Shuhaib Mehri

prof_pic.jpg

Hi 👋! I am a PhD Student at the University of Illinois Urbana-Champaign, advised by Prof. Dilek Hakkani-Tur.

I am interested in builing agents that know how to interact with users. My current work explores:

  • Multi-turn interactions: Loading… ⌛️.
  • Multi-session interactions: We introduced the first benchmark for multi-session collaboration, and demonstrated that equipping agents with memory can improve collaboration quality over time (through both simulated experiments and human studies) [tweet] [paper].
  • Reliable and realistic user simulation: We identified that user simulators struggle to consistently adhere to their assigned goals throughout multi-turn interactions, and introduced user goal state tracking to address this [tweet] [paper].

Before starting my PhD, I earned my BSc in Honours Computer Science from the University of British Columbia. I was fortunate to work with Prof. Vered Shwartz and Prof. Giuseppe Carenini. I also interned at Amazon (x3), iClinic Systems, and Clir Renewables.

news

Jan 04, 2026 Really excited to release the preprint for our work on improving multi-session collaboration with memory, check it out here.
Jan 04, 2026 Received news that our work on data synthesis has been accepted as an oral at EACL 2026 ✈️ See you in Morocco!
Dec 11, 2025 Came full circle with a visit to the UBC NLP Group (where my research journey began!) and gave a talk on goal alignment for LLM-based user simulators.
Sep 18, 2025 Our work on user simulator goal alignment has been accepted to TACL!
Jan 08, 2024 I was awarded the Mitacs Accelerate Fellowship for Master’s and PhD Students as an undergrad. Really excited to start working with iClinic Systems Inc.!

selected publications

  1. Learning User Preferences Through Interaction for Long-Term Collaboration
    Shuhaib Mehri, Priyanka Kargupta, Tal August, and Dilek Hakkani-Tür
    Preprint, 2026
  2. oral
    Goal alignment in llm-based user simulators for conversational ai
    Shuhaib Mehri, Xiaocheng Yang, Takyoung Kim, Gokhan Tur, Shikib Mehri, and Dilek Hakkani-Tür
    TACL 2025 (Oral at ACL 2026), 2025
  3. oral
    Beyond Sample-Level Feedback: Using Reference-Level Feedback to Guide Data Synthesis
    Shuhaib Mehri, Xiusi Chen, Heng Ji, and Dilek Hakkani-Tür
    EACL 2026 (Oral), 2025