Mengxu Pan

Mengxu Pan

Auto-generated profile, based on publicly available information

Mengxu Pan

Khoury College of Computer Sciences, Northeastern University, Vancouver, British Columbia, Canada

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications

13 April 2026
Verified
Conference Paper
Open access
MPMengxu Pan
Mengxu Pan
PLPanxin Liu
Panxin Liu
JZJinda Zhang
Jinda Zhang
RCRaina Cao
Raina Cao
VAViduni Ariyawansa
Viduni Ariyawansa
MPMirjana Prpa
Mirjana Prpa
Foreign language speaking anxiety (FLSA) poses a major challenge for English-language learners, suppressing confidence and triggering a cycle of avoidance that hinders language acquisition. To address this, we explored the use of LLM-based embodied conversational agents (ECA) in social virtual reality (VR), which provide personalized support and multimodal interaction in a contextualized environment. We developed three English-language learning scenarios in social VR and conducted a five-day mixed-methods study where participants (N=20) engaged in daily 30-minute role-play practice with an LLM-based ECA to evaluate the efficacy of the system. Quantitative results showed a significant reduction in self-reported FLAS after 3 days, along with subtle gains in speaking proficiency measures. Qualitatively, learners perceived increased confidence, attributing it to the LLM-based ECA’s non-judgmental stance, linguistic scaffolding, affective encouragement, and adaptive feedback. Our findings suggest the potential of LLM-based ECAs in social VR for language learning and offer considerations for future agent design.

13 June 2026
Verified
Conference Paper
Open access
CWChantelle Wu
Chantelle Wu
MPMengxu Pan
Mengxu Pan
PWPeinan Wang
Peinan Wang
NNNafi Nibras
Nafi Nibras
MLMeida Li
Meida Li
MPMirjana Prpa
Mirjana Prpa
We present a case study of Persona-L, a system that leverages large language models (LLMs) and retrieval-augmented generation (RAG) to model personas of people with Down syndrome. Existing approaches to persona creation can often lead to oversimplified or stereotypical profiles of people with Down syndrome. To that end, we built stereotype detection capabilities into Persona-L as a design probe to open conversations. We then conducted interviews with caregivers and healthcare professionals (N=10) to examine how Down syndrome stereotypes could manifest in the content and delivery of LLM outputs, and interface design. Our findings show the challenges in defining stereotypes, and reveal potential pathways where stereotypes could emerge, including the training data, LLM outputs and interface design. This highlights the need for participatory methods that capture the heterogeneity of lived experiences of people with Down syndrome.