Towards Scalable AI Feedback Systems: Preparing A Turing-Test-Inspired Experiment

Peter A.M. Ruijten-Dodoiu; Manuel Oliveira; Esther Ventura-Medina

Towards Scalable AI Feedback Systems: Preparing A Turing-Test-Inspired Experiment

Peter A.M. Ruijten-Dodoiu
, Manuel Oliveira (Corresponding author)
, Esther Ventura-Medina

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

64 Downloads (Pure)

Abstract

Generative AI (GenAI) is increasingly positioned as a transformative tool in education. This work explores how GenAI can enhance reflective practices to foster growth mindsets-an essential trait for resilience, motivation, and lifelong learning. Drawing on frameworks for process-oriented education and ongoing experimentation, we propose an approach leveraging prompt engineering and fine-tuning to create human-like, iterative feedback on student reflections. To evaluate this, a Turing-test-style experiment is designed to assess whether students can differentiate between AI- and human-generated feedback. By addressing challenges such as feedback scalability, ethical transparency, and student trust, we hope to find ways to design more adaptive, inclusive, and growth-focused educational ecosystems.

Original language	English
Title of host publication	GenAI-LA 2025 Generative AI for Learning Analytics 2025
Subtitle of host publication	Proceedings of the Second International Workshop on Generative AI for Learning Analytics co-located with the 15th International Conference on Learning Analytics and Knowledge (LAK 2025) Dublin, Ireland, March 3, 2025
Editors	Lixiang Yan, Andy Nguyen, Ryan Baker
Publisher	CEUR-WS.org
Pages	60-64
Number of pages	5
Publication status	Published - 2025
Event	GenAI-LA 2025 Generative AI for Learning Analytics 2025 : 2nd International Workshop on Generative AI for Learning Analytics co-located with the 15th International Conference on Learning Analytics and Knowledge (LAK 2025) - Dublin, Ireland Duration: 3 Mar 2025 → 3 Mar 2025 Conference number: 2

Publication series

Name	CEUR Workshop Proceedings
Volume	3994
ISSN (Print)	1613-0073

Conference

Conference	GenAI-LA 2025 Generative AI for Learning Analytics 2025
Abbreviated title	GenAI-LA 2025
Country/Territory	Ireland
City	Dublin
Period	3/03/25 → 3/03/25

Bibliographical note

Publisher Copyright:
© 2025 Copyright for this paper by its authors.

Keywords

Generative AI
Growth Mindsets
Reflective Feedback
Turing Test

Access to Document

pdfFinal published version, 997 KB

https://ceur-ws.org/Vol-3994/short3.pdf

Cite this

Ruijten-Dodoiu, P. A. M., Oliveira, M., & Ventura-Medina, E. (2025). Towards Scalable AI Feedback Systems: Preparing A Turing-Test-Inspired Experiment. In L. Yan, A. Nguyen, & R. Baker (Eds.), GenAI-LA 2025 Generative AI for Learning Analytics 2025: Proceedings of the Second International Workshop on Generative AI for Learning Analytics co-located with the 15th International Conference on Learning Analytics and Knowledge (LAK 2025) Dublin, Ireland, March 3, 2025 (pp. 60-64). (CEUR Workshop Proceedings; Vol. 3994). CEUR-WS.org. https://ceur-ws.org/Vol-3994/short3.pdf

Ruijten-Dodoiu, Peter A.M. ; Oliveira, Manuel ; Ventura-Medina, Esther. / Towards Scalable AI Feedback Systems : Preparing A Turing-Test-Inspired Experiment. GenAI-LA 2025 Generative AI for Learning Analytics 2025: Proceedings of the Second International Workshop on Generative AI for Learning Analytics co-located with the 15th International Conference on Learning Analytics and Knowledge (LAK 2025) Dublin, Ireland, March 3, 2025. editor / Lixiang Yan ; Andy Nguyen ; Ryan Baker. CEUR-WS.org, 2025. pp. 60-64 (CEUR Workshop Proceedings).

@inproceedings{5b80f20bbce34851a6583998581e5f61,

title = "Towards Scalable AI Feedback Systems: Preparing A Turing-Test-Inspired Experiment",

abstract = "Generative AI (GenAI) is increasingly positioned as a transformative tool in education. This work explores how GenAI can enhance reflective practices to foster growth mindsets-an essential trait for resilience, motivation, and lifelong learning. Drawing on frameworks for process-oriented education and ongoing experimentation, we propose an approach leveraging prompt engineering and fine-tuning to create human-like, iterative feedback on student reflections. To evaluate this, a Turing-test-style experiment is designed to assess whether students can differentiate between AI- and human-generated feedback. By addressing challenges such as feedback scalability, ethical transparency, and student trust, we hope to find ways to design more adaptive, inclusive, and growth-focused educational ecosystems.",

keywords = "Generative AI, Growth Mindsets, Reflective Feedback, Turing Test",

author = "Ruijten-Dodoiu, \{Peter A.M.\} and Manuel Oliveira and Esther Ventura-Medina",

note = "Publisher Copyright: {\textcopyright} 2025 Copyright for this paper by its authors.; GenAI-LA 2025 Generative AI for Learning Analytics 2025<br/> : 2nd International Workshop on Generative AI for Learning Analytics co-located with the 15th International Conference on Learning Analytics and Knowledge (LAK 2025), GenAI-LA 2025 ; Conference date: 03-03-2025 Through 03-03-2025",

year = "2025",

language = "English",

series = "CEUR Workshop Proceedings",

publisher = "CEUR-WS.org",

pages = "60--64",

editor = "Lixiang Yan and Andy Nguyen and Ryan Baker",

booktitle = "GenAI-LA 2025 Generative AI for Learning Analytics 2025",

}

Ruijten-Dodoiu, PAM , Oliveira, M & Ventura-Medina, E 2025, Towards Scalable AI Feedback Systems: Preparing A Turing-Test-Inspired Experiment. in L Yan, A Nguyen & R Baker (eds), GenAI-LA 2025 Generative AI for Learning Analytics 2025: Proceedings of the Second International Workshop on Generative AI for Learning Analytics co-located with the 15th International Conference on Learning Analytics and Knowledge (LAK 2025) Dublin, Ireland, March 3, 2025. CEUR Workshop Proceedings, vol. 3994, CEUR-WS.org, pp. 60-64, GenAI-LA 2025 Generative AI for Learning Analytics 2025
, Dublin, Ireland, 3/03/25. <https://ceur-ws.org/Vol-3994/short3.pdf>

Towards Scalable AI Feedback Systems: Preparing A Turing-Test-Inspired Experiment. / Ruijten-Dodoiu, Peter A.M.; Oliveira, Manuel (Corresponding author); Ventura-Medina, Esther.
GenAI-LA 2025 Generative AI for Learning Analytics 2025: Proceedings of the Second International Workshop on Generative AI for Learning Analytics co-located with the 15th International Conference on Learning Analytics and Knowledge (LAK 2025) Dublin, Ireland, March 3, 2025. ed. / Lixiang Yan; Andy Nguyen; Ryan Baker. CEUR-WS.org, 2025. p. 60-64 (CEUR Workshop Proceedings; Vol. 3994).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Towards Scalable AI Feedback Systems

T2 - GenAI-LA 2025 Generative AI for Learning Analytics 2025<br/>

AU - Ruijten-Dodoiu, Peter A.M.

AU - Oliveira, Manuel

AU - Ventura-Medina, Esther

N1 - Conference code: 2

PY - 2025

Y1 - 2025

N2 - Generative AI (GenAI) is increasingly positioned as a transformative tool in education. This work explores how GenAI can enhance reflective practices to foster growth mindsets-an essential trait for resilience, motivation, and lifelong learning. Drawing on frameworks for process-oriented education and ongoing experimentation, we propose an approach leveraging prompt engineering and fine-tuning to create human-like, iterative feedback on student reflections. To evaluate this, a Turing-test-style experiment is designed to assess whether students can differentiate between AI- and human-generated feedback. By addressing challenges such as feedback scalability, ethical transparency, and student trust, we hope to find ways to design more adaptive, inclusive, and growth-focused educational ecosystems.

AB - Generative AI (GenAI) is increasingly positioned as a transformative tool in education. This work explores how GenAI can enhance reflective practices to foster growth mindsets-an essential trait for resilience, motivation, and lifelong learning. Drawing on frameworks for process-oriented education and ongoing experimentation, we propose an approach leveraging prompt engineering and fine-tuning to create human-like, iterative feedback on student reflections. To evaluate this, a Turing-test-style experiment is designed to assess whether students can differentiate between AI- and human-generated feedback. By addressing challenges such as feedback scalability, ethical transparency, and student trust, we hope to find ways to design more adaptive, inclusive, and growth-focused educational ecosystems.

KW - Generative AI

KW - Growth Mindsets

KW - Reflective Feedback

KW - Turing Test

UR - https://www.scopus.com/pages/publications/105011271489

M3 - Conference contribution

AN - SCOPUS:105011271489

T3 - CEUR Workshop Proceedings

SP - 60

EP - 64

BT - GenAI-LA 2025 Generative AI for Learning Analytics 2025

A2 - Yan, Lixiang

A2 - Nguyen, Andy

A2 - Baker, Ryan

PB - CEUR-WS.org

Y2 - 3 March 2025 through 3 March 2025

ER -

Ruijten-Dodoiu PAM , Oliveira M , Ventura-Medina E. Towards Scalable AI Feedback Systems: Preparing A Turing-Test-Inspired Experiment. In Yan L, Nguyen A, Baker R, editors, GenAI-LA 2025 Generative AI for Learning Analytics 2025: Proceedings of the Second International Workshop on Generative AI for Learning Analytics co-located with the 15th International Conference on Learning Analytics and Knowledge (LAK 2025) Dublin, Ireland, March 3, 2025. CEUR-WS.org. 2025. p. 60-64. (CEUR Workshop Proceedings).

Towards Scalable AI Feedback Systems: Preparing A Turing-Test-Inspired Experiment

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this