Login

2026 ASEE Annual Conference & Exposition

Using Generative AI to Enhance Community Support for Alternative Grading Practices

Presented at DSAI-Session 8: Generative AI in Assessment, Grading, and Accreditation

Computing and engineering educators are increasingly adopting alternative grading practices to foster more supportive and successful learning environments. These practices de-emphasize the traditional focus on points, empowering students to demonstrate mastery of learning outcomes with greater clarity and reduced stress. The Playbook of Equitable Grading Practices is an open-source community effort to support this transition, but many contributions suffer from inconsistent structural quality and a lack of concrete implementation detail. This paper introduces a transferable, three-phase framework for using Generative AI (GenAI) to systematically evaluate, enhance, and expand structured educational documentation. The method comprises: (1) the iterative calibration of a GenAI-based rubric against expert quality standards, first on a six-play pilot set and then across all thirty community-contributed plays; (2) the enhancement of documentation through source-grounded extraction of missing methodological details; and (3) the discovery of novel grading mechanisms via an exclusion-based discovery strategy designed to overcome search bias. Experimental results demonstrate that the calibrated evaluator attained 85.3% section-level agreement (within ±1) with expert judgments. Significant quality improvements were observed in practitioner-oriented sections, such as “How to Implement” and “Applicability,” where documentation was previously most deficient. This work contributes a reproducible calibration strategy for “LLM-as-a-Judge” applications and demonstrates that GenAI can serve as a collaborative editor that lowers the barrier to high-quality documentation meeting structural quality criteria, provided it is constrained by rigorous source grounding and human review to maintain authentic practitioner voice.

Authors
  1. Mr. Abhinav Menon Virginia Polytechnic Institute and State University [biography]
  2. Prof. Stephen H Edwards Orcid 16x16http://orcid.org/https://0000-0002-5162-9314 Virginia Polytechnic Institute and State University [biography]
  3. Bob Edmison Virginia Polytechnic Institute and State University [biography]
  4. Dr. Adrienne Decker Orcid 16x16http://orcid.org/0000-0002-0822-4813 University at Buffalo, The State University of New York [biography]
  6. Audrey Rorrer Orcid 16x16http://orcid.org/0000-0003-0600-6545 University of North Carolina at Charlotte [biography]
Note

The full paper will be available to logged in and registered conference attendees once the conference starts on June 21, 2026, and to all visitors after the conference ends on June 24, 2026

« View session

For those interested in:

  • computer science
  • information technology
  • undergraduate