Motivation: Undergraduate computing students increasingly turn to generative AI (GenAI) tools to understand abstract concepts through analogies. Analogies compare an unfamiliar concept to something familiar, but judging whether the comparison holds requires knowledge of both. GenAI may also embed assumptions about who the learner is. GenAI education research centers on output correctness, leaving students' critical reception of analogies largely unexamined. Method: We investigate how students evaluate the accuracy, appropriateness, and assumptions in GenAI-generated analogies, and their perceptions of interest-personalized versus generic technical explanations. Ten students with CS2 experience participated in a pre-survey, a think-aloud task with linked-list and recursion explanations, and a semi-structured interview grounded in the Paul-Elder framework. They judged accuracy, clarity, engagement, and trust separately. Results: Most participants described interest-personalized analogies as more engaging or memorable than generic technical explanations, while trust was mixed. Some trusted the tailored analogies more; others scrutinized them more closely or distrusted the tailoring. Participants with deep source-domain knowledge identified structural flaws requiring that knowledge to recognize. Because personalization and explanation format differed together, these findings do not isolate an effect of personalization alone. Implications: A familiar source flips the student's role. On the concept they are still learners, but on the familiar source they are the expert, and that is the position from which an analogy can be judged. We call this two-sided analogy auditing. GenAI systems should ask what students know, not just what interests them, and treat a flawed analogy as something to inspect and fix rather than accept.
Figures & tables
Figure 1. Study procedure. A pre-study survey informed the personalized analogies. Participants then evaluated four explanations (personalized and generic for linked lists and recursion), with explanation order counterbalanced within each concept, in a think-aloud task, followed by a semi-structured interview that opened with general background before turning to the study materials.
ID
Yr
Intended Major
Interests
P1
3
Computer Science and Statistics
Soccer; Avengers (film)
P2
2
Information Security and Computer Science
DaVinci Resolve (video editing); Valorant (game)
P3
2
Computer Science
Piano; Valorant (game)
P4
3
Computer Science and Statistics
Karate; Piano
P5
1
Computer Science
The Last of Us (game); Chess
P6
1
Computer Science and Applied Statistics
One Piece (manga/anime); Badminton
Table 1. Participant year, major, and interest domains used for personalized analogies. Odd-numbered participants were assigned to Condition A, even-numbered to Condition B.
Figure 2. Generic (left) and personalized (right) linked list explanations from the study. The personalized version incorporates a participant’s stated interest in One Piece , a long-running manga and anime series. P6 later identified a structural mismatch in this mapping: the island route loops back to its start, making the source domain closer to a circular linked list than the singly linked list under study.
Theme
What it captures
Learning preferences
Students’ initial approaches to understanding unfamiliar CS concepts before using AI.
Personalized analogies
Reactions to explanations tailored to participants’ stated interests.
Fairness & assumptions
Perceived assumptions about learners’ backgrounds, prior knowledge, and tone.
Trust & verification
How students judged the credibility of explanations and when they chose to verify them.
Evaluation criteria
The qualities participants used to assess explanation quality (e.g., clarity, accuracy, usefulness).
Design recommendations
Participants’ suggestions for improving AI-generated explanations and analogies.
Table 2. Top-level themes constructed through reflexive thematic analysis. Each theme encompasses multiple lower-level codes.
Analogies help learners understand unfamiliar concepts by relating them to known concepts. Despite recent advances, large language models (LLMs) continue to struggle to generate analogies of comparable quality to those produced by humans. We present a modular pipeline for educational analogy generation, decomposing the task into four stages: source finding, sub-concept generation, explanation generation, and evaluation. Grounded in Structure Mapping Theory, the pipeline enables systematic, stage-by-stage analysis of how model choice and input configuration affect analogy quality. We evaluate 12 state-of-the-art LLMs across six model families on two datasets with structured sub-concept annotations (SCAR and ParallelPARC), alongside seven embedding models for closed-setting retrieval. Our results show that sub-concepts substantially improve explanation quality and closed setting retrieval precision but provide limited benefit in open-ended source generation. We further introduce an LLM-as-a-judge evaluation methodology and validate its scoring against human annotations from seven annotators, finding that Claude Sonnet 4.6 aligns more reliably with human rankings than with fine-grained absolute scores. Taken together, our findings reveal cross-stage interactions that isolated studies cannot capture, and highlight sub-concept grounding as a key driver of analogy quality generation.
Mariam Barakat, Ekaterina Kochmar
Mohamed bin Zayed University of Artificial Intelligence, UAE
The integration of GenAI tools into higher education assessment raises important questions about how students understand, interpret, and respond to AI-mediated evaluation. As instructors increasingly explore AI tools for providing feedback, prior research has examined whether GenAI-generated feedback improves writing performance and how students perceive its usefulness; comparatively little is known, however, about how students interpret such evaluation when they are explicitly informed that an AI system, rather than a human instructor, produced the feedback and the score. This study reports findings from a qualitative pedagogical inquiry conducted in an undergraduate technical communication course for computing students at a Saudi public university. Thirteen male undergraduate computing students completed an in-class handwritten writing task; the scanned submissions were evaluated by ChatGPT using a rubric-based prompt aligned with the task objectives. Students were then explicitly informed that ChatGPT had generated the score and feedback and were invited to reflect on the evaluation in writing. Inductive thematic analysis of these reflections identified four themes: perceived usefulness of feedback; awareness of AI's contextual and pedagogical limitations; conditional trust, distinguishing feedback utility from evaluative authority; and reflection on the institutional and pedagogical role of the human instructor. Participants accepted GenAI feedback as useful for surface-level revision but consistently positioned the human instructor as the appropriate authority over grading decisions. The study identifies this as a distinction between feedback utility and evaluative authority, two judgments that students treat as analytically separate rather than as opposite ends of a single approval scale...
Rayed AlGhamdi
Department of Information Technology Faculty of Computing and Information Technology King Abdulaziz University, Jeddah, Saudi Arabia
As generative AI (GenAI) tools become easily accessible, there is promise in using such tools to support instructors. To that end, this paper examines using GenAI to help generate slides from instructor authored course notes, emphasizing instructor and student perceptions. We examine an end-to-end education tool (NotebookLM), two general-purpose LLMs (Claude, M365 Copilot), and two coding assistants (Cursor, Claude Code). We first analyze whether GenAI generated slides are good'' via narrative assessment by educators. We choose the best slides to use (with some modification) in a real course setting, and compare the student perception of human vs. AI generated slides. We find that coding assistant tools produce slides that were most accurate, complete, and pedagogically sound. Additionally, students rate GenAI slides to be of similar quality as instructor-created slides, and cannot reliably identify which slides are AI-generated. Additionally, we find a negative correlation between a high quality rating and a high AI-generated'' rating, suggesting students associate poor quality with the source of the slides being AI. These findings highlight promising opportunities for integrating GenAI into instructional design workflows and call for further research on how educators can best harness such tools responsibly and effectively.
Juho Leinonen, Lisa Zhang, Arto Hellas
Aalto University · Espoo, Finland · University of Toronto Mississauga +1