publications

Research publications focused on human-centered AI safety and conversational agents.

2026

  1. scampilot.png
    ScamPilot: Simulating Conversations with LLMs to Protect Against Online Scams
    Owen Hoffman, Kangze Peng, Sajid Kamal, and 2 more authors
    In Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems (CHI ’26), Barcelona, Spain, Apr 2026
    Conditionally accepted; to appear at CHI ’26 (Apr. 13–17, 2026). DOI will be active upon publication.
    arXiv

2025

  1. Promoting Online Safety by Simulating Unsafe Conversations with LLMs
    Owen Hoffman, Kangze Peng, Zehua You, and 2 more authors
    Jul 2025
    Non-archival position paper; presented at the ACM 2025 Conference on Conversational User Interfaces Workshop on Personas Evolved: Designing Ethical LLM-Based Conversational Agent Personalities.
    DOI arXiv