Erfan Al-Hossami
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Erfan Al-Hossami has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Razvan Bunescu
Department of Computer Science University of North Carolina at Charlotte 28223 Charlotte NC
2 shared publications - Ryan Teehan
Center for Data Science, New York University, New York, NY, USA
2 shared publications - Justin Smith
Computer Science, University of North Carolina at Charlotte, Charlotte, NC, USA
1 shared publication - Khyati Mahajan
University of North Carolina at Charlotte Charlotte NC
1 shared publication - Laurel Powell
University of North Carolina at Charlotte
1 shared publication - Mohsen Dorodchi
University of North Carolina at Charlotte, Charlotte, NC, USA
1 shared publication
Latest Publications
- Open Access
- 7 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 53-59
Can Language Models Employ the Socratic Method? Experiments with Code Debugging
When employing the Socratic method of teaching, instructors guide students toward solving a problem on their own rather than providing the solution directly. While this strategy can substantially improve learning outcomes, it is usually time-consuming and cognitively demanding. Automated Socratic conversational agents can augment human instruction and provide the necessary scale, however their development is hampered by the lack of suitable data for training and evaluation. In this paper, we introduce a manually created dataset of multi-turn Socratic advice that is aimed at helping a novice programmer fix buggy solutions to simple computational problems. The dataset is then used for benchmarking the Socratic debugging abilities of a number of language models, ranging from fine-tuning the instruction-based text-to-text transformer Flan-T5 to zero-shot and chain of thought prompting of the much larger GPT-4. The code and datasets are made freely available for research at the link below.
- 7 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 53-59
Open AccessCan Language Models Employ the Socratic Method? Experiments with Code Debugging
When employing the Socratic method of teaching, instructors guide students toward solving a problem on their own rather than providing the solution directly. While this strategy can substantially improve learning outcomes, it is usually time-consuming and cognitively demanding. Automated Socratic conversational agents can augment human instruction and provide the necessary scale, however their development is hampered by the lack of suitable data for training and evaluation. In this paper, we introduce a manually created dataset of multi-turn Socratic advice that is aimed at helping a novice programmer fix buggy solutions to simple computational problems. The dataset is then used for benchmarking the Socratic debugging abilities of a number of language models, ranging from fine-tuning the instruction-based text-to-text transformer Flan-T5 to zero-shot and chain of thought prompting of the much larger GPT-4. The code and datasets are made freely available for research at the link below.
- Top Cited PapersOpen Access
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 709-726
Socratic Questioning of Novice Debuggers: A Benchmark Dataset and Preliminary Evaluations
Erfan Al-Hossami, Razvan Bunescu, Ryan Teehan, Laurel Powell, Khyati Mahajan, Mohsen Dorodchi. Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023). 2023.
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 709-726
Top Cited PapersOpen AccessSocratic Questioning of Novice Debuggers: A Benchmark Dataset and Preliminary Evaluations
Erfan Al-Hossami, Razvan Bunescu, Ryan Teehan, Laurel Powell, Khyati Mahajan, Mohsen Dorodchi. Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023). 2023.