Ilya Musabirov

Ilya Musabirov

Auto-generated profile, based on publicly available information

Ilya Musabirov

University of British Columbia, Vancouver, Canada

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
11 May 2024
Verified
Conference Paper
Open access
MRMohi Reza
Mohi Reza
NLNathan M Laundry
Nathan M Laundry
IMIlya Musabirov
Ilya Musabirov
PDPeter Dushniku
Peter Dushniku
ZYZhi Yuan “Michael” Yu
Zhi Yuan “Michael” Yu
JWJoseph Jay Williams
Joseph Jay Williams
Exploring alternative ideas by rewriting text is integral to the writing process. State-of-the-art Large Language Models (LLMs) can simplify writing variation generation. However, current interfaces pose challenges for simultaneous consideration of multiple variations: creating new variations without overwriting text can be difficult, and pasting them sequentially can clutter documents, increasing workload and disrupting writers’ flow. To tackle this, we present ABScribe, an interface that supports rapid, yet visually structured, exploration and organization of writing variations in human-AI co-writing tasks. With ABScribe, users can swiftly modify variations using LLM prompts, which are auto-converted into reusable buttons. Variations are stored adjacently within text fields for rapid in-place comparisons using mouse-over interactions on a popup toolbar. Our user study with 12 writers shows that ABScribe significantly reduces task workload (d = 1.20, p < 0.001), enhances user perceptions of the revision process (d = 2.41, p < 0.001) compared to a popular baseline workflow, and provides insights into how writers explore variations using LLMs.

9 July 2024
Verified
Conference Paper
Open access
HKHarsh Kumar
Harsh Kumar
RXRuiwei Xiao
Ruiwei Xiao
BLBenjamin Lawson
Benjamin Lawson
IMIlya Musabirov
Ilya Musabirov
JSJiakai Shi
Jiakai Shi
MLMichael Liut
Michael Liut
Self-reflection on learning experiences constitutes a fundamental cognitive process, essential for consolidating knowledge and enhancing learning efficacy. However, traditional methods to facilitate reflection often face challenges in personalization, immediacy of feedback, engagement, and scalability. Integration of Large Language Models (LLMs) into the reflection process could mitigate these limitations. In this paper, we conducted two randomized field experiments in undergraduate computer science courses to investigate the potential of LLMs to help students engage in post-lesson reflection. In the first experiment (N=145), students completed a take-home assignment with the support of an LLM assistant; half of these students were then provided access to an LLM designed to facilitate self-reflection. The results indicated that the students assigned to LLM-guided reflection reported somewhat increased self-confidence compared to peers in a no-reflection control and a non-significant trend towards higher scores on a later assessment. Thematic analysis of students' interactions with the LLM showed that the LLM often affirmed the student's understanding, expanded on the student's reflection, and prompted additional reflection; these behaviors suggest ways LLM-interaction might facilitate reflection. In the second experiment (N=112), we evaluated the impact of LLM-guided self-reflection against other scalable reflection methods, such as questionnaire-based activities and review of key lecture slides, after assignment. Our findings suggest that the students in the questionnaire and LLM-based reflection groups performed equally well and better than those who were only exposed to lecture slides, according to their scores on a proctored exam two weeks later on the same subject matter. These results underscore the utility of LLM-guided reflection and questionnaire-based activities in improving learning outcomes. Our work highlights that focusing solely on the accuracy of LLMs can overlook their potential to enhance metacognitive skills through practices such as self-reflection. We discuss the implications of our research for the learning-at-scale community, highlighting the potential of LLMs to enhance learning experiences through personalized, engaging, and scalable reflection practices.

19 April 2023
Verified
Conference Paper
Open access
HKHarsh Kumar
Harsh Kumar
YWYiyi Wang
Yiyi Wang
JSJiakai Shi
Jiakai Shi
IMIlya Musabirov
Ilya Musabirov
NFNorman Farb
Norman Farb
JWJoseph Jay Williams
Joseph Jay Williams
Teachable self-help techniques, such as mindfulness, can reduce anxiety and improve mental well-being outcomes. However, people lack proper awareness of such techniques. In this work, we explore the design space of using online dissemination channels to help people learn about mindfulness. We investigate the potential benefits of using Large Language Models (LLMs) to improve awareness and willingness to practice these techniques, building on a video-based intervention to introduce mindfulness. We designed a pilot between subjects randomized factorial experiment of 2 (Informational Chatbot: present vs. absent) x 2 (Tutorial Video: present vs. absent) x 2 (Reflection Chatbot: present vs. absent). Our preliminary findings suggest that interaction with either of the chatbots improved the participants’ intent to practice Mindfulness again, and the tutorial video improved the participants’ reported overall experience of the exercise. This highlights the potential promise and outlines the directions for exploring the use of LLM-based chatbots for awareness-related interventions.

7 November 2024 in Proceedings of the ACM on Human-Computer Interaction
Verified
Journal Article
Open access
HKHarsh Kumar
Harsh Kumar
IMIlya Musabirov
Ilya Musabirov
MRMohi Reza
Mohi Reza
JSJiakai Shi
Jiakai Shi
XWXinyuan Wang
Xinyuan Wang
MLMichael Liut
Michael Liut
Personalized chatbot-based teaching assistants can be crucial in addressing increasing classroom sizes, especially where direct teacher presence is limited. Large language models (LLMs) offer a promising avenue, with increasing research exploring their educational utility. However, the challenge lies not only in establishing the efficacy of LLMs but also in discerning the nuances of interaction between learners and these models, which impact learners' engagement and results. We conducted a formative study in an undergraduate computer science classroom (N=145) and a controlled experiment on Prolific (N=356) to explore the impact of four pedagogically informed guidance strategies on the learners' performance, confidence and trust in LLMs. Direct LLM answers marginally improved performance, while refining student solutions fostered trust. Structured guidance reduced random queries as well as instances of students copy-pasting assignment questions to the LLM. Our work highlights the role that teachers can play in shaping LLM-supported learning environments.

20 April 2018
Verified
Conference Paper
Open access
PDF file
IMIlya Musabirov
Ilya Musabirov
DBDenis Bulygin
Denis Bulygin
POPaul Okopny
Paul Okopny
KKKsenia Konstantinova
Ksenia Konstantinova

8 March 2016 in Voprosy Obrazovaniya / Educational Studies Moscow
Verified
Journal Article
Closed access
VIValeria Ivaniushina
Valeria Ivaniushina
DADaniil Alexandrov
Daniil Alexandrov
IMIlya Musabirov
Ilya Musabirov
In this paper we explore motivational structure of students taking a challenging university course. The participants were second-year undergraduate students majoring in Economics, Sociology, Management and Humanities, enrolled in the Data Science minor. Using expectancy-value theory as a framework, we aim (1) to analyze gender differences in motivation; (2) to identify the link between the components of motivation and academic achievement; (3) to estimate the role of the previous academic achievement and educational choices. Two alternativetheoretical models are proposed and tested on empirical data. Structural equation modeling (SEM) in M Plus 7.31 was used for analysis. We found that the course is more popular among males students, who also demonstrate higher level of expectancy for success. However, there is no gender difference in academic performance. Students majoring in Sociology and Economics perceive Data Science as more interesting and useful than Management and Humanities students. SEM analysis empirically validated the model in which expectancy of success directly influences academic achievement, and values influence is mediated by expectancies. The final model that includes motivation, gender, student’s major, and previous achievement explains 34% of variance in academic performance. We discuss the role of different components of student motivation and practical significance of our results.