Roy Ka-Wei Lee
39 papers · 2020–2026 · 10 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 ↑
🗺️ Taxonomy Completionist (69) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Gold 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird
🧬
Topic Evolution
🔬
Deep Specialist
(11)
👥
Mega-Team · Squad
⚡
Prolific Year · Prolific
🔥
Unstoppable · Bronze
❓
The Questioner
(2)
💎
Century Club · Bronze
🗃️
Keyword Collector
(179)
Venues
Top co-authors
Research topics
Artificial Intelligence
(26)
Core AI
(26)
Machine Learning
(25)
Natural Language Processing
(23)
Deep Learning
(14)
Applications
(14)
Learning Types · Machine Learning
(14)
Resources & Methods
(10)
Learning Types · Deep Learning
(9)
Application Areas
(8)
Core Methods
(5)
Generation
(4)
Architectures
(3)
Optimization & Theory
(3)
Learning Paradigms
(2)
Keywords
large language model
(14)
hate speech detection
(9)
multimodal learning
(8)
content moderation
(4)
low-resource language
(4)
vision-language model
(3)
text classification
(3)
multilingual nlp
(3)
few-shot learning
(2)
retrieval-augmented generation
(2)
bias evaluation
(2)
sparse autoencoder
(2)
machine translation
(2)
refusal behavior
(2)
cross-lingual transfer
(2)
domain adaptation
(2)
in-context learning
(2)
text generation
(2)
offensive language detection
(2)
large multimodal model
(2)
Papers
AdaMCoT: Rethinking Cross-Lingual Factual Reasoning Through Adaptive Multilingual Chain-of-Thought
AAAI 2026
Beyond I’m Sorry, I Can’t: Dissecting Large-Language-Model Refusal
AAAI 2026
BLEnD-Vis: Benchmarking Multimodal Cultural Understanding in Vision Language Models
EACL 2026
Can Persona-Prompted LLMs Emulate Subgroup Values? An Empirical Analysis of Generalisability and Fairness in Cultural Alignment
ACL 2026
HateXScore: A Metric Suite for Evaluating Reasoning Quality in Hate Speech Explanations
EACL 2026
MMAC: A Multilingual, Multimodal Alignment Framework for Cultural Grounding Evaluation
ACL 2026
Multi-Agent VLMs Guided Self-Training with PNU Loss for Low-Resource Offensive Content Detection
AAAI 2026
SafeLens: Segment-Level Hate Speech Detection in Online Videos
AAAI 2026
SemEval-2026 Task 7: Everyday Knowledge Across Diverse Languages and Cultures
SemEval 2026
A Closer Look at Backdoor Attacks on CLIP
ICML 2025
CCL-XCoT: An Efficient Cross-Lingual Knowledge Transfer Method for Mitigating Hallucination Generation
EMNLP 2025
Finding the Sweet Spot: Preference Data Construction for Scaling Preference Optimization
ACL 2025
Humor in Pixels: Benchmarking Large Multimodal Models Understanding of Online Comics
EMNLP 2025
Is LLM an Overconfident Judge? Unveiling the Capabilities of LLMs in Detecting Offensive Language with Annotation Disagreement
ACL 2025
LionGuard 2: Building Lightweight, Data-Efficient & Localised Multilingual Content Moderators
EMNLP 2025
LongGenBench: Benchmarking Long-Form Generation in Long Context LLMs
ICLR 2025
Persuasion Dynamics in LLMs: Investigating Robustness and Adaptability in Knowledge and Safety with DuET-PD
EMNLP 2025
Resolving Conflicting Evidence in Automated Fact-Checking: A Study on Retrieval-Augmented LLMs
IJCAI 2025
Toxicity Red-Teaming: Benchmarking LLM Safety in Singapore’s Low-Resource Languages
EMNLP 2025
Understanding Refusal in Language Models with Sparse Autoencoders
EMNLP 2025
Unmasking Implicit Bias: Evaluating Persona-Prompted LLM Responses in Power-Disparate Social Scenarios
NAACL 2025
Bridging Modalities: Enhancing Cross-Modality Hate Speech Detection with Few-Shot In-Context Learning
EMNLP 2024
Improving Covert Toxicity Detection by Retrieving and Generating References
NAACL 2024
Math-LLaVA: Bootstrapping Mathematical Reasoning for Multimodal Large Language Models
EMNLP 2024
Recent Advances in Online Hate Speech Moderation: Multimodality and the Role of Large Models
EMNLP 2024
SGHateCheck: Functional Tests for Detecting Hate Speech in Low-Resource Languages of Singapore
NAACL 2024
ToxiCloakCN: Evaluating Robustness of Offensive Language Detection in Chinese with Cloaking Perturbations
EMNLP 2024
Decoding the Underlying Meaning of Multimodal Hateful Memes
IJCAI 2023
Evaluating GPT-3 Generated Explanations for Hateful Content Moderation
IJCAI 2023
Improving the Detection of Multilingual Online Attacks with Rich Social Media Data from Singapore
ACL 2023
Layered Bias: Interpreting Bias in Pretrained Large Language Models
EMNLP 2023
Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models
ACL 2023
Prompting for Multimodal Hateful Meme Classification
EMNLP 2022
Improving Text Auto-Completion with Next Phrase Prediction
EMNLP 2021
On Orthogonality Constraints for Transformers
ACL 2021
Graph-to-Tree Learning for Solving Math Word Problems
ACL 2020
HateGAN: Adversarial Generative-Based Data Augmentation for Hate Speech Detection
COLING 2020
I miss you babe: Analyzing Emotion Dynamics During COVID-19 Pandemic
EMNLP 2020
Teacher-Student Networks with Multiple Decoders for Solving Math Word Problem
IJCAI 2020