# Exploring Student Behaviors and Motivations using AI TAs with Optional Guardrails

arXiv: https://arxiv.org/abs/2504.11146 · HTML: https://mlsanity.com/paper/2504.11146/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Safety alignment, refusal and guardrails, one of 12 directions in LLM safety and security.
- Builds on 19 of its 53 references that are in the map.
- First posted on arXiv 15 Apr 2025.

## Placed in

- LLM safety and security / [Safety alignment, refusal and guardrails](https://mlsanity.com/safety/safety-alignment-refusal-and-guardrails/)

## Builds on (most cited first, 19 of 19)

- [The Robots are Here: Navigating the Generative AI Revolution in Computing Education](https://mlsanity.com/paper/2310.00658/) (2023)
- [CodeAid: Evaluating a Classroom Deployment of an LLM-based Programming Assistant that Balances Student and Educator Needs](https://mlsanity.com/paper/2401.11314/) (2024)
- [CodeHelp: Using Large Language Models with Guardrails for Scalable Support in Programming Classes](https://mlsanity.com/paper/2308.06921/) (2023)
- [Computing Education in the Era of Generative AI](https://mlsanity.com/paper/2306.02608/) (2023)
- [The Widening Gap: The Benefits and Harms of Generative AI for Novice Programmers](https://mlsanity.com/paper/2405.17739/) (2024)
- [Exploring the Responses of Large Language Models to Beginner Programmers' Help Requests](https://mlsanity.com/paper/2306.05715/) (2023)
- [The Effects of Generative AI on Computing Students' Help-Seeking Preferences](https://mlsanity.com/paper/2401.02262/) (2024)
- [AI-TA: Towards an Intelligent Question-Answer Teaching Assistant using Open-Source LLMs](https://mlsanity.com/paper/2311.02775/) (2023)
- [Open Source Language Models Can Provide Feedback: Evaluating LLMs' Ability to Help Students Using GPT-4-As-A-Judge](https://mlsanity.com/paper/2405.05253/) (2024)
- [Desirable Characteristics for AI Teaching Assistants in Programming Education](https://mlsanity.com/paper/2405.14178/) (2024)
- [CS1-LLM: Integrating LLMs into CS1 Instruction](https://mlsanity.com/paper/2406.15379/) (2024)
- [Beyond the Hype: A Comprehensive Review of Current Trends in Generative AI Research, Teaching Practices, and Tools](https://mlsanity.com/paper/2412.14732/) (2024)
- [More Robots are Coming: Large Multimodal Models (ChatGPT) can Solve Visually Diverse Images of Parsons Problems](https://mlsanity.com/paper/2311.04926/) (2023)
- [Integrating AI Tutors in a Programming Course](https://mlsanity.com/paper/2407.15718/) (2024)
- [Oversight in Action: Experiences with Instructor-Moderated LLM Responses in an Online Discussion Forum](https://mlsanity.com/paper/2412.09048/) (2024)
- [Challenges Faced by Teaching Assistants in Computer Science Education Across Europe](https://mlsanity.com/paper/2207.11602/) (2022)
- [Howzat? Appealing to Expert Judgement for Evaluating Human and AI Next-Step Hints for Novice Programmers](https://mlsanity.com/paper/2411.18151/) (2024)
- [Seeing the Forest and the Trees: Solving Visual Graph and Tree Based Data Structure Problems using Large Multimodal Models](https://mlsanity.com/paper/2412.11088/) (2024)
- [Prompt Programming: A Platform for Dialogue-based Computational Problem Solving with Generative AI Models](https://mlsanity.com/paper/2503.04267/) (2025)

## Built on by (most cited first, 3 of 3)

- [Reflective Dialogue or Prompt Refinement? Effects of Tutor Scaffolding on Students' Independent LLM Use for Programming](https://mlsanity.com/paper/2607.03303/) (2026)
- [TutorTrace: A Dataset and Taxonomy for Classifying Learner Behavioral States during AI-Assisted Programming Education](https://mlsanity.com/paper/2608.26184/) (2026)
- [Guardrails or Roadblocks? Effects of Pedagogical Style and Context Awareness in AI Teaching Assistants for Programming](https://mlsanity.com/paper/2609.29995/) (2026)

## Abstract (arXiv)

AI-powered chatbots and digital teaching assistants (AI TAs) are gaining popularity in programming education, offering students timely and personalized feedback. Despite their potential benefits, concerns about student over-reliance and academic misconduct have prompted the introduction of "guardrails" into AI TAs - features that provide scaffolded support rather than direct solutions. However, overly restrictive guardrails may lead students to bypass these tools and use unconstrained AI models, where interactions are not observable, thus limiting our understanding of students' help-seeking behaviors. To investigate this, we designed and deployed a novel AI TA tool with optional guardrails in one lab of a large introductory programming course. As students completed three code writing and debugging tasks, they had the option to receive guardrailed help or use a "See Solution" feature which disabled the guardrails and generated a verbatim response from the underlying model. We investigate students' motivations and use of this feature and examine the association between usage and their course performance. We found that 50% of the 885 students used the "See Solution" feature for at least one problem and 14% used it for all three problems. Additionally, low-performing students were more likely to use this feature and use it close to the deadline as they started assignments later. The predominant factors that motivated students to disable the guardrails were assistance in solving problems, time pressure, lack of self-regulation, and curiosity. Our work provides insights into students' solution-seeking motivations and behaviors, which has implications for the design of AI TAs that balance pedagogical goals with student preferences.