Ninareh Mehrabi
19 papers · 2021–2026 · 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 ↓+8 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (43) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver π£ Hot Topic Early Bird
π€
Dynamic Duo
(17)
π§¬
Topic Evolution
β‘
Prolific Year Β· Productive
π₯
Unstoppable Β· Bronze
β
The Questioner
π
Century Club Β· Bronze
π
Trend Setter
ποΈ
Keyword Collector
(86)
Top co-authors
Research topics
Artificial Intelligence
(15)
Core AI
(15)
Natural Language Processing
(12)
Machine Learning
(11)
Application Areas
(8)
Learning Types Β· Machine Learning
(7)
Deep Learning
(6)
Generation
(6)
Resources & Methods
(5)
Learning Types Β· Deep Learning
(3)
Models
(3)
Knowledge & Reasoning
(2)
Applications
(2)
Representation
(2)
Optimization & Theory
(1)
Keywords
large language model
(8)
bias mitigation
(3)
text generation
(3)
in-context learning
(2)
toxicity detection
(2)
adversarial attack
(2)
bias detection
(1)
data augmentation
(1)
data poisoning
(1)
chain-of-thought reasoning
(1)
commonsense knowledge
(1)
attention mechanism
(1)
question answering
(1)
knowledge graph question answering
(1)
text-to-image generation
(1)
ambiguity resolution
(1)
intent classification
(1)
responsible ai
(1)
abstract meaning representation
(1)
kl divergence
(1)
Papers
SWAN: Semantic Watermarking with Abstract Meaning Representation
ACL 2026
Diagnosing Memorization in Chain-of-Thought Reasoning, One Token at a Time
EMNLP 2025
DiCoRe: Enhancing Zero-shot Event Detection via Divergent-Convergent LLM Reasoning
EMNLP 2025
On Localizing and Deleting Toxic Memories in Large Language Models
NAACL 2025
Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation
ACL 2025
Attribute Controlled Fine-tuning for Large Language Models: A Case Study on Detoxification
EMNLP 2024
BELIEVE: Belief-Enhanced Instruction Generation and Augmentation for Zero-Shot Bias Mitigation
NAACL 2024
Data Advisor: Dynamic Data Curation for Safety Alignment of Large Language Models
EMNLP 2024
FLIRT: Feedback Loop In-context Red Teaming
EMNLP 2024
MICo: Preventative Detoxification of Large Language Models through Inhibition Control
NAACL 2024
Prompt Perturbation Consistency Learning for Robust Language Models
EACL 2024
The steerability of large language models toward data-driven personas
NAACL 2024
Tokenization Matters: Navigating Data-Scarce Tokenization for Gender Inclusive Language Technologies
NAACL 2024
Tree-of-Traversals: A Zero-Shot Reasoning Algorithm for Augmenting Black-box Language Models with Knowledge Graphs
ACL 2024
Resolving Ambiguities in Text-to-Image Generative Models
ACL 2023
Attributing Fair Decisions with Attention Interventions
NAACL 2022
Robust Conversational Agents against Imperceptible Toxicity Triggers
NAACL 2022
Exacerbating Algorithmic Bias through Fairness Attacks
AAAI 2021
Lawyers are Dishonest? Quantifying Representational Harms in Commonsense Knowledge Resources
EMNLP 2021