Dajun Yuan
Dajun Yuan has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Chantelle Wu
Khoury College of Computer Sciences, Northeastern University, Vancouver, British Columbia, Canada
1 shared publication - Jiahuan He
Northeastern University
1 shared publication - Meida Li
Khoury College of Computer Sciences, Northeastern University, Vancouver, British Columbia, Canada
1 shared publication - Mengxu Pan
Khoury College of Computer Sciences, Northeastern University, Vancouver, British Columbia, Canada
1 shared publication - Mirjana Prpa
Computational Media and Arts, The Hong Kong University of Science and Technology (GZ), Guangzhou, China
1 shared publication - Mona Ali
Faculty of Computing and Informatics, Suez Canal University, Edmonton, Alberta, Canada
1 shared publication
Latest Publications
- Open Access
- 13 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 2371-2391
Understanding Down Syndrome Stereotypes in LLM-Based Personas
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.
- 13 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 2371-2391
Open AccessUnderstanding Down Syndrome Stereotypes in LLM-Based Personas
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.