Skip to content

Allow LLM use with required attribution while increasing the weight of proctored assessments with retakes to guard against over-reliance

Design · All designs
Evidence · 2 claims (1 for, 1 mixed) · 1 study (1 design), q2 · 0 of 1 report an effect size · 2 claims rest on one study

Description

Rather than banning or unconditionally allowing LLMs, the course permits their use with a required attribution statement on every code file, while grade weight shifts from programming assignments to proctored assessments with retakes. The authors state this approach "allows the use of LLMs but with assessment design to provide guardrails against over-reliance," so students can still meet learning objectives without assistance. The attribution statement's final sentence makes students responsible for completing work unassisted.

Design Implications

Context

Requirements

  • In-class proctored retakes of each test, with question banks of assignment-aligned questions created over a summer with UTA support
  • Office-hours test review with a TA or instructor after the first attempt

Constraints

  • Assessment alignment with programming assignments is course specific and time-intensive; generating question variations was not reliable without oversight

Target Learners

  • undergraduate CS2 students
  • instructors of large introductory programming courses

Learning Goals

  • independent mastery of course learning outcomes
  • responsible and documented LLM use
  • independent comprehension of assignment skills

Claims

Examples

-

Key Sources

  • Margaret Ellis, Nikitha Donekal Chandrashekar, Sehrish Basir Nizamani, Mohammed Farghally, Jake O'Brien, and Naren Ramakrishnan. (2026). Demystify, Use, Reflect, Assess (DURA): An Experience Report on LLM Integration in CS2. arXiv. https://arxiv.org/abs/2606.30908
Page metadata
Field Value
type design
id llm-attribution-with-proctored-retake-guardrail
title Allow LLM use with required attribution while increasing the weight of proctored assessments with retakes to guard against over-reliance
description Rather than banning or unconditionally allowing LLMs, the course permits their use with a required attribution statement on every code file, while grade weight shifts from programming assignments to proctored assessme...
status review
generated by process:settle-candidates on 2026-10-10
trust unverified — no one has confirmed this page's content
sources 1 — margaret-ellis-2026

Frontmatter is the page's machine-readable record — see the Schema & Guide.