Fareya Ikram
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Fareya Ikram has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Alexander Scarlatos
University of Massachusetts Amherst
2 shared publications - Andrew Lan
University of Massachusetts Amherst
2 shared publications - Andrew Lan
University of Massachusetts Amherst
2 shared publications - Hunter McNichols
University of Massachusetts Amherst
2 shared publications - Candace Walkington
Department of Teaching and Learning, Southern Methodist University, Dallas, USA
1 shared publication - Junyang Lu
University of Massachusetts Amherst
1 shared publication
Latest Publications
- 27 June 2026
- Published by Springer Nature
- p. 233-247
A Multi-agent Approach to Validate and Refine LLM-Generated Personalized Math Problems
- 27 June 2026
- Published by Springer Nature
- p. 233-247
A Multi-agent Approach to Validate and Refine LLM-Generated Personalized Math Problems
- Top Cited PapersOpen Access
- 26 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 53-63
The StudyChat Dataset: Analyzing Student Dialogues With ChatGPT in an Artificial Intelligence Course
- 26 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 53-63
Top Cited PapersOpen AccessThe StudyChat Dataset: Analyzing Student Dialogues With ChatGPT in an Artificial Intelligence Course
- Open Access
Exploring LLMs for Predicting Tutor Strategy and Student Outcomes in Dialogues
Tutoring dialogues have gained significant attention in recent years, given the prominence of online learning and the emerging tutoring abilities of artificial intelligence (AI) agents powered by large language models (LLMs). Recent studies have shown that the strategies used by tutors can have significant effects on student outcomes, necessitating methods to predict how tutors will behave and how their actions impact students. However, few works have studied predicting tutor strategy in dialogues. Therefore, in this work we investigate the ability of modern LLMs, particularly Llama 3 and GPT-4o, to predict both future tutor moves and student outcomes in dialogues, using two math tutoring dialogue datasets. We find that even state-of-the-art LLMs struggle to predict future tutor strategy while tutor strategy is highly indicative of student outcomes, outlining a need for more powerful methods to approach this task.
Open AccessExploring LLMs for Predicting Tutor Strategy and Student Outcomes in Dialogues
Tutoring dialogues have gained significant attention in recent years, given the prominence of online learning and the emerging tutoring abilities of artificial intelligence (AI) agents powered by large language models (LLMs). Recent studies have shown that the strategies used by tutors can have significant effects on student outcomes, necessitating methods to predict how tutors will behave and how their actions impact students. However, few works have studied predicting tutor strategy in dialogues. Therefore, in this work we investigate the ability of modern LLMs, particularly Llama 3 and GPT-4o, to predict both future tutor moves and student outcomes in dialogues, using two math tutoring dialogue datasets. We find that even state-of-the-art LLMs struggle to predict future tutor strategy while tutor strategy is highly indicative of student outcomes, outlining a need for more powerful methods to approach this task.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 765-779
Exploring LLMs for Predicting Tutor Strategy and Student Outcomes in Dialogues
Fareya Ikram, Alexander Scarlatos, Andrew Lan. Proceedings of the 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025). 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 765-779
Open AccessExploring LLMs for Predicting Tutor Strategy and Student Outcomes in Dialogues
Fareya Ikram, Alexander Scarlatos, Andrew Lan. Proceedings of the 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025). 2025.