Nicholas Meade
Scholar

Nicholas Meade

Google Scholar ID: -aLqCbgAAAAJ
PhD Student, McGill University and Mila
Natural Language ProcessingAI Safety
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
2,065
 
H-index
9
 
i10-index
9
 
Publications
12
 
Co-authors
0
 
Contact
CVOpen ↗TwitterOpen ↗GitHubOpen ↗
Publications
8 items
Toward Open Weight Models Without Risks: Separating Public and Private Capabilities in LLMs
2026
Cited
0
The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents
2026
Cited
0
AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories
2025
Cited
0
DeepSeek-R1 Thoughtology: Let's think about LLM Reasoning
2025
Cited
0
Exploiting Instruction-Following Retrievers for Malicious Information Retrieval
2025
Cited
0
SafeArena: Evaluating the Safety of Autonomous Web Agents
2025
Cited
0
Societal Alignment Frameworks Can Improve LLM Alignment
2025
Cited
0
Investigating Adversarial Trigger Transfer in Large Language Models
2024
Cited
6
Resume
Academic Achievements
  • ICML 2025: Co-first author of 'SafeArena: Evaluating Safety in Autonomous Web Agents'
  • TACL 2025: Published 'Investigating Adversarial Trigger Transfer in Large Language Models'
  • Findings of EMNLP 2023: Published 'Using In-Context Learning to Improve Dialogue Safety'
  • ACL 2022: Published 'An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models'
  • Presenting work at ICML 2025 and ACL 2025