Zia Qi

Biographic Data

ID4446249
NAMEZia Qi
GIVEN NAMESZia
FAMILY NAMEQi
SIGNATUREQI Z
AFFILIATIONSUniversity of Michigan
ORCID0009-0001-2159-8713
VERIFIEDYes
TOTAL WORKS8
TOTAL CITATIONS5
AUTHOR COUNT8
EDITOR COUNT0
FIRST PUBLICATION YEAR2023
LATEST PUBLICATION YEAR2026
H-INDEX1

  • Parental Cooperation from Swiss Child Protection Reports

    Open AccessDragan Stoll, Brian E Perron et al.ARTICLEResearch on Social Work Practice2026

    Purpose: Assessing parental cooperation during child protection services (CPSs) interventions raises distinctive analytical challenges due to ambiguous, conflicting information. We compared reasoning language models (RLMs) to retrieval-augmented generation (RAG) in classifying parental cooperation from Swiss CPS reports. Methods: RLMs of three parameter sizes (255B, 32B, 4B) were benchmarked against a RAG-based approach using a consensus dataset …

  • AI-Assisted Curation of Conference Scholarship

    Open AccessBrian E Perron, Bryan G Victor et al.ARTICLEJournal of the Society for Social…2026References: 1

  • Evolution of Social Work Knowledge Production Over 35 Years

    Open AccessBrian E Perron, B PERRON et al.ARTICLEResearch on Social Work Practice2026References: 6

    Purpose: This study developed a comprehensive bibliographic infrastructure addressing systematic coverage gaps in social work literature indexing and examined disciplinary knowledge production patterns from 1989 to 2025. Method: Article metadata was compiled from Web of Science, Scopus, Directory of Open Access Journals, and web scraping. A small language model performed classification and extraction tasks on abstracts. Results: Analysis of 62,60…

  • Theoretical and Methodological Shifts in Social Work Research

    Open AccessBrian E Perron, Zia QiARTICLEResearch on Social Work Practice2025Cited by: 1References: 1

    Purpose: This study empirically documents temporal patterns in social work research's engagement with postmodern and critical theory (P/CT) frameworks. Methods: Large language models (LLMs) were used to analyze 19,134 conference abstracts presented at the Society for Social Work and Research (2012–2025) for P/CT alignment and methodology. Multimodel evaluation demonstrated excellent reliability across six frontier LLMs (kappa = .73). Results: Tem…

  • Artificial Intelligence and Cultural Context

    Open AccessZia Qi, Brian E Perron et al.ARTICLEJournal of the Society for Social…2025References: 17

    Objective: This study examines how well leading Chinese and Western large language models (LLMs) understand and apply Chinese social work principles, testing whether cultural context influences model reasoning and accuracy in non-Western professional settings. Method: Using the Chinese National Social Work Examination covering jurisprudence and applied knowledge, we administered three testing conditions to eight cloud-based LLMs—four Chinese and …

  • Demystifying Application Programming Interfaces (APIs)

    Open AccessBrian E Perron, H Luan et al.ARTICLEJournal of the Society for Social…2025Cited by: 3References: 1

  • A Primer on Word Embeddings

    Open AccessBrian E Perron, Kelley A Rivenburgh et al.ARTICLEJournal of the Society for Social…2025References: 3

  • Construct-Irrelevant Variance on the ASWB Clinical Social Work Licensing Exam

    Open AccessBryan G Victor, Kellan Mcnally et al.ARTICLEResearch on Social Work Practice2023Cited by: 1References: 1

    Purpose: This study sought to replicate a previous investigation of construct-irrelevant variance on the Association of Social Work Boards (ASWB) clinical licensing exam completed by Albright and Thyer over a decade ago. Method: The performance of ChatGPT was assessed on a modified version of 50 newly developed clinical exam questions currently distributed by the ASWB, where only the four multiple-choice options for each item were presented witho…