuning of Long Prompts
ACL 2025
Enhancing Zero-shot Chain of Thought Prompting via Uncertainty-Guided Strategy Selection
COLING 2025
SAGE: A Generic Framework for LLM Safety Evaluation
EMNLP 2025
AlphaPO: Reward Shape Matters for LLM Alignment
ICML 2025
Towards Safer Pretraining: Analyzing and Filtering Harmful Content in Webscale Datasets for Responsible LLMs
IJCAI 2025
Navigating the Cultural Kaleidoscope: A Hitchhiker’s Guide to Sensitivity in Large Language Models
NAACL 2025
LLM Safety for Children
NAACL 2025
NELEC at SemEval-2019 Task 3: Think Twice Before Going Deep
SEMEVAL 2019