avatar

Nicholas Meade

PhD Candidate
McGill University and Mila
nicholas.meade (at) mail.mcgill.ca

About Me

I am a PhD Candidate at McGill University and Mila supervised by Siva Reddy. I previously completed my undergraduate degree at Dalhousie University in Computer Science where I worked with Sageev Oore. At Dalhousie, I worked on conditional music generation. During my studies, I have interned at Amazon Alexa AI where I worked with Spandana Gella and Devamanyu Hazarika.

News

July 2025 I'll be attending ICML 2025 in Vancouver to present our work on LLM-based web agent safety.
July 2025 I'll be attending ACL 2025 in Vienna to present our work investigating adversarial trigger transfer.
April 2025 I'm attending the Safety-Guranteed LLMs Workshop.
March 2025 I'm a visiting graduate student at the Simons Institute for their Special Year on Large Language Models and Transformers.
April 2024 I'm attending the Bellairs Invitational Workshop on Contemporary, Foreseeable and Catastrophic Risks of Large Language Models

Selected Papers

  1. ICML
    SafeArena: Evaluating Safety in Autonomous Web Agents
    Ada Defne Tur*, Nicholas Meade*, Xing Han Lù*, Alejandra Zambrano, Arkil Patel, Esin Durmus, Spandana Gella, Karolina Stańczak, Siva Reddy
    ICML 2025
    PDF Code Tweet

  2. TACL
    Investigating Adversarial Trigger Transfer in Large Language Models
    Nicholas Meade, Arkil Patel, Siva Reddy
    TACL 2025
    PDF Code Tweet

  3. EMNLP
    Using In-Context Learning to Improve Dialogue Safety
    Nicholas Meade, Spandana Gella, Devamanyu Hazarika, Prakhar Gupta, Di Jin, Siva Reddy, Yang Liu, Dilek Hakkani-Tür
    Findings of EMNLP 2023
    PDF Tweet

  4. ACL
    An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models
    Nicholas Meade, Elinor Poole-Dayan, Siva Reddy
    ACL 2022
    PDF Code Tweet