@inproceedings{al-hossami-etal-2023-socratic,
title = "Socratic Questioning of Novice Debuggers: A Benchmark Dataset and Preliminary Evaluations",
author = "Al-Hossami, Erfan and
Bunescu, Razvan and
Teehan, Ryan and
Powell, Laurel and
Mahajan, Khyati and
Dorodchi, Mohsen",
editor = {Kochmar, Ekaterina and
Burstein, Jill and
Horbach, Andrea and
Laarmann-Quante, Ronja and
Madnani, Nitin and
Tack, Ana{\"\i}s and
Yaneva, Victoria and
Yuan, Zheng and
Zesch, Torsten},
booktitle = "Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.bea-1.57",
doi = "10.18653/v1/2023.bea-1.57",
pages = "709--726",
abstract = "Socratic questioning is a teaching strategy where the student is guided towards solving a problem on their own, instead of being given the solution directly. In this paper, we introduce a dataset of Socratic conversations where an instructor helps a novice programmer fix buggy solutions to simple computational problems. The dataset is then used for benchmarking the Socratic debugging abilities of GPT-based language models. While GPT-4 is observed to perform much better than GPT-3.5, its precision, and recall still fall short of human expert abilities, motivating further work in this area.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="al-hossami-etal-2023-socratic">
<titleInfo>
<title>Socratic Questioning of Novice Debuggers: A Benchmark Dataset and Preliminary Evaluations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Erfan</namePart>
<namePart type="family">Al-Hossami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Razvan</namePart>
<namePart type="family">Bunescu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Teehan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laurel</namePart>
<namePart type="family">Powell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khyati</namePart>
<namePart type="family">Mahajan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohsen</namePart>
<namePart type="family">Dorodchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Horbach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ronja</namePart>
<namePart type="family">Laarmann-Quante</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nitin</namePart>
<namePart type="family">Madnani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anaïs</namePart>
<namePart type="family">Tack</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Victoria</namePart>
<namePart type="family">Yaneva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Torsten</namePart>
<namePart type="family">Zesch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Socratic questioning is a teaching strategy where the student is guided towards solving a problem on their own, instead of being given the solution directly. In this paper, we introduce a dataset of Socratic conversations where an instructor helps a novice programmer fix buggy solutions to simple computational problems. The dataset is then used for benchmarking the Socratic debugging abilities of GPT-based language models. While GPT-4 is observed to perform much better than GPT-3.5, its precision, and recall still fall short of human expert abilities, motivating further work in this area.</abstract>
<identifier type="citekey">al-hossami-etal-2023-socratic</identifier>
<identifier type="doi">10.18653/v1/2023.bea-1.57</identifier>
<location>
<url>https://aclanthology.org/2023.bea-1.57</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>709</start>
<end>726</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Socratic Questioning of Novice Debuggers: A Benchmark Dataset and Preliminary Evaluations
%A Al-Hossami, Erfan
%A Bunescu, Razvan
%A Teehan, Ryan
%A Powell, Laurel
%A Mahajan, Khyati
%A Dorodchi, Mohsen
%Y Kochmar, Ekaterina
%Y Burstein, Jill
%Y Horbach, Andrea
%Y Laarmann-Quante, Ronja
%Y Madnani, Nitin
%Y Tack, Anaïs
%Y Yaneva, Victoria
%Y Yuan, Zheng
%Y Zesch, Torsten
%S Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F al-hossami-etal-2023-socratic
%X Socratic questioning is a teaching strategy where the student is guided towards solving a problem on their own, instead of being given the solution directly. In this paper, we introduce a dataset of Socratic conversations where an instructor helps a novice programmer fix buggy solutions to simple computational problems. The dataset is then used for benchmarking the Socratic debugging abilities of GPT-based language models. While GPT-4 is observed to perform much better than GPT-3.5, its precision, and recall still fall short of human expert abilities, motivating further work in this area.
%R 10.18653/v1/2023.bea-1.57
%U https://aclanthology.org/2023.bea-1.57
%U https://doi.org/10.18653/v1/2023.bea-1.57
%P 709-726
Markdown (Informal)
[Socratic Questioning of Novice Debuggers: A Benchmark Dataset and Preliminary Evaluations](https://aclanthology.org/2023.bea-1.57) (Al-Hossami et al., BEA 2023)
ACL