About

Zachary A. Pardos is an Associate Professor of Education at UC Berkeley, specializing in adaptive learning and artificial intelligence. His research focuses on knowledge representation and recommender systems aimed at increasing upward mobility in postsecondary education through the analysis of behavioral and semantic data. He earned his PhD in Computer Science from Worcester Polytechnic Institute, where his dissertation centered on computational models of cognitive mastery. His academic journey includes a postdoctoral position at MIT, and he currently directs the Computational Approaches to Human Learning research lab at UC Berkeley. In addition to teaching in the data science undergraduate program, he is an affiliated faculty member in Cognitive Science. His work involves developing educational technology tools and systems, such as open-source adaptive tutoring platforms, and exploring AI-driven approaches to improve educational outcomes.

Research topics

• Computer Science
• Data Mining
• Mathematics
• World Wide Web
• Psychology
• Mathematics education
• Data science
• Engineering
• Human–computer interaction

Selected publications

• Strengthening Course Transfer Pathways Using Graph-Theoretic Articulation Networks

  2026-04-25

  articleOpen accessSenior author

  Academic pathway research investigates how students navigate their postsecondary education over time to support academic attainment and equitable learning experiences. In this context, upward transfer from two-year to four-year institutions is critical for bachelor’s degree attainment, yet the process of manually establishing course equivalencies (i.e., articulation) to facilitate this transfer remains labor-intensive. This study contributes systematic evaluations of how existing human-curated articulation agreements can be leveraged for data-assistive course-to-course articulation within an interpretable graph-theoretic framework. Specifically, we construct Articulation Networks using articulation data between California community colleges and universities to identify and rank candidate course equivalencies based on node-similarity measures. Analyzing data from over 56,000 courses, we find that among the evaluated similarity measures, Personalized PageRank achieves the highest accuracy–approaching the recall upper bound imposed by the graph structure–and outperforms course title text similarity baselines. Further, we demonstrate how the network approach can integrate additional information, such as the Course Identification Numbering (C-ID) system, to improve equivalency recommendations and support the assignment of appropriate C-ID designations for community college courses. Our findings highlight how network-based methods can serve as a valuable resource to support faculty and policymakers in streamlining course-equivalency decisions and strengthening pathways for transfer students.

  PublisherDOI

• Survey of Computerized Adaptive Testing: a Machine Learning Perspective

  IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-01-01 · 1 citations

  article

  Computerized Adaptive Testing (CAT) offers an efficient and personalized method for assessing examinee proficiency by dynamically adjusting test questions based on individual performance. Compared to traditional, non-personalized testing methods, CAT requires fewer questions and provides more accurate assessments. As a result, CAT has been widely adopted across various fields, including education, healthcare, sports, sociology, and the evaluation of AI models. While traditional methods rely on psychometrics and statistics, the increasing complexity of large-scale testing has spurred the integration of machine learning techniques. This paper aims to provide a machine learning-focused survey on CAT, presenting a fresh perspective on this adaptive testing paradigm. We delve into measurement models, question selection algorithm, bank construction, and test control within CAT, exploring how machine learning can optimize these components. Through an analysis of current methods, strengths, limitations, and challenges, we strive to develop robust, fair, and efficient CAT systems. By bridging psychometric-driven CAT research with machine learning, this survey advocates for a more inclusive and interdisciplinary approach to the future of adaptive testing.

  PublisherDOI

• The Future of Feedback: How Can AI Help Transform Feedback to Be More Engaging, Effective, and Scalable?

  arXiv (Cornell University) · 2026-03-12

  preprintOpen access

  With digital learning environments becoming more prevalent, the ease with which generative AI enables the scalable production of real-time, automated feedback holds the potential to reshape learning and teaching experiences. This meeting report synthesizes the interdisciplinary perspectives of 50 scholars from educational psychology, computer science, science education, and the learning sciences on the use of generative AI for feedback and its promises and risks in educational practice. We highlight points of convergence in the scholarship, identify areas of debate and unresolved challenges, and outline open questions and future directions for research and educational practice that emerged from structured small-group activities designed to bridge disciplinary barriers.

  PublisherDOI

• PromptHive: Demonstrating Collaborative, Human-Centered OER Creation with LLMs

  2025-07-17

  articleSenior author
  PublisherDOI

• AI-Augmented Advising

  Journal of Learning Analytics · 2025-03-14 · 5 citations

  articleOpen accessSenior author

  Choosing an undergraduate major is an important decision that impacts academic and career outcomes. In this work, we investigate augmenting personalized human advising for major selection using a large language model (LLM), GPT-4. Through a three-phase survey, we compare GPT suggestions and responses for undeclared first- and second-year students (n = 33) to expert responses from university advisors (n = 25). Undeclared students were first surveyed on their interests and goals. These responses were then given to both campus advisors and GPT to produce a major recommendation for each student. In the case of GPT, information about the majors offered on campus was added to the prompt. Overall, advisors rated the recommendations of GPT to be highly helpful (4.0 out of 5 on its explanation for the recommendation and 3.8 on its answers to individual student questions) and agreed with its recommendations 33% of the time. Additionally, we observe more agreement with AI’s major recommendations when advisors see the AI recommendations before making their own. However, this result was not statistically significant. We categorize qualitative feedback from advisors with an affinity diagram and outline five design implications for future AI-assisted academic advising systems. The results provide a first signal as to the viability of LLMs for personalized major recommendation and shed light on the promise and limitations of AI for advising support.

  PublisherOA PDFDOI

• When LLMs Hallucinate: Examining the Effects of Erroneous Feedback in Math Tutoring Systems

  2025-07-17 · 4 citations

  articleSenior author
  PublisherDOI

• PromptHive: Demonstrating Collaborative, Human-Centered OER Creation with LLMs

  Lecture notes in computer science · 2025-09-02

  book-chapter1st authorCorresponding
  PublisherDOI

• Generating Change: AI as an Opportunity to Address Long-Standing OER Challenges

  Lecture notes in computer science · 2025-09-02

  book-chapterSenior author
  PublisherDOI

• Temperature is All You Need: Approximating Human Mathematics Hint Efficacy with LLMs

  Lecture notes in computer science · 2025-09-02

  book-chapter1st authorCorresponding
  PublisherDOI

• Adaptive Tutoring Goes to Sweden: Machine Translation and Alignment of English OERs to a Swedish Calculus Course

  2025-07-17

  articleSenior author

  Adaptive tutoring systems have demonstrated significant improvements in math learning, yet their adoption outside of the United States remains limited. The absence of these technologies, along with a lack of research on localizing tutoring systems to different educational contexts, presents a significant barrier for institutions seeking to integrate these tools into their classrooms to support students' math learning. This paper presents a case study on the localization and deployment of OATutor, an adaptive tutoring system developed in the U.S., for use in a math course at KTH Royal Institute of Technology in Sweden. Our study explores using artificial intelligence to automate and validate this process, focusing on translation and syllabus adaptation to ensure the content aligns with the course curriculum and the Swedish educational context. We successfully deployed the system in the course, demonstrating a novel method for translating math content and providing an analysis of syllabus adaptation tailored to the local context. By documenting this process, we contribute to the broader effort to make educational technologies more accessible to diverse learner populations by providing a scalable approach to localization.

  PublisherDOI

Recent grants

• Collaborative Research: Personalizing Recommendations in a Large-scale Education Analytics Pipeline

  NSF · $100k · 2015–2020

• BIGDATA: EAGER: Deep Learning in Higher Education Big Data to Explore Latent Student Archetypes and Knowledge Profiles

  NSF · $290k · 2015–2019

Frequent coauthors

• Neil T. Heffernan

  Worcester Polytechnic Institute

  36 shared

• Ting-Chuen Pong

  Hong Kong University of Science and Technology

  25 shared

• Russ Meier

  Milwaukee School of Engineering

  25 shared

• Kerrie Douglas

  Purdue University West Lafayette

  25 shared

• Kristina Wilson

  25 shared

• Dhawal Shah

  University of California, Berkeley

  25 shared

• Steven Tang

  16 shared

• Weijie Jiang

  Tsinghua University

  12 shared

Labs

• Graduate Group in Cognitive SciencePI

Awards & honors

• National Science Foundation Fellowship (GK-12)
• best short paper award (2024)
• best paper nominated (2023)