Ryan Teehan

Ryan Teehan

Auto-generated profile, based on publicly available information

Ryan Teehan

Center for Data Science, New York University, New York, NY, USA

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
7 March 2024
Verified
Conference Paper
Open access
EAErfan Al-Hossami
Erfan Al-Hossami
RBRazvan Bunescu
Razvan Bunescu
JSJustin Smith
Justin Smith
RTRyan Teehan
Ryan Teehan
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.

1 January 2023
Verified
Conference Paper
Open access
PDF file
EAErfan Al-Hossami
Erfan Al-Hossami
RBRazvan Bunescu
Razvan Bunescu
RTRyan Teehan
Ryan Teehan
LPLaurel Powell
Laurel Powell
KMKhyati Mahajan
Khyati Mahajan
MDMohsen Dorodchi
Mohsen Dorodchi
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.