Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2606.08807

A Classroom Study of LLM-Generated Feedback Intervention in Introductory Programming

Hasnain Heickal·Andrew Lan
View original source ↗Read source document ↗Export metadata ↓

Abstract

Large language models (LLMs) are increasingly used to provide automated feedback in introductory programming courses, yet empirical evidence from authentic classroom deployments comparing different feedback modalities remains limited. In this work, we present a large-scale classroom study in which AI-generated feedback was deployed through a randomized protocol in an introductory Python programming course. Students received one of three feedback conditions on incorrect submissions: natural language hints, AI-generated failing test cases, or no AI feedback. We release the resulting dataset, ProgFeed, which captures 6,693 submissions from 215 consenting students across 17 labs, including feedback conditions, execution-based performance measures, and fine-grained temporal information. Using this data, we analyze learning trajectories, feedback quality, and submission behavior over repeated attempts. We find that natural language feedback is significantly associated with higher completion rates and faster convergence to correct solutions. Test case feedback, by contrast, exhibits heterogeneous effects that depend critically on feedback validity. Our results suggest that the form of AI-generated feedback matters, and that evaluating feedback quality -- not just its presence -- is essential for understanding its pedagogical impact.

Explore related subjects

cs.CY

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Hasnain Heickal, Andrew Lan. 2026-06-07. A Classroom Study of LLM-Generated Feedback Intervention in Introductory Programming. https://arxiv.org/abs/2606.08807

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Printed but not benchmarkable: most building-decarbonisation disclosure cannot be matched to the pathways that stranding regulation assumes

Cities are beginning to enforce carbon limits on existing buildings. Science-based decarbonisation pathways set those limits one asset type and one jurisdiction at a time. Owners, however, report for the whole firm. We measure what that mismatch costs on two sets of public corporate reports: a census of 502 reports from the 119 listed built-environment firms with a collected report inside a 2,246-firm panel (2003-2023), and 519 real-estate reports from 101 firms (2007-2024). BeDA, a multimodal language-model tool whose reliability we test first, read them. Running the pathway frameworks' own entry tests over published disclosure: 16.5% of census reports (43.7% of real-estate reports) print an operational carbon intensity per square metre; 6.6% (25.0%) can be matched to a pathway for their property type in a covered jurisdiction; and only 5.0% (16.4%) disclose the floor area they divided by. Of the failures at the pathway test, 82-84% follow from reports lumping the portfolio together and 16-18% from a missing curve in the pathway library. The obstacle is the reporting unit, not missing data. The rate is roughly twice as high for European as for US listings (65-71% versus 35% in listed real estate). We also show that a US portfolio's carbon verdict cannot be worked out from disclosure at all. Within one climate zone, the pathway's carbon limit varies by up to 2.79-fold with the electricity subregion, which no report names; its energy limit does not move. Extraction is checked against the source PDFs (97.3% of extracted intensities appear verbatim) and repeats on a second extractor (kappa = 0.97). Recall of the non-disclosing class was 95.1% in a blinded hand audit of 122 reports. The fix follows from the measurement: split intensity by asset type and jurisdiction, and report floor area.

cs.CY↗
arXiv2026

Incipit: Axiom-Grounded Scaffolding for Human-AI Literary Creation

Large language models can produce fluent prose from short prompts, but a direct interaction gives writers little access to the assumptions that shape a long narrative. We present Incipit, an implemented research prototype that inserts an explicit planning layer between writer intent and generated prose. The layer is grounded in literary axioms, which are curated and reusable propositions about human experience and narrative craft. The prototype connects a knowledge base of 1455 axioms and 472 typed relationships to a five round direction dialogue, a retrieval and selection pipeline, and a three level blueprint covering creative premises, story beats, character arcs, and chapter outlines. Writers can inspect and edit the resulting structures before using them as context for scene generation. Additional modules support real event abstraction and five dimensional diagnostic feedback. We describe the design rationale, data flow, implementation boundaries, and a worked design example. Because no controlled user study or independently rated output study has yet been completed, we do not claim that the system improves literary quality. Instead, we outline a future preregistered comparison designed to distinguish the contribution of axiom grounding from that of hierarchical planning. The paper contributes a concrete architecture for making literary knowledge an inspectable coordination object in human AI writing.

cs.CY↗
arXiv2026

Automating Constructive Assessment with Large Language Models: Toward Scalable and Repeated Evaluation of Practical Competence

This study aimed to automate hierarchical diagnostic reasoning (HDR), a constructive method for evaluating practical judgment skills, by developing and testing an evaluation process using a large language model. HDR is a descriptive task that measures higher-order cognitive skills by requiring students to identify and explain errors in case-study-based problems. However, it requires expertise and effort to develop and evaluate. Hence, we proposed and empirically validated the automatic (1) generation of case problems containing errors aligned with educational intentions, (2) scoring of descriptive answers, and (3) generation of structured feedback based on incorrect answers, achieved solely through prompt design without fine-tuning. The internal consistency and construct validity of the generated problems were supported by the experimental score distribution and Cronbach's alpha (0.78). The agreement between automated and human ratings reached 100% under some conditions. The feedback was rated as being as convincing and useful as that from human instructors, demonstrating a practical framework for implementing HDR-based constructive assessment with reproducibility, immediacy, and low cost. The flexibility of large language models will also enable repeated and longitudinal assessments while maintaining structure, showing broad potential for application in educational settings.

cs.CY↗