Verifix: Verified Repair of Programming Assignments

06/30/2021
by   Umair Z. Ahmed, et al.
0

Automated feedback generation for introductory programming assignments is useful for programming education. Most works try to generate feedback to correct a student program by comparing its behavior with an instructor's reference program on selected tests. In this work, our aim is to generate verifiably correct program repairs as student feedback. The student assignment is aligned and composed with a reference solution in terms of control flow, and differences in data variables are automatically summarized via predicates to relate the variable names. Failed verification attempts for the equivalence of the two programs are exploited to obtain a collection of maxSMT queries, whose solutions point to repairs of the student assignment. We have conducted experiments on student assignments curated from a widely deployed intelligent tutoring system. Our results indicate that we can generate verified feedback in up to 58 able to generate a verified feedback, which is then usable by novice students with high confidence.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/08/2012

Automated Feedback Generation for Introductory Programming Assignments

We present a new method for automatically providing feedback for introdu...
research
11/15/2020

Model-Driven Synthesis for Programming Tutors

When giving automated feedback to a student working on a beginner's exer...
research
06/30/2023

Large Language Models (GPT) for automating feedback on programming assignments

Addressing the challenge of generating personalized feedback for program...
research
03/24/2021

Discovering Multiple Design Approaches in Programming Assignment Submissions

In this paper, we present a novel approach of automated evaluation of pr...
research
10/15/2020

Program Equivalence for Assisted Grading of Functional Programs (Extended Version)

In courses that involve programming assignments, giving meaningful feedb...
research
03/05/2018

Natural Deduction and the Isabelle Proof Assistant

We describe our Natural Deduction Assistant (NaDeA) and the interfaces b...
research
01/24/2023

Generating High-Precision Feedback for Programming Syntax Errors using Large Language Models

Large language models (LLMs), such as Codex, hold great promise in enhan...

Please sign up or login with your details

Forgot password? Click here to reset